STW AMD EPYC Milan vs. Intel Xeon Ice Lake Server Benchmarks

Benchmarks by Michael Larabel, preparations for a future article on Phoronix.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2305089-PTS-STWSERVE31
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:

Timed Code Compilation 3 Tests
C/C++ Compiler Tests 8 Tests
CPU Massive 14 Tests
Creator Workloads 12 Tests
Database Test Suite 5 Tests
Encoding 6 Tests
Fortran Tests 2 Tests
HPC - High Performance Computing 13 Tests
Common Kernel Benchmarks 3 Tests
Machine Learning 4 Tests
Molecular Dynamics 5 Tests
MPI Benchmarks 4 Tests
Multi-Core 21 Tests
NVIDIA GPU Compute 3 Tests
Intel oneAPI 4 Tests
OpenMPI Tests 7 Tests
Programmer / Developer System Benchmarks 3 Tests
Python Tests 6 Tests
Renderers 3 Tests
Scientific Computing 5 Tests
Server 8 Tests
Server CPU Tests 10 Tests
Single-Threaded 2 Tests
Video Encoding 6 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

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
Performance Per
Dollar
Date
Run
  Test
  Duration
EPYC 7343
April 26 2023
  16 Hours, 30 Minutes
EPYC 7343 2P
April 25 2023
  16 Hours, 48 Minutes
EPYC 7413
March 13 2023
  16 Hours, 11 Minutes
EPYC 7413 2P
March 24 2023
  17 Hours, 39 Minutes
EPYC 7513
March 09 2023
  17 Hours, 17 Minutes
EPYC 7513 2P
March 29 2023
  17 Hours, 11 Minutes
EPYC 7543
March 08 2023
  16 Hours, 14 Minutes
EPYC 7713P
March 06 2023
  17 Hours, 24 Minutes
Xeon Gold 6338
April 03 2023
  14 Hours, 15 Minutes
Xeon Gold 6338 2P
March 22 2023
  15 Hours, 18 Minutes
Xeon Gold 6342
April 05 2023
  12 Hours, 26 Minutes
Xeon Gold 6342 2P
March 20 2023
  15 Hours, 1 Minute
Xeon Gold 6346
April 20 2023
  16 Hours, 25 Minutes
Xeon Gold 6346 2P
March 18 2023
  17 Hours, 22 Minutes
Invert Hiding All Results Option
  16 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):


STW AMD EPYC Milan vs. Intel Xeon Ice Lake Server BenchmarksProcessorMotherboardMemoryDiskGraphicsMonitorOSKernelCompilerFile-SystemScreen ResolutionEPYC 7343EPYC 7343 2PEPYC 7413EPYC 7413 2PEPYC 7513EPYC 7513 2PEPYC 7543EPYC 7713PXeon Gold 6338Xeon Gold 6338 2PXeon Gold 6342Xeon Gold 6342 2PXeon Gold 6346Xeon Gold 6346 2PAMD EPYC 7343 16-Core @ 3.20GHz (16 Cores / 32 Threads)Supermicro H12SSL-i v1.02 (2.4 BIOS)8 x 64 GB DDR4-3200MT/s Samsung M393A8G40AB2-CWE2 x 1920GB SAMSUNG MZQL21T9HCJR-00A07astdrmfbDELL E207WFPAlmaLinux 9.15.14.0-162.12.1.el9_1.x86_64 (x86_64)GCC 11.3.1 20220421ext41680x10502 x AMD EPYC 7343 16-Core @ 3.20GHz (32 Cores / 64 Threads)Supermicro H12DSi-N6 v1.02 (2.3 BIOS)16 x 32 GB DDR4-3200MT/s Samsung M393A4K40EB3-CWE5.14.0-162.18.1.el9_1.x86_64 (x86_64)1280x1024AMD EPYC 7413 24-Core @ 2.65GHz (24 Cores / 48 Threads)Supermicro H12SSL-i v1.02 (2.4 BIOS)8 x 64 GB DDR4-3200MT/s Samsung M393A8G40AB2-CWE5.14.0-162.12.1.el9_1.x86_64 (x86_64)1024x7682 x AMD EPYC 7413 24-Core @ 2.65GHz (48 Cores / 96 Threads)Supermicro H12DSi-N6 v1.02 (2.3 BIOS)512GB5.14.0-162.18.1.el9_1.x86_64 (x86_64)AMD EPYC 7513 32-Core @ 2.60GHz (32 Cores / 64 Threads)Supermicro H12SSL-i v1.02 (2.4 BIOS)8 x 64 GB DDR4-3200MT/s Samsung M393A8G40AB2-CWE5.14.0-162.12.1.el9_1.x86_64 (x86_64)2 x AMD EPYC 7513 32-Core @ 2.60GHz (64 Cores / 128 Threads)Supermicro H12DSi-N6 v1.02 (2.3 BIOS)512GB5.14.0-162.18.1.el9_1.x86_64 (x86_64)AMD EPYC 7543 32-Core @ 2.80GHz (32 Cores / 64 Threads)Supermicro H12SSL-i v1.02 (2.4 BIOS)8 x 64 GB DDR4-3200MT/s Samsung M393A8G40AB2-CWEDELL E207WFP5.14.0-162.12.1.el9_1.x86_64 (x86_64)1680x1050AMD EPYC 7713P 64-Core @ 2.00GHz (64 Cores / 128 Threads)1024x768Intel Xeon Gold 6338 @ 3.20GHz (32 Cores / 64 Threads)Supermicro X12SPO-NTF v2.00 (1.2 BIOS)DELL E207WFP1280x10242 x Intel Xeon Gold 6338 @ 3.20GHz (64 Cores / 128 Threads)Supermicro X12DPi-N6 v1.01 (1.4 BIOS)16 x 32 GB DDR4-3200MT/s Samsung M393A4K40EB3-CWEIntel Xeon Gold 6342 @ 3.50GHz (24 Cores / 48 Threads)Supermicro X12SPO-NTF v2.00 (1.2 BIOS)8 x 64 GB DDR4-3200MT/s Samsung M393A8G40AB2-CWE2 x Intel Xeon Gold 6342 @ 3.50GHz (48 Cores / 96 Threads)Supermicro X12DPi-N6 v1.01 (1.4 BIOS)16 x 32 GB DDR4-3200MT/s Samsung M393A4K40EB3-CWEIntel Xeon Gold 6346 @ 3.60GHz (16 Cores / 32 Threads)Supermicro X12SPO-NTF v2.00 (1.2 BIOS)8 x 64 GB DDR4-3200MT/s Samsung M393A8G40AB2-CWE2 x Intel Xeon Gold 6346 @ 3.60GHz (32 Cores / 64 Threads)Supermicro X12DPi-N6 v1.01 (1.4 BIOS)16 x 32 GB DDR4-3200MT/s Samsung M393A4K40EB3-CWE1024x768OpenBenchmarking.orgKernel Details- Transparent Huge Pages: alwaysCompiler Details- --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-host-bind-now --enable-host-pie --enable-initfini-array --enable-languages=c,c++,fortran,lto --enable-link-serialization=1 --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=x86-64 --with-arch_64=x86-64-v2 --with-build-config=bootstrap-lto --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver --without-islProcessor Details- EPYC 7343: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001173- EPYC 7343 2P: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001173- EPYC 7413: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001173- EPYC 7413 2P: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001173- EPYC 7513: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001173- EPYC 7513 2P: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001173- EPYC 7543: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001173- EPYC 7713P: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001173- Xeon Gold 6338: Scaling Governor: intel_cpufreq performance - CPU Microcode: 0xd000375- Xeon Gold 6338 2P: Scaling Governor: intel_cpufreq performance - CPU Microcode: 0xd000375- Xeon Gold 6342: Scaling Governor: intel_cpufreq performance - CPU Microcode: 0xd000375- Xeon Gold 6342 2P: Scaling Governor: intel_cpufreq performance - CPU Microcode: 0xd000375- Xeon Gold 6346: Scaling Governor: intel_cpufreq performance - CPU Microcode: 0xd000375- Xeon Gold 6346 2P: Scaling Governor: intel_cpufreq performance - CPU Microcode: 0xd000375Java Details- OpenJDK Runtime Environment (Red_Hat-11.0.18.0.10-2.el9_1) (build 11.0.18+10-LTS)Python Details- Python 3.9.14Security Details- EPYC 7343: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + 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 IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected- EPYC 7343 2P: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + 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 IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected- EPYC 7413: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + 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 IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected- EPYC 7413 2P: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + 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 IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected- EPYC 7513: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + 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 IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected- EPYC 7513 2P: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + 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 IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected- EPYC 7543: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + 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 IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected- EPYC 7713P: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + 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 IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected- Xeon Gold 6338: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Vulnerable: Clear buffers attempted no microcode; SMT vulnerable + retbleed: Not affected + 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 IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected- Xeon Gold 6338 2P: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + retbleed: Not affected + 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 IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected- Xeon Gold 6342: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Vulnerable: Clear buffers attempted no microcode; SMT vulnerable + retbleed: Not affected + 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 IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected- Xeon Gold 6342 2P: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + retbleed: Not affected + 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 IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected- Xeon Gold 6346: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Vulnerable: Clear buffers attempted no microcode; SMT vulnerable + retbleed: Not affected + 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 IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected- Xeon Gold 6346 2P: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + retbleed: Not affected + 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 IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected

EPYC 7343EPYC 7343 2PEPYC 7413EPYC 7413 2PEPYC 7513EPYC 7513 2PEPYC 7543EPYC 7713PXeon Gold 6338Xeon Gold 6338 2PXeon Gold 6342Xeon Gold 6342 2PXeon Gold 6346Xeon Gold 6346 2PResult OverviewPhoronix Test Suite100%200%300%400%500%OSPRay StudioCloudSuite In-Memory AnalyticsPennantOpenSSLLULESHTensorFlowBlenderNAMDEmbreeOpenVINOXcompact3d Incompact3dTimed Node.js CompilationHigh Performance Conjugate GradientTimed LLVM CompilationSVT-HEVCLuxCoreRenderTimed Linux Kernel CompilationPostgreSQLKvazaarMemcacheduvg266Neural Magic DeepSparseApache CassandraCloudSuite Graph AnalyticsSVT-VP9ClickHouseCloudSuite Web ServingSVT-AV1PHPBenchFFmpeg

