AMD EPYC Zen 4C Power Efficiency

AMD EPYC Zen 4C power efficiency benchmarks by Michael Larabel for a future article.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2401147-NE-AMDEPYCZE24
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results
Show Result Confidence Charts

Limit displaying results to tests within:

AV1 2 Tests
BLAS (Basic Linear Algebra Sub-Routine) Tests 2 Tests
C++ Boost Tests 3 Tests
Timed Code Compilation 5 Tests
C/C++ Compiler Tests 8 Tests
CPU Massive 13 Tests
Creator Workloads 14 Tests
Cryptography 2 Tests
Database Test Suite 4 Tests
Encoding 6 Tests
Fortran Tests 3 Tests
Game Development 2 Tests
HPC - High Performance Computing 15 Tests
Java Tests 2 Tests
Common Kernel Benchmarks 2 Tests
Machine Learning 5 Tests
Molecular Dynamics 5 Tests
MPI Benchmarks 3 Tests
Multi-Core 24 Tests
NVIDIA GPU Compute 3 Tests
Intel oneAPI 5 Tests
OpenMPI Tests 7 Tests
Programmer / Developer System Benchmarks 6 Tests
Python Tests 9 Tests
Raytracing 2 Tests
Renderers 5 Tests
Scientific Computing 8 Tests
Server 8 Tests
Server CPU Tests 8 Tests
Video Encoding 6 Tests
Common Workstation Benchmarks 2 Tests

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Geometric Means Per-Suite/Category
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Disable Color Branding
Prefer Vertical Bar Graphs
No Box Plots
On Line Graphs With Missing Data, Connect The Line Gaps

Additional Graphs

Show Perf Per Core/Thread Calculation Graphs Where Applicable
Show Perf Per Clock Calculation Graphs Where Applicable
Show Perf Per RAM Channel Calculation Graphs Where Applicable

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs
Condense Test Profiles With Multiple Version Results Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
EPYC 7601 - Zen 1
January 13
  1 Day, 1 Hour, 20 Minutes
EPYC 8324P - Zen 4C
January 12
  13 Hours, 1 Minute
EPYC 8324P - Zen 4C, 155W
January 12
  13 Hours, 3 Minutes
EPYC 8324PN - Zen 4C
January 10
  12 Hours, 44 Minutes
EPYC 8534PN - Zen 4C
January 09
  11 Hours, 36 Minutes
Invert Hiding All Results Option
  15 Hours, 9 Minutes

Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):

EPYC 8534PN - Zen 4C

Processor: AMD EPYC 8534PN 64-Core @ 2.00GHz (64 Cores / 128 Threads), Motherboard: AMD Cinnabar (RCB1009C BIOS), Chipset: AMD Device 14a4, Memory: 6 x 32 GB DRAM-4800MT/s Samsung M321R4GA0BB0-CQKMG, Disk: 1000GB INTEL SSDPE2KX010T8, Graphics: llvmpipe, Network: 2 x Broadcom NetXtreme BCM5720 PCIe

OS: Ubuntu 23.10, Kernel: 6.6.9-060609-generic (x86_64), Desktop: GNOME Shell 45.0, Display Server: X Server 1.21.1.7, OpenGL: 4.5 Mesa 23.2.1-1ubuntu3.1 (LLVM 15.0.7 256 bits), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xaa00212
Java Notes: OpenJDK Runtime Environment (build 11.0.21+9-post-Ubuntu-0ubuntu123.10)
Python Notes: Python 3.11.6
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

EPYC 8324PN - Zen 4C

Changed Processor to AMD EPYC 8534PN 32-Core @ 2.05GHz (32 Cores / 64 Threads).

EPYC 8324P - Zen 4C

Changed Processor to AMD EPYC 8324P 32-Core @ 2.65GHz (32 Cores / 64 Threads).

EPYC 8324P - Zen 4C, 155W

Processor: AMD EPYC 8324P 32-Core @ 2.65GHz (32 Cores / 64 Threads), Motherboard: AMD Cinnabar (RCB1009C BIOS), Chipset: AMD Device 14a4, Memory: 6 x 32 GB DRAM-4800MT/s Samsung M321R4GA0BB0-CQKMG, Disk: 1000GB INTEL SSDPE2KX010T8, Graphics: ASPEED, Network: 2 x Broadcom NetXtreme BCM5720 PCIe

OS: Ubuntu 23.10, Kernel: 6.6.9-060609-generic (x86_64), Desktop: GNOME Shell 45.0, Display Server: X Server 1.21.1.7, Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200

EPYC 7601 - Zen 1

Processor: AMD EPYC 7601 32-Core @ 2.20GHz (32 Cores / 64 Threads), Motherboard: TYAN B8026T70AE24HR (V1.02.B10 BIOS), Chipset: AMD 17h, Memory: 8 x 16 GB 2667MT/s Samsung M393A2K40BB2-CTD, Disk: 1000GB INTEL SSDPE2KX010T8 + 280GB INTEL SSDPE21D280GA, Graphics: ASPEED, Monitor: VE228, Network: 2 x Broadcom NetXtreme BCM5720 PCIe

OS: Ubuntu 23.10, Kernel: 6.6.9-060609-generic (x86_64), Desktop: GNOME Shell 45.0, Display Server: X Server 1.21.1.7, OpenGL: 4.5 Mesa 23.2.1-1ubuntu3.1 (LLVM 15.0.7 256 bits), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1080

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0x800126e
Java Notes: OpenJDK Runtime Environment (build 11.0.21+9-post-Ubuntu-0ubuntu123.10)
Python Notes: Python 3.11.6
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Mitigation of untrained return thunk; SMT vulnerable + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional STIBP: disabled RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

AMD EPYC Zen 4C Power EfficiencyProcessorMotherboardChipsetMemoryDiskGraphicsNetworkMonitorOSKernelDesktopDisplay ServerOpenGLCompilerFile-SystemScreen ResolutionEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1AMD EPYC 8534PN 64-Core @ 2.00GHz (64 Cores / 128 Threads)AMD Cinnabar (RCB1009C BIOS)AMD Device 14a46 x 32 GB DRAM-4800MT/s Samsung M321R4GA0BB0-CQKMG1000GB INTEL SSDPE2KX010T8llvmpipe2 x Broadcom NetXtreme BCM5720 PCIeUbuntu 23.106.6.9-060609-generic (x86_64)GNOME Shell 45.0X Server 1.21.1.74.5 Mesa 23.2.1-1ubuntu3.1 (LLVM 15.0.7 256 bits)GCC 13.2.0ext41920x1200AMD EPYC 8534PN 32-Core @ 2.05GHz (32 Cores / 64 Threads)AMD EPYC 8324P 32-Core @ 2.65GHz (32 Cores / 64 Threads)ASPEEDAMD EPYC 7601 32-Core @ 2.20GHz (32 Cores / 64 Threads)TYAN B8026T70AE24HR (V1.02.B10 BIOS)AMD 17h8 x 16 GB 2667MT/s Samsung M393A2K40BB2-CTD1000GB INTEL SSDPE2KX010T8 + 280GB INTEL SSDPE21D280GAVE2284.5 Mesa 23.2.1-1ubuntu3.1 (LLVM 15.0.7 256 bits)1920x1080OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Processor Details- EPYC 8534PN - Zen 4C: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xaa00212- EPYC 8324PN - Zen 4C: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xaa00212- EPYC 8324P - Zen 4C: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xaa00212- EPYC 8324P - Zen 4C, 155W: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xaa00212- EPYC 7601 - Zen 1: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0x800126eJava Details- OpenJDK Runtime Environment (build 11.0.21+9-post-Ubuntu-0ubuntu123.10)Python Details- Python 3.11.6Security Details- EPYC 8534PN - Zen 4C: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - EPYC 8324PN - Zen 4C: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - EPYC 8324P - Zen 4C: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - EPYC 8324P - Zen 4C, 155W: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - EPYC 7601 - Zen 1: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Mitigation of untrained return thunk; SMT vulnerable + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional STIBP: disabled RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

EPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1Logarithmic Result OverviewPhoronix Test SuiteminiBUDETensorFlowACES DGEMMOSPRay StudioOpenSSLOpenVINOXmrigIntel Open Image DenoiseeasyWaveOSPRayEmbreeY-CruncherNeural Magic DeepSparseChaos Group V-RAY7-Zip CompressionBlenderIndigoBenchnginxSVT-AV1QuantLibRocksDBRedis 7.0.12 + memtier_benchmarkNAMDTimed Node.js CompilationGPAWFFmpegTimed LLVM CompilationTimed FFmpeg CompilationPyTorchuvg266SpeedbTimed Linux Kernel Compilationx265CloverLeafXcompact3d Incompact3dLAMMPS Molecular Dynamics SimulatorVVenCTimed Gem5 Compilationrav1eOpenRadiossOpenFOAMApache CassandraKripkeApache IoTDBQuicksilverDuckDB

EPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1Logarithmic Per Watt Result OverviewPhoronix Test SuiteACES DGEMMTensorFlowEmbreeIntel Open Image DenoiseXmrigRedis 7.0.12 + memtier_benchmarkOpenSSLOSPRayPyTorchSVT-AV1IndigoBench7-Zip Compressionuvg266Chaos Group V-RAYRocksDBx265QuantLibnginxVVenCFFmpegSpeedbApache Cassandrarav1eKripkeQuicksilverLAMMPS Molecular Dynamics SimulatorminiBUDEP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.MP.W.G.M

AMD EPYC Zen 4C Power Efficiencyincompact3d: X3D-benchmarking input.i3dcloverleaf: clover_bm16build-linux-kernel: allmodconfiglammps: 20k Atomsblender: Barbershop - CPU-Onlyopenradioss: Chrysler Neon 1Mbuild-gem5: Time To Compilexmrig: GhostRider - 1Mbuild-llvm: Unix Makefilesllama-cpp: llama-2-70b-chat.Q5_0.ggufquicksilver: CTS2openfoam: drivaerFastback, Medium Mesh Size - Execution Timeopenfoam: drivaerFastback, Medium Mesh Size - Mesh Timeeasywave: e2Asean Grid + BengkuluSept2007 Source - 2400build-llvm: Ninjaduckdb: TPC-H Parquetbuild-nodejs: Time To Compileffmpeg: libx265 - Video On Demandffmpeg: libx265 - Platformffmpeg: libx265 - Uploadllama-cpp: llama-2-13b.Q4_0.ggufxmrig: Monero - 1Mxmrig: CryptoNight-Femto UPX2 - 1Mxmrig: KawPow - 1Mxmrig: CryptoNight-Heavy - 1Mapache-iotdb: 500 - 100 - 500 - 100apache-iotdb: 500 - 100 - 500 - 100duckdb: IMDBospray-studio: 3 - 4K - 32 - Path Tracer - CPUopenssl: SHA256openssl: ChaCha20-Poly1305openssl: ChaCha20openssl: AES-256-GCMopenssl: AES-128-GCMopenssl: SHA512cassandra: Writesblender: Pabellon Barcelona - CPU-Onlyrocksdb: Read While Writingospray-studio: 1 - 4K - 32 - Path Tracer - CPUospray: particle_volume/scivis/real_timespeedb: Read While Writingospray: particle_volume/pathtracer/real_timellama-cpp: llama-2-7b.Q4_0.ggufminibude: OpenMP - BM2minibude: OpenMP - BM2blender: Classroom - CPU-Onlyspeedb: Update Randospray: particle_volume/ao/real_timeospray-studio: 3 - 4K - 16 - Path Tracer - CPUgpaw: Carbon Nanotubeospray-studio: 1 - 4K - 16 - Path Tracer - CPUnginx: 1000nginx: 500deepsparse: BERT-Large, NLP Question Answering - Asynchronous Multi-Streamdeepsparse: BERT-Large, NLP Question Answering - Asynchronous Multi-Streamospray-studio: 3 - 4K - 1 - Path Tracer - CPUospray-studio: 1 - 4K - 1 - Path Tracer - CPUopenvino: Handwritten English Recognition FP16-INT8 - CPUopenvino: Handwritten English Recognition FP16-INT8 - CPUv-ray: CPUrav1e: 10quantlib: Multi-Threadedffmpeg: libx265 - Livetensorflow: CPU - 16 - ResNet-50cloverleaf: clover_bm64_shortblender: Fishy Cat - CPU-Onlyindigobench: CPU - Bedroommemtier-benchmark: Redis - 100 - 1:10memtier-benchmark: Redis - 100 - 1:5vvenc: Bosphorus 4K - Fastereasywave: e2Asean Grid + BengkuluSept2007 Source - 1200quicksilver: CORAL2 P1openvino: Face Detection FP16-INT8 - CPUopenvino: Face Detection FP16-INT8 - CPUindigobench: CPU - Supercarospray: gravity_spheres_volume/dim_512/pathtracer/real_timepytorch: CPU - 256 - ResNet-50speedb: Rand Readopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Face Detection Retail FP16-INT8 - CPUopenvino: Face Detection Retail FP16-INT8 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUospray: gravity_spheres_volume/dim_512/scivis/real_timeopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUspeedb: Read Rand Write Randbuild-linux-kernel: defconfigospray: gravity_spheres_volume/dim_512/ao/real_timeopenssl: RSA4096openssl: RSA4096rocksdb: Rand Readxmrig: Wownero - 1Mblender: BMW27 - CPU-Onlydeepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamrav1e: 6mt-dgemm: Sustained Floating-Point Ratedeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamopenfoam: drivaerFastback, Small Mesh Size - Execution Timedeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamnamd: ATPase Simulation - 327,506 Atomscompress-7zip: Decompression Ratingcompress-7zip: Compression Ratingdeepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamdeepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: ResNet-50, Baseline - Asynchronous Multi-Streamdeepsparse: ResNet-50, Baseline - Asynchronous Multi-Streamsvt-av1: Preset 4 - Bosphorus 4Koidn: RT.ldr_alb_nrm.3840x2160 - CPU-Onlykripke: pytorch: CPU - 1 - ResNet-50x265: Bosphorus 4Kbuild-ffmpeg: Time To Compileincompact3d: input.i3d 193 Cells Per Directionembree: Pathtracer ISPC - Crownminibude: OpenMP - BM1minibude: OpenMP - BM1svt-av1: Preset 8 - Bosphorus 4Ky-cruncher: 1Bsvt-av1: Preset 12 - Bosphorus 4Kembree: Pathtracer ISPC - Asian Dragonuvg266: Bosphorus 4K - Very Fastuvg266: Bosphorus 4K - Super Fasty-cruncher: 500Muvg266: Bosphorus 4K - Ultra FastEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1563.346781496.55341.47725.715267.58300.62230.9904374.0277.91016300000687.42305184.16204109.827190.992178.698174.00247.0847.0323.3120484.320477.120487.220489.854.7182731495127.20187860699104309871960125738532846962933734244000382074934344962502269726620724417795.4466880897475214.854912585315164.20599.5682489.19776.3234974514.90864747265.47240603232146.41229161.91776.543440.64102544214658.781086.685420412.186154830.9115.1148.5657.4238.669.9732568868.492513019.3211.27239.33021233333644.8049.4321.76716.895436.23248842616157.93202.29108.06295.6112.472547.7334.14934.597.528310.7111.242816.0914.61310.6171960.4112.974878.00227202644.42315.0596828697.421064.124896938735370.030.5724.81841287.8778982.610932.155452.1235613.2269982.329832.14614.86821.138819556.145756.841958.610212113.4506281.48980.43200343946332922166.9491191.0676166.0267192.061674.4270429.32709.25203450.433474.4102429.36036.5561.7128839430045.2327.5119.37620.975618459.051399.6472491.16564.33610.442190.88774.926847.6549.225.20751.33628.844299492.50539.24015.690518.21391.36295.0603938.5371.5363.1114030000793.87207172.68566116.031300.444182.934253.14244.9945.0322.2417.0616892.316799.216877.916932.858.9277285152123.6671672093579582607310106502312314760207765021643566020725141555837011644867590212207182.4741073131421608.143586934544147.22028.5651.0591276.472146.903057298.132318667890.06574023139259.26136660.96722.104121.90965004422257.50555.712817711.82480175.3109.7747.7757.5272.965.1272562876.162500035.0910.29142.25718273333627.4625.4111.2498.8936140.36132248192121.74131.2497.91163.0911.151424.5330.69520.247.134405.6210.391527.327.665320.5743375.5512.582520.77198225758.5197.97910430171.611909.213120683021769.258.2023.6852674.9294892.103917.764149.7973320.8637894.195617.66644.72711.517272493.988732.128982.15286104.8987152.20680.82790179072212458154.2821103.4399153.3968104.130669.6037229.53508.37451906.387069.5078229.91235.5510.9324750013352.9024.0327.57424.346738831.081451.1211278.03051.53713.971167.16339.600633.8236.756.65341.02608.229716489.47449.98618.407426.62381.88263.5334043.2334.2933.4314313333763.50167153.15408115.288258.219182.775222.06745.0745.0122.2417.9318908.918922.718875.218883.257.2180321359121.4851397374303308236311310589287715944767551726530311345730820730843713803340747223293148.7643943101185148.770437290610147.25329.7261.2911532.274119.583172508.797737312780.91662633166799.14164234.98611.148125.83684152349346.39688.603351011.79098717.2109.8451.7056.9159.646.1772842511.462795965.0510.74142.08918880000510.7131.2513.57310.493940.59163771762106.00150.7482.00194.719.341701.1825.21633.215.775418.928.521860.658.836220.4752709.1910.203102.13223374452.1449.14257457516.315040.716167887625644.347.5019.5341818.3145751.624421.023041.6397383.7004752.512121.00444.70611.645616410.465838.820273.51338888.1549181.23200.67728211187240083130.4161122.3679129.8432122.925659.8698266.95677.28162193.090659.8723266.98565.9111.1126877326752.7225.5524.49223.905040736.891761.1541528.84858.00011.927182.26045.508539.2542.945.74746.54612.204793489.04487.57617.423463.27382.57266.9514031.7349.6112.9314376667779.50949163.04119115.253274.946181.394234.23145.0645.1222.2517.0918129.018090.918088.718155.062.6070294901122.1431504104020035340011234408384315943100862024283052687328119187856712993940737224034161.9543013431281548.758967162203147.28129.3857.0131425.324130.673176348.757847861084.37967153151923.62149458.34647.885524.47364493378751.41621.823153611.81890654.1109.7151.0357.0465.035.7202789711.342720321.3010.63541.99618950000558.2928.5812.5729.8737340.54147991555110.77144.2788.55180.3210.181563.3627.56579.346.34977.139.291710.428.456340.5149194.5511.122851.01213331154.7988.78898457514.113565.814772176924096.252.0221.2407752.5874803.821919.639044.7159357.2953801.190119.75304.73111.434849443.429935.792975.25070294.2013169.56280.73558200034228957139.1784114.6161138.2263115.421262.8155254.30287.60642099.324662.8813254.13075.8161.0325871616752.9125.4525.67923.773293834.240257.0961427.41255.71712.887175.74643.127037.3340.506.19244.811092.51253954.73752.60313.781765.20498.23394.6191042.7529.3980.46114433331164.3926229.49406357.692435.252249.189389.70021.0021.0210.402.494973.35061.34687.95087.486.1951950735198.94033194527015393267303410466374793558006089976610817977070348208355425337150277246.7134636952811375.22927595425198.89694.2014.240355.990191.712038235.28576170871144.01214556090952.1594936.991289.822712.2244100548452169.21188.86199146.99564469.458.098.77106.27101.103.9851277853.471159654.336.358152.337130300002096.013.818.5864.1465520.4885990445188.2542.43206.7238.6317.20464.4853.64149.019.09878.7126.96296.422.452762.4413039.7084.77376.97144781976.1962.59961292445.34497.1846164089331.672.4364.7981246.64401501.605110.4527124.0928128.66921515.679210.33642.9633.8867761840.94948.5097122.25778189.318684.42870.97282133490123746234.021268.1629231.403568.9537115.7775138.0333104.4436152.9618115.3465138.52913.0650.4818179596724.8914.2939.89137.988997118.438714.330358.25426.75333.90870.77321.842122.2623.5815.51527.29OpenBenchmarking.org

Xcompact3d Incompact3d

Xcompact3d Incompact3d is a Fortran-MPI based, finite difference high-performance code for solving the incompressible Navier-Stokes equation and as many as you need scalar transport equations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: X3D-benchmarking input.i3dEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 12004006008001000SE +/- 0.84, N = 3SE +/- 0.29, N = 3SE +/- 0.69, N = 3SE +/- 0.57, N = 3SE +/- 15.13, N = 9563.35628.84608.23612.201092.511. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz
OpenBenchmarking.orgWatts, Fewer Is BetterXcompact3d Incompact3d 2021-03-11CPU Power Consumption MonitorEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1306090120150Min: 14.11 / Avg: 126.57 / Max: 133.41Min: 12.94 / Avg: 93.37 / Max: 98.13Min: 12.9 / Avg: 104.53 / Max: 115.04Min: 13.85 / Avg: 102.88 / Max: 107.73Min: 65.72 / Avg: 150.35 / Max: 171.921. EPYC 8534PN - Zen 4C: Approximate power consumption of 72400 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 59726 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 64531 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 63923 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 164864 Joules per run.