EPYC 7343EPYC 7343 2PEPYC 7413EPYC 7413 2PEPYC 7513EPYC 7513 2PEPYC 7543EPYC 7713PXeon Gold 6338Xeon Gold 6338 2PXeon Gold 6342Xeon Gold 6342 2PXeon Gold 6346Xeon Gold 6346 2PPer Watt Result OverviewPhoronix Test Suite100%166%232%298%364%TensorFlowOpenSSLApache CassandraLuxCoreRenderCloudSuite Web ServingEmbreePHPBenchSVT-HEVCSVT-VP9uvg266SVT-AV1MemcachedKvazaarFFmpegLULESHClickHouseHigh Performance Conjugate GradientP.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

STW AMD EPYC Milan vs. Intel Xeon Ice Lake Server Benchmarkstensorflow: CPU - 512 - ResNet-50tensorflow: CPU - 256 - ResNet-50incompact3d: X3D-benchmarking input.i3dblender: Barbershop - CPU-Onlypgbench: 1000 - 800 - Read Only - Average Latencypgbench: 1000 - 800 - Read Onlypgbench: 1000 - 1000 - Read Only - Average Latencypgbench: 1000 - 1000 - Read Onlycloudsuite-ws: 500cloudsuite-ga: Triangle Countgraph500: 26graph500: 26graph500: 26graph500: 26pgbench: 1000 - 1000 - Read Write - Average Latencypgbench: 1000 - 1000 - Read Writepgbench: 1000 - 800 - Read Write - Average Latencypgbench: 1000 - 800 - Read Writebuild-llvm: Unix Makefilescloudsuite-ws: 400clickhouse: 100M Rows Hits Dataset, Third Runclickhouse: 100M Rows Hits Dataset, Second Runclickhouse: 100M Rows Hits Dataset, First Run / Cold Cachebuild-nodejs: Time To Compilebuild-llvm: Ninjacloudsuite-ma: Largeffmpeg: libx265 - Video On Demandffmpeg: libx265 - Video On Demandffmpeg: libx265 - Platformffmpeg: libx265 - Platformffmpeg: libx265 - Uploadffmpeg: libx265 - Uploadopenssl: SHA256hpcg: nekrs: TurboPipe Periodicmemcached: 1:100rocksdb: Seq Fillospray-studio: 3 - 4K - 32 - Path Tracerrocksdb: Read While Writingospray-studio: 3 - 4K - 1 - Path Tracerospray-studio: 1 - 4K - 32 - Path Tracerblender: Classroom - CPU-Onlyospray-studio: 1 - 4K - 1 - Path Tracermemcached: 1:5cassandra: Writesmemcached: 1:10cloudsuite-ws: 100cloudsuite-ga: Connected Componentssvt-hevc: 1 - Bosphorus 4Krocksdb: Update Randnginx: 500nginx: 200luxcorerender: LuxCore Benchmark - CPUcloudsuite-ga: Page Ranknginx: 1000rocksdb: Read Rand Write Randrocksdb: Rand Fill Synccloudsuite-ma: Smallopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP32 - CPUopenvino: Person Detection FP32 - CPUluxcorerender: Danish Mood - CPUopenvino: Face Detection FP16 - CPUopenvino: Face Detection FP16 - CPUffmpeg: libx265 - Liveffmpeg: libx265 - Liveluxcorerender: Orange Juice - CPUopenvino: Face Detection FP16-INT8 - CPUopenvino: Face Detection FP16-INT8 - 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: Vehicle Detection FP16-INT8 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16 - CPUopenvino: Weld Porosity Detection FP16 - CPUopenvino: 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 - CPUopenvino: Vehicle Detection FP16 - CPUopenvino: Vehicle Detection FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenssl: RSA4096openssl: RSA4096deepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Streamrocksdb: Rand Readdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamdeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Streamdeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streambuild-linux-kernel: defconfigdeepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamuvg266: Bosphorus 4K - Slowblender: BMW27 - CPU-Onlygromacs: MPI CPU - water_GMX50_bareuvg266: Bosphorus 4K - Mediumffmpeg: libx264 - Livedeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamincompact3d: input.i3d 193 Cells Per Directiondeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamnamd: ATPase Simulation - 327,506 Atomskvazaar: Bosphorus 4K - Mediumluxcorerender: Rainbow Colors and Prism - CPUphpbench: PHP Benchmark Suitesvt-vp9: VMAF Optimized - Bosphorus 4Kkvazaar: Bosphorus 4K - Super Fastpennant: sedovbigembree: Pathtracer ISPC - Crownembree: Pathtracer - Crownembree: Pathtracer - Asian Dragonkvazaar: Bosphorus 4K - Very Fastuvg266: Bosphorus 4K - Very Fastuvg266: Bosphorus 4K - Super Fastembree: Pathtracer ISPC - Asian Dragonuvg266: Bosphorus 1080p - Slowuvg266: Bosphorus 4K - Ultra Fastlulesh: minibude: OpenMP - BM1minibude: OpenMP - BM1uvg266: Bosphorus 1080p - Mediumpennant: leblancbigsvt-vp9: PSNR/SSIM Optimized - Bosphorus 4Konednn: Convolution Batch Shapes Auto - f32 - CPUsvt-vp9: Visual Quality Optimized - Bosphorus 4Ksvt-hevc: 7 - Bosphorus 4Ksvt-hevc: 10 - Bosphorus 4Ksvt-av1: Preset 12 - Bosphorus 4Kuvg266: Bosphorus 1080p - Super Fastuvg266: Bosphorus 1080p - Very Fastsvt-av1: Preset 13 - Bosphorus 4Kuvg266: Bosphorus 1080p - Ultra FastEPYC 7343EPYC 7343 2PEPYC 7413EPYC 7413 2PEPYC 7513EPYC 7513 2PEPYC 7543EPYC 7713PXeon Gold 6338Xeon Gold 6338 2PXeon Gold 6342Xeon Gold 6342 2PXeon Gold 6346Xeon Gold 6346 2P22.9122.37880.639262815.391.1506957611.45968523911.610898831298900014971000011429500030981700040.2942482131.15825679392.19411.833345.53346.00336.88337.220347.36312257549.82152.0549.89151.8524.29103.962489110126718.13671610909.222652388172224298219.8368052199582.801727132548333.197.333157183.792.7211525139952790.522.842813.452.822.481850.234.27123.7640.815.05854.229.36162.4049.2012.37646.1512.22654.1419.76404.561.1114256.4017.50913.7520.51389.711.2113149.71287549.04398.6450.603317.7432152.830652.2641629.185912.646648.8605163.5554627.685312.620163.491148.958453.59919.2682.6010.4223.1875.4144105.957635.555610655.4127144.22821.1434014.9412.12732752111.8241.2426.9280720.006721.217023.764732.3528.9430.0023.061338.5235.2810323.17643.1116.69242115.8083.7371.41143.45179.068116.79110.98172.161130.3025.4324.03484.985402435.020.9358556421.17884901911.21777278444474000218986000174219000422529000119.682835694.5908492240.49311.433443.72443.07423.79190.997190.96914794446.84161.7246.66162.33916891223.56107.194969400004735.31961669010000002373328.3732359814261148642994336120264109.6436282421891.742365442826219.165.55145477.28481479157128.24155325.614.469820151418.972195191170828460591445.135.531447.065.524.101028.987.76103.9348.598.59423.5518.8584.8794.187.051132.276.421243.2410.13788.141.1427742.3416.531934.0710.88734.991.2325795.58574456.98794.6475.871333.4196164.140797.1983181223940636.276924.918356.9767280.4317634.729625.024338.974152.1486104.891214.8941.304.08316.7823.4177.3427206.532318.024458655.5978287.18130.5926022.5013.03735624152.3157.1313.4743435.489837.750338.966745.8641.2042.9538.010943.9246.6527713.94355.9361398.41149.157.618046158.141.18840130.23116.56191.99204.549142.78134.43191.017155.3324.1623.43766.720540616.510.8779124271.13188421314.5838411438.9702567433.21324251320.94214.733360.64363.28351.34270.840275.25412400247.31160.1347.38159.8923.21108.803309540780017.84871123503333332309617.4282127920005741176436067170190165.3951212917560.702248753431617.247.583140114.89638378131406.38129033.293.689815129682.722369439199221235753275.513.613280.273.593.332183.995.44117.2343.086.56979.2112.17197.5860.6715.57769.9114.38833.9923.18517.321.2718711.9219.801211.3125.03479.001.3917211.28390326.35947.9515.056623.2903178.211467.2045120400741729.310416.321953.0316226.0494729.060216.370052.718170.163670.412810.5462.033.00511.8724.8886.0790139.271932.395085762.1975192.68050.8867716.1015.11670928140.2843.0221.4193625.830127.424031.896533.4131.3033.1030.453538.4538.889682.799336.074901.85043.2712.95789143.852.13731107.7785.67181.39210.554125.26118.56195.798138.7925.3624.04700.101786330.021.0517650901.37772818412.08374003601120000294782000225284000584034000102.073979891.6028736216.18411.967440.92437.50429.39165.471161.53022585543.84172.8143.80172.9622.07114.416620623195727.63261942216666672952893.82286858110558695720432529383482.5527222164592.242257843691244.975.3144269.18336131133788.29135890.545.56983121909941654801112241688.627.011689.487.015.141190.6810.0698.3751.3411.24483.3724.72100.17119.689.121313.767.631570.3811.701024.681.3036411.0118.662570.6714.07852.081.434019.21778483.011846.8544.615843.9125187.6814127.5406238439429738.781732.250062.3607384.2896739.762432.253533.819174.6170137.041716.0031.804.82018.0625.2488.6308270.274015.689407764.7191370.19370.4705323.2015.73680136154.6061.7510.7985146.597449.949648.349148.9345.9848.0746.293059.5249.7725716.76868.7571718.93666.475.976653161.190.940455145.30136.95208.59217.432163.18164.25193.778165.3324.6623.77784.797160482.820.8229843941.02497633215.2677789352820000022623900017637100051781000072.3991386558.07013777282.42314.883379.67377.03362.00226.631230.68913457547.73158.7147.61159.1223.35108.164228495443017.68031289043333332981451.3286480215909751306844769135636130.3540143632495.022636274198464.117.417131026.22707656159784.56160998.234.649917156398.742750066238127368083561.394.443537.874.454.352369.526.67118.6542.568.181038.3615.29212.2275.2816.18987.7714.861076.3024.55651.201.3723116.8221.031520.4626.50603.361.4921308.51501938.97637.8546.280729.2692193.469982.5527150974278791.974519.895956.3260283.7118792.457119.978844.751183.717086.937113.4349.243.54715.1024.3592.5433172.730530.735649166.4697240.40950.7158520.3317.44678084161.2652.8117.8868933.143034.184540.210742.3239.5241.4638.350540.5246.0718098.80447.1031177.57145.6010.83575164.171.95016129.22111.95207.54231.540138.95129.79210.235153.9723.9622.75432.073659262.941.1786900191.56963873111.8177004269198300032247500025503600066565500093.9031065197.5178552199.57511.2435.85436.77412.09143.597140.27730163044.16171.5344.19171.4122.20113.728436576722334.53442186030000003518612.7429973286704806305025387456664.9621501867112.742452264105338.275.4171389111.56351517140932.43151573.486.759587135921.7022048711972271813491803.098.821804.958.816.431272.5812.55101.0549.9813.40507.6231.43105.07152.109.321713.907.622097.5913.321196.031.3945746.2719.643255.7513.621173.421.5042487.491003089.415222.3575.365855.4706204.2260156.2377299129297803.446839.592965.3924488.6254802.156939.655729.784187.5171170.256217.2625.465.58919.5924.4695.0848335.989015.813343068.1249468.92630.3671625.0217.44686597163.5863.538.76146258.900462.356053.811654.1351.0551.4651.936463.0053.2137170.85593.3502333.75570.754.827648165.460.786803148.84149.01201.76217.701173.74173.58193.151175.3526.2625.34716.618001456.270.74510747650.991100874113.057425055408200026801600020451900054434200083.0241206867.53811845260.90813.8425.48425.45410.64209.943212.30213012347.82158.4147.87158.2423.40107.904432482309019.33851491153333332848831.2477476514899051474994486127078122.9737673574540.352463393481927.796.583133586.69688172165787.42161270.014.749247165810.672690298233743373153186.874.953217.574.944.362162.687.32113.5744.478.42961.4116.56190.8783.7314.371112.6213.701166.6922.30716.951.2725079.4119.631628.9923.66675.881.3723118.27522787.37963.1507.663131.3942174.360291.5684161712224716.024122.070754.3162294.2079716.119522.118342.087169.934993.965714.0046.244.00115.7723.8685.8688186.088724.108243362.2907256.52350.6555421.0416.69687000171.6554.2715.3971735.116237.280441.951943.2540.6742.8140.509641.0947.2421129.41250.4581261.44146.148.575596175.181.30138137.52119.84219.43237.131139.65130.26214.387154.3821.8520.70663.825195297.720.9638350871.38672133515.2837008971515400028895900022717500069134800064.5001568365.34812245225.69813.267380.10375.36365.79166.988163.54325011543.46174.2843.44174.3921.32118.466971583309719.05581702293333333893409.9545229198653793293328748400179.3024243378044.122530584786407.257.1131699.79436633156012.00167224.226.709112151997.7227618362672821367214538.436.924533.126.926.103072.3910.33105.5047.8712.441279.1524.81274.66116.3020.721542.7318.421735.5730.951033.391.7434339.2125.832475.9534.00940.291.933271.17823388.712568.1684.847046.6790241.3333132.29722464645211010.000831.445570.2051455.11841010.583331.400033.746230.9178138.136213.9930.365.09815.7124.20117.4838271.880623.094244086.4635369.54200.4559119.0318.73678966172.2450.6711.3194451.679552.747762.565641.5942.5645.4960.097856.0748.3122242.53076.5101912.74461.666.246704179.740.937918146.48138.52224.80231.997180.55168.38203.194196.3368.3868.08626.976115604.760.71211236630.927107858613.3179323151929400021309600016837400051058700044.5522244635.99522228323.07312.383325.93325.13311.11272.730268.94416385142.08180.0341.92180.7120.59122.642088891597319.89311278093333332937926.06126994613365047931373967113149161.5033144271575.651762844262554.197.517142854.4793742160307.52160541.793.6711245164486.942770547297029366462962.185.363023.565.263.471771.708.96112.8044.777.01450.5835.43142.53112.1217.77899.059.611661.4835.34904.011.2325216.389.553345.7133.19481.601.3822808.14419447.96442.7471.629733.8978173.201492.2695113495056855.996818.669244.1261362.2935855.778118.694351.838191.308883.62209.7659.553.71710.8828.2492.0537173.771233.003833749.9551320.00580.7021513.6913.20719675143.4233.7130.8694735.836229.839735.907827.4726.7928.5045.794728.1331.6718868.72340.4111010.27731.3514.44702148.731.71129111.9291.70171.63194.14194.9887.55176.036105.9674.6873.49357.235290302.141.0667502181.3487541049.67815066798200029501000023846000065567500051.7741932240.94219540227.37111.933407.09405.08388.39168.425160.39928752841.63181.9741.89180.8220.89120.864265338129339.13632422956666672802626.2648865969538743644419795264680.1716413270779.441564873551712.127.35147518.25466697180812.11205570.626.5711235178255.9525799263071331476531467.6710.841495.9210.636.09862.0918.48111.6045.2512.30217.1873.5878.16204.179.851619.834.693402.8235.121813.341.1654275.428.867209.1617.01939.071.3247801.07838351.812874.9488.406665.2131179.8852177.5939226944746847.375537.699645.3578704.9499848.910437.629733.036190.8367167.383212.5629.667.37914.1229.1492.6396345.181614.686358149.9661639.76870.3550217.6311.33722240137.4741.4419.6462069.588958.326967.126636.4736.0137.2284.863544.4838.9239798.69180.3892009.71649.397.347379144.222.46627131.90128.72176.67201.074133.13131.93180.919136.6062.1861.90659.145325680.310.8139834731.07892785815.4338778639.4092537732.84224360346.26414.7325.08321.66312.11295.587292.72914025245.28167.3145.13167.8622.21113.702025639800018.80441177910000002842403.96144321615206138253464621127865176.5537694068619.972009584053902.817.517135424.09743700141031.60141544.553.2910340153700.702420422277553219602358.375.032400.774.953.041413.058.43122.3641.276.46360.4933.22116.82102.6714.78810.687.751544.9528.09853.151.0522510.587.753090.2826.68449.391.1920000.76398769.36109.7386.881131.0113144.306183.0341104010467689.675417.392840.6830294.7603690.235417.384355.485158.555775.67239.3764.903.37610.5126.0776.1206157.596933.300643941.8063286.87840.7517313.1713.77788731141.6834.3531.8319329.174825.345431.011327.0326.6528.8240.976133.0233.309964.410535.561889.01437.0815.69182148.121.82190109.3185.66173.16206.814106.2998.13190.736118.4766.1266.43461.110891342.370.9538501611.17685146412.7177345945.1772213836.48321929220.50011.7425.45433.55411.38175.006166.31019679045.18167.65808746345.31167.1622.57111.874035510232737.01552276353333332971169.0559746580780623096723306777587.2819563701213.861908733969670.997.183135517.90640738204325.45205476.786.1610381200467.732779890367162822871198.229.941217.979.785.84689.0517.34121.0841.7111.19177.6967.4465.81181.988.651382.223.983005.7228.731664.200.9947664.177.306564.4714.19844.381.1441669.50798077.112235.1399.332759.9668151.8582157.8120210724462685.957634.786240.6995589.2842686.447634.855033.790159.7519150.089014.2232.256.76116.0027.0976.5637313.140516.508776741.4567578.25290.3809119.2712.60789297139.8847.4918.2664661.183351.394559.677539.2539.0341.7375.248551.7444.2426940.97668.5091712.71857.707.523824148.452.99340138.19136.71176.18213.420152.28150.71200.381155.3850.0149.28889.882751889.711.0727463021.34774255012.9512701536291800015420900011791900035968900035.8962786128.72327853421.48513.55295.42294.82283.16374.171373.67714889645.51166.4345.66165.8922.29113.291461463873016.1504967125333332164237.05150860720712831420666321171646233.9051993346967.771773473159962.477.383178203.11700379113630.04118110.632.5913034109860.582311235208713138552047.933.872081.753.802.341232.646.43124.4640.585.01313.1425.52102.5177.9912.93617.716.791175.7224.93640.880.9217148.896.82347.8321.72368.021.0415262.36286703.74397.2338.983023.5945126.160763.350077391048605.666513.207833.0304242.0444605.573013.209967.647143.487355.74788.1886.382.6199.1624.9969.1881115.598340.552017237.0399215.84220.9874212.2111.45812732109.4733.9341.9676223.165519.758923.389026.6424.7026.2629.313933.0531.0310152.75727.619690.47037.0019.49328115.371.9420083.3865.82134.34173.290100.8793.17166.785113.1856.7354.33725.346436445.240.75010677161.00299795712.38460857179300024505300018765400056217200042.4232358034.36023290256.36411.733379.26378.61360.92209.370204.22715722945.89165.0646.10164.3322.81110.712941521043026.37861903690000002874778.009661891030474943670300187290115.7725343597757.551711383912323.127.533144086.12803231207339.64207770.194.6810597199978.552762454289896410961043.487.621072.357.424.46604.1713.20121.9241.428.77155.1551.5155.49144.017.411076.163.412339.1624.611296.570.8636784.836.414979.2711.49695.060.9932137.13580306.38906.1350.634445.5497127.1627125.5955154099244599.808026.539133.1059482.9247600.724626.516440.403141.3563113.071213.4542.355.39115.0526.0469.0371231.512621.224064936.3820439.33410.4935418.3912.05809727141.5045.1722.1426746.270438.904343.507736.8435.8938.4655.409138.4342.0822099.32454.9171372.93343.049.733065150.483.34125130.49117.26176.86211.627127.62116.97200.424139.86OpenBenchmarking.org

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 too. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.10Device: CPU - Batch Size: 512 - Model: ResNet-50Xeon Gold 6338 2PXeon Gold 6338Xeon Gold 6342 2PXeon Gold 6342Xeon Gold 6346 2PXeon Gold 6346EPYC 7543EPYC 7343 2PEPYC 7413 2PEPYC 7513EPYC 7413EPYC 7513 2PEPYC 7343EPYC 7713P20406080100SE +/- 0.37, N = 3SE +/- 0.01, N = 3SE +/- 0.52, N = 3SE +/- 0.03, N = 3SE +/- 0.15, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 374.6868.3866.1262.1856.7350.0126.2625.4325.3624.6624.1623.9622.9121.85