CloverLeaf

CloverLeaf is a Lagrangian-Eulerian hydrodynamics benchmark. This test profile currently makes use of CloverLeaf's OpenMP version. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterCloverLeaf 1.3Input: clover_bm16EPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 12004006008001000SE +/- 0.16, N = 3SE +/- 0.30, N = 3SE +/- 0.11, N = 3SE +/- 0.34, N = 3SE +/- 3.58, N = 3496.55492.50489.47489.04954.731. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp
OpenBenchmarking.orgWatts, Fewer Is BetterCloverLeaf 1.3CPU Power Consumption MonitorEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1306090120150Min: 14.26 / Avg: 127.08 / Max: 131.51Min: 12.95 / Avg: 99.07 / Max: 101.75Min: 13.29 / Avg: 107.42 / Max: 111.27Min: 13.89 / Avg: 107.71 / Max: 111.6Min: 65.7 / Avg: 148.58 / Max: 160.531. EPYC 8534PN - Zen 4C: Approximate power consumption of 63412 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 49039 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 52853 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 52957 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 141842 Joules per run.

Timed Linux Kernel Compilation

This test times how long it takes to build the Linux kernel in a default configuration (defconfig) for the architecture being tested or alternatively an allmodconfig for building all possible kernel modules for the build. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.1Build: allmodconfigEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1160320480640800SE +/- 0.92, N = 3SE +/- 0.77, N = 3SE +/- 0.84, N = 3SE +/- 0.47, N = 3SE +/- 0.46, N = 3341.48539.24449.99487.58752.60
MinAvgMaxEPYC 8534PN - Zen 4C13.1123.1141.4EPYC 8324PN - Zen 4C12.484.892.0EPYC 8324P - Zen 4C13.0110.3125.9EPYC 8324P - Zen 4C, 155W13.498.2106.7EPYC 7601 - Zen 163.3169.3179.5OpenBenchmarking.orgWatts, Fewer Is BetterTimed Linux Kernel Compilation 6.1CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 43955 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 47036 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 51341 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 49411 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 130301 Joules per run.

LAMMPS Molecular Dynamics Simulator

LAMMPS is a classical molecular dynamics code, and an acronym for Large-scale Atomic/Molecular Massively Parallel Simulator. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022Model: 20k AtomsEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1612182430SE +/- 0.28, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 325.7215.6918.4117.4213.781. (CXX) g++ options: -O3 -lm -ldl
OpenBenchmarking.orgns/day Per Watt, More Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022Model: 20k AtomsEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 10.04520.09040.13560.18080.2260.2010.1920.1670.1810.080
MinAvgMaxEPYC 8534PN - Zen 4C12.9128.0132.4EPYC 8324PN - Zen 4C13.081.784.7EPYC 8324P - Zen 4C13.5110.0122.8EPYC 8324P - Zen 4C, 155W13.996.5105.3EPYC 7601 - Zen 165.6172.4175.7OpenBenchmarking.orgWatts, Fewer Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 43606 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 45365 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 52074 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 48232 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 108584 Joules per run.

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: Barbershop - Compute: CPU-OnlyEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1160320480640800SE +/- 0.08, N = 3SE +/- 0.45, N = 3SE +/- 0.14, N = 3SE +/- 0.21, N = 3SE +/- 0.25, N = 3267.58518.21426.62463.27765.20
MinAvgMaxEPYC 8534PN - Zen 4C14.0135.1140.8EPYC 8324PN - Zen 4C13.086.790.9EPYC 8324P - Zen 4C13.5115.4124.1EPYC 8324P - Zen 4C, 155W14.0103.8110.5EPYC 7601 - Zen 165.6175.3178.7OpenBenchmarking.orgWatts, Fewer Is BetterBlender 4.0CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 37060 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 45536 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 49976 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 48774 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 135340 Joules per run.

OpenRadioss

OpenRadioss is an open-source AGPL-licensed finite element solver for dynamic event analysis OpenRadioss is based on Altair Radioss and open-sourced in 2022. This open-source finite element solver is benchmarked with various example models available from https://www.openradioss.org/models/ and https://github.com/OpenRadioss/ModelExchange/tree/main/Examples. This test is currently using a reference OpenRadioss binary build offered via GitHub. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Chrysler Neon 1MEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1110220330440550SE +/- 0.58, N = 3SE +/- 0.66, N = 3SE +/- 0.38, N = 3SE +/- 0.48, N = 3SE +/- 0.95, N = 3300.62391.36381.88382.57498.23
MinAvgMaxEPYC 8534PN - Zen 4C14.9125.7137.9EPYC 8324PN - Zen 4C12.993.399.2EPYC 8324P - Zen 4C13.0109.6120.3EPYC 8324P - Zen 4C, 155W13.9107.2114.8EPYC 7601 - Zen 165.7156.7172.2OpenBenchmarking.orgWatts, Fewer Is BetterOpenRadioss 2023.09.15CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 42391 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 39914 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 45842 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 44916 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 85943 Joules per run.

Timed Gem5 Compilation

This test times how long it takes to compile Gem5. Gem5 is a simulator for computer system architecture research. Gem5 is widely used for computer architecture research within the industry, academia, and more. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Gem5 Compilation 23.0.1Time To CompileEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 190180270360450SE +/- 2.69, N = 4SE +/- 3.60, N = 3SE +/- 2.62, N = 9SE +/- 1.97, N = 3SE +/- 4.56, N = 3230.99295.06263.53266.95394.62
MinAvgMaxEPYC 8534PN - Zen 4C13.180.4136.2EPYC 8324PN - Zen 4C12.868.489.8EPYC 8324P - Zen 4C11.281.5124.9EPYC 8324P - Zen 4C, 155W13.676.8105.3EPYC 7601 - Zen 136.0132.1179.2OpenBenchmarking.orgWatts, Fewer Is BetterTimed Gem5 Compilation 23.0.1CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 19049 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 20580 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 21943 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 20972 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 52911 Joules per run.

Xmrig

Xmrig is an open-source cross-platform CPU/GPU miner for RandomX, KawPow, CryptoNight and AstroBWT. This test profile is setup to measure the Xmrig CPU mining performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: GhostRider - Hash Count: 1MEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 19001800270036004500SE +/- 6.81, N = 3SE +/- 16.58, N = 3SE +/- 7.57, N = 3SE +/- 19.57, N = 3SE +/- 12.26, N = 34374.03938.54043.24031.71042.71. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenBenchmarking.orgH/s Per Watt, More Is BetterXmrig 6.21Variant: GhostRider - Hash Count: 1MEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1112233445535.48150.34041.05040.5277.453
MinAvgMaxEPYC 8534PN - Zen 4C14.9123.3127.0EPYC 8324PN - Zen 4C13.078.288.5EPYC 8324P - Zen 4C12.798.5101.3EPYC 8324P - Zen 4C, 155W13.599.5102.3EPYC 7601 - Zen 165.8139.9146.3OpenBenchmarking.orgWatts, Fewer Is BetterXmrig 6.21CPU Power Consumption Monitor40801201602001. EPYC 8534PN - Zen 4C: Approximate power consumption of 28764 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 20290 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 24854 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 25202 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 134495 Joules per run.

Timed LLVM Compilation

This test times how long it takes to compile/build the LLVM compiler stack. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 16.0Build System: Unix MakefilesEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1110220330440550SE +/- 0.46, N = 3SE +/- 0.95, N = 3SE +/- 0.60, N = 3SE +/- 1.23, N = 3SE +/- 1.30, N = 3277.91371.54334.29349.61529.40
MinAvgMaxEPYC 8534PN - Zen 4C13.595.2143.0EPYC 8324PN - Zen 4C12.774.893.4EPYC 8324P - Zen 4C13.093.0129.4EPYC 8324P - Zen 4C, 155W13.685.3110.0EPYC 7601 - Zen 163.2148.4179.0OpenBenchmarking.orgWatts, Fewer Is BetterTimed LLVM Compilation 16.0CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 28928 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 29802 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 33579 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 32095 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 83327 Joules per run.

Llama.cpp

Llama.cpp is a port of Facebook's LLaMA model in C/C++ developed by Georgi Gerganov. Llama.cpp allows the inference of LLaMA and other supported models in C/C++. For CPU inference Llama.cpp supports AVX2/AVX-512, ARM NEON, and other modern ISAs along with features like OpenBLAS usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b1808Model: llama-2-70b-chat.Q5_0.ggufEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 10.77181.54362.31543.08723.859SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 33.113.432.930.461. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -march=native -mtune=native -lopenblas
OpenBenchmarking.orgTokens Per Second Per Watt, More Is BetterLlama.cpp b1808Model: llama-2-70b-chat.Q5_0.ggufEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 10.0070.0140.0210.0280.0350.0310.0270.0280.003
MinAvgMaxEPYC 8324PN - Zen 4C12.8101.1109.8EPYC 8324P - Zen 4C13.0126.4141.3EPYC 8324P - Zen 4C, 155W12.2104.0121.2EPYC 7601 - Zen 164.0134.9177.0OpenBenchmarking.orgWatts, Fewer Is BetterLlama.cpp b1808CPU Power Consumption Monitor501001502002501. EPYC 8324PN - Zen 4C: Approximate power consumption of 15373 Joules per run.2. EPYC 8324P - Zen 4C: Approximate power consumption of 22208 Joules per run.3. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 20417 Joules per run.4. EPYC 7601 - Zen 1: Approximate power consumption of 129159 Joules per run.

Quicksilver

Quicksilver is a proxy application that represents some elements of the Mercury workload by solving a simplified dynamic Monte Carlo particle transport problem. Quicksilver is developed by Lawrence Livermore National Laboratory (LLNL) and this test profile currently makes use of the OpenMP CPU threaded code path. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFigure Of Merit, More Is BetterQuicksilver 20230818Input: CTS2EPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 13M6M9M12M15MSE +/- 23094.01, N = 3SE +/- 25166.11, N = 3SE +/- 29627.31, N = 3SE +/- 43333.33, N = 3SE +/- 54569.02, N = 316300000140300001431333314376667114433331. (CXX) g++ options: -fopenmp -O3 -march=native
OpenBenchmarking.orgFigure Of Merit Per Watt, More Is BetterQuicksilver 20230818Input: CTS2EPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 140K80K120K160K200K144074.42171302.45156624.76156169.0372917.48
MinAvgMaxEPYC 8534PN - Zen 4C13.7113.1116.6EPYC 8324PN - Zen 4C12.881.987.7EPYC 8324P - Zen 4C11.891.493.8EPYC 8324P - Zen 4C, 155W13.792.194.7EPYC 7601 - Zen 166.8156.9165.2OpenBenchmarking.orgWatts, Fewer Is BetterQuicksilver 20230818CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 35713 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 29949 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 32777 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 32896 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 70359 Joules per run.

OpenFOAM

OpenFOAM is the leading free, open-source software for computational fluid dynamics (CFD). This test profile currently uses the drivaerFastback test case for analyzing automotive aerodynamics or alternatively the older motorBike input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Medium Mesh Size - Execution TimeEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 130060090012001500687.42793.87763.50779.511164.391. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm
MinAvgMaxEPYC 8534PN - Zen 4C13.8134.2139.0EPYC 8324PN - Zen 4C12.296.6101.2EPYC 8324P - Zen 4C13.2117.5128.6EPYC 8324P - Zen 4C, 155W13.6107.9112.7EPYC 7601 - Zen 165.0159.9174.9OpenBenchmarking.orgWatts, Fewer Is BetterOpenFOAM 10CPU Power Consumption Monitor50100150200250

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Medium Mesh Size - Mesh TimeEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 150100150200250184.16172.69153.15163.04229.491. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm

easyWave

The easyWave software allows simulating tsunami generation and propagation in the context of early warning systems. EasyWave supports making use of OpenMP for CPU multi-threading and there are also GPU ports available but not currently incorporated as part of this test profile. The easyWave tsunami generation software is run with one of the example/reference input files for measuring the CPU execution time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BettereasyWave r34Input: e2Asean Grid + BengkuluSept2007 Source - Time: 2400EPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 180160240320400SE +/- 0.94, N = 3SE +/- 0.25, N = 3SE +/- 0.36, N = 3SE +/- 0.25, N = 3SE +/- 4.58, N = 9109.83116.03115.29115.25357.691. (CXX) g++ options: -O3 -fopenmp
MinAvgMaxEPYC 8534PN - Zen 4C13.593.9103.6EPYC 8324PN - Zen 4C11.577.983.9EPYC 8324P - Zen 4C12.783.490.7EPYC 8324P - Zen 4C, 155W13.683.390.6EPYC 7601 - Zen 164.0131.6149.1OpenBenchmarking.orgWatts, Fewer Is BettereasyWave r34CPU Power Consumption Monitor40801201602001. EPYC 8534PN - Zen 4C: Approximate power consumption of 10950 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 9585 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 10176 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 10191 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 48028 Joules per run.

Timed LLVM Compilation

This test times how long it takes to compile/build the LLVM compiler stack. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 16.0Build System: NinjaEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 190180270360450SE +/- 0.14, N = 3SE +/- 0.16, N = 3SE +/- 1.36, N = 3SE +/- 1.25, N = 3SE +/- 0.41, N = 3190.99300.44258.22274.95435.25
MinAvgMaxEPYC 8534PN - Zen 4C14.0111.7145.3EPYC 8324PN - Zen 4C12.780.993.6EPYC 8324P - Zen 4C13.3104.4129.2EPYC 8324P - Zen 4C, 155W13.793.7109.1EPYC 7601 - Zen 163.9161.3179.0OpenBenchmarking.orgWatts, Fewer Is BetterTimed LLVM Compilation 16.0CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 23574 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 25931 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 29060 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 27653 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 74091 Joules per run.

DuckDB

DuckDB is an in-progress SQL OLAP database management system optimized for analytics and features a vectorized and parallel engine. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDuckDB 0.9.1Benchmark: TPC-H ParquetEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 150100150200250SE +/- 0.63, N = 3SE +/- 0.25, N = 3SE +/- 0.21, N = 3SE +/- 0.48, N = 3SE +/- 1.55, N = 3178.70182.93182.78181.39249.191. (CXX) g++ options: -O3 -rdynamic -lssl -lcrypto -ldl
MinAvgMaxEPYC 8534PN - Zen 4C12.952.989.1EPYC 8324PN - Zen 4C12.149.774.3EPYC 8324P - Zen 4C12.251.187.6EPYC 8324P - Zen 4C, 155W13.151.085.1EPYC 7601 - Zen 164.179.1142.3OpenBenchmarking.orgWatts, Fewer Is BetterDuckDB 0.9.1CPU Power Consumption Monitor40801201602001. EPYC 8534PN - Zen 4C: Approximate power consumption of 12829 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 12358 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 12695 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 12716 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 27253 Joules per run.

Timed Node.js Compilation

This test profile times how long it takes to build/compile Node.js itself from source. Node.js is a JavaScript run-time built from the Chrome V8 JavaScript engine while itself is written in C/C++. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 19.8.1Time To CompileEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 180160240320400SE +/- 0.04, N = 3SE +/- 0.22, N = 3SE +/- 0.12, N = 3SE +/- 0.15, N = 3SE +/- 0.67, N = 3174.00253.14222.07234.23389.70
MinAvgMaxEPYC 8534PN - Zen 4C13.5105.1142.2EPYC 8324PN - Zen 4C11.878.797.6EPYC 8324P - Zen 4C12.4100.3130.4EPYC 8324P - Zen 4C, 155W13.590.5113.3EPYC 7601 - Zen 164.0156.0178.9OpenBenchmarking.orgWatts, Fewer Is BetterTimed Node.js Compilation 19.8.1CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 19191 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 20625 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 23180 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 21992 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 62259 Joules per run.

FFmpeg

This is a benchmark of the FFmpeg multimedia framework. The FFmpeg test profile is making use of a modified version of vbench from Columbia University's Architecture and Design Lab (ARCADE) [http://arcade.cs.columbia.edu/vbench/] that is a benchmark for video-as-a-service workloads. The test profile offers the options of a range of vbench scenarios based on freely distributable video content and offers the options of using the x264 or x265 video encoders for transcoding. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: Video On DemandEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 11122334455SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 347.0844.9945.0745.0621.001. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFPS Per Watt, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: Video On DemandEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 10.1730.3460.5190.6920.8650.7650.7690.7530.7440.241
MinAvgMaxEPYC 8534PN - Zen 4C12.961.579.2EPYC 8324PN - Zen 4C12.758.574.5EPYC 8324P - Zen 4C12.659.878.4EPYC 8324P - Zen 4C, 155W13.260.578.7EPYC 7601 - Zen 137.887.0127.4OpenBenchmarking.orgWatts, Fewer Is BetterFFmpeg 6.1CPU Power Consumption Monitor40801201602001. EPYC 8534PN - Zen 4C: Approximate power consumption of 11549 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 11448 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 11685 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 11845 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 34331 Joules per run.

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: PlatformEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 11122334455SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 347.0345.0345.0145.1221.021. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFPS Per Watt, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: PlatformEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 10.1730.3460.5190.6920.8650.7660.7690.7530.7450.241
MinAvgMaxEPYC 8534PN - Zen 4C11.361.477.5EPYC 8324PN - Zen 4C11.958.675.3EPYC 8324P - Zen 4C12.559.875.2EPYC 8324P - Zen 4C, 155W13.360.578.2EPYC 7601 - Zen 162.587.1125.3OpenBenchmarking.orgWatts, Fewer Is BetterFFmpeg 6.1CPU Power Consumption Monitor40801201602001. EPYC 8534PN - Zen 4C: Approximate power consumption of 11502 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 11458 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 11715 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 11824 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 34386 Joules per run.

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: UploadEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1612182430SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 323.3122.2422.2422.2510.401. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFPS Per Watt, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: UploadEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 10.09110.18220.27330.36440.45550.4040.4050.3960.3910.123
MinAvgMaxEPYC 8534PN - Zen 4C12.257.789.3EPYC 8324PN - Zen 4C12.755.076.7EPYC 8324P - Zen 4C12.756.286.2EPYC 8324P - Zen 4C, 155W13.357.089.0EPYC 7601 - Zen 163.084.5141.4OpenBenchmarking.orgWatts, Fewer Is BetterFFmpeg 6.1CPU Power Consumption Monitor40801201602001. EPYC 8534PN - Zen 4C: Approximate power consumption of 11161 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 11051 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 11307 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 11471 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 29100 Joules per run.

Llama.cpp

Llama.cpp is a port of Facebook's LLaMA model in C/C++ developed by Georgi Gerganov. Llama.cpp allows the inference of LLaMA and other supported models in C/C++. For CPU inference Llama.cpp supports AVX2/AVX-512, ARM NEON, and other modern ISAs along with features like OpenBLAS usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b1808Model: llama-2-13b.Q4_0.ggufEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 148121620SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 1217.0617.9317.092.491. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -march=native -mtune=native -lopenblas
OpenBenchmarking.orgTokens Per Second Per Watt, More Is BetterLlama.cpp b1808Model: llama-2-13b.Q4_0.ggufEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 10.04190.08380.12570.16760.20950.1860.1740.1790.019
MinAvgMaxEPYC 8324PN - Zen 4C12.691.5104.2EPYC 8324P - Zen 4C12.9103.1130.5EPYC 8324P - Zen 4C, 155W13.295.6116.7EPYC 7601 - Zen 164.3132.7166.7OpenBenchmarking.orgWatts, Fewer Is BetterLlama.cpp b1808CPU Power Consumption Monitor501001502002501. EPYC 8324PN - Zen 4C: Approximate power consumption of 3295 Joules per run.2. EPYC 8324P - Zen 4C: Approximate power consumption of 3814 Joules per run.3. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 3698 Joules per run.4. EPYC 7601 - Zen 1: Approximate power consumption of 26867 Joules per run.

Xmrig

Xmrig is an open-source cross-platform CPU/GPU miner for RandomX, KawPow, CryptoNight and AstroBWT. This test profile is setup to measure the Xmrig CPU mining performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: Monero - Hash Count: 1MEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 14K8K12K16K20KSE +/- 5.73, N = 3SE +/- 34.05, N = 3SE +/- 56.24, N = 3SE +/- 43.26, N = 3SE +/- 155.10, N = 1220484.316892.318908.918129.04973.31. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenBenchmarking.orgH/s Per Watt, More Is BetterXmrig 6.21Variant: Monero - Hash Count: 1MEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 14080120160200160.74189.12150.56174.2032.66
MinAvgMaxEPYC 8534PN - Zen 4C13.6127.4140.9EPYC 8324PN - Zen 4C12.889.395.4EPYC 8324P - Zen 4C12.8125.6136.7EPYC 8324P - Zen 4C, 155W12.8104.1113.6EPYC 7601 - Zen 166.9152.3164.3OpenBenchmarking.orgWatts, Fewer Is BetterXmrig 6.21CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 6839 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 5776 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 7326 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 6314 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 32155 Joules per run.

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: CryptoNight-Femto UPX2 - Hash Count: 1MEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 14K8K12K16K20KSE +/- 12.46, N = 3SE +/- 103.09, N = 3SE +/- 50.80, N = 3SE +/- 49.53, N = 3SE +/- 202.60, N = 1220477.116799.218922.718090.95061.31. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenBenchmarking.orgH/s Per Watt, More Is BetterXmrig 6.21Variant: CryptoNight-Femto UPX2 - Hash Count: 1MEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 14080120160200157.77188.75149.20172.6633.27
MinAvgMaxEPYC 8534PN - Zen 4C14.6129.8142.6EPYC 8324PN - Zen 4C13.189.095.5EPYC 8324P - Zen 4C11.2126.8137.8EPYC 8324P - Zen 4C, 155W13.4104.8115.5EPYC 7601 - Zen 165.4152.1165.1OpenBenchmarking.orgWatts, Fewer Is BetterXmrig 6.21CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 7009 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 5785 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 7356 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 6392 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 31798 Joules per run.

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: KawPow - Hash Count: 1MEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 14K8K12K16K20KSE +/- 5.33, N = 3SE +/- 33.52, N = 3SE +/- 43.40, N = 3SE +/- 61.47, N = 3SE +/- 218.18, N = 1120487.216877.918875.218088.74687.91. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenBenchmarking.orgH/s Per Watt, More Is BetterXmrig 6.21Variant: KawPow - Hash Count: 1MEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 14080120160200155.95189.15148.73171.5031.23
MinAvgMaxEPYC 8534PN - Zen 4C14.1131.4143.8EPYC 8324PN - Zen 4C13.189.295.6EPYC 8324P - Zen 4C13.6126.9138.0EPYC 8324P - Zen 4C, 155W13.0105.5115.0EPYC 7601 - Zen 165.7150.1166.7OpenBenchmarking.orgWatts, Fewer Is BetterXmrig 6.21CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 7050 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 5800 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 7445 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 6399 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 33899 Joules per run.

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: CryptoNight-Heavy - Hash Count: 1MEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 14K8K12K16K20KSE +/- 6.48, N = 3SE +/- 35.06, N = 3SE +/- 41.98, N = 3SE +/- 44.77, N = 3SE +/- 166.19, N = 1220489.816932.818883.218155.05087.41. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenBenchmarking.orgH/s Per Watt, More Is BetterXmrig 6.21Variant: CryptoNight-Heavy - Hash Count: 1MEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 14080120160200157.28190.30148.12173.4933.30
MinAvgMaxEPYC 8534PN - Zen 4C14.9130.3143.1EPYC 8324PN - Zen 4C13.189.095.9EPYC 8324P - Zen 4C13.5127.5138.3EPYC 8324P - Zen 4C, 155W13.6104.6114.3EPYC 7601 - Zen 165.9152.8165.7OpenBenchmarking.orgWatts, Fewer Is BetterXmrig 6.21CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 7078 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 5784 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 7437 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 6279 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 31590 Joules per run.

Apache IoTDB

Apache IotDB is a time series database and this benchmark is facilitated using the IoT Benchmaark [https://github.com/thulab/iot-benchmark/]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgAverage Latency, Fewer Is BetterApache IoTDB 1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 100EPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 120406080100SE +/- 0.27, N = 3SE +/- 0.18, N = 3SE +/- 0.50, N = 3SE +/- 0.98, N = 12SE +/- 0.92, N = 354.7158.9257.2162.6086.19MAX: 10074.09MAX: 10097.01MAX: 10096.05MAX: 11339.9MAX: 12666.75
MinAvgMaxEPYC 8534PN - Zen 4C12.755.7128.6EPYC 8324PN - Zen 4C12.549.199.2EPYC 8324P - Zen 4C12.654.7118.9EPYC 8324P - Zen 4C, 155W13.155.6125.1EPYC 7601 - Zen 162.6113.6173.4OpenBenchmarking.orgWatts, Fewer Is BetterApache IoTDB 1.2CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 7185 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 6558 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 7214 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 6288 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 20529 Joules per run.

OpenBenchmarking.orgpoint/sec, More Is BetterApache IoTDB 1.2Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 500 - Client Number: 100EPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 120M40M60M80M100MSE +/- 820005.27, N = 3SE +/- 90002.32, N = 3SE +/- 458351.52, N = 3SE +/- 1107129.95, N = 12SE +/- 395656.07, N = 38273149577285152803213597029490151950735

DuckDB

DuckDB is an in-progress SQL OLAP database management system optimized for analytics and features a vectorized and parallel engine. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDuckDB 0.9.1Benchmark: IMDBEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 14080120160200SE +/- 0.08, N = 3SE +/- 0.10, N = 3SE +/- 0.12, N = 3SE +/- 0.10, N = 3SE +/- 0.90, N = 3127.20123.67121.49122.14198.941. (CXX) g++ options: -O3 -rdynamic -lssl -lcrypto -ldl
MinAvgMaxEPYC 8534PN - Zen 4C13.166.695.3EPYC 8324PN - Zen 4C12.661.685.7EPYC 8324P - Zen 4C12.866.496.5EPYC 8324P - Zen 4C, 155W13.465.291.1EPYC 7601 - Zen 162.299.7146.8OpenBenchmarking.orgWatts, Fewer Is BetterDuckDB 0.9.1CPU Power Consumption Monitor40801201602001. EPYC 8534PN - Zen 4C: Approximate power consumption of 11693 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 10489 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 11089 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 10947 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 30599 Joules per run.

OSPRay Studio

Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.13Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPUEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 170K140K210K280K350KSE +/- 229.98, N = 3SE +/- 85.59, N = 3SE +/- 125.49, N = 3SE +/- 149.58, N = 3SE +/- 408.43, N = 387860167209139737150410331945
MinAvgMaxEPYC 8534PN - Zen 4C13.9115.1136.5EPYC 8324PN - Zen 4C12.980.890.5EPYC 8324P - Zen 4C13.2105.6124.0EPYC 8324P - Zen 4C, 155W13.794.1108.3EPYC 7601 - Zen 165.1167.1178.6OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 0.13CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 11975 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 14835 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 16472 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 15675 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 58659 Joules per run.

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: SHA256EPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 115000M30000M45000M60000M75000MSE +/- 41929433.75, N = 3SE +/- 16148314.98, N = 3SE +/- 11419799.65, N = 3SE +/- 12904999.14, N = 3SE +/- 58715423.07, N = 369910430987357958260734303308236340200353400270153932671. (CC) gcc options: -pthread -m64 -O3 -ldl
OpenBenchmarking.orgbyte/s Per Watt, More Is BetterOpenSSL 3.1Algorithm: SHA256EPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1120M240M360M480M600M546243197.78436238930.85387067179.89416875314.97155415474.32
MinAvgMaxEPYC 8534PN - Zen 4C13.1128.0136.2EPYC 8324PN - Zen 4C12.882.190.4EPYC 8324P - Zen 4C13.0111.2118.1EPYC 8324P - Zen 4C, 155W13.596.4102.1EPYC 7601 - Zen 165.3173.8178.2OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 3.1CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 23549 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 15126 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 20420 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 17711 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 31984 Joules per run.

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: ChaCha20-Poly1305EPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 140000M80000M120000M160000M200000MSE +/- 52537274.39, N = 3SE +/- 36167959.31, N = 3SE +/- 5327895.48, N = 3SE +/- 3407926.56, N = 3SE +/- 21793844.67, N = 3196012573853101065023123113105892877112344083843303410466371. (CC) gcc options: -pthread -m64 -O3 -ldl
OpenBenchmarking.orgbyte/s Per Watt, More Is BetterOpenSSL 3.1Algorithm: ChaCha20-Poly1305EPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1300M600M900M1200M1500M1450412054.661181271903.83947613075.921067969605.53177417166.50
MinAvgMaxEPYC 8534PN - Zen 4C14.2135.1142.3EPYC 8324PN - Zen 4C12.785.695.5EPYC 8324P - Zen 4C13.3119.4130.2EPYC 8324P - Zen 4C, 155W13.9105.2110.7EPYC 7601 - Zen 165.9171.0177.9OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 3.1CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 24866 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 15742 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 21922 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 19321 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 31410 Joules per run.

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: ChaCha20EPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 160000M120000M180000M240000M300000MSE +/- 8141159.25, N = 3SE +/- 4106091.67, N = 3SE +/- 3614035.56, N = 3SE +/- 2748202.21, N = 3SE +/- 18792715.18, N = 3284696293373147602077650159447675517159431008620479355800601. (CC) gcc options: -pthread -m64 -O3 -ldl
OpenBenchmarking.orgbyte/s Per Watt, More Is BetterOpenSSL 3.1Algorithm: ChaCha20EPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1400M800M1200M1600M2000M2095501066.501694474523.221370606684.981474962096.07280245644.36
MinAvgMaxEPYC 8534PN - Zen 4C14.3135.9143.4EPYC 8324PN - Zen 4C12.587.190.7EPYC 8324P - Zen 4C13.3116.3131.9EPYC 8324P - Zen 4C, 155W13.7108.1113.9EPYC 7601 - Zen 165.3171.0177.6OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 3.1CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 24998 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 15999 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 21367 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 19853 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 31416 Joules per run.

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: AES-256-GCMEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 190000M180000M270000M360000M450000MSE +/- 171818503.35, N = 3SE +/- 288672373.67, N = 3SE +/- 72395520.64, N = 3SE +/- 104993783.37, N = 3SE +/- 220160896.72, N = 3424400038207216435660207265303113457242830526873899766108171. (CC) gcc options: -pthread -m64 -O3 -ldl
OpenBenchmarking.orgbyte/s Per Watt, More Is BetterOpenSSL 3.1Algorithm: AES-256-GCMEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1700M1400M2100M2800M3500M3123938397.232539685896.322258891761.222396310835.77516298912.20
MinAvgMaxEPYC 8534PN - Zen 4C14.4135.9141.5EPYC 8324PN - Zen 4C13.085.293.8EPYC 8324P - Zen 4C13.3117.4132.0EPYC 8324P - Zen 4C, 155W13.7101.3115.1EPYC 7601 - Zen 165.3174.3178.2OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 3.1CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 24907 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 15709 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 21610 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 18679 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 32008 Joules per run.

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: AES-128-GCMEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1110000M220000M330000M440000M550000MSE +/- 350336826.28, N = 3SE +/- 43613214.37, N = 3SE +/- 338919345.53, N = 3SE +/- 1389668244.12, N = 3SE +/- 228892930.90, N = 3493434496250251415558370308207308437281191878567977070348201. (CC) gcc options: -pthread -m64 -O3 -ldl
OpenBenchmarking.orgbyte/s Per Watt, More Is BetterOpenSSL 3.1Algorithm: AES-128-GCMEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1800M1600M2400M3200M4000M3626240465.702927424070.202612982097.092743728420.23559684188.57
MinAvgMaxEPYC 8534PN - Zen 4C14.3136.1141.2EPYC 8324PN - Zen 4C12.985.994.2EPYC 8324P - Zen 4C13.3118.0131.8EPYC 8324P - Zen 4C, 155W13.6102.5112.1EPYC 7601 - Zen 165.9174.6178.2OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 3.1CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 25037 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 15802 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 21664 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 18823 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 32064 Joules per run.

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: SHA512EPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 15000M10000M15000M20000M25000MSE +/- 1693446.92, N = 3SE +/- 3220312.96, N = 3SE +/- 1511880.16, N = 3SE +/- 794607.82, N = 3SE +/- 7664614.59, N = 32269726620711644867590138033407471299394073783554253371. (CC) gcc options: -pthread -m64 -O3 -ldl
OpenBenchmarking.orgbyte/s Per Watt, More Is BetterOpenSSL 3.1Algorithm: SHA512EPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 140M80M120M160M200M175273393.29142108901.03122734575.99132126423.4047835855.20
MinAvgMaxEPYC 8534PN - Zen 4C14.3129.5138.1EPYC 8324PN - Zen 4C13.081.988.0EPYC 8324P - Zen 4C12.8112.5125.9EPYC 8324P - Zen 4C, 155W13.698.3106.9EPYC 7601 - Zen 165.5174.7178.2OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 3.1CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 23827 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 15050 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 20656 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 18063 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 32023 Joules per run.

Apache Cassandra

This is a benchmark of the Apache Cassandra NoSQL database management system making use of cassandra-stress. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 4.1.3Test: WritesEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 150K100K150K200K250KSE +/- 1997.81, N = 3SE +/- 423.47, N = 3SE +/- 371.97, N = 3SE +/- 522.48, N = 3SE +/- 1316.75, N = 8244177212207223293224034150277
OpenBenchmarking.orgOp/s Per Watt, More Is BetterApache Cassandra 4.1.3Test: WritesEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 160012001800240030002486.662829.252451.592447.90977.63
MinAvgMaxEPYC 8534PN - Zen 4C12.598.2123.2EPYC 8324PN - Zen 4C11.875.087.7EPYC 8324P - Zen 4C12.791.1108.3EPYC 8324P - Zen 4C, 155W13.491.5104.6EPYC 7601 - Zen 163.3153.7181.9OpenBenchmarking.orgWatts, Fewer Is BetterApache Cassandra 4.1.3CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 15318 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 10926 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 13298 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 13332 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 21232 Joules per run.

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: Pabellon Barcelona - Compute: CPU-OnlyEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 150100150200250SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.09, N = 3SE +/- 0.10, N = 3SE +/- 0.18, N = 395.44182.47148.76161.95246.71
MinAvgMaxEPYC 8534PN - Zen 4C14.1127.8135.8EPYC 8324PN - Zen 4C12.985.489.4EPYC 8324P - Zen 4C12.7113.1126.5EPYC 8324P - Zen 4C, 155W13.9100.5107.9EPYC 7601 - Zen 165.4174.7178.7OpenBenchmarking.orgWatts, Fewer Is BetterBlender 4.0CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 12818 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 15974 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 17301 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 16714 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 43861 Joules per run.

RocksDB

This is a benchmark of Meta/Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 8.0Test: Read While WritingEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 11.4M2.8M4.2M5.6M7MSE +/- 64443.01, N = 15SE +/- 3126.89, N = 3SE +/- 38567.21, N = 15SE +/- 47925.84, N = 5SE +/- 36400.82, N = 3668808941073134394310430134334636951. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.orgOp/s Per Watt, More Is BetterRocksDB 8.0Test: Read While WritingEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 112K24K36K48K60K57031.6451316.2938762.7243556.2620446.35
MinAvgMaxEPYC 8534PN - Zen 4C13.7117.3138.2EPYC 8324PN - Zen 4C12.180.093.0EPYC 8324P - Zen 4C13.2113.4129.0EPYC 8324P - Zen 4C, 155W13.598.8110.3EPYC 7601 - Zen 165.8169.4177.9OpenBenchmarking.orgWatts, Fewer Is BetterRocksDB 8.0CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 7521 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 5149 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 7255 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 6320 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 10842 Joules per run.

OSPRay Studio

Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.13Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPUEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 160K120K180K240K300KSE +/- 78.83, N = 3SE +/- 49.00, N = 3SE +/- 153.74, N = 3SE +/- 87.82, N = 3SE +/- 491.07, N = 374752142160118514128154281137
MinAvgMaxEPYC 8534PN - Zen 4C13.8111.9135.9EPYC 8324PN - Zen 4C12.279.790.8EPYC 8324P - Zen 4C12.5103.1127.2EPYC 8324P - Zen 4C, 155W13.792.5105.3EPYC 7601 - Zen 165.1165.8178.7OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 0.13CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 10184 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 12642 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 13954 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 13376 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 49856 Joules per run.