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.10Device: CPU - Batch Size: 256 - Model: ResNet-50Xeon Gold 6338 2PXeon Gold 6338Xeon Gold 6342 2PXeon Gold 6342Xeon Gold 6346 2PXeon Gold 6346EPYC 7543EPYC 7413 2PEPYC 7343 2PEPYC 7513EPYC 7413EPYC 7513 2PEPYC 7343EPYC 7713P1632486480SE +/- 0.21, N = 3SE +/- 0.03, N = 3SE +/- 0.23, N = 3SE +/- 0.03, N = 3SE +/- 0.10, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 373.4968.0866.4361.9054.3349.2825.3424.0424.0323.7723.4322.7522.3720.70

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.i3dXeon Gold 6338 2PEPYC 7513 2PXeon Gold 6342 2PEPYC 7343 2PXeon Gold 6338Xeon Gold 6342EPYC 7713PEPYC 7413 2PEPYC 7543Xeon Gold 6346 2PEPYC 7413EPYC 7513EPYC 7343Xeon Gold 63462004006008001000SE +/- 0.43, N = 3SE +/- 0.45, N = 3SE +/- 3.99, N = 9SE +/- 0.39, N = 3SE +/- 0.51, N = 3SE +/- 9.17, N = 3SE +/- 0.20, N = 3SE +/- 9.39, N = 3SE +/- 1.05, N = 3SE +/- 0.98, N = 3SE +/- 5.59, N = 3SE +/- 0.87, N = 3SE +/- 0.88, N = 3SE +/- 0.67, N = 3357.24432.07461.11484.99626.98659.15663.83700.10716.62725.35766.72784.80880.64889.881. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -lmpi_usempif08 -lmpi_mpifh -lmpi

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 3.4Blend File: Barbershop - Compute: CPU-OnlyEPYC 7513 2PEPYC 7713PXeon Gold 6338 2PEPYC 7413 2PXeon Gold 6342 2PEPYC 7343 2PXeon Gold 6346 2PEPYC 7543EPYC 7513Xeon Gold 6338EPYC 7413Xeon Gold 6342EPYC 7343Xeon Gold 63462004006008001000SE +/- 0.82, N = 3SE +/- 0.59, N = 3SE +/- 0.29, N = 3SE +/- 0.36, N = 3SE +/- 0.18, N = 3SE +/- 0.53, N = 3SE +/- 0.38, N = 3SE +/- 0.45, N = 3SE +/- 0.04, N = 3SE +/- 0.64, N = 3SE +/- 2.04, N = 3SE +/- 3.07, N = 3SE +/- 0.57, N = 3SE +/- 0.21, N = 3262.94297.72302.14330.02342.37435.02445.24456.27482.82604.76616.51680.31815.39889.71

PostgreSQL

This is a benchmark of PostgreSQL using the integrated pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 15Scaling Factor: 1000 - Clients: 800 - Mode: Read Only - Average LatencyXeon Gold 6338EPYC 7543Xeon Gold 6346 2PXeon Gold 6342EPYC 7513EPYC 7413EPYC 7343 2PXeon Gold 6342 2PEPYC 7713PEPYC 7413 2PXeon Gold 6338 2PXeon Gold 6346EPYC 7343EPYC 7513 2P0.26510.53020.79531.06041.3255SE +/- 0.000, N = 3SE +/- 0.003, N = 3SE +/- 0.008, N = 12SE +/- 0.001, N = 3SE +/- 0.032, N = 11SE +/- 0.002, N = 3SE +/- 0.011, N = 3SE +/- 0.031, N = 12SE +/- 0.020, N = 12SE +/- 0.025, N = 9SE +/- 0.006, N = 3SE +/- 0.006, N = 3SE +/- 0.012, N = 3SE +/- 0.060, N = 60.7120.7450.7500.8130.8220.8770.9350.9530.9631.0511.0661.0721.1501.1781. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 1000 - Clients: 800 - Mode: Read OnlyXeon Gold 6338EPYC 7543Xeon Gold 6346 2PEPYC 7513Xeon Gold 6342EPYC 7413EPYC 7343 2PXeon Gold 6342 2PEPYC 7713PEPYC 7413 2PXeon Gold 6338 2PXeon Gold 6346EPYC 7343EPYC 7513 2P200K400K600K800K1000KSE +/- 137.25, N = 3SE +/- 4126.34, N = 3SE +/- 10990.82, N = 12SE +/- 28926.74, N = 11SE +/- 1328.10, N = 3SE +/- 2318.40, N = 3SE +/- 9801.20, N = 3SE +/- 30362.30, N = 12SE +/- 19623.01, N = 12SE +/- 19094.08, N = 9SE +/- 4309.16, N = 3SE +/- 4113.36, N = 3SE +/- 7215.33, N = 3SE +/- 41984.11, N = 61123663107476510677169843949834739124278556428501618350877650907502187463026957616900191. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 15Scaling Factor: 1000 - Clients: 1000 - Mode: Read Only - Average LatencyXeon Gold 6338EPYC 7543Xeon Gold 6346 2PEPYC 7513Xeon Gold 6342EPYC 7413Xeon Gold 6342 2PEPYC 7343 2PXeon Gold 6346Xeon Gold 6338 2PEPYC 7413 2PEPYC 7713PEPYC 7343EPYC 7513 2P0.3530.7061.0591.4121.765SE +/- 0.004, N = 3SE +/- 0.004, N = 3SE +/- 0.008, N = 3SE +/- 0.002, N = 3SE +/- 0.001, N = 3SE +/- 0.010, N = 3SE +/- 0.014, N = 12SE +/- 0.005, N = 3SE +/- 0.003, N = 3SE +/- 0.050, N = 12SE +/- 0.021, N = 12SE +/- 0.009, N = 3SE +/- 0.003, N = 3SE +/- 0.027, N = 90.9270.9911.0021.0241.0781.1311.1761.1781.3471.3481.3771.3861.4591.5691. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 1000 - Clients: 1000 - Mode: Read OnlyXeon Gold 6338EPYC 7543Xeon Gold 6346 2PEPYC 7513Xeon Gold 6342EPYC 7413Xeon Gold 6342 2PEPYC 7343 2PXeon Gold 6338 2PXeon Gold 6346EPYC 7413 2PEPYC 7713PEPYC 7343EPYC 7513 2P200K400K600K800K1000KSE +/- 4354.62, N = 3SE +/- 4439.63, N = 3SE +/- 8418.28, N = 3SE +/- 2084.66, N = 3SE +/- 1181.85, N = 3SE +/- 7500.42, N = 3SE +/- 10454.75, N = 12SE +/- 3271.24, N = 3SE +/- 30718.02, N = 12SE +/- 1889.54, N = 3SE +/- 11363.61, N = 12SE +/- 4640.40, N = 3SE +/- 1636.62, N = 3SE +/- 10642.91, N = 9107858610087419979579763329278588842138514648490197541047425507281847213356852396387311. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

CloudSuite Web Serving

CloudSuite Web Serving is a Docker-based web server benchmark making use of a web server with Memcached and a MySQL database server. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgops/sec, More Is BetterCloudSuite Web ServingLoad Scale: 500Xeon Gold 6342EPYC 7713PEPYC 7513EPYC 7413Xeon Gold 6338EPYC 7543Xeon Gold 6346Xeon Gold 6342 2PXeon Gold 6346 2PEPYC 7413 2PEPYC 7513 2PEPYC 7343EPYC 7343 2PXeon Gold 6338 2P4812162015.43315.28315.26714.58313.31713.05012.95012.71712.30012.08311.81711.60011.2179.600

CloudSuite Graph Analytics

CloudSuite Graph Analytics uses Apache GraphX + Spark to perform graph analytics (PageRank) on sample Twitter data. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterCloudSuite Graph Analytics 4.0GraphX Algorithm: Triangle CountEPYC 7513 2PEPYC 7713PXeon Gold 6342 2PEPYC 7413 2PEPYC 7543EPYC 7343 2PEPYC 7513Xeon Gold 6338 2PEPYC 7413Xeon Gold 6346 2PXeon Gold 6342Xeon Gold 6338EPYC 7343Xeon Gold 634630K60K90K120K150KSE +/- 3129.18, N = 15SE +/- 1101.67, N = 15SE +/- 486.76, N = 3SE +/- 4547.27, N = 12SE +/- 816.75, N = 5SE +/- 2111.36, N = 15SE +/- 844.55, N = 3SE +/- 1737.14, N = 15SE +/- 911.07, N = 15SE +/- 1088.95, N = 15SE +/- 969.69, N = 3SE +/- 1190.06, N = 15SE +/- 192.25, N = 3SE +/- 2880.79, N = 12700427008973459740037425077278778937815084114846088778693231108988127015

Graph500

This is a benchmark of the reference implementation of Graph500, an HPC benchmark focused on data intensive loads and commonly tested on supercomputers for complex data problems. Graph500 primarily stresses the communication subsystem of the hardware under test. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbfs max_TEPS, More Is BetterGraph500 3.0Scale: 26EPYC 7713PEPYC 7513 2PXeon Gold 6338 2PEPYC 7413 2PXeon Gold 6346 2PEPYC 7543EPYC 7513Xeon Gold 6338EPYC 7343 2PXeon Gold 6346EPYC 7343150M300M450M600M750M7151540006919830006679820006011200005717930005540820005282000005192940004444740003629180003129890001. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi

Scale: 26

EPYC 7413: The test quit with a non-zero exit status. E: AML: Fatal: non power2 groupsize unsupported. Define macro PROCS_PER_NODE_NOT_POWER_OF_TWO to override

Xeon Gold 6342: The test quit with a non-zero exit status. E: AML: Fatal: non power2 groupsize unsupported. Define macro PROCS_PER_NODE_NOT_POWER_OF_TWO to override

Xeon Gold 6342 2P: The test quit with a non-zero exit status. E: AML: Fatal: non power2 groupsize unsupported. Define macro PROCS_PER_NODE_NOT_POWER_OF_TWO to override