OSPRay

Intel OSPRay is a portable ray-tracing engine for high-performance, high-fidelity scientific visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.12Benchmark: particle_volume/scivis/real_timeEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 148121620SE +/- 0.01627, N = 3SE +/- 0.00550, N = 3SE +/- 0.00419, N = 3SE +/- 0.01425, N = 3SE +/- 0.00416, N = 314.854908.143588.770438.758965.22927
OpenBenchmarking.orgItems Per Second Per Watt, More Is BetterOSPRay 2.12Benchmark: particle_volume/scivis/real_timeEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 10.0320.0640.0960.1280.160.1420.1110.0930.1000.034
MinAvgMaxEPYC 8534PN - Zen 4C13.6104.4125.1EPYC 8324PN - Zen 4C12.673.485.4EPYC 8324P - Zen 4C12.894.0110.8EPYC 8324P - Zen 4C, 155W13.887.3109.1EPYC 7601 - Zen 160.0155.5175.7OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay 2.12CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 15688 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 11891 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 15102 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 14020 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 27998 Joules per run.

Speedb

Speedb is a next-generation key value storage engine that is RocksDB compatible and aiming for stability, efficiency, and performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Read While WritingEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 13M6M9M12M15MSE +/- 117697.08, N = 15SE +/- 50044.04, N = 3SE +/- 52967.61, N = 15SE +/- 7924.49, N = 3SE +/- 81525.26, N = 31258531569345447290610716220359542511. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.orgOp/s Per Watt, More Is BetterSpeedb 2.7Test: Read While WritingEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 120K40K60K80K100K108503.0288296.4564987.0774216.6535300.60
MinAvgMaxEPYC 8534PN - Zen 4C12.6116.0134.1EPYC 8324PN - Zen 4C12.878.591.1EPYC 8324P - Zen 4C11.8112.2124.5EPYC 8324P - Zen 4C, 155W13.696.5108.8EPYC 7601 - Zen 165.3168.7178.1OpenBenchmarking.orgWatts, Fewer Is BetterSpeedb 2.7CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 7447 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 5079 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 7202 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 6208 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 10851 Joules per run.

OSPRay

Intel OSPRay is a portable ray-tracing engine for high-performance, high-fidelity scientific visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.12Benchmark: particle_volume/pathtracer/real_timeEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 14080120160200SE +/- 0.09, N = 3SE +/- 0.02, N = 3SE +/- 0.07, N = 3SE +/- 0.09, N = 3SE +/- 0.06, N = 3164.21147.22147.25147.2898.90
OpenBenchmarking.orgItems Per Second Per Watt, More Is BetterOSPRay 2.12Benchmark: particle_volume/pathtracer/real_timeEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 10.4410.8821.3231.7642.2051.4601.9601.5011.7210.651
MinAvgMaxEPYC 8534PN - Zen 4C13.8112.4131.6EPYC 8324PN - Zen 4C12.875.188.1EPYC 8324P - Zen 4C12.698.1119.5EPYC 8324P - Zen 4C, 155W13.685.6106.9EPYC 7601 - Zen 165.4151.9175.1OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay 2.12CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 20428 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 11016 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 16938 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 12441 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 23594 Joules per run.

Llama.cpp

Llama.cpp is a port of Facebook's LLaMA model in C/C++ developed by Georgi Gerganov. Llama.cpp allows the inference of LLaMA and other supported models in C/C++. For CPU inference Llama.cpp supports AVX2/AVX-512, ARM NEON, and other modern ISAs along with features like OpenBLAS usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTokens Per Second, More Is BetterLlama.cpp b1808Model: llama-2-7b.Q4_0.ggufEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1714212835SE +/- 0.05, N = 3SE +/- 0.06, N = 3SE +/- 0.04, N = 3SE +/- 0.12, N = 1528.5629.7229.384.201. (CXX) g++ options: -std=c++11 -fPIC -O3 -pthread -march=native -mtune=native -lopenblas
OpenBenchmarking.orgTokens Per Second Per Watt, More Is BetterLlama.cpp b1808Model: llama-2-7b.Q4_0.ggufEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 10.07790.15580.23370.31160.38950.3460.3200.3300.032
MinAvgMaxEPYC 8324PN - Zen 4C12.682.4100.5EPYC 8324P - Zen 4C11.892.9119.1EPYC 8324P - Zen 4C, 155W12.589.1113.3EPYC 7601 - Zen 164.9132.4154.0OpenBenchmarking.orgWatts, Fewer Is BetterLlama.cpp b1808CPU Power Consumption Monitor40801201602001. EPYC 8324PN - Zen 4C: Approximate power consumption of 1924 Joules per run.2. EPYC 8324P - Zen 4C: Approximate power consumption of 2199 Joules per run.3. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 2138 Joules per run.4. EPYC 7601 - Zen 1: Approximate power consumption of 14661 Joules per run.

miniBUDE

MiniBUDE is a mini application for the the core computation of the Bristol University Docking Engine (BUDE). This test profile currently makes use of the OpenMP implementation of miniBUDE for CPU benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBillion Interactions/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM2EPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 120406080100SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 399.5751.0661.2957.0114.241. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
OpenBenchmarking.orgBillion Interactions/s Per Watt, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM2EPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 10.18590.37180.55770.74360.92950.8260.6450.5700.6060.084
MinAvgMaxEPYC 8534PN - Zen 4C12.8120.5131.6EPYC 8324PN - Zen 4C12.179.288.9EPYC 8324P - Zen 4C12.4107.5121.8EPYC 8324P - Zen 4C, 155W13.894.1106.1EPYC 7601 - Zen 165.5169.5175.3OpenBenchmarking.orgWatts, Fewer Is BetterminiBUDE 20210901CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 6708 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 8344 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 9425 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 8849 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 61765 Joules per run.

OpenBenchmarking.orgGFInst/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM2EPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 15001000150020002500SE +/- 0.34, N = 3SE +/- 0.10, N = 3SE +/- 0.47, N = 3SE +/- 0.17, N = 3SE +/- 0.44, N = 32489.201276.471532.271425.32355.991. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: Classroom - Compute: CPU-OnlyEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 14080120160200SE +/- 0.07, N = 3SE +/- 0.08, N = 3SE +/- 0.09, N = 3SE +/- 0.12, N = 3SE +/- 0.03, N = 376.32146.90119.58130.67191.71
MinAvgMaxEPYC 8534PN - Zen 4C14.2124.3133.0EPYC 8324PN - Zen 4C12.583.191.5EPYC 8324P - Zen 4C13.3109.7119.9EPYC 8324P - Zen 4C, 155W13.799.4106.9EPYC 7601 - Zen 165.7174.0178.2OpenBenchmarking.orgWatts, Fewer Is BetterBlender 4.0CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 10023 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 12610 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 13637 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 13423 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 34167 Joules per run.

Speedb

Speedb is a next-generation key value storage engine that is RocksDB compatible and aiming for stability, efficiency, and performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Update RandomEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 170K140K210K280K350KSE +/- 2986.90, N = 15SE +/- 863.96, N = 3SE +/- 579.72, N = 3SE +/- 167.58, N = 3SE +/- 190.36, N = 33497453057293172503176342038231. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.orgOp/s Per Watt, More Is BetterSpeedb 2.7Test: Update RandomEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 190018002700360045003874.594423.424050.084047.081640.50
MinAvgMaxEPYC 8534PN - Zen 4C13.190.3116.2EPYC 8324PN - Zen 4C12.969.179.1EPYC 8324P - Zen 4C12.278.388.2EPYC 8324P - Zen 4C, 155W13.678.588.0EPYC 7601 - Zen 165.1124.2142.7OpenBenchmarking.orgWatts, Fewer Is BetterSpeedb 2.7CPU Power Consumption Monitor40801201602001. EPYC 8534PN - Zen 4C: Approximate power consumption of 5825 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 4446 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 5039 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 5075 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 8034 Joules per run.

OSPRay

Intel OSPRay is a portable ray-tracing engine for high-performance, high-fidelity scientific visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.12Benchmark: particle_volume/ao/real_timeEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 148121620SE +/- 0.02133, N = 3SE +/- 0.01797, N = 3SE +/- 0.00420, N = 3SE +/- 0.02372, N = 3SE +/- 0.00450, N = 314.908608.132318.797738.757845.28576
OpenBenchmarking.orgItems Per Second Per Watt, More Is BetterOSPRay 2.12Benchmark: particle_volume/ao/real_timeEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 10.02860.05720.08580.11440.1430.1270.1050.0830.0910.031
MinAvgMaxEPYC 8534PN - Zen 4C13.7117.1126.2EPYC 8324PN - Zen 4C12.577.286.1EPYC 8324P - Zen 4C13.2106.5111.2EPYC 8324P - Zen 4C, 155W13.795.9110.1EPYC 7601 - Zen 165.2170.3175.8OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay 2.12CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 11985 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 8754 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 11826 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 10681 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 21453 Joules per run.

OSPRay Studio

Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.13Camera: 3 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPUEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 140K80K120K160K200KSE +/- 85.58, N = 3SE +/- 286.09, N = 3SE +/- 65.51, N = 3SE +/- 239.39, N = 3SE +/- 111.00, N = 347472866787312778610170871
MinAvgMaxEPYC 8534PN - Zen 4C14.2101.8135.4EPYC 8324PN - Zen 4C12.876.291.4EPYC 8324P - Zen 4C11.196.9122.6EPYC 8324P - Zen 4C, 155W13.687.5106.3EPYC 7601 - Zen 165.3159.9178.7OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 0.13CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 6515 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 7899 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 8685 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 8342 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 30479 Joules per run.

GPAW

GPAW is a density-functional theory (DFT) Python code based on the projector-augmented wave (PAW) method and the atomic simulation environment (ASE). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGPAW 23.6Input: Carbon NanotubeEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1306090120150SE +/- 0.11, N = 3SE +/- 0.19, N = 3SE +/- 0.45, N = 3SE +/- 0.21, N = 3SE +/- 1.20, N = 365.4790.0780.9284.38144.011. (CC) gcc options: -shared -fwrapv -O2 -lxc -lblas -lmpi
MinAvgMaxEPYC 8534PN - Zen 4C13.0133.5153.7EPYC 8324PN - Zen 4C12.687.698.5EPYC 8324P - Zen 4C12.8119.9137.5EPYC 8324P - Zen 4C, 155W13.6103.8117.3EPYC 7601 - Zen 166.2166.8178.9OpenBenchmarking.orgWatts, Fewer Is BetterGPAW 23.6CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 9479 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 8355 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 10310 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 9272 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 24905 Joules per run.

OSPRay Studio

Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.13Camera: 1 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPUEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 130K60K90K120K150KSE +/- 242.81, N = 3SE +/- 220.99, N = 3SE +/- 328.77, N = 3SE +/- 266.18, N = 3SE +/- 111.55, N = 340603740236263367153145560
MinAvgMaxEPYC 8534PN - Zen 4C13.598.3134.6EPYC 8324PN - Zen 4C12.974.987.7EPYC 8324P - Zen 4C13.192.0126.7EPYC 8324P - Zen 4C, 155W13.785.9108.4EPYC 7601 - Zen 165.5157.3178.6OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 0.13CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 5601 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 6790 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 7451 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 7189 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 25952 Joules per run.

nginx

This is a benchmark of the lightweight Nginx HTTP(S) web-server. This Nginx web server benchmark test profile makes use of the wrk program for facilitating the HTTP requests over a fixed period time with a configurable number of concurrent clients/connections. HTTPS with a self-signed OpenSSL certificate is used by this test for local benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.23.2Connections: 1000EPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 150K100K150K200K250KSE +/- 302.03, N = 3SE +/- 199.18, N = 3SE +/- 343.16, N = 3SE +/- 49.01, N = 3SE +/- 357.56, N = 3232146.41139259.26166799.14151923.6290952.151. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
OpenBenchmarking.orgRequests Per Second Per Watt, More Is Betternginx 1.23.2Connections: 1000EPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 14008001200160020001785.711663.271365.651532.61540.03
MinAvgMaxEPYC 8534PN - Zen 4C13.4130.0141.7EPYC 8324PN - Zen 4C12.883.792.6EPYC 8324P - Zen 4C12.3122.1134.6EPYC 8324P - Zen 4C, 155W13.599.1113.1EPYC 7601 - Zen 163.9168.4177.8OpenBenchmarking.orgWatts, Fewer Is Betternginx 1.23.2CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 12610 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 8149 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 11807 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 9582 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 16337 Joules per run.

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.23.2Connections: 500EPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 150K100K150K200K250KSE +/- 217.83, N = 3SE +/- 213.01, N = 3SE +/- 549.43, N = 3SE +/- 1108.21, N = 3SE +/- 911.83, N = 3229161.91136660.96164234.98149458.3494936.991. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2
OpenBenchmarking.orgRequests Per Second Per Watt, More Is Betternginx 1.23.2Connections: 500EPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 14008001200160020001802.111656.121355.861536.38561.58
MinAvgMaxEPYC 8534PN - Zen 4C12.6127.2140.0EPYC 8324PN - Zen 4C11.782.591.8EPYC 8324P - Zen 4C11.6121.1132.4EPYC 8324P - Zen 4C, 155W12.997.3110.2EPYC 7601 - Zen 160.9169.1178.8OpenBenchmarking.orgWatts, Fewer Is Betternginx 1.23.2CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 12335 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 8004 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 11750 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 9436 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 16398 Joules per run.

Neural Magic DeepSparse

This is a benchmark of Neural Magic's DeepSparse using its built-in deepsparse.benchmark utility and various models from their SparseZoo (https://sparsezoo.neuralmagic.com/). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-StreamEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 130060090012001500SE +/- 0.25, N = 3SE +/- 0.30, N = 3SE +/- 0.30, N = 3SE +/- 0.27, N = 3SE +/- 8.56, N = 3776.54722.10611.15647.891289.82
MinAvgMaxEPYC 8534PN - Zen 4C13.780.1127.4EPYC 8324PN - Zen 4C12.860.386.0EPYC 8324P - Zen 4C12.171.4119.7EPYC 8324P - Zen 4C, 155W13.267.0108.3EPYC 7601 - Zen 164.8109.6177.6OpenBenchmarking.orgWatts, Fewer Is BetterNeural Magic DeepSparse 1.6CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 6834 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 5248 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 6215 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 5783 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 12090 Joules per run.

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-StreamEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1918273645SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.13, N = 340.6421.9125.8424.4712.22

OSPRay Studio

Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.13Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPUEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 12K4K6K8K10KSE +/- 0.88, N = 3SE +/- 2.03, N = 3SE +/- 1.33, N = 3SE +/- 2.31, N = 3SE +/- 27.62, N = 3254450044152449310054
MinAvgMaxEPYC 8534PN - Zen 4C12.7108.6136.1EPYC 8324PN - Zen 4C12.574.589.2EPYC 8324P - Zen 4C12.096.2122.4EPYC 8324P - Zen 4C, 155W13.786.0105.2EPYC 7601 - Zen 165.8144.5178.8OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 0.13CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 8762 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 6581 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 8209 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 7421 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 14644 Joules per run.

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.13Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPUEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 12K4K6K8K10KSE +/- 1.20, N = 3SE +/- 0.88, N = 3SE +/- 2.31, N = 3SE +/- 1.76, N = 3SE +/- 15.18, N = 321464222349337878452
MinAvgMaxEPYC 8534PN - Zen 4C13.5106.9135.0EPYC 8324PN - Zen 4C12.773.988.3EPYC 8324P - Zen 4C13.194.5126.4EPYC 8324P - Zen 4C, 155W13.685.3105.7EPYC 7601 - Zen 165.3144.1178.5OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 0.13CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 8377 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 6407 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 7879 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 7140 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 14264 Joules per run.

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Handwritten English Recognition FP16-INT8 - Device: CPUEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 14080120160200SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.47, N = 8SE +/- 0.68, N = 358.7857.5046.3951.41169.21MIN: 36.54 / MAX: 118.54MIN: 36.68 / MAX: 102.88MIN: 30.48 / MAX: 56.26MIN: 31.75 / MAX: 122.86MIN: 140.86 / MAX: 197.951. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
MinAvgMaxEPYC 8534PN - Zen 4C14.7129.3140.0EPYC 8324PN - Zen 4C12.380.789.5EPYC 8324P - Zen 4C12.4106.7121.1EPYC 8324P - Zen 4C, 155W12.795.9108.8EPYC 7601 - Zen 164.7168.1177.3OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2023.2.devCPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 8320 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 5243 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 6901 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 6187 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 10981 Joules per run.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Handwritten English Recognition FP16-INT8 - Device: CPUEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 12004006008001000SE +/- 0.42, N = 3SE +/- 0.39, N = 3SE +/- 0.64, N = 3SE +/- 5.36, N = 8SE +/- 0.74, N = 31086.68555.71688.60621.82188.861. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

Chaos Group V-RAY

This is a test of Chaos Group's V-RAY benchmark. V-RAY is a commercial renderer that can integrate with various creator software products like SketchUp and 3ds Max. The V-RAY benchmark is standalone and supports CPU and NVIDIA CUDA/RTX based rendering. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgvsamples, More Is BetterChaos Group V-RAY 5.02Mode: CPUEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 112K24K36K48K60KSE +/- 123.39, N = 3SE +/- 326.21, N = 3SE +/- 277.30, N = 3SE +/- 150.82, N = 3SE +/- 105.66, N = 35420428177335103153619914
OpenBenchmarking.orgvsamples Per Watt, More Is BetterChaos Group V-RAY 5.02Mode: CPUEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1110220330440550487.44377.52351.76361.93136.76
MinAvgMaxEPYC 8534PN - Zen 4C13.7111.2137.4EPYC 8324PN - Zen 4C12.274.691.5EPYC 8324P - Zen 4C12.995.3122.0EPYC 8324P - Zen 4C, 155W13.587.1106.2EPYC 7601 - Zen 164.1145.6179.2OpenBenchmarking.orgWatts, Fewer Is BetterChaos Group V-RAY 5.02CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 9341 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 6269 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 8002 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 7319 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 12814 Joules per run.

rav1e

Xiph rav1e is a Rust-written AV1 video encoder that claims to be the fastest and safest AV1 encoder. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.7Speed: 10EPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 13691215SE +/- 0.125, N = 5SE +/- 0.146, N = 4SE +/- 0.141, N = 4SE +/- 0.138, N = 4SE +/- 0.075, N = 412.18611.82411.79011.8186.995
OpenBenchmarking.orgFrames Per Second Per Watt, More Is Betterrav1e 0.7Speed: 10EPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 10.05090.10180.15270.20360.25450.2230.2260.2220.2210.079
MinAvgMaxEPYC 8534PN - Zen 4C12.954.659.0EPYC 8324PN - Zen 4C12.252.356.9EPYC 8324P - Zen 4C12.653.158.3EPYC 8324P - Zen 4C, 155W13.353.658.5EPYC 7601 - Zen 145.588.596.7OpenBenchmarking.orgWatts, Fewer Is Betterrav1e 0.7CPU Power Consumption Monitor204060801001. EPYC 8534PN - Zen 4C: Approximate power consumption of 2907 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 2878 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 2918 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 2973 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 7946 Joules per run.