OpenBenchmarking.orgsssp max_TEPS, More Is BetterGraph500 3.0Scale: 26EPYC 7513 2PXeon Gold 6338 2PEPYC 7413 2PEPYC 7713PEPYC 7543Xeon Gold 6346 2PEPYC 7513EPYC 7343 2PXeon Gold 6338Xeon Gold 6346EPYC 734370M140M210M280M350M3224750002950100002947820002889590002680160002450530002262390002189860002130960001542090001497100001. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi

Scale: 26

EPYC 7413: The test quit with a non-zero exit status. E: AML: Fatal: non power2 groupsize unsupported. Define macro PROCS_PER_NODE_NOT_POWER_OF_TWO to override

Xeon Gold 6342: The test quit with a non-zero exit status. E: AML: Fatal: non power2 groupsize unsupported. Define macro PROCS_PER_NODE_NOT_POWER_OF_TWO to override

Xeon Gold 6342 2P: The test quit with a non-zero exit status. E: AML: Fatal: non power2 groupsize unsupported. Define macro PROCS_PER_NODE_NOT_POWER_OF_TWO to override

OpenBenchmarking.orgsssp median_TEPS, More Is BetterGraph500 3.0Scale: 26EPYC 7513 2PXeon Gold 6338 2PEPYC 7713PEPYC 7413 2PEPYC 7543Xeon Gold 6346 2PEPYC 7513EPYC 7343 2PXeon Gold 6338Xeon Gold 6346EPYC 734350M100M150M200M250M2550360002384600002271750002252840002045190001876540001763710001742190001683740001179190001142950001. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi

Scale: 26

EPYC 7413: The test quit with a non-zero exit status. E: AML: Fatal: non power2 groupsize unsupported. Define macro PROCS_PER_NODE_NOT_POWER_OF_TWO to override

Xeon Gold 6342: The test quit with a non-zero exit status. E: AML: Fatal: non power2 groupsize unsupported. Define macro PROCS_PER_NODE_NOT_POWER_OF_TWO to override

Xeon Gold 6342 2P: The test quit with a non-zero exit status. E: AML: Fatal: non power2 groupsize unsupported. Define macro PROCS_PER_NODE_NOT_POWER_OF_TWO to override

OpenBenchmarking.orgbfs median_TEPS, More Is BetterGraph500 3.0Scale: 26EPYC 7713PEPYC 7513 2PXeon Gold 6338 2PEPYC 7413 2PXeon Gold 6346 2PEPYC 7543EPYC 7513Xeon Gold 6338EPYC 7343 2PXeon Gold 6346EPYC 7343150M300M450M600M750M6913480006656550006556750005840340005621720005443420005178100005105870004225290003596890003098170001. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi

Scale: 26

EPYC 7413: The test quit with a non-zero exit status. E: AML: Fatal: non power2 groupsize unsupported. Define macro PROCS_PER_NODE_NOT_POWER_OF_TWO to override

Xeon Gold 6342: The test quit with a non-zero exit status. E: AML: Fatal: non power2 groupsize unsupported. Define macro PROCS_PER_NODE_NOT_POWER_OF_TWO to override

Xeon Gold 6342 2P: The test quit with a non-zero exit status. E: AML: Fatal: non power2 groupsize unsupported. Define macro PROCS_PER_NODE_NOT_POWER_OF_TWO to override

PostgreSQL

This is a benchmark of PostgreSQL using the integrated pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 15Scaling Factor: 1000 - Clients: 1000 - Mode: Read Write - Average LatencyXeon Gold 6346EPYC 7413Xeon Gold 6342EPYC 7343Xeon Gold 6346 2PXeon Gold 6338Xeon Gold 6342 2PXeon Gold 6338 2PEPYC 7713PEPYC 7513EPYC 7543EPYC 7513 2PEPYC 7413 2PEPYC 7343 2P306090120150SE +/- 0.27, N = 3SE +/- 0.37, N = 7SE +/- 0.23, N = 3SE +/- 0.34, N = 3SE +/- 0.54, N = 3SE +/- 0.17, N = 3SE +/- 0.37, N = 3SE +/- 0.71, N = 3SE +/- 2.55, N = 9SE +/- 1.40, N = 12SE +/- 1.07, N = 12SE +/- 0.78, N = 3SE +/- 0.71, N = 3SE +/- 0.63, N = 335.9038.9739.4140.2942.4244.5545.1851.7764.5072.4083.0293.90102.07119.681. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 1000 - Clients: 1000 - Mode: Read WriteXeon Gold 6346EPYC 7413Xeon Gold 6342EPYC 7343Xeon Gold 6346 2PXeon Gold 6338Xeon Gold 6342 2PXeon Gold 6338 2PEPYC 7713PEPYC 7513EPYC 7543EPYC 7513 2PEPYC 7413 2PEPYC 7343 2P6K12K18K24K30KSE +/- 212.63, N = 3SE +/- 239.71, N = 7SE +/- 144.91, N = 3SE +/- 210.94, N = 3SE +/- 300.77, N = 3SE +/- 84.27, N = 3SE +/- 180.74, N = 3SE +/- 265.07, N = 3SE +/- 567.20, N = 9SE +/- 246.74, N = 12SE +/- 167.15, N = 12SE +/- 88.49, N = 3SE +/- 68.86, N = 3SE +/- 43.57, N = 3278612567425377248212358022446221381932215683138651206810651979883561. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 15Scaling Factor: 1000 - Clients: 800 - Mode: Read Write - Average LatencyXeon Gold 6346EPYC 7343Xeon Gold 6342EPYC 7413Xeon Gold 6346 2PXeon Gold 6338Xeon Gold 6342 2PXeon Gold 6338 2PEPYC 7513EPYC 7713PEPYC 7543EPYC 7413 2PEPYC 7343 2PEPYC 7513 2P20406080100SE +/- 0.06, N = 3SE +/- 0.26, N = 3SE +/- 0.18, N = 3SE +/- 0.81, N = 12SE +/- 0.44, N = 3SE +/- 0.31, N = 3SE +/- 0.22, N = 3SE +/- 0.18, N = 3SE +/- 0.22, N = 3SE +/- 0.72, N = 3SE +/- 0.15, N = 3SE +/- 1.13, N = 3SE +/- 1.69, N = 12SE +/- 7.23, N = 928.7231.1632.8433.2134.3636.0036.4840.9458.0765.3567.5491.6094.5997.521. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 15Scaling Factor: 1000 - Clients: 800 - Mode: Read WriteXeon Gold 6346EPYC 7343Xeon Gold 6342EPYC 7413Xeon Gold 6346 2PXeon Gold 6338Xeon Gold 6342 2PXeon Gold 6338 2PEPYC 7513EPYC 7713PEPYC 7543EPYC 7413 2PEPYC 7513 2PEPYC 7343 2P6K12K18K24K30KSE +/- 55.23, N = 3SE +/- 214.52, N = 3SE +/- 132.14, N = 3SE +/- 611.47, N = 12SE +/- 299.85, N = 3SE +/- 190.25, N = 3SE +/- 131.27, N = 3SE +/- 83.93, N = 3SE +/- 52.15, N = 3SE +/- 136.50, N = 3SE +/- 26.13, N = 3SE +/- 109.43, N = 3SE +/- 590.01, N = 9SE +/- 176.72, N = 1227853256792436024251232902222821929195401377712245118458736855284921. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

Timed LLVM Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 13.0Build System: Unix MakefilesEPYC 7513 2PEPYC 7413 2PXeon Gold 6342 2PEPYC 7713PXeon Gold 6338 2PEPYC 7343 2PXeon Gold 6346 2PEPYC 7543EPYC 7513EPYC 7413Xeon Gold 6338Xeon Gold 6342EPYC 7343Xeon Gold 634690180270360450SE +/- 1.00, N = 3SE +/- 0.83, N = 3SE +/- 1.05, N = 3SE +/- 0.36, N = 3SE +/- 0.66, N = 3SE +/- 3.14, N = 3SE +/- 2.63, N = 5SE +/- 2.17, N = 9SE +/- 1.45, N = 3SE +/- 3.55, N = 5SE +/- 1.83, N = 3SE +/- 2.99, N = 3SE +/- 1.84, N = 3SE +/- 3.03, N = 3199.58216.18220.50225.70227.37240.49256.36260.91282.42320.94323.07346.26392.19421.49

CloudSuite Web Serving

CloudSuite Web Serving is a Docker-based web server benchmark making use of a web server with Memcached and a MySQL database server. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgops/sec, More Is BetterCloudSuite Web ServingLoad Scale: 400EPYC 7513EPYC 7413Xeon Gold 6342EPYC 7543Xeon Gold 6346EPYC 7713PXeon Gold 6338EPYC 7413 2PXeon Gold 6338 2PEPYC 7343Xeon Gold 6346 2PXeon Gold 6342 2PEPYC 7343 2PEPYC 7513 2P4812162014.8814.7314.7013.8013.5513.2712.3811.9711.9311.8311.7311.7011.4311.20

ClickHouse

ClickHouse is an open-source, high performance OLAP data management system. This test profile uses ClickHouse's standard benchmark recommendations per https://clickhouse.com/docs/en/operations/performance-test/ / https://github.com/ClickHouse/ClickBench/tree/main/clickhouse with the 100 million rows web analytics dataset. The reported value is the query processing time using the geometric mean of all separate queries performed as an aggregate. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, Third RunEPYC 7343 2PEPYC 7413 2PEPYC 7513 2PEPYC 7543Xeon Gold 6342 2PXeon Gold 6338 2PEPYC 7713PEPYC 7513Xeon Gold 6346 2PEPYC 7413EPYC 7343Xeon Gold 6338Xeon Gold 6342Xeon Gold 6346100200300400500SE +/- 1.18, N = 3SE +/- 5.82, N = 3SE +/- 2.98, N = 3SE +/- 0.23, N = 3SE +/- 3.32, N = 3SE +/- 4.19, N = 3SE +/- 1.15, N = 3SE +/- 2.21, N = 3SE +/- 9.11, N = 12SE +/- 2.07, N = 3SE +/- 1.99, N = 3SE +/- 1.64, N = 3SE +/- 1.90, N = 3SE +/- 1.18, N = 3443.72440.92435.85425.48425.45407.09380.10379.67379.26360.64345.53325.93325.08295.42MIN: 24.16 / MAX: 6000MIN: 31.68 / MAX: 4615.38MIN: 35.71 / MAX: 4615.38MIN: 22.74 / MAX: 6000MIN: 28.42 / MAX: 5000MIN: 29.41 / MAX: 5454.55MIN: 31.95 / MAX: 6000MIN: 21.33 / MAX: 6666.67MIN: 20.98 / MAX: 6000MIN: 17.17 / MAX: 6666.67MIN: 13.57 / MAX: 7500MIN: 15.81 / MAX: 6000MIN: 14.7 / MAX: 6666.67MIN: 10.91 / MAX: 7500