QuantLib

QuantLib is an open-source library/framework around quantitative finance for modeling, trading and risk management scenarios. QuantLib is written in C++ with Boost and its built-in benchmark used reports the QuantLib Benchmark Index benchmark score. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMFLOPS, More Is BetterQuantLib 1.32Configuration: Multi-ThreadedEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 130K60K90K120K150KSE +/- 29.72, N = 3SE +/- 122.23, N = 3SE +/- 60.04, N = 3SE +/- 100.68, N = 3SE +/- 165.76, N = 3154830.980175.398717.290654.164469.41. (CXX) g++ options: -O3 -march=native -fPIE -pie
OpenBenchmarking.orgMFLOPS Per Watt, More Is BetterQuantLib 1.32Configuration: Multi-ThreadedEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1300600900120015001273.591007.58945.62967.97384.04
MinAvgMaxEPYC 8534PN - Zen 4C12.5121.6136.3EPYC 8324PN - Zen 4C12.579.695.3EPYC 8324P - Zen 4C12.8104.4122.9EPYC 8324P - Zen 4C, 155W13.393.7108.8EPYC 7601 - Zen 164.3167.9179.0OpenBenchmarking.orgWatts, Fewer Is BetterQuantLib 1.32CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 10455 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 6658 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 7238 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 6962 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 17235 Joules per run.

FFmpeg

This is a benchmark of the FFmpeg multimedia framework. The FFmpeg test profile is making use of a modified version of vbench from Columbia University's Architecture and Design Lab (ARCADE) [http://arcade.cs.columbia.edu/vbench/] that is a benchmark for video-as-a-service workloads. The test profile offers the options of a range of vbench scenarios based on freely distributable video content and offers the options of using the x264 or x265 video encoders for transcoding. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: LiveEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1306090120150SE +/- 0.20, N = 3SE +/- 0.17, N = 3SE +/- 0.30, N = 3SE +/- 0.31, N = 3SE +/- 0.11, N = 3115.11109.77109.84109.7158.091. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFPS Per Watt, More Is BetterFFmpeg 6.1Encoder: libx265 - Scenario: LiveEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 10.4590.9181.3771.8362.2952.0052.0401.9881.9770.704
MinAvgMaxEPYC 8534PN - Zen 4C13.257.478.9EPYC 8324PN - Zen 4C12.353.871.4EPYC 8324P - Zen 4C12.055.274.9EPYC 8324P - Zen 4C, 155W13.555.574.6EPYC 7601 - Zen 164.082.5112.1OpenBenchmarking.orgWatts, Fewer Is BetterFFmpeg 6.1CPU Power Consumption Monitor40801201602001. EPYC 8534PN - Zen 4C: Approximate power consumption of 4037 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 3963 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 4052 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 4107 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 10012 Joules per run.

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 16 - Model: ResNet-50EPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 11224364860SE +/- 0.03, N = 3SE +/- 0.09, N = 3SE +/- 0.08, N = 3SE +/- 0.04, N = 3SE +/- 0.07, N = 348.5647.7751.7051.038.77
OpenBenchmarking.orgimages/sec Per Watt, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 16 - Model: ResNet-50EPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 10.13140.26280.39420.52560.6570.5190.5840.5530.5510.068
MinAvgMaxEPYC 8534PN - Zen 4C13.093.6109.8EPYC 8324PN - Zen 4C6.781.997.1EPYC 8324P - Zen 4C13.093.5112.6EPYC 8324P - Zen 4C, 155W13.292.6109.9EPYC 7601 - Zen 164.2129.4142.8OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow 2.12CPU Power Consumption Monitor40801201602001. EPYC 8534PN - Zen 4C: Approximate power consumption of 4273 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 3792 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 4084 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 4075 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 27515 Joules per run.

CloverLeaf

CloverLeaf is a Lagrangian-Eulerian hydrodynamics benchmark. This test profile currently makes use of CloverLeaf's OpenMP version. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterCloverLeaf 1.3Input: clover_bm64_shortEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 120406080100SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.18, N = 357.4257.5256.9157.04106.271. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp
MinAvgMaxEPYC 8534PN - Zen 4C13.5115.8126.2EPYC 8324PN - Zen 4C12.691.099.0EPYC 8324P - Zen 4C13.099.2108.3EPYC 8324P - Zen 4C, 155W13.798.3107.3EPYC 7601 - Zen 166.3146.4160.4OpenBenchmarking.orgWatts, Fewer Is BetterCloverLeaf 1.3CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 7335 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 5736 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 6217 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 6162 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 16396 Joules per run.

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: Fishy Cat - Compute: CPU-OnlyEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 120406080100SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.04, N = 3SE +/- 0.06, N = 3SE +/- 0.14, N = 338.6672.9659.6465.03101.10
MinAvgMaxEPYC 8534PN - Zen 4C14.4119.8137.2EPYC 8324PN - Zen 4C12.882.793.6EPYC 8324P - Zen 4C12.7108.0124.1EPYC 8324P - Zen 4C, 155W14.096.7106.3EPYC 7601 - Zen 165.7170.3178.6OpenBenchmarking.orgWatts, Fewer Is BetterBlender 4.0CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 5231 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 6447 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 6981 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 6772 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 18055 Joules per run.

IndigoBench

This is a test of Indigo Renderer's IndigoBench benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: CPU - Scene: BedroomEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 13691215SE +/- 0.011, N = 3SE +/- 0.010, N = 3SE +/- 0.021, N = 3SE +/- 0.013, N = 3SE +/- 0.010, N = 39.9735.1276.1775.7203.985
OpenBenchmarking.orgM samples/s Per Watt, More Is BetterIndigoBench 4.4Acceleration: CPU - Scene: BedroomEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 10.02210.04420.06630.08840.11050.0980.0610.0550.0580.024
MinAvgMaxEPYC 8534PN - Zen 4C7.0101.7142.9EPYC 8324PN - Zen 4C12.483.691.8EPYC 8324P - Zen 4C13.3112.5129.6EPYC 8324P - Zen 4C, 155W13.898.9111.2EPYC 7601 - Zen 165.4165.8179.2OpenBenchmarking.orgWatts, Fewer Is BetterIndigoBench 4.4CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 8980 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 5571 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 7461 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 6526 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 11333 Joules per run.

Redis 7.0.12 + memtier_benchmark

Memtier_benchmark is a NoSQL Redis/Memcache traffic generation plus benchmarking tool developed by Redis Labs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is BetterRedis 7.0.12 + memtier_benchmark 2.0Protocol: Redis - Clients: 100 - Set To Get Ratio: 1:10EPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1600K1200K1800K2400K3000KSE +/- 20726.56, N = 3SE +/- 11338.77, N = 3SE +/- 3585.70, N = 3SE +/- 16343.62, N = 3SE +/- 10214.62, N = 32568868.492562876.162842511.462789711.341277853.471. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.orgOps/sec Per Watt, More Is BetterRedis 7.0.12 + memtier_benchmark 2.0Protocol: Redis - Clients: 100 - Set To Get Ratio: 1:10EPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 19K18K27K36K45K28227.2541473.4632673.7937066.257946.04
MinAvgMaxEPYC 8534PN - Zen 4C13.591.0106.9EPYC 8324PN - Zen 4C11.361.876.7EPYC 8324P - Zen 4C11.287.099.1EPYC 8324P - Zen 4C, 155W13.675.393.2EPYC 7601 - Zen 164.4160.8178.4OpenBenchmarking.orgWatts, Fewer Is BetterRedis 7.0.12 + memtier_benchmark 2.0CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 6492 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 4367 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 6119 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 5369 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 11418 Joules per run.

OpenBenchmarking.orgOps/sec, More Is BetterRedis 7.0.12 + memtier_benchmark 2.0Protocol: Redis - Clients: 100 - Set To Get Ratio: 1:5EPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1600K1200K1800K2400K3000KSE +/- 10691.43, N = 3SE +/- 18767.16, N = 3SE +/- 10431.24, N = 3SE +/- 15002.29, N = 3SE +/- 11184.62, N = 32513019.322500035.092795965.052720321.301159654.331. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.orgOps/sec Per Watt, More Is BetterRedis 7.0.12 + memtier_benchmark 2.0Protocol: Redis - Clients: 100 - Set To Get Ratio: 1:5EPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 19K18K27K36K45K27624.5339908.9132252.2836173.127148.89
MinAvgMaxEPYC 8534PN - Zen 4C12.391.0105.2EPYC 8324PN - Zen 4C12.362.675.6EPYC 8324P - Zen 4C12.086.799.3EPYC 8324P - Zen 4C, 155W13.475.293.2EPYC 7601 - Zen 166.5162.2178.4OpenBenchmarking.orgWatts, Fewer Is BetterRedis 7.0.12 + memtier_benchmark 2.0CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 6489 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 4427 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 6126 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 5289 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 11409 Joules per run.

VVenC

VVenC is the Fraunhofer Versatile Video Encoder as a fast/efficient H.266/VVC encoder. The vvenc encoder makes use of SIMD Everywhere (SIMDe). The vvenc software is published under the Clear BSD License. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.9Video Input: Bosphorus 4K - Video Preset: FasterEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 13691215SE +/- 0.012, N = 3SE +/- 0.030, N = 3SE +/- 0.010, N = 3SE +/- 0.030, N = 3SE +/- 0.044, N = 311.27210.29110.74110.6356.3581. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterVVenC 1.9Video Input: Bosphorus 4K - Video Preset: FasterEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 10.03560.07120.10680.14240.1780.1580.1470.1340.1350.049
MinAvgMaxEPYC 8534PN - Zen 4C13.071.1115.0EPYC 8324PN - Zen 4C12.969.889.3EPYC 8324P - Zen 4C11.880.4107.5EPYC 8324P - Zen 4C, 155W13.178.7103.8EPYC 7601 - Zen 164.8129.1162.9OpenBenchmarking.orgWatts, Fewer Is BetterVVenC 1.9CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 5263 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 4493 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 4987 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 4905 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 12997 Joules per run.

easyWave

The easyWave software allows simulating tsunami generation and propagation in the context of early warning systems. EasyWave supports making use of OpenMP for CPU multi-threading and there are also GPU ports available but not currently incorporated as part of this test profile. The easyWave tsunami generation software is run with one of the example/reference input files for measuring the CPU execution time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BettereasyWave r34Input: e2Asean Grid + BengkuluSept2007 Source - Time: 1200EPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1306090120150SE +/- 0.50, N = 3SE +/- 0.10, N = 3SE +/- 0.17, N = 3SE +/- 0.18, N = 3SE +/- 1.85, N = 339.3342.2642.0942.00152.341. (CXX) g++ options: -O3 -fopenmp
MinAvgMaxEPYC 8534PN - Zen 4C13.385.8104.1EPYC 8324PN - Zen 4C12.473.083.8EPYC 8324P - Zen 4C12.179.390.5EPYC 8324P - Zen 4C, 155W13.778.790.5EPYC 7601 - Zen 165.8131.1148.5OpenBenchmarking.orgWatts, Fewer Is BettereasyWave r34CPU Power Consumption Monitor40801201602001. EPYC 8534PN - Zen 4C: Approximate power consumption of 3919 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 3528 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 3808 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 3778 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 20887 Joules per run.

Quicksilver

Quicksilver is a proxy application that represents some elements of the Mercury workload by solving a simplified dynamic Monte Carlo particle transport problem. Quicksilver is developed by Lawrence Livermore National Laboratory (LLNL) and this test profile currently makes use of the OpenMP CPU threaded code path. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFigure Of Merit, More Is BetterQuicksilver 20230818Input: CORAL2 P1EPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 15M10M15M20M25MSE +/- 18559.21, N = 3SE +/- 24037.01, N = 3SE +/- 66583.28, N = 3SE +/- 106926.77, N = 3SE +/- 105830.05, N = 321233333182733331888000018950000130300001. (CXX) g++ options: -fopenmp -O3 -march=native
OpenBenchmarking.orgFigure Of Merit Per Watt, More Is BetterQuicksilver 20230818Input: CORAL2 P1EPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 150K100K150K200K250K195063.32243826.72208439.28208244.5987231.32
MinAvgMaxEPYC 8534PN - Zen 4C12.3108.9118.9EPYC 8324PN - Zen 4C12.574.988.5EPYC 8324P - Zen 4C13.290.697.7EPYC 8324P - Zen 4C, 155W14.091.098.6EPYC 7601 - Zen 165.4149.4162.5OpenBenchmarking.orgWatts, Fewer Is BetterQuicksilver 20230818CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 6350 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 5021 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 5857 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 5885 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 13792 Joules per run.

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Face Detection FP16-INT8 - Device: CPUEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1400800120016002000SE +/- 0.12, N = 3SE +/- 0.08, N = 3SE +/- 0.06, N = 3SE +/- 0.06, N = 3SE +/- 0.15, N = 3644.80627.46510.71558.292096.01MIN: 320.58 / MAX: 691.03MIN: 560 / MAX: 672.37MIN: 471.88 / MAX: 558.37MIN: 500.71 / MAX: 574MIN: 2092.33 / MAX: 2113.241. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
MinAvgMaxEPYC 8534PN - Zen 4C13.0120.2133.3EPYC 8324PN - Zen 4C12.878.589.0EPYC 8324P - Zen 4C13.3104.3122.2EPYC 8324P - Zen 4C, 155W13.294.1105.1EPYC 7601 - Zen 164.8149.2164.7OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2023.2.devCPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 8172 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 5365 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 7093 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 6369 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 10794 Joules per run.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Face Detection FP16-INT8 - Device: CPUEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 11122334455SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.00, N = 349.4325.4131.2528.583.811. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

IndigoBench

This is a test of Indigo Renderer's IndigoBench benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: CPU - Scene: SupercarEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1510152025SE +/- 0.020, N = 3SE +/- 0.010, N = 3SE +/- 0.058, N = 3SE +/- 0.005, N = 3SE +/- 0.024, N = 321.76711.24913.57312.5728.586
OpenBenchmarking.orgM samples/s Per Watt, More Is BetterIndigoBench 4.4Acceleration: CPU - Scene: SupercarEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 10.04370.08740.13110.17480.21850.1940.1370.1220.1300.051
MinAvgMaxEPYC 8534PN - Zen 4C13.4112.4140.3EPYC 8324PN - Zen 4C12.482.088.8EPYC 8324P - Zen 4C12.6111.0122.4EPYC 8324P - Zen 4C, 155W13.796.6108.8EPYC 7601 - Zen 164.9166.9178.8OpenBenchmarking.orgWatts, Fewer Is BetterIndigoBench 4.4CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 8581 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 5438 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 7327 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 6408 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 11070 Joules per run.

OSPRay

Intel OSPRay is a portable ray-tracing engine for high-performance, high-fidelity scientific visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.12Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_timeEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 148121620SE +/- 0.00619, N = 3SE +/- 0.00484, N = 3SE +/- 0.00075, N = 3SE +/- 0.00699, N = 3SE +/- 0.00520, N = 316.895408.8936110.493909.873734.14655
OpenBenchmarking.orgItems Per Second Per Watt, More Is BetterOSPRay 2.12Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_timeEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 10.0340.0680.1020.1360.170.1510.1190.1070.1130.026
MinAvgMaxEPYC 8534PN - Zen 4C14.2111.9133.3EPYC 8324PN - Zen 4C12.674.986.9EPYC 8324P - Zen 4C13.098.1122.1EPYC 8324P - Zen 4C, 155W13.787.1106.8EPYC 7601 - Zen 164.9158.4177.4OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay 2.12CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 6752 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 4995 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 6309 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 5692 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 13253 Joules per run.

PyTorch

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 256 - Model: ResNet-50EPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1918273645SE +/- 0.14, N = 3SE +/- 0.10, N = 3SE +/- 0.06, N = 3SE +/- 0.09, N = 3SE +/- 0.12, N = 336.2340.3640.5940.5420.48MIN: 14.59 / MAX: 36.98MIN: 18.81 / MAX: 40.93MIN: 14.97 / MAX: 41.27MIN: 14.7 / MAX: 41.23MIN: 11.38 / MAX: 21.17
OpenBenchmarking.orgbatches/sec Per Watt, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 256 - Model: ResNet-50EPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 10.12110.24220.36330.48440.60550.3890.5380.5270.5190.127
MinAvgMaxEPYC 8534PN - Zen 4C12.893.2106.3EPYC 8324PN - Zen 4C12.675.085.7EPYC 8324P - Zen 4C12.877.188.7EPYC 8324P - Zen 4C, 155W13.178.089.1EPYC 7601 - Zen 164.7161.6173.2OpenBenchmarking.orgWatts, Fewer Is BetterPyTorch 2.1CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 5841 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 4198 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 4265 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 4318 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 17186 Joules per run.

Speedb

Speedb is a next-generation key value storage engine that is RocksDB compatible and aiming for stability, efficiency, and performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Random ReadEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 150M100M150M200M250MSE +/- 139678.30, N = 3SE +/- 227689.47, N = 3SE +/- 141623.12, N = 3SE +/- 1751764.05, N = 3SE +/- 986396.38, N = 3248842616132248192163771762147991555859904451. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.orgOp/s Per Watt, More Is BetterSpeedb 2.7Test: Random ReadEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1500K1000K1500K2000K2500K2534080.331749308.711624547.011658329.33505924.53
MinAvgMaxEPYC 8534PN - Zen 4C13.198.2128.2EPYC 8324PN - Zen 4C12.875.686.1EPYC 8324P - Zen 4C13.1100.8111.0EPYC 8324P - Zen 4C, 155W13.789.297.6EPYC 7601 - Zen 165.6170.0178.3OpenBenchmarking.orgWatts, Fewer Is BetterSpeedb 2.7CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 7332 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 4864 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 6485 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 5711 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 10935 Joules per run.

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Person Detection FP16 - Device: CPUEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 14080120160200SE +/- 0.61, N = 3SE +/- 0.62, N = 3SE +/- 0.35, N = 3SE +/- 0.19, N = 3SE +/- 0.84, N = 3157.93121.74106.00110.77188.25MIN: 61.12 / MAX: 229.82MIN: 59.66 / MAX: 172.6MIN: 49.62 / MAX: 149.63MIN: 56.47 / MAX: 138.98MIN: 171.32 / MAX: 233.131. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
MinAvgMaxEPYC 8534PN - Zen 4C14.0135.5149.3EPYC 8324PN - Zen 4C13.087.099.0EPYC 8324P - Zen 4C13.0116.5130.1EPYC 8324P - Zen 4C, 155W13.5102.0112.3EPYC 7601 - Zen 164.8166.9177.2OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2023.2.devCPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 8940 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 5744 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 7569 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 6662 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 11014 Joules per run.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Person Detection FP16 - Device: CPUEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 14080120160200SE +/- 0.77, N = 3SE +/- 0.65, N = 3SE +/- 0.51, N = 3SE +/- 0.22, N = 3SE +/- 0.18, N = 3202.29131.24150.74144.2742.431. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Machine Translation EN To DE FP16 - Device: CPUEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 150100150200250SE +/- 0.19, N = 3SE +/- 0.04, N = 3SE +/- 0.07, N = 3SE +/- 0.02, N = 3SE +/- 0.83, N = 3108.0697.9182.0088.55206.72MIN: 53.32 / MAX: 156.54MIN: 52.76 / MAX: 116.94MIN: 44.77 / MAX: 103.78MIN: 48.33 / MAX: 138.85MIN: 173.41 / MAX: 362.841. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
MinAvgMaxEPYC 8534PN - Zen 4C14.5131.7146.8EPYC 8324PN - Zen 4C12.685.097.1EPYC 8324P - Zen 4C13.3113.1127.7EPYC 8324P - Zen 4C, 155W13.5101.9112.7EPYC 7601 - Zen 164.9165.7175.9OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2023.2.devCPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 8648 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 5607 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 7427 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 6625 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 10936 Joules per run.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Machine Translation EN To DE FP16 - Device: CPUEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 160120180240300SE +/- 0.54, N = 3SE +/- 0.05, N = 3SE +/- 0.19, N = 3SE +/- 0.04, N = 3SE +/- 0.16, N = 3295.61163.09194.71180.3238.631. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Person Vehicle Bike Detection FP16 - Device: CPUEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 148121620SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 312.4711.159.3410.1817.20MIN: 7.72 / MAX: 24.35MIN: 7.24 / MAX: 68.4MIN: 5.89 / MAX: 67.06MIN: 6.06 / MAX: 60MIN: 16.21 / MAX: 31.681. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
MinAvgMaxEPYC 8534PN - Zen 4C14.6123.5136.6EPYC 8324PN - Zen 4C12.682.188.2EPYC 8324P - Zen 4C13.3110.5119.3EPYC 8324P - Zen 4C, 155W13.598.0108.0EPYC 7601 - Zen 164.7165.9176.2OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2023.2.devCPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 8111 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 5337 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 7147 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 6400 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 10783 Joules per run.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Person Vehicle Bike Detection FP16 - Device: CPUEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 15001000150020002500SE +/- 2.30, N = 3SE +/- 1.32, N = 3SE +/- 1.86, N = 3SE +/- 1.13, N = 3SE +/- 1.37, N = 32547.731424.531701.181563.36464.481. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Road Segmentation ADAS FP16-INT8 - Device: CPUEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 11224364860SE +/- 0.13, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 334.1430.6925.2127.5653.64MIN: 18.62 / MAX: 101.35MIN: 17.73 / MAX: 77.96MIN: 14.47 / MAX: 81.04MIN: 15.77 / MAX: 72.29MIN: 52.65 / MAX: 65.911. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
MinAvgMaxEPYC 8534PN - Zen 4C13.5124.7135.8EPYC 8324PN - Zen 4C12.979.088.7EPYC 8324P - Zen 4C11.9104.0120.7EPYC 8324P - Zen 4C, 155W13.392.6106.0EPYC 7601 - Zen 165.0153.8166.6OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2023.2.devCPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 8149 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 5134 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 6757 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 6020 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 10046 Joules per run.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Road Segmentation ADAS FP16-INT8 - Device: CPUEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 12004006008001000SE +/- 3.62, N = 3SE +/- 0.24, N = 3SE +/- 0.09, N = 3SE +/- 0.14, N = 3SE +/- 0.05, N = 3934.59520.24633.21579.34149.011. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Face Detection Retail FP16-INT8 - Device: CPUEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 13691215SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 37.527.135.776.309.09MIN: 3.38 / MAX: 63.31MIN: 3.71 / MAX: 59.81MIN: 3.23 / MAX: 59.13MIN: 3.34 / MAX: 35.73MIN: 9.03 / MAX: 17.521. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
MinAvgMaxEPYC 8534PN - Zen 4C14.4126.6136.6EPYC 8324PN - Zen 4C12.280.189.9EPYC 8324P - Zen 4C12.9105.9120.6EPYC 8324P - Zen 4C, 155W13.294.2106.4EPYC 7601 - Zen 165.0151.0162.8OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2023.2.devCPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 8228 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 5204 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 6846 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 6122 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 9716 Joules per run.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Face Detection Retail FP16-INT8 - Device: CPUEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 12K4K6K8K10KSE +/- 9.00, N = 3SE +/- 1.85, N = 3SE +/- 1.73, N = 3SE +/- 1.37, N = 3SE +/- 0.47, N = 38310.714405.625418.924977.13878.711. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Vehicle Detection FP16-INT8 - Device: CPUEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1612182430SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 311.2410.398.529.2926.96MIN: 6.13 / MAX: 91.04MIN: 6.01 / MAX: 19.76MIN: 4.86 / MAX: 58.62MIN: 5.21 / MAX: 64.17MIN: 26.82 / MAX: 36.461. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
MinAvgMaxEPYC 8534PN - Zen 4C14.6128.8140.9EPYC 8324PN - Zen 4C12.980.690.1EPYC 8324P - Zen 4C12.7106.6124.5EPYC 8324P - Zen 4C, 155W13.594.2105.1EPYC 7601 - Zen 164.6153.2165.8OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2023.2.devCPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 8326 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 5237 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 6890 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 6091 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 9909 Joules per run.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Vehicle Detection FP16-INT8 - Device: CPUEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 16001200180024003000SE +/- 0.56, N = 3SE +/- 1.22, N = 3SE +/- 0.21, N = 3SE +/- 0.65, N = 3SE +/- 0.10, N = 32816.091527.321860.651710.42296.421. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OSPRay

Intel OSPRay is a portable ray-tracing engine for high-performance, high-fidelity scientific visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.12Benchmark: gravity_spheres_volume/dim_512/scivis/real_timeEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 148121620SE +/- 0.00073, N = 3SE +/- 0.01310, N = 3SE +/- 0.01463, N = 3SE +/- 0.02613, N = 3SE +/- 0.01198, N = 314.613107.665328.836228.456342.45276
OpenBenchmarking.orgItems Per Second Per Watt, More Is BetterOSPRay 2.12Benchmark: gravity_spheres_volume/dim_512/scivis/real_timeEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 10.02930.05860.08790.11720.14650.1300.1010.0830.0950.016
MinAvgMaxEPYC 8534PN - Zen 4C13.8112.7134.3EPYC 8324PN - Zen 4C12.475.589.1EPYC 8324P - Zen 4C11.4106.4122.1EPYC 8324P - Zen 4C, 155W13.789.2107.3EPYC 7601 - Zen 165.1155.2177.3OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay 2.12CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 6910 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 5186 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 7092 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 5979 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 9159 Joules per run.

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 10.5491.0981.6472.1962.745SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.610.570.470.512.44MIN: 0.27 / MAX: 24.31MIN: 0.29 / MAX: 15.45MIN: 0.27 / MAX: 11.17MIN: 0.28 / MAX: 50.42MIN: 2.39 / MAX: 9.341. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
MinAvgMaxEPYC 8534PN - Zen 4C13.5120.8131.1EPYC 8324PN - Zen 4C13.079.789.2EPYC 8324P - Zen 4C11.7108.3128.7EPYC 8324P - Zen 4C, 155W13.095.1107.0EPYC 7601 - Zen 164.4158.2170.3OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2023.2.devCPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 7852 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 5130 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 7003 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 6152 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 10126 Joules per run.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 115K30K45K60K75KSE +/- 93.27, N = 3SE +/- 33.66, N = 3SE +/- 23.70, N = 3SE +/- 37.85, N = 3SE +/- 8.89, N = 371960.4143375.5552709.1949194.5513039.701. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Weld Porosity Detection FP16-INT8 - Device: CPUEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 120406080100SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 312.9712.5810.2011.1284.77MIN: 6.18 / MAX: 27.89MIN: 6.69 / MAX: 66.41MIN: 5.92 / MAX: 71.44MIN: 76.49 / MAX: 98.51. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
MinAvgMaxEPYC 8534PN - Zen 4C14.7123.5133.3EPYC 8324PN - Zen 4C12.179.589.5EPYC 8324P - Zen 4C13.4105.0123.3EPYC 8324P - Zen 4C, 155W13.093.2104.2EPYC 7601 - Zen 165.0150.9163.1OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2023.2.devCPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 7942 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 5142 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 6755 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 5997 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 9760 Joules per run.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Weld Porosity Detection FP16-INT8 - Device: CPUEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 110002000300040005000SE +/- 1.98, N = 3SE +/- 0.51, N = 3SE +/- 0.48, N = 3SE +/- 0.72, N = 3SE +/- 0.03, N = 34878.002520.773102.132851.01376.971. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

Speedb

Speedb is a next-generation key value storage engine that is RocksDB compatible and aiming for stability, efficiency, and performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Read Random Write RandomEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1500K1000K1500K2000K2500KSE +/- 2240.30, N = 3SE +/- 1833.01, N = 3SE +/- 3849.48, N = 3SE +/- 1300.80, N = 3SE +/- 4528.27, N = 3227202619822572233744213331114478191. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.orgOp/s Per Watt, More Is BetterSpeedb 2.7Test: Read Random Write RandomEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 16K12K18K24K30K20292.3625808.6820899.6322326.899121.91
MinAvgMaxEPYC 8534PN - Zen 4C14.1112.0127.0EPYC 8324PN - Zen 4C12.276.890.2EPYC 8324P - Zen 4C13.1106.9119.8EPYC 8324P - Zen 4C, 155W13.795.5110.7EPYC 7601 - Zen 165.3158.7177.5OpenBenchmarking.orgWatts, Fewer Is BetterSpeedb 2.7CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 7240 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 4967 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 6876 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 6115 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 10264 Joules per run.

Timed Linux Kernel Compilation

This test times how long it takes to build the Linux kernel in a default configuration (defconfig) for the architecture being tested or alternatively an allmodconfig for building all possible kernel modules for the build. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.1Build: defconfigEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 120406080100SE +/- 0.52, N = 4SE +/- 0.71, N = 3SE +/- 0.71, N = 3SE +/- 0.67, N = 3SE +/- 0.84, N = 344.4258.5252.1454.8076.20
MinAvgMaxEPYC 8534PN - Zen 4C13.580.7135.1EPYC 8324PN - Zen 4C12.666.390.0EPYC 8324P - Zen 4C13.078.5123.4EPYC 8324P - Zen 4C, 155W13.574.0109.8EPYC 7601 - Zen 163.8131.7179.3OpenBenchmarking.orgWatts, Fewer Is BetterTimed Linux Kernel Compilation 6.1CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 4460 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 4704 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 5047 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 4930 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 11812 Joules per run.

OSPRay

Intel OSPRay is a portable ray-tracing engine for high-performance, high-fidelity scientific visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.12Benchmark: gravity_spheres_volume/dim_512/ao/real_timeEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 148121620SE +/- 0.01491, N = 3SE +/- 0.02953, N = 3SE +/- 0.02105, N = 3SE +/- 0.02664, N = 3SE +/- 0.00308, N = 315.059607.979109.142578.788982.59961
OpenBenchmarking.orgItems Per Second Per Watt, More Is BetterOSPRay 2.12Benchmark: gravity_spheres_volume/dim_512/ao/real_timeEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 10.03020.06040.09060.12080.1510.1340.1060.0860.0990.017
MinAvgMaxEPYC 8534PN - Zen 4C13.7112.5134.5EPYC 8324PN - Zen 4C13.175.389.0EPYC 8324P - Zen 4C13.5105.7121.6EPYC 8324P - Zen 4C, 155W13.788.9106.3EPYC 7601 - Zen 165.9154.5177.4OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay 2.12CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 6900 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 5149 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 7013 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 5958 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 9066 Joules per run.

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgverify/s, More Is BetterOpenSSL 3.1Algorithm: RSA4096EPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1200K400K600K800K1000KSE +/- 136.41, N = 3SE +/- 22.57, N = 3SE +/- 61.89, N = 3SE +/- 30.98, N = 3SE +/- 714.27, N = 3828697.4430171.6457516.3457514.1292445.31. (CC) gcc options: -pthread -m64 -O3 -ldl
OpenBenchmarking.orgverify/s Per Watt, More Is BetterOpenSSL 3.1Algorithm: RSA4096EPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1150030004500600075007110.605622.234477.075076.371719.96
MinAvgMaxEPYC 8534PN - Zen 4C14.6116.5129.4EPYC 8324PN - Zen 4C12.276.583.6EPYC 8324P - Zen 4C13.4102.2116.0EPYC 8324P - Zen 4C, 155W13.790.1102.2EPYC 7601 - Zen 165.7170.0178.2OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 3.1CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 7498 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 4897 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 6574 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 5798 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 10825 Joules per run.

OpenBenchmarking.orgsign/s, More Is BetterOpenSSL 3.1Algorithm: RSA4096EPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 15K10K15K20K25KSE +/- 4.13, N = 3SE +/- 3.00, N = 3SE +/- 2.49, N = 3SE +/- 3.08, N = 3SE +/- 12.09, N = 321064.111909.215040.713565.84497.11. (CC) gcc options: -pthread -m64 -O3 -ldl

RocksDB

This is a benchmark of Meta/Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 8.0Test: Random ReadEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 150M100M150M200M250MSE +/- 187915.38, N = 3SE +/- 242981.96, N = 3SE +/- 126210.06, N = 3SE +/- 294601.47, N = 3SE +/- 709803.02, N = 3248969387131206830161678876147721769846164081. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.orgOp/s Per Watt, More Is BetterRocksDB 8.0Test: Random ReadEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1500K1000K1500K2000K2500K2230797.091742913.891613507.121652219.58499648.82
MinAvgMaxEPYC 8534PN - Zen 4C12.8111.6129.8EPYC 8324PN - Zen 4C12.775.380.3EPYC 8324P - Zen 4C12.6100.2110.8EPYC 8324P - Zen 4C, 155W13.689.496.6EPYC 7601 - Zen 166.2169.4178.6OpenBenchmarking.orgWatts, Fewer Is BetterRocksDB 8.0CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 7143 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 4818 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 6413 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 5722 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 10895 Joules per run.

Xmrig

Xmrig is an open-source cross-platform CPU/GPU miner for RandomX, KawPow, CryptoNight and AstroBWT. This test profile is setup to measure the Xmrig CPU mining performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: Wownero - Hash Count: 1MEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 18K16K24K32K40KSE +/- 47.09, N = 3SE +/- 107.46, N = 3SE +/- 52.06, N = 3SE +/- 6.52, N = 3SE +/- 120.26, N = 335370.021769.225644.324096.29331.61. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenBenchmarking.orgH/s Per Watt, More Is BetterXmrig 6.21Variant: Wownero - Hash Count: 1MEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 160120180240300265.91247.53219.80233.1057.58
MinAvgMaxEPYC 8534PN - Zen 4C14.3133.0154.3EPYC 8324PN - Zen 4C13.187.995.9EPYC 8324P - Zen 4C13.3116.4133.1EPYC 8324P - Zen 4C, 155W12.8103.4113.7EPYC 7601 - Zen 165.7162.1172.1OpenBenchmarking.orgWatts, Fewer Is BetterXmrig 6.21CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 4478 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 4544 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 5198 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 4859 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 18801 Joules per run.

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: BMW27 - Compute: CPU-OnlyEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 11632486480SE +/- 0.04, N = 3SE +/- 0.06, N = 3SE +/- 0.13, N = 3SE +/- 0.15, N = 3SE +/- 0.20, N = 330.5758.2047.5052.0272.43
MinAvgMaxEPYC 8534PN - Zen 4C14.5114.5132.8EPYC 8324PN - Zen 4C12.980.091.2EPYC 8324P - Zen 4C13.0104.0116.7EPYC 8324P - Zen 4C, 155W13.995.1107.1EPYC 7601 - Zen 165.7169.3178.5OpenBenchmarking.orgWatts, Fewer Is BetterBlender 4.0CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 4083 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 5013 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 5406 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 5389 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 13036 Joules per run.

Neural Magic DeepSparse

This is a benchmark of Neural Magic's DeepSparse using its built-in deepsparse.benchmark utility and various models from their SparseZoo (https://sparsezoo.neuralmagic.com/). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-StreamEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 11428425670SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.70, N = 324.8223.6919.5321.2464.80
MinAvgMaxEPYC 8534PN - Zen 4C13.279.6118.6EPYC 8324PN - Zen 4C12.664.682.1EPYC 8324P - Zen 4C12.181.3112.8EPYC 8324P - Zen 4C, 155W13.473.797.1EPYC 7601 - Zen 164.8139.0177.3OpenBenchmarking.orgWatts, Fewer Is BetterNeural Magic DeepSparse 1.6CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 4911 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 3357 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 4226 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 3831 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 8343 Joules per run.

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-StreamEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 130060090012001500SE +/- 0.39, N = 3SE +/- 0.29, N = 3SE +/- 1.14, N = 3SE +/- 0.55, N = 3SE +/- 2.58, N = 31287.88674.93818.31752.59246.64

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-StreamEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 130060090012001500SE +/- 0.18, N = 3SE +/- 0.38, N = 3SE +/- 1.08, N = 3SE +/- 1.07, N = 3SE +/- 7.41, N = 3982.61892.10751.62803.821501.61
MinAvgMaxEPYC 8534PN - Zen 4C13.386.8132.4EPYC 8324PN - Zen 4C12.569.484.7EPYC 8324P - Zen 4C12.189.9119.5EPYC 8324P - Zen 4C, 155W13.180.9105.1EPYC 7601 - Zen 164.7140.6177.4OpenBenchmarking.orgWatts, Fewer Is BetterNeural Magic DeepSparse 1.6CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 5237 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 3517 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 4467 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 4071 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 8155 Joules per run.

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-StreamEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1714212835SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.07, N = 3SE +/- 0.05, N = 3SE +/- 0.08, N = 332.1617.7621.0219.6410.45

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-StreamEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1306090120150SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.18, N = 3SE +/- 0.15, N = 3SE +/- 1.37, N = 352.1249.8041.6444.72124.09
MinAvgMaxEPYC 8534PN - Zen 4C11.892.3120.3EPYC 8324PN - Zen 4C12.764.980.5EPYC 8324P - Zen 4C12.881.7112.7EPYC 8324P - Zen 4C, 155W13.074.196.2EPYC 7601 - Zen 165.2138.7176.8OpenBenchmarking.orgWatts, Fewer Is BetterNeural Magic DeepSparse 1.6CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 4648 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 3290 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 4141 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 3754 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 8228 Joules per run.

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-StreamEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1130260390520650SE +/- 0.38, N = 3SE +/- 0.28, N = 3SE +/- 1.61, N = 3SE +/- 1.23, N = 3SE +/- 1.39, N = 3613.23320.86383.70357.30128.67

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-StreamEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 130060090012001500SE +/- 0.09, N = 3SE +/- 0.79, N = 3SE +/- 1.23, N = 3SE +/- 0.47, N = 3SE +/- 0.89, N = 3982.33894.20752.51801.191515.68
MinAvgMaxEPYC 8534PN - Zen 4C13.5101.9133.4EPYC 8324PN - Zen 4C12.569.789.0EPYC 8324P - Zen 4C11.888.8121.7EPYC 8324P - Zen 4C, 155W13.280.1102.2EPYC 7601 - Zen 165.5140.7177.7OpenBenchmarking.orgWatts, Fewer Is BetterNeural Magic DeepSparse 1.6CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 5128 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 3506 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 4497 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 4088 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 8206 Joules per run.

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-StreamEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1714212835SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 332.1517.6721.0019.7510.34

rav1e

Xiph rav1e is a Rust-written AV1 video encoder that claims to be the fastest and safest AV1 encoder. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.7Speed: 6EPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 11.09532.19063.28594.38125.4765SE +/- 0.006, N = 3SE +/- 0.017, N = 3SE +/- 0.003, N = 3SE +/- 0.014, N = 3SE +/- 0.020, N = 34.8684.7274.7064.7312.963
OpenBenchmarking.orgFrames Per Second Per Watt, More Is Betterrav1e 0.7Speed: 6EPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 10.02030.04060.06090.08120.10150.0900.0900.0890.0880.032
MinAvgMaxEPYC 8534PN - Zen 4C12.254.261.9EPYC 8324PN - Zen 4C12.752.459.7EPYC 8324P - Zen 4C12.553.160.2EPYC 8324P - Zen 4C, 155W13.354.061.3EPYC 7601 - Zen 165.793.2104.7OpenBenchmarking.orgWatts, Fewer Is Betterrav1e 0.7CPU Power Consumption Monitor204060801001. EPYC 8534PN - Zen 4C: Approximate power consumption of 2456 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 2444 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 2477 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 2504 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 6714 Joules per run.