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, Second RunEPYC 7343 2PEPYC 7413 2PEPYC 7513 2PXeon Gold 6342 2PEPYC 7543Xeon Gold 6338 2PXeon Gold 6346 2PEPYC 7513EPYC 7713PEPYC 7413EPYC 7343Xeon Gold 6338Xeon Gold 6342Xeon Gold 6346100200300400500SE +/- 1.63, N = 3SE +/- 7.88, N = 3SE +/- 2.78, N = 3SE +/- 2.05, N = 3SE +/- 0.54, N = 3SE +/- 5.74, N = 3SE +/- 9.42, N = 12SE +/- 1.23, N = 3SE +/- 3.18, N = 3SE +/- 2.06, N = 3SE +/- 3.50, N = 3SE +/- 2.19, N = 3SE +/- 3.16, N = 3SE +/- 1.01, N = 3443.07437.50436.77433.55425.45405.08378.61377.03375.36363.28346.00325.13321.66294.82MIN: 23.91 / MAX: 5454.55MIN: 31.66 / MAX: 5000MIN: 35.19 / MAX: 5454.55MIN: 28.48 / MAX: 6000MIN: 22.68 / MAX: 6666.67MIN: 29.11 / MAX: 5000MIN: 20.51 / MAX: 6666.67MIN: 21.37 / MAX: 6666.67MIN: 32 / MAX: 6000MIN: 17.19 / MAX: 7500MIN: 13.53 / MAX: 7500MIN: 15.85 / MAX: 5454.55MIN: 14.82 / MAX: 6666.67MIN: 10.95 / MAX: 7500

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, First Run / Cold CacheEPYC 7413 2PEPYC 7343 2PEPYC 7513 2PXeon Gold 6342 2PEPYC 7543Xeon Gold 6338 2PEPYC 7713PEPYC 7513Xeon Gold 6346 2PEPYC 7413EPYC 7343Xeon Gold 6342Xeon Gold 6338Xeon Gold 634690180270360450SE +/- 0.97, N = 3SE +/- 2.96, N = 3SE +/- 2.43, N = 3SE +/- 1.29, N = 3SE +/- 1.20, N = 3SE +/- 2.01, N = 3SE +/- 3.48, N = 3SE +/- 3.29, N = 3SE +/- 9.20, N = 12SE +/- 1.47, N = 3SE +/- 2.07, N = 3SE +/- 3.58, N = 3SE +/- 1.98, N = 3SE +/- 0.53, N = 3429.39423.79412.09411.38410.64388.39365.79362.00360.92351.34336.88312.11311.11283.16MIN: 31.35 / MAX: 5000MIN: 23.78 / MAX: 4285.71MIN: 34.8 / MAX: 4000MIN: 28.04 / MAX: 5000MIN: 22.56 / MAX: 6666.67MIN: 29.17 / MAX: 5454.55MIN: 31.86 / MAX: 5454.55MIN: 21.03 / MAX: 6000MIN: 20.41 / MAX: 6000MIN: 17.17 / MAX: 6666.67MIN: 13.48 / MAX: 7500MIN: 14.74 / MAX: 6666.67MIN: 15.86 / MAX: 5454.55MIN: 10.81 / MAX: 6666.67

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 18.8Time To CompileEPYC 7513 2PEPYC 7413 2PEPYC 7713PXeon Gold 6338 2PXeon Gold 6342 2PEPYC 7343 2PXeon Gold 6346 2PEPYC 7543EPYC 7513EPYC 7413Xeon Gold 6338Xeon Gold 6342EPYC 7343Xeon Gold 634680160240320400SE +/- 0.52, N = 3SE +/- 0.06, N = 3SE +/- 0.62, N = 3SE +/- 0.38, N = 3SE +/- 0.55, N = 3SE +/- 0.12, N = 3SE +/- 0.41, N = 3SE +/- 0.19, N = 3SE +/- 0.25, N = 3SE +/- 0.09, N = 3SE +/- 0.36, N = 3SE +/- 0.06, N = 3SE +/- 0.12, N = 3SE +/- 0.37, N = 3143.60165.47166.99168.43175.01191.00209.37209.94226.63270.84272.73295.59337.22374.17

Timed LLVM Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 13.0Build System: NinjaEPYC 7513 2PXeon Gold 6338 2PEPYC 7413 2PEPYC 7713PXeon Gold 6342 2PEPYC 7343 2PXeon Gold 6346 2PEPYC 7543EPYC 7513Xeon Gold 6338EPYC 7413Xeon Gold 6342EPYC 7343Xeon Gold 634680160240320400SE +/- 0.09, N = 3SE +/- 0.33, N = 3SE +/- 0.67, N = 3SE +/- 0.16, N = 3SE +/- 0.64, N = 3SE +/- 0.24, N = 3SE +/- 0.24, N = 3SE +/- 0.16, N = 3SE +/- 0.43, N = 3SE +/- 0.32, N = 3SE +/- 0.09, N = 3SE +/- 0.11, N = 3SE +/- 0.08, N = 3SE +/- 0.12, N = 3140.28160.40161.53163.54166.31190.97204.23212.30230.69268.94275.25292.73347.36373.68

CloudSuite In-Memory Analytics

CloudSuite In-Memory Analytics uses Apache Spark and runs a collaborative filtering algorithm in-memory on a dataset of user-movie ratings from Movielens. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterCloudSuite In-Memory Analytics 4.0Training Set Size: LargeEPYC 7343EPYC 7413EPYC 7543EPYC 7513Xeon Gold 6342EPYC 7343 2PXeon Gold 6346Xeon Gold 6346 2PXeon Gold 6338Xeon Gold 6342 2PEPYC 7413 2PEPYC 7713PXeon Gold 6338 2PEPYC 7513 2P60K120K180K240K300KSE +/- 535.64, N = 3SE +/- 235.29, N = 3SE +/- 210.33, N = 3SE +/- 796.65, N = 3SE +/- 623.63, N = 3SE +/- 1774.21, N = 4SE +/- 800.80, N = 3SE +/- 725.41, N = 3SE +/- 2349.58, N = 3SE +/- 546.89, N = 3SE +/- 530.20, N = 3SE +/- 955.82, N = 3SE +/- 775.32, N = 3SE +/- 859.70, N = 3122575124002130123134575140252147944148896157229163851196790225855250115287528301630

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 6.0Encoder: libx265 - Scenario: Video On DemandEPYC 7343EPYC 7543EPYC 7513EPYC 7413EPYC 7343 2PXeon Gold 6346 2PXeon Gold 6346Xeon Gold 6342Xeon Gold 6342 2PEPYC 7513 2PEPYC 7413 2PEPYC 7713PXeon Gold 6338Xeon Gold 6338 2P1122334455SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.11, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.09, N = 3SE +/- 0.05, N = 3SE +/- 0.15, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.06, N = 3SE +/- 0.05, N = 349.8247.8247.7347.3146.8445.8945.5145.2845.1844.1643.8443.4642.0841.631. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 6.0Encoder: libx265 - Scenario: Video On DemandEPYC 7343EPYC 7543EPYC 7513EPYC 7413EPYC 7343 2PXeon Gold 6346 2PXeon Gold 6346Xeon Gold 6342Xeon Gold 6342 2PEPYC 7513 2PEPYC 7413 2PEPYC 7713PXeon Gold 6338Xeon Gold 6338 2P4080120160200SE +/- 0.16, N = 3SE +/- 0.13, N = 3SE +/- 0.12, N = 3SE +/- 0.13, N = 3SE +/- 0.38, N = 3SE +/- 0.06, N = 3SE +/- 0.10, N = 3SE +/- 0.33, N = 3SE +/- 0.17, N = 3SE +/- 0.58, N = 3SE +/- 0.12, N = 3SE +/- 0.04, N = 3SE +/- 0.24, N = 3SE +/- 0.22, N = 3152.05158.41158.71160.13161.72165.06166.43167.31167.66171.53172.81174.28180.03181.971. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.0Encoder: libx265 - Scenario: PlatformEPYC 7343EPYC 7543EPYC 7513EPYC 7413EPYC 7343 2PXeon Gold 6346 2PXeon Gold 6346Xeon Gold 6342 2PXeon Gold 6342EPYC 7513 2PEPYC 7413 2PEPYC 7713PXeon Gold 6338Xeon Gold 6338 2P1122334455SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.10, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.07, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 349.8947.8747.6147.3846.6646.1045.6645.3145.1344.1943.8043.4441.9241.891. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 6.0Encoder: libx265 - Scenario: PlatformEPYC 7343EPYC 7543EPYC 7513EPYC 7413EPYC 7343 2PXeon Gold 6346 2PXeon Gold 6346Xeon Gold 6342 2PXeon Gold 6342EPYC 7513 2PEPYC 7413 2PEPYC 7713PXeon Gold 6338Xeon Gold 6338 2P4080120160200SE +/- 0.09, N = 3SE +/- 0.06, N = 3SE +/- 0.05, N = 3SE +/- 0.12, N = 3SE +/- 0.17, N = 3SE +/- 0.36, N = 3SE +/- 0.16, N = 3SE +/- 0.11, N = 3SE +/- 0.27, N = 3SE +/- 0.19, N = 3SE +/- 0.14, N = 3SE +/- 0.19, N = 3SE +/- 0.09, N = 3SE +/- 0.23, N = 3151.85158.24159.12159.89162.34164.33165.89167.16167.86171.41172.96174.39180.71180.821. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 6.0Encoder: libx265 - Scenario: UploadEPYC 7343EPYC 7343 2PEPYC 7543EPYC 7513EPYC 7413Xeon Gold 6346 2PXeon Gold 6342 2PXeon Gold 6346Xeon Gold 6342EPYC 7513 2PEPYC 7413 2PEPYC 7713PXeon Gold 6338 2PXeon Gold 6338612182430SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 324.2923.5623.4023.3523.2122.8122.5722.2922.2122.2022.0721.3220.8920.591. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 6.0Encoder: libx265 - Scenario: UploadEPYC 7343EPYC 7343 2PEPYC 7543EPYC 7513EPYC 7413Xeon Gold 6346 2PXeon Gold 6342 2PXeon Gold 6346Xeon Gold 6342EPYC 7513 2PEPYC 7413 2PEPYC 7713PXeon Gold 6338 2PXeon Gold 6338306090120150SE +/- 0.07, N = 3SE +/- 0.20, N = 3SE +/- 0.06, N = 3SE +/- 0.08, N = 3SE +/- 0.07, N = 3SE +/- 0.22, N = 3SE +/- 0.10, N = 3SE +/- 0.25, N = 3SE +/- 0.04, N = 3SE +/- 0.06, N = 3SE +/- 0.13, N = 3SE +/- 0.17, N = 3SE +/- 0.30, N = 3SE +/- 0.07, N = 3103.96107.19107.90108.16108.80110.71111.87113.29113.70113.72114.41118.46120.86122.641. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl

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 3.0Algorithm: SHA256EPYC 7513 2PEPYC 7713PEPYC 7413 2PEPYC 7343 2PEPYC 7543Xeon Gold 6338 2PEPYC 7513Xeon Gold 6342 2PEPYC 7413Xeon Gold 6346 2PEPYC 7343Xeon Gold 6338Xeon Gold 6342Xeon Gold 634620000M40000M60000M80000M100000MSE +/- 316349484.45, N = 3SE +/- 8398498.36, N = 3SE +/- 54030773.40, N = 3SE +/- 24582365.01, N = 3SE +/- 186860140.69, N = 3SE +/- 10952442.61, N = 3SE +/- 68531235.70, N = 3SE +/- 3033485.03, N = 3SE +/- 27629858.10, N = 3SE +/- 1989217.69, N = 3SE +/- 29163674.08, N = 3SE +/- 10848440.04, N = 3SE +/- 11924426.00, N = 3SE +/- 9109685.37, N = 384365767223697158330976620623195749694000047443248230904265338129342284954430403551023273309540780029415210430248911012672088891597320256398000146146387301. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

High Performance Conjugate Gradient

HPCG is the High Performance Conjugate Gradient and is a new scientific benchmark from Sandia National Lans focused for super-computer testing with modern real-world workloads compared to HPCC. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.1Xeon Gold 6338 2PXeon Gold 6342 2PEPYC 7343 2PEPYC 7513 2PEPYC 7413 2PXeon Gold 6346 2PXeon Gold 6338EPYC 7543EPYC 7713PXeon Gold 6342EPYC 7343EPYC 7413EPYC 7513Xeon Gold 6346918273645SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.21, N = 5SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 339.1437.0235.3234.5327.6326.3819.8919.3419.0618.8018.1417.8517.6816.151. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -lmpi_cxx -lmpi

nekRS

nekRS is an open-source Navier Stokes solver based on the spectral element method. NekRS supports both CPU and GPU/accelerator support though this test profile is currently configured for CPU execution. NekRS is part of Nek5000 of the Mathematics and Computer Science MCS at Argonne National Laboratory. This nekRS benchmark is primarily relevant to large core count HPC servers and otherwise may be very time consuming. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFLOP/s, More Is BetternekRS 22.0Input: TurboPipe PeriodicXeon Gold 6338 2PXeon Gold 6342 2PEPYC 7513 2PEPYC 7413 2PXeon Gold 6346 2PEPYC 7713PEPYC 7343 2PEPYC 7543EPYC 7513Xeon Gold 6338Xeon Gold 6342EPYC 7413Xeon Gold 634650000M100000M150000M200000M250000MSE +/- 1194804633.03, N = 3SE +/- 233956073.75, N = 3SE +/- 716358150.65, N = 3SE +/- 716743639.28, N = 3SE +/- 124957326.05, N = 3SE +/- 603340791.85, N = 3SE +/- 194054116.16, N = 3SE +/- 37382408.22, N = 3SE +/- 130435595.01, N = 3SE +/- 165905930.51, N = 3SE +/- 206475987.30, N = 3SE +/- 1160248871.77, N = 3SE +/- 285712164.79, N = 3242295666667227635333333218603000000194221666667190369000000170229333333166901000000149115333333128904333333127809333333117791000000112350333333967125333331. (CXX) g++ options: -fopenmp -O2 -march=native -mtune=native -ftree-vectorize -lmpi_cxx -lmpi

Input: TurboPipe Periodic

EPYC 7343: The test quit with a non-zero exit status. E: mpirun noticed that process rank 0 with PID 0 on node amd-test-02 exited on signal 4 (Illegal instruction).

Memcached

Memcached is a high performance, distributed memory object caching system. This Memcached test profiles makes use of memtier_benchmark for excuting this CPU/memory-focused server benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is BetterMemcached 1.6.18Set To Get Ratio: 1:100EPYC 7713PEPYC 7513 2PEPYC 7513Xeon Gold 6342 2PEPYC 7413 2PXeon Gold 6338Xeon Gold 6346 2PEPYC 7543Xeon Gold 6342Xeon Gold 6338 2PEPYC 7343 2PEPYC 7413Xeon Gold 6346EPYC 7343800K1600K2400K3200K4000KSE +/- 31526.72, N = 9SE +/- 1121.75, N = 3SE +/- 20057.86, N = 3SE +/- 43191.93, N = 15SE +/- 22542.41, N = 15SE +/- 34881.31, N = 3SE +/- 24448.73, N = 3SE +/- 40574.62, N = 3SE +/- 34942.45, N = 3SE +/- 60239.97, N = 15SE +/- 4664.77, N = 3SE +/- 18487.99, N = 3SE +/- 27101.83, N = 15SE +/- 9721.14, N = 33893409.953518612.742981451.322971169.052952893.822937926.062874778.002848831.242842403.962802626.262373328.372309617.422164237.051610909.221. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

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 7.9.2Test: Sequential FillXeon Gold 6346Xeon Gold 6342Xeon Gold 6338Xeon Gold 6346 2PEPYC 7513EPYC 7413EPYC 7543Xeon Gold 6342 2PXeon Gold 6338 2PEPYC 7713PEPYC 7343 2PEPYC 7513 2PEPYC 7413 2P300K600K900K1200K1500KSE +/- 2179.57, N = 3SE +/- 1492.53, N = 3SE +/- 4969.08, N = 3SE +/- 6746.06, N = 3SE +/- 2451.41, N = 3SE +/- 3079.56, N = 3SE +/- 1902.35, N = 3SE +/- 4947.74, N = 3SE +/- 3588.97, N = 3SE +/- 106.07, N = 3SE +/- 532.43, N = 3SE +/- 597.87, N = 3SE +/- 319.69, N = 31508607144321612699469661898648028212797747655974654886594522913235982997322868581. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti

Test: Sequential Fill

EPYC 7343: The test quit with a non-zero exit status.

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 0.11Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path TracerXeon Gold 6338 2PXeon Gold 6342 2PEPYC 7513 2PEPYC 7713PXeon Gold 6346 2PEPYC 7413 2PXeon Gold 6338EPYC 7343 2PEPYC 7543Xeon Gold 6342EPYC 7513EPYC 7413Xeon Gold 6346EPYC 734360K120K180K240K300KSE +/- 150.12, N = 3SE +/- 207.56, N = 3SE +/- 337.67, N = 3SE +/- 89.37, N = 3SE +/- 152.22, N = 3SE +/- 865.73, N = 3SE +/- 384.33, N = 3SE +/- 359.93, N = 3SE +/- 601.99, N = 3SE +/- 873.63, N = 3SE +/- 453.13, N = 3SE +/- 1060.89, N = 3SE +/- 339.77, N = 3SE +/- 981.14, N = 3695388078086704986531030471105581336501426111489901520611590972000572071282652381. (CXX) g++ options: -O3 -lm -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 7.9.2Test: Read While WritingEPYC 7513 2PEPYC 7713PXeon Gold 6338 2PEPYC 7413 2PXeon Gold 6342 2PEPYC 7543EPYC 7513Xeon Gold 6346 2PEPYC 7343 2PXeon Gold 6338EPYC 7413Xeon Gold 6342Xeon Gold 63462M4M6M8M10MSE +/- 135593.38, N = 15SE +/- 68024.06, N = 3SE +/- 153728.35, N = 12SE +/- 142144.80, N = 15SE +/- 44785.37, N = 3SE +/- 15721.89, N = 3SE +/- 32029.62, N = 3SE +/- 42331.24, N = 15SE +/- 76523.17, N = 13SE +/- 22775.73, N = 3SE +/- 43415.41, N = 4SE +/- 40873.57, N = 5SE +/- 23057.76, N = 380630507932933743644469572046230967514749951306844943670486429947931374117643382534631420661. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti

Test: Read While Writing

EPYC 7343: The test quit with a non-zero exit status.

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 0.11Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path TracerXeon Gold 6338 2PXeon Gold 6342 2PEPYC 7513 2PEPYC 7713PXeon Gold 6346 2PEPYC 7413 2PXeon Gold 6338EPYC 7343 2PEPYC 7543Xeon Gold 6342EPYC 7513EPYC 7413Xeon Gold 6346EPYC 73432K4K6K8K10KSE +/- 0.88, N = 3SE +/- 11.06, N = 3SE +/- 12.06, N = 3SE +/- 8.33, N = 3SE +/- 12.78, N = 3SE +/- 6.98, N = 3SE +/- 15.01, N = 3SE +/- 5.04, N = 3SE +/- 6.51, N = 3SE +/- 16.80, N = 3SE +/- 22.62, N = 3SE +/- 17.21, N = 3SE +/- 7.21, N = 3SE +/- 14.64, N = 3197923302538287430013252396743364486462147696067632181721. (CXX) g++ options: -O3 -lm -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path TracerXeon Gold 6338 2PXeon Gold 6342 2PEPYC 7513 2PEPYC 7713PXeon Gold 6346 2PEPYC 7413 2PXeon Gold 6338EPYC 7343 2PEPYC 7543Xeon Gold 6342EPYC 7513EPYC 7413Xeon Gold 6346EPYC 734350K100K150K200K250KSE +/- 247.04, N = 3SE +/- 130.77, N = 3SE +/- 95.38, N = 3SE +/- 129.50, N = 3SE +/- 405.08, N = 3SE +/- 593.91, N = 3SE +/- 153.33, N = 3SE +/- 322.54, N = 3SE +/- 100.17, N = 3SE +/- 380.50, N = 3SE +/- 22.36, N = 3SE +/- 660.98, N = 3SE +/- 433.96, N = 3SE +/- 1066.52, N = 35264667775745668400187290938341131491202641270781278651356361701901716462242981. (CXX) g++ options: -O3 -lm -ldl

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 3.4Blend File: Classroom - Compute: CPU-OnlyEPYC 7513 2PEPYC 7713PXeon Gold 6338 2PEPYC 7413 2PXeon Gold 6342 2PEPYC 7343 2PXeon Gold 6346 2PEPYC 7543EPYC 7513Xeon Gold 6338EPYC 7413Xeon Gold 6342EPYC 7343Xeon Gold 634650100150200250SE +/- 0.05, N = 3SE +/- 0.06, N = 3SE +/- 0.25, N = 3SE +/- 0.18, N = 3SE +/- 0.13, N = 3SE +/- 0.30, N = 3SE +/- 0.14, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.08, N = 3SE +/- 0.20, N = 3SE +/- 0.14, N = 3SE +/- 0.29, N = 3SE +/- 0.37, N = 364.9679.3080.1782.5587.28109.64115.77122.97130.35161.50165.39176.55219.83233.90

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 0.11Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path TracerXeon Gold 6338 2PXeon Gold 6342 2PEPYC 7513 2PEPYC 7713PXeon Gold 6346 2PEPYC 7413 2PXeon Gold 6338EPYC 7343 2PEPYC 7543Xeon Gold 6342EPYC 7513EPYC 7413Xeon Gold 6346EPYC 734315003000450060007500SE +/- 10.00, N = 3SE +/- 3.18, N = 3SE +/- 0.33, N = 3SE +/- 2.96, N = 3SE +/- 7.69, N = 3SE +/- 4.18, N = 3SE +/- 17.29, N = 3SE +/- 15.06, N = 3SE +/- 5.24, N = 3SE +/- 6.57, N = 3SE +/- 19.73, N = 3SE +/- 10.48, N = 3SE +/- 34.35, N = 3SE +/- 30.83, N = 3164119562150242425342722331436283767376940145121519968051. (CXX) g++ options: -O3 -lm -ldl

Memcached

Memcached is a high performance, distributed memory object caching system. This Memcached test profiles makes use of memtier_benchmark for excuting this CPU/memory-focused server benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is BetterMemcached 1.6.18Set To Get Ratio: 1:5Xeon Gold 6338Xeon Gold 6342Xeon Gold 6342 2PEPYC 7513Xeon Gold 6346 2PEPYC 7543EPYC 7713PXeon Gold 6346Xeon Gold 6338 2PEPYC 7413EPYC 7343 2PEPYC 7343EPYC 7413 2PEPYC 7513 2P900K1800K2700K3600K4500KSE +/- 26712.28, N = 3SE +/- 34848.84, N = 8SE +/- 28979.64, N = 3SE +/- 6378.36, N = 3SE +/- 20598.32, N = 3SE +/- 6964.53, N = 3SE +/- 47663.26, N = 3SE +/- 27130.94, N = 3SE +/- 21079.66, N = 14SE +/- 20367.20, N = 3SE +/- 24137.01, N = 3SE +/- 3957.77, N = 3SE +/- 51036.74, N = 15SE +/- 36603.84, N = 154271575.654068619.973701213.863632495.023597757.553574540.353378044.123346967.773270779.442917560.702421891.742199582.802164592.241867112.741. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

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 4.0Test: WritesEPYC 7513EPYC 7713PEPYC 7543EPYC 7513 2PEPYC 7343 2PEPYC 7413 2PEPYC 7413Xeon Gold 6342Xeon Gold 6342 2PXeon Gold 6346Xeon Gold 6338EPYC 7343Xeon Gold 6346 2PXeon Gold 6338 2P60K120K180K240K300KSE +/- 591.09, N = 3SE +/- 1599.50, N = 3SE +/- 1364.13, N = 3SE +/- 432.91, N = 3SE +/- 2617.59, N = 3SE +/- 1215.21, N = 3SE +/- 369.63, N = 3SE +/- 408.15, N = 3SE +/- 950.77, N = 3SE +/- 609.52, N = 3SE +/- 104.54, N = 3SE +/- 902.56, N = 3SE +/- 894.00, N = 3SE +/- 515.32, N = 3263627253058246339245226236544225784224875200958190873177347176284172713171138156487

Memcached

Memcached is a high performance, distributed memory object caching system. This Memcached test profiles makes use of memtier_benchmark for excuting this CPU/memory-focused server benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is BetterMemcached 1.6.18Set To Get Ratio: 1:10EPYC 7713PXeon Gold 6338EPYC 7513EPYC 7513 2PXeon Gold 6342Xeon Gold 6342 2PXeon Gold 6346 2PEPYC 7413 2PXeon Gold 6338 2PEPYC 7543EPYC 7413Xeon Gold 6346EPYC 7343 2PEPYC 73431000K2000K3000K4000K5000KSE +/- 53174.54, N = 4SE +/- 14309.07, N = 3SE +/- 10592.08, N = 3SE +/- 10361.68, N = 3SE +/- 13454.68, N = 3SE +/- 44938.98, N = 15SE +/- 36081.97, N = 15SE +/- 12992.60, N = 3SE +/- 79008.26, N = 15SE +/- 16723.87, N = 3SE +/- 9446.47, N = 3SE +/- 23174.23, N = 3SE +/- 10464.07, N = 3SE +/- 6608.23, N = 34786407.254262554.194198464.114105338.274053902.813969670.993912323.123691244.973551712.123481927.793431617.243159962.472826219.162548333.191. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

CloudSuite Web Serving

CloudSuite Web Serving is a Docker-based web server benchmark making use of a web server with Memcached and a MySQL database server. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgops/sec, More Is BetterCloudSuite Web ServingLoad Scale: 100EPYC 7413Xeon Gold 6346 2PXeon Gold 6342Xeon Gold 6338EPYC 7513Xeon Gold 6346Xeon Gold 6338 2PEPYC 7343Xeon Gold 6342 2PEPYC 7713PEPYC 7543EPYC 7343 2PEPYC 7513 2PEPYC 7413 2P2468107.5837.5337.5177.5177.4177.3837.3507.3337.1837.1006.5835.5505.4175.300

CloudSuite Graph Analytics

CloudSuite Graph Analytics uses Apache GraphX + Spark to perform graph analytics (PageRank) on sample Twitter data. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterCloudSuite Graph Analytics 4.0GraphX Algorithm: Connected ComponentsEPYC 7513EPYC 7713PEPYC 7543Xeon Gold 6342Xeon Gold 6342 2PEPYC 7513 2PEPYC 7413Xeon Gold 6338Xeon Gold 6346 2PEPYC 7413 2PEPYC 7343 2PXeon Gold 6338 2PEPYC 7343Xeon Gold 63464K8K12K16K20KSE +/- 194.18, N = 13SE +/- 128.32, N = 15SE +/- 220.91, N = 15SE +/- 140.39, N = 15SE +/- 57.52, N = 3SE +/- 134.07, N = 3SE +/- 188.00, N = 15SE +/- 97.53, N = 3SE +/- 268.97, N = 12SE +/- 176.86, N = 15SE +/- 400.63, N = 15SE +/- 180.53, N = 15SE +/- 216.00, N = 15SE +/- 155.90, N = 151310213169133581354213551138911401114285144081442614547147511571817820

SVT-HEVC

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 1 - Input: Bosphorus 4KEPYC 7513 2PEPYC 7713PEPYC 7413 2PXeon Gold 6338 2PXeon Gold 6342 2PEPYC 7343 2PEPYC 7543EPYC 7513Xeon Gold 6346 2PEPYC 7413Xeon Gold 6338Xeon Gold 6342EPYC 7343Xeon Gold 63463691215SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 311.569.799.188.257.907.286.696.226.124.894.404.093.793.111. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

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 7.9.2Test: Update RandomXeon Gold 6346 2PXeon Gold 6338Xeon Gold 6342EPYC 7513Xeon Gold 6346EPYC 7543Xeon Gold 6342 2PEPYC 7413EPYC 7343 2PXeon Gold 6338 2PEPYC 7713PEPYC 7513 2PEPYC 7413 2P200K400K600K800K1000KSE +/- 1819.77, N = 3SE +/- 1039.48, N = 3SE +/- 1500.76, N = 3SE +/- 1717.10, N = 3SE +/- 648.59, N = 3SE +/- 2864.72, N = 3SE +/- 9205.01, N = 15SE +/- 708.38, N = 3SE +/- 17553.74, N = 12SE +/- 379.98, N = 3SE +/- 339.25, N = 3SE +/- 3148.37, N = 3SE +/- 3018.40, N = 38032317937427437007076567003796881726407386383784814794666974366333515173361311. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti

Test: Update Random

EPYC 7343: The test quit with a non-zero exit status.

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: 500Xeon Gold 6346 2PXeon Gold 6342 2PXeon Gold 6338 2PEPYC 7543Xeon Gold 6338EPYC 7513EPYC 7343 2PEPYC 7713PXeon Gold 6342EPYC 7513 2PEPYC 7413 2PEPYC 7413Xeon Gold 634640K80K120K160K200KSE +/- 232.73, N = 3SE +/- 580.70, N = 3SE +/- 313.96, N = 3SE +/- 72.87, N = 3SE +/- 37.98, N = 3SE +/- 89.54, N = 3SE +/- 185.36, N = 3SE +/- 309.16, N = 3SE +/- 169.87, N = 3SE +/- 800.94, N = 3SE +/- 279.41, N = 3SE +/- 37.87, N = 3SE +/- 92.60, N = 3207339.64204325.45180812.11165787.42160307.52159784.56157128.24156012.00141031.60140932.43133788.29131406.38113630.04-std=c99 -O2-std=c99 -O2-std=c99 -O2-std=c99 -O2-std=c99 -O2-std=c99 -O2-std=c99 -O21. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl

Connections: 500

EPYC 7343: The test quit with a non-zero exit