ACES DGEMM

This is a multi-threaded DGEMM benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOP/s, More Is BetterACES DGEMM 1.0Sustained Floating-Point RateEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1510152025SE +/- 0.111892, N = 5SE +/- 0.073791, N = 3SE +/- 0.076181, N = 15SE +/- 0.135732, N = 3SE +/- 0.031226, N = 321.13881911.51727211.64561611.4348493.8867761. (CC) gcc options: -O3 -march=native -fopenmp
OpenBenchmarking.orgGFLOP/s Per Watt, More Is BetterACES DGEMM 1.0Sustained Floating-Point RateEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 10.0540.1080.1620.2160.270.2400.1700.1330.1400.025
MinAvgMaxEPYC 8534PN - Zen 4C12.988.1130.7EPYC 8324PN - Zen 4C12.667.989.1EPYC 8324P - Zen 4C12.387.3115.0EPYC 8324P - Zen 4C, 155W13.581.5109.9EPYC 7601 - Zen 164.6154.9170.2OpenBenchmarking.orgWatts, Fewer Is BetterACES DGEMM 1.0CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 1339 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 1674 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 2089 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 1984 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 9859 Joules per run.

Neural Magic DeepSparse

This is a benchmark of Neural Magic's DeepSparse using its built-in deepsparse.benchmark utility and various models from their SparseZoo (https://sparsezoo.neuralmagic.com/). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-StreamEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1400800120016002000SE +/- 0.40, N = 3SE +/- 0.37, N = 3SE +/- 0.25, N = 3SE +/- 0.46, N = 3SE +/- 6.61, N = 3556.15493.99410.47443.431840.95
MinAvgMaxEPYC 8534PN - Zen 4C13.6103.7123.1EPYC 8324PN - Zen 4C12.869.881.3EPYC 8324P - Zen 4C13.089.2114.7EPYC 8324P - Zen 4C, 155W13.181.297.7EPYC 7601 - Zen 164.6142.0172.7OpenBenchmarking.orgWatts, Fewer Is BetterNeural Magic DeepSparse 1.6CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 4737 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 3233 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 4105 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 3708 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 7099 Joules per run.

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-StreamEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 11326395265SE +/- 0.1049, N = 3SE +/- 0.0604, N = 3SE +/- 0.0215, N = 3SE +/- 0.0667, N = 3SE +/- 0.0850, N = 356.841932.128938.820235.79298.5097

OpenFOAM

OpenFOAM is the leading free, open-source software for computational fluid dynamics (CFD). This test profile currently uses the drivaerFastback test case for analyzing automotive aerodynamics or alternatively the older motorBike input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Small Mesh Size - Execution TimeEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 130609012015058.6182.1573.5175.25122.261. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm
MinAvgMaxEPYC 8534PN - Zen 4C13.495.5133.8EPYC 8324PN - Zen 4C12.181.888.1EPYC 8324P - Zen 4C13.1115.1127.9EPYC 8324P - Zen 4C, 155W13.797.0104.6EPYC 7601 - Zen 164.4164.4173.9OpenBenchmarking.orgWatts, Fewer Is BetterOpenFOAM 10CPU Power Consumption Monitor50100150200250

Neural Magic DeepSparse

This is a benchmark of Neural Magic's DeepSparse using its built-in deepsparse.benchmark utility and various models from their SparseZoo (https://sparsezoo.neuralmagic.com/). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-StreamEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 14080120160200SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 1.56, N = 3113.45104.9088.1594.20189.32
MinAvgMaxEPYC 8534PN - Zen 4C13.899.4123.8EPYC 8324PN - Zen 4C12.667.583.1EPYC 8324P - Zen 4C12.987.7109.6EPYC 8324P - Zen 4C, 155W12.778.591.9EPYC 7601 - Zen 165.4148.0176.5OpenBenchmarking.orgWatts, Fewer Is BetterNeural Magic DeepSparse 1.6CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 4407 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 3016 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 3857 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 3482 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 7253 Joules per run.

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-StreamEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 160120180240300SE +/- 0.08, N = 3SE +/- 0.12, N = 3SE +/- 0.11, N = 3SE +/- 0.11, N = 3SE +/- 0.71, N = 3281.49152.21181.23169.5684.43

NAMD

NAMD is a parallel molecular dynamics code designed for high-performance simulation of large biomolecular systems. NAMD was developed by the Theoretical and Computational Biophysics Group in the Beckman Institute for Advanced Science and Technology at the University of Illinois at Urbana-Champaign. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 AtomsEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 10.21890.43780.65670.87561.0945SE +/- 0.00128, N = 3SE +/- 0.00094, N = 3SE +/- 0.00067, N = 3SE +/- 0.00161, N = 3SE +/- 0.00038, N = 30.432000.827900.677280.735580.97282
MinAvgMaxEPYC 8534PN - Zen 4C14.7118.1142.8EPYC 8324PN - Zen 4C12.180.990.2EPYC 8324P - Zen 4C13.5106.4125.6EPYC 8324P - Zen 4C, 155W13.994.8107.7EPYC 7601 - Zen 165.7165.3178.5OpenBenchmarking.orgWatts, Fewer Is BetterNAMD 2.14CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 3346 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 3990 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 4044 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 3857 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 10909 Joules per run.

7-Zip Compression

This is a test of 7-Zip compression/decompression with its integrated benchmark feature. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Decompression RatingEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 170K140K210K280K350KSE +/- 107.49, N = 3SE +/- 170.94, N = 3SE +/- 111.02, N = 3SE +/- 181.34, N = 3SE +/- 602.42, N = 33439461790722111872000341334901. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
OpenBenchmarking.orgMIPS Per Watt, More Is Better7-Zip Compression 22.01Test: Decompression RatingEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 170014002100280035003105.302439.422150.102334.06846.16
MinAvgMaxEPYC 8534PN - Zen 4C13.2110.8145.7EPYC 8324PN - Zen 4C12.373.490.8EPYC 8324P - Zen 4C12.898.2130.5EPYC 8324P - Zen 4C, 155W13.685.7113.3EPYC 7601 - Zen 165.9157.8178.5OpenBenchmarking.orgWatts, Fewer Is Better7-Zip Compression 22.01CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 5132 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 3059 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 3601 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 3285 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 9203 Joules per run.

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Compression RatingEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 170K140K210K280K350KSE +/- 303.12, N = 3SE +/- 39.63, N = 3SE +/- 329.87, N = 3SE +/- 172.23, N = 3SE +/- 1639.95, N = 33329222124582400832289571237461. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

Neural Magic DeepSparse

This is a benchmark of Neural Magic's DeepSparse using its built-in deepsparse.benchmark utility and various models from their SparseZoo (https://sparsezoo.neuralmagic.com/). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-StreamEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 150100150200250SE +/- 0.14, N = 3SE +/- 0.07, N = 3SE +/- 0.08, N = 3SE +/- 0.07, N = 3SE +/- 0.88, N = 3166.95154.28130.42139.18234.02
MinAvgMaxEPYC 8534PN - Zen 4C12.7106.4129.0EPYC 8324PN - Zen 4C12.370.881.0EPYC 8324P - Zen 4C13.091.9117.7EPYC 8324P - Zen 4C, 155W13.082.698.1EPYC 7601 - Zen 164.8157.0176.8OpenBenchmarking.orgWatts, Fewer Is BetterNeural Magic DeepSparse 1.6CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 4505 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 2975 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 3862 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 3495 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 6959 Joules per run.

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-StreamEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 14080120160200SE +/- 0.20, N = 3SE +/- 0.03, N = 3SE +/- 0.11, N = 3SE +/- 0.10, N = 3SE +/- 0.28, N = 3191.07103.44122.37114.6268.16

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-StreamEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 150100150200250SE +/- 0.07, N = 3SE +/- 0.09, N = 3SE +/- 0.14, N = 3SE +/- 0.04, N = 3SE +/- 1.50, N = 3166.03153.40129.84138.23231.40
MinAvgMaxEPYC 8534PN - Zen 4C13.8105.5121.8EPYC 8324PN - Zen 4C12.669.883.0EPYC 8324P - Zen 4C11.491.0116.6EPYC 8324P - Zen 4C, 155W13.482.5101.3EPYC 7601 - Zen 164.4156.5176.5OpenBenchmarking.orgWatts, Fewer Is BetterNeural Magic DeepSparse 1.6CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 4466 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 2953 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 3823 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 3436 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 6885 Joules per run.

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-StreamEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 14080120160200SE +/- 0.11, N = 3SE +/- 0.03, N = 3SE +/- 0.18, N = 3SE +/- 0.07, N = 3SE +/- 0.44, N = 3192.06104.13122.93115.4268.95

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-StreamEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1306090120150SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.35, N = 374.4369.6059.8762.82115.78
MinAvgMaxEPYC 7601 - Zen 166.0156.5177.4EPYC 8324P - Zen 4C13.096.8111.3EPYC 8324P - Zen 4C, 155W13.380.5100.1EPYC 8324PN - Zen 4C11.667.879.3EPYC 8534PN - Zen 4C13.1101.0122.6OpenBenchmarking.orgWatts, Fewer Is BetterNeural Magic DeepSparse 1.6CPU Power Consumption Monitor501001502002501. EPYC 7601 - Zen 1: Approximate power consumption of 6992 Joules per run.2. EPYC 8324P - Zen 4C: Approximate power consumption of 4034 Joules per run.3. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 3328 Joules per run.4. EPYC 8324PN - Zen 4C: Approximate power consumption of 2849 Joules per run.5. EPYC 8534PN - Zen 4C: Approximate power consumption of 4210 Joules per run.

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-StreamEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 190180270360450SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.10, N = 3SE +/- 0.08, N = 3SE +/- 0.41, N = 3429.33229.54266.96254.30138.03

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-StreamEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 120406080100SE +/- 0.0062, N = 3SE +/- 0.0084, N = 3SE +/- 0.0229, N = 3SE +/- 0.0078, N = 3SE +/- 0.1244, N = 39.25208.37457.28167.6064104.4436
MinAvgMaxEPYC 8534PN - Zen 4C12.796.8114.2EPYC 8324PN - Zen 4C12.466.576.5EPYC 8324P - Zen 4C12.993.1108.1EPYC 8324P - Zen 4C, 155W13.277.095.3EPYC 7601 - Zen 164.5159.1177.2OpenBenchmarking.orgWatts, Fewer Is BetterNeural Magic DeepSparse 1.6CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 4034 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 2794 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 3879 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 3207 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 7054 Joules per run.

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-StreamEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 17001400210028003500SE +/- 2.41, N = 3SE +/- 2.26, N = 3SE +/- 7.34, N = 3SE +/- 2.41, N = 3SE +/- 0.21, N = 33450.431906.392193.092099.32152.96

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-StreamEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1306090120150SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.07, N = 3SE +/- 0.02, N = 3SE +/- 0.43, N = 374.4169.5159.8762.88115.35

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.6Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-StreamEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 190180270360450SE +/- 0.37, N = 3SE +/- 0.16, N = 3SE +/- 0.34, N = 3SE +/- 0.06, N = 3SE +/- 0.48, N = 3429.36229.91266.99254.13138.53

SVT-AV1

This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 4 - Input: Bosphorus 4KEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1246810SE +/- 0.026, N = 3SE +/- 0.003, N = 3SE +/- 0.020, N = 3SE +/- 0.004, N = 3SE +/- 0.004, N = 36.5565.5515.9115.8163.0651. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 4 - Input: Bosphorus 4KEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 10.02050.0410.06150.0820.10250.0900.0910.0800.0820.024
MinAvgMaxEPYC 8534PN - Zen 4C12.672.9105.4EPYC 8324PN - Zen 4C12.661.386.3EPYC 8324P - Zen 4C12.774.3120.0EPYC 8324P - Zen 4C, 155W13.370.5101.6EPYC 7601 - Zen 163.4125.1171.7OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 1.8CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 2431 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 2328 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 2673 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 2563 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 8009 Joules per run.

Intel Open Image Denoise

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.1Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-OnlyEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 10.38480.76961.15441.53921.924SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 31.710.931.111.030.48
OpenBenchmarking.orgImages / Sec Per Watt, More Is BetterIntel Open Image Denoise 2.1Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-OnlyEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 10.00380.00760.01140.01520.0190.0170.0130.0120.0120.003
MinAvgMaxEPYC 8534PN - Zen 4C12.9101.2124.6EPYC 8324PN - Zen 4C11.772.983.5EPYC 8324P - Zen 4C13.296.0121.1EPYC 8324P - Zen 4C, 155W13.785.6101.3EPYC 7601 - Zen 165.5165.0174.6OpenBenchmarking.orgWatts, Fewer Is BetterIntel Open Image Denoise 2.1CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 2227 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 2698 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 3070 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 2911 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 11057 Joules per run.

Kripke

Kripke is a simple, scalable, 3D Sn deterministic particle transport code. Its primary purpose is to research how data layout, programming paradigms and architectures effect the implementation and performance of Sn transport. Kripke is developed by LLNL. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgThroughput FoM, More Is BetterKripke 1.2.6EPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 160M120M180M240M300MSE +/- 1948629.96, N = 3SE +/- 363531.75, N = 3SE +/- 634968.78, N = 3SE +/- 2369703.74, N = 3SE +/- 1494376.42, N = 32883943002475001332687732672587161671817959671. (CXX) g++ options: -O3 -fopenmp -ldl
OpenBenchmarking.orgThroughput FoM Per Watt, More Is BetterKripke 1.2.6EPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1600K1200K1800K2400K3000K2490692.282943707.262566916.472674408.731133698.87
MinAvgMaxEPYC 8534PN - Zen 4C14.7115.8137.0EPYC 8324PN - Zen 4C13.084.1103.7EPYC 8324P - Zen 4C12.6104.7123.6EPYC 8324P - Zen 4C, 155W14.296.7118.5EPYC 7601 - Zen 166.0160.4176.7OpenBenchmarking.orgWatts, Fewer Is BetterKripke 1.2.6CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 3898 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 3167 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 3665 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 3515 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 7911 Joules per run.

PyTorch

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 1 - Model: ResNet-50EPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 11224364860SE +/- 0.10, N = 3SE +/- 0.07, N = 3SE +/- 0.20, N = 3SE +/- 0.07, N = 3SE +/- 0.09, N = 345.2352.9052.7252.9124.89MIN: 16.58 / MAX: 46.26MIN: 50.6 / MAX: 53.56MIN: 50.17 / MAX: 53.72MIN: 50.65 / MAX: 53.55MIN: 12.04 / MAX: 25.89
OpenBenchmarking.orgbatches/sec Per Watt, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 1 - Model: ResNet-50EPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 10.18160.36320.54480.72640.9080.5520.8070.7840.7810.162
MinAvgMaxEPYC 8534PN - Zen 4C13.482.098.6EPYC 8324PN - Zen 4C12.965.679.0EPYC 8324P - Zen 4C12.867.381.3EPYC 8324P - Zen 4C, 155W13.367.881.9EPYC 7601 - Zen 163.8153.6174.3OpenBenchmarking.orgWatts, Fewer Is BetterPyTorch 2.1CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 2651 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 1880 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 1929 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 1943 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 8194 Joules per run.

x265

This is a simple test of the x265 encoder run on the CPU with 1080p and 4K options for H.265 video encode performance with x265. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 4KEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1612182430SE +/- 0.17, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.10, N = 327.5124.0325.5525.4514.291. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFrames Per Second Per Watt, More Is Betterx265 3.4Video Input: Bosphorus 4KEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 10.08780.17560.26340.35120.4390.3620.3900.3430.3420.112
MinAvgMaxEPYC 8534PN - Zen 4C12.676.196.9EPYC 8324PN - Zen 4C12.161.676.0EPYC 8324P - Zen 4C10.474.695.5EPYC 8324P - Zen 4C, 155W13.274.491.2EPYC 7601 - Zen 164.3128.0150.6OpenBenchmarking.orgWatts, Fewer Is Betterx265 3.4CPU Power Consumption Monitor40801201602001. EPYC 8534PN - Zen 4C: Approximate power consumption of 2003 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 1828 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 2064 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 2082 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 5887 Joules per run.

Timed FFmpeg Compilation

This test times how long it takes to build the FFmpeg multimedia library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed FFmpeg Compilation 6.1Time To CompileEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1918273645SE +/- 0.10, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.06, N = 3SE +/- 0.08, N = 319.3827.5724.4925.6839.89
MinAvgMaxEPYC 8534PN - Zen 4C13.076.2137.8EPYC 8324PN - Zen 4C12.565.194.8EPYC 8324P - Zen 4C12.876.7126.7EPYC 8324P - Zen 4C, 155W13.372.3109.6EPYC 7601 - Zen 163.7132.0179.3OpenBenchmarking.orgWatts, Fewer Is BetterTimed FFmpeg Compilation 6.1CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 2082 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 2300 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 2454 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 2411 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 6335 Joules per run.

Xcompact3d Incompact3d

Xcompact3d Incompact3d is a Fortran-MPI based, finite difference high-performance code for solving the incompressible Navier-Stokes equation and as many as you need scalar transport equations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: input.i3d 193 Cells Per DirectionEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1918273645SE +/- 0.18, N = 3SE +/- 0.02, N = 3SE +/- 0.16, N = 3SE +/- 0.22, N = 3SE +/- 0.06, N = 320.9824.3523.9123.7737.991. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz
MinAvgMaxEPYC 8534PN - Zen 4C13.7109.4133.8EPYC 8324PN - Zen 4C13.184.899.1EPYC 8324P - Zen 4C13.392.5109.1EPYC 8324P - Zen 4C, 155W13.994.2111.7EPYC 7601 - Zen 165.4144.5159.8OpenBenchmarking.orgWatts, Fewer Is BetterXcompact3d Incompact3d 2021-03-11CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 2880 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 2517 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 2684 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 2701 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 6214 Joules per run.

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs (and GPUs via SYCL) and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.3Binary: Pathtracer ISPC - Model: CrownEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 11326395265SE +/- 0.11, N = 3SE +/- 0.07, N = 3SE +/- 0.12, N = 3SE +/- 0.08, N = 3SE +/- 0.04, N = 359.0531.0836.8934.2418.44MIN: 57.98 / MAX: 61.17MIN: 30.63 / MAX: 31.81MIN: 36.22 / MAX: 37.68MIN: 33.72 / MAX: 35.12MIN: 18.15 / MAX: 18.78
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterEmbree 4.3Binary: Pathtracer ISPC - Model: CrownEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 10.18270.36540.54810.73080.91350.8120.3980.3610.3730.112
MinAvgMaxEPYC 8534PN - Zen 4C13.772.7142.1EPYC 8324PN - Zen 4C12.978.196.0EPYC 8324P - Zen 4C12.5102.3133.5EPYC 8324P - Zen 4C, 155W13.791.8110.4EPYC 7601 - Zen 165.9165.2178.1OpenBenchmarking.orgWatts, Fewer Is BetterEmbree 4.3CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 1987 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 2240 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 2524 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 2386 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 7487 Joules per run.

miniBUDE

MiniBUDE is a mini application for the the core computation of the Bristol University Docking Engine (BUDE). This test profile currently makes use of the OpenMP implementation of miniBUDE for CPU benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBillion Interactions/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM1EPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 120406080100SE +/- 0.02, N = 6SE +/- 0.06, N = 4SE +/- 0.01, N = 4SE +/- 0.03, N = 4SE +/- 0.02, N = 399.6551.1261.1557.1014.331. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
OpenBenchmarking.orgBillion Interactions/s Per Watt, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM1EPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 10.24460.48920.73380.97841.2231.0870.7460.6840.7180.087
MinAvgMaxEPYC 8534PN - Zen 4C14.491.7132.3EPYC 8324PN - Zen 4C13.168.588.4EPYC 8324P - Zen 4C12.789.5122.9EPYC 8324P - Zen 4C, 155W14.179.5107.9EPYC 7601 - Zen 166.1164.9176.2OpenBenchmarking.orgWatts, Fewer Is BetterminiBUDE 20210901CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 1116 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 1354 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 1543 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 1452 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 9841 Joules per run.

OpenBenchmarking.orgGFInst/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM1EPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 15001000150020002500SE +/- 0.47, N = 6SE +/- 1.51, N = 4SE +/- 0.21, N = 4SE +/- 0.86, N = 4SE +/- 0.43, N = 32491.171278.031528.851427.41358.251. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm

SVT-AV1

This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 8 - Input: Bosphorus 4KEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 11428425670SE +/- 0.39, N = 4SE +/- 0.05, N = 4SE +/- 0.13, N = 4SE +/- 0.14, N = 4SE +/- 0.28, N = 564.3451.5458.0055.7226.751. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 8 - Input: Bosphorus 4KEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 10.21710.43420.65130.86841.08550.9650.8820.8260.8550.215
MinAvgMaxEPYC 8534PN - Zen 4C12.266.7108.8EPYC 8324PN - Zen 4C12.558.584.2EPYC 8324P - Zen 4C12.470.2112.0EPYC 8324P - Zen 4C, 155W13.265.297.5EPYC 7601 - Zen 163.7124.3172.5OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 1.8CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 1151 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 1140 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 1281 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 1222 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 4202 Joules per run.

Y-Cruncher

Y-Cruncher is a multi-threaded Pi benchmark capable of computing Pi to trillions of digits. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterY-Cruncher 0.8.3Pi Digits To Calculate: 1BEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 1816243240SE +/- 0.01, N = 4SE +/- 0.01, N = 3SE +/- 0.01, N = 4SE +/- 0.02, N = 3SE +/- 0.10, N = 310.4413.9711.9312.8933.91
MinAvgMaxEPYC 8534PN - Zen 4C13.488.5143.6EPYC 8324PN - Zen 4C12.269.498.8EPYC 8324P - Zen 4C12.985.6133.1EPYC 8324P - Zen 4C, 155W13.577.5114.5EPYC 7601 - Zen 165.7150.4179.3OpenBenchmarking.orgWatts, Fewer Is BetterY-Cruncher 0.8.3CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 1726 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 1574 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 1755 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 1680 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 6315 Joules per run.

SVT-AV1

This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 12 - Input: Bosphorus 4KEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 14080120160200SE +/- 2.10, N = 5SE +/- 1.17, N = 5SE +/- 1.24, N = 13SE +/- 1.73, N = 6SE +/- 0.47, N = 3190.89167.16182.26175.7570.771. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-AV1 1.8Encoder Mode: Preset 12 - Input: Bosphorus 4KEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 10.88291.76582.64873.53164.41453.9243.7393.6653.6660.726
MinAvgMaxEPYC 8534PN - Zen 4C12.748.6109.6EPYC 8324PN - Zen 4C12.544.582.7EPYC 8324P - Zen 4C12.049.7112.3EPYC 8324P - Zen 4C, 155W13.247.9100.4EPYC 7601 - Zen 165.497.5157.6OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 1.8CPU Power Consumption Monitor40801201602001. EPYC 8534PN - Zen 4C: Approximate power consumption of 642 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 622 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 669 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 647 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 2112 Joules per run.

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs (and GPUs via SYCL) and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.3Binary: Pathtracer ISPC - Model: Asian DragonEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 120406080100SE +/- 0.10, N = 5SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 374.9339.6045.5143.1321.84MIN: 73.96 / MAX: 76.92MIN: 39.34 / MAX: 40.89MIN: 45.23 / MAX: 46.5MIN: 42.84 / MAX: 43.66MIN: 21.59 / MAX: 22.16
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterEmbree 4.3Binary: Pathtracer ISPC - Model: Asian DragonEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 10.16940.33880.50820.67760.8470.7530.5220.4340.4980.135
MinAvgMaxEPYC 8534PN - Zen 4C14.499.5140.7EPYC 8324PN - Zen 4C12.875.995.2EPYC 8324P - Zen 4C12.7105.0134.4EPYC 8324P - Zen 4C, 155W14.086.6107.3EPYC 7601 - Zen 165.7162.4177.6OpenBenchmarking.orgWatts, Fewer Is BetterEmbree 4.3CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 1493 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 1797 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 2240 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 1904 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 6333 Joules per run.

uvg266

uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Very FastEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 11122334455SE +/- 0.04, N = 4SE +/- 0.03, N = 3SE +/- 0.02, N = 4SE +/- 0.02, N = 4SE +/- 0.08, N = 347.6533.8239.2537.3322.26
OpenBenchmarking.orgFrames Per Second Per Watt, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Very FastEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 10.12170.24340.36510.48680.60850.5410.4940.4390.4640.146
MinAvgMaxEPYC 8534PN - Zen 4C13.788.2122.3EPYC 8324PN - Zen 4C12.868.588.7EPYC 8324P - Zen 4C13.089.3117.0EPYC 8324P - Zen 4C, 155W13.780.5105.1EPYC 7601 - Zen 164.3152.6171.9OpenBenchmarking.orgWatts, Fewer Is Betteruvg266 0.4.1CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 1477 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 1506 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 1742 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 1630 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 4782 Joules per run.

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Super FastEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 11122334455SE +/- 0.06, N = 4SE +/- 0.03, N = 4SE +/- 0.03, N = 4SE +/- 0.08, N = 4SE +/- 0.02, N = 349.2236.7542.9440.5023.58
OpenBenchmarking.orgFrames Per Second Per Watt, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Super FastEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 10.12870.25740.38610.51480.64350.5720.5350.4850.5060.155
MinAvgMaxEPYC 8534PN - Zen 4C12.086.0119.7EPYC 8324PN - Zen 4C12.568.789.9EPYC 8324P - Zen 4C12.988.5116.2EPYC 8324P - Zen 4C, 155W13.680.0102.0EPYC 7601 - Zen 165.3152.6171.2OpenBenchmarking.orgWatts, Fewer Is Betteruvg266 0.4.1CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 1419 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 1409 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 1615 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 1500 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 4475 Joules per run.

Y-Cruncher

Y-Cruncher is a multi-threaded Pi benchmark capable of computing Pi to trillions of digits. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterY-Cruncher 0.8.3Pi Digits To Calculate: 500MEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 148121620SE +/- 0.005, N = 5SE +/- 0.006, N = 5SE +/- 0.003, N = 5SE +/- 0.010, N = 5SE +/- 0.140, N = 75.2076.6535.7476.19215.515
MinAvgMaxEPYC 8534PN - Zen 4C13.971.4138.3EPYC 8324PN - Zen 4C12.060.299.8EPYC 8324P - Zen 4C12.571.5129.1EPYC 8324P - Zen 4C, 155W13.666.7111.1EPYC 7601 - Zen 165.5138.2179.0OpenBenchmarking.orgWatts, Fewer Is BetterY-Cruncher 0.8.3CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 914 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 819 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 901 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 867 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 3060 Joules per run.

uvg266

uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Ultra FastEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 11224364860SE +/- 0.14, N = 4SE +/- 0.04, N = 4SE +/- 0.05, N = 4SE +/- 0.06, N = 4SE +/- 0.03, N = 351.3341.0246.5444.8127.29
OpenBenchmarking.orgFrames Per Second Per Watt, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Ultra FastEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 10.14270.28540.42810.57080.71350.6340.6230.5460.5810.184
MinAvgMaxEPYC 8534PN - Zen 4C13.481.0114.6EPYC 8324PN - Zen 4C12.665.887.1EPYC 8324P - Zen 4C12.885.3111.9EPYC 8324P - Zen 4C, 155W13.577.1102.8EPYC 7601 - Zen 164.4148.0169.3OpenBenchmarking.orgWatts, Fewer Is Betteruvg266 0.4.1CPU Power Consumption Monitor501001502002501. EPYC 8534PN - Zen 4C: Approximate power consumption of 1315 Joules per run.2. EPYC 8324PN - Zen 4C: Approximate power consumption of 1234 Joules per run.3. EPYC 8324P - Zen 4C: Approximate power consumption of 1450 Joules per run.4. EPYC 8324P - Zen 4C, 155W: Approximate power consumption of 1349 Joules per run.5. EPYC 7601 - Zen 1: Approximate power consumption of 3897 Joules per run.

CPU Power Consumption Monitor

OpenBenchmarking.orgWattsCPU Power Consumption MonitorPhoronix Test Suite System MonitoringEPYC 8534PN - Zen 4CEPYC 8324PN - Zen 4CEPYC 8324P - Zen 4CEPYC 8324P - Zen 4C, 155WEPYC 7601 - Zen 14080120160200Min: 6.99 / Avg: 97.94 / Max: 154.25Min: 6.71 / Avg: 71.8 / Max: 108.62Min: 6.76 / Avg: 88.61 / Max: 141.34Min: 11.47 / Avg: 82.06 / Max: 125.14Min: 32.69 / Avg: 143.24 / Max: 192.83

150 Results Shown

Xcompact3d Incompact3d
CloverLeaf
Timed Linux Kernel Compilation
LAMMPS Molecular Dynamics Simulator
Blender
OpenRadioss
Timed Gem5 Compilation
Xmrig
Timed LLVM Compilation
Llama.cpp
Quicksilver
OpenFOAM:
  drivaerFastback, Medium Mesh Size - Execution Time
  drivaerFastback, Medium Mesh Size - Mesh Time
easyWave
Timed LLVM Compilation
DuckDB
Timed Node.js Compilation
FFmpeg:
  libx265 - Video On Demand
  libx265 - Platform
  libx265 - Upload
Llama.cpp
Xmrig:
  Monero - 1M
  CryptoNight-Femto UPX2 - 1M
  KawPow - 1M
  CryptoNight-Heavy - 1M
Apache IoTDB:
  500 - 100 - 500 - 100:
    Average Latency
    point/sec
DuckDB
OSPRay Studio
OpenSSL:
  SHA256
  ChaCha20-Poly1305
  ChaCha20
  AES-256-GCM
  AES-128-GCM
  SHA512
Apache Cassandra
Blender
RocksDB
OSPRay Studio
OSPRay
Speedb
OSPRay
Llama.cpp
miniBUDE:
  OpenMP - BM2:
    Billion Interactions/s
    GFInst/s
Blender
Speedb
OSPRay
OSPRay Studio
GPAW
OSPRay Studio
nginx:
  1000
  500
Neural Magic DeepSparse:
  BERT-Large, NLP Question Answering - Asynchronous Multi-Stream:
    ms/batch
    items/sec
OSPRay Studio:
  3 - 4K - 1 - Path Tracer - CPU
  1 - 4K - 1 - Path Tracer - CPU
OpenVINO:
  Handwritten English Recognition FP16-INT8 - CPU:
    ms
    FPS
Chaos Group V-RAY
rav1e
QuantLib
FFmpeg
TensorFlow
CloverLeaf
Blender
IndigoBench
Redis 7.0.12 + memtier_benchmark:
  Redis - 100 - 1:10
  Redis - 100 - 1:5
VVenC
easyWave
Quicksilver
OpenVINO:
  Face Detection FP16-INT8 - CPU:
    ms
    FPS
IndigoBench
OSPRay
PyTorch
Speedb
OpenVINO:
  Person Detection FP16 - CPU:
    ms
    FPS
  Machine Translation EN To DE FP16 - CPU:
    ms
    FPS
  Person Vehicle Bike Detection FP16 - CPU:
    ms
    FPS
  Road Segmentation ADAS FP16-INT8 - CPU:
    ms
    FPS
  Face Detection Retail FP16-INT8 - CPU:
    ms
    FPS
  Vehicle Detection FP16-INT8 - CPU:
    ms
    FPS
OSPRay
OpenVINO:
  Age Gender Recognition Retail 0013 FP16-INT8 - CPU:
    ms
    FPS
  Weld Porosity Detection FP16-INT8 - CPU:
    ms
    FPS
Speedb
Timed Linux Kernel Compilation
OSPRay
OpenSSL:
  RSA4096:
    verify/s
    sign/s
RocksDB
Xmrig
Blender
Neural Magic DeepSparse:
  NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream:
    ms/batch
    items/sec
rav1e
ACES DGEMM
Neural Magic DeepSparse:
  CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Stream:
    ms/batch
    items/sec
OpenFOAM
Neural Magic DeepSparse:
  NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream:
    ms/batch
    items/sec
NAMD
7-Zip Compression:
  Decompression Rating
  Compression Rating
Neural Magic DeepSparse:
  CV Detection, YOLOv5s COCO - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  ResNet-50, Sparse INT8 - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  ResNet-50, Baseline - Asynchronous Multi-Stream:
    ms/batch
    items/sec
SVT-AV1
Intel Open Image Denoise
Kripke
PyTorch
x265
Timed FFmpeg Compilation
Xcompact3d Incompact3d
Embree
miniBUDE:
  OpenMP - BM1:
    Billion Interactions/s
    GFInst/s
SVT-AV1
Y-Cruncher
SVT-AV1
Embree
uvg266:
  Bosphorus 4K - Very Fast
  Bosphorus 4K - Super Fast
Y-Cruncher
uvg266
CPU Power Consumption Monitor

EPYC 8534PN - Zen 4C

Processor: AMD EPYC 8534PN 64-Core @ 2.00GHz (64 Cores / 128 Threads), Motherboard: AMD Cinnabar (RCB1009C BIOS), Chipset: AMD Device 14a4, Memory: 6 x 32 GB DRAM-4800MT/s Samsung M321R4GA0BB0-CQKMG, Disk: 1000GB INTEL SSDPE2KX010T8, Graphics: llvmpipe, Network: 2 x Broadcom NetXtreme BCM5720 PCIe

OS: Ubuntu 23.10, Kernel: 6.6.9-060609-generic (x86_64), Desktop: GNOME Shell 45.0, Display Server: X Server 1.21.1.7, OpenGL: 4.5 Mesa 23.2.1-1ubuntu3.1 (LLVM 15.0.7 256 bits), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xaa00212
Java Notes: OpenJDK Runtime Environment (build 11.0.21+9-post-Ubuntu-0ubuntu123.10)
Python Notes: Python 3.11.6
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 9 January 2024 15:21 by user phoronix.

EPYC 8324PN - Zen 4C

Processor: AMD EPYC 8534PN 32-Core @ 2.05GHz (32 Cores / 64 Threads), Motherboard: AMD Cinnabar (RCB1009C BIOS), Chipset: AMD Device 14a4, Memory: 6 x 32 GB DRAM-4800MT/s Samsung M321R4GA0BB0-CQKMG, Disk: 1000GB INTEL SSDPE2KX010T8, Graphics: llvmpipe, Network: 2 x Broadcom NetXtreme BCM5720 PCIe

OS: Ubuntu 23.10, Kernel: 6.6.9-060609-generic (x86_64), Desktop: GNOME Shell 45.0, Display Server: X Server 1.21.1.7, OpenGL: 4.5 Mesa 23.2.1-1ubuntu3.1 (LLVM 15.0.7 256 bits), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xaa00212
Java Notes: OpenJDK Runtime Environment (build 11.0.21+9-post-Ubuntu-0ubuntu123.10)
Python Notes: Python 3.11.6
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 10 January 2024 14:58 by user phoronix.

EPYC 8324P - Zen 4C

Processor: AMD EPYC 8324P 32-Core @ 2.65GHz (32 Cores / 64 Threads), Motherboard: AMD Cinnabar (RCB1009C BIOS), Chipset: AMD Device 14a4, Memory: 6 x 32 GB DRAM-4800MT/s Samsung M321R4GA0BB0-CQKMG, Disk: 1000GB INTEL SSDPE2KX010T8, Graphics: llvmpipe, Network: 2 x Broadcom NetXtreme BCM5720 PCIe

OS: Ubuntu 23.10, Kernel: 6.6.9-060609-generic (x86_64), Desktop: GNOME Shell 45.0, Display Server: X Server 1.21.1.7, OpenGL: 4.5 Mesa 23.2.1-1ubuntu3.1 (LLVM 15.0.7 256 bits), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xaa00212
Java Notes: OpenJDK Runtime Environment (build 11.0.21+9-post-Ubuntu-0ubuntu123.10)
Python Notes: Python 3.11.6
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 12 January 2024 00:50 by user phoronix.

EPYC 8324P - Zen 4C, 155W

Processor: AMD EPYC 8324P 32-Core @ 2.65GHz (32 Cores / 64 Threads), Motherboard: AMD Cinnabar (RCB1009C BIOS), Chipset: AMD Device 14a4, Memory: 6 x 32 GB DRAM-4800MT/s Samsung M321R4GA0BB0-CQKMG, Disk: 1000GB INTEL SSDPE2KX010T8, Graphics: ASPEED, Network: 2 x Broadcom NetXtreme BCM5720 PCIe

OS: Ubuntu 23.10, Kernel: 6.6.9-060609-generic (x86_64), Desktop: GNOME Shell 45.0, Display Server: X Server 1.21.1.7, Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xaa00212
Java Notes: OpenJDK Runtime Environment (build 11.0.21+9-post-Ubuntu-0ubuntu123.10)
Python Notes: Python 3.11.6
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 12 January 2024 19:57 by user phoronix.

EPYC 7601 - Zen 1

Processor: AMD EPYC 7601 32-Core @ 2.20GHz (32 Cores / 64 Threads), Motherboard: TYAN B8026T70AE24HR (V1.02.B10 BIOS), Chipset: AMD 17h, Memory: 8 x 16 GB 2667MT/s Samsung M393A2K40BB2-CTD, Disk: 1000GB INTEL SSDPE2KX010T8 + 280GB INTEL SSDPE21D280GA, Graphics: ASPEED, Monitor: VE228, Network: 2 x Broadcom NetXtreme BCM5720 PCIe

OS: Ubuntu 23.10, Kernel: 6.6.9-060609-generic (x86_64), Desktop: GNOME Shell 45.0, Display Server: X Server 1.21.1.7, OpenGL: 4.5 Mesa 23.2.1-1ubuntu3.1 (LLVM 15.0.7 256 bits), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1080

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0x800126e
Java Notes: OpenJDK Runtime Environment (build 11.0.21+9-post-Ubuntu-0ubuntu123.10)
Python Notes: Python 3.11.6
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Mitigation of untrained return thunk; SMT vulnerable + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional STIBP: disabled RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 13 January 2024 15:35 by user phoronix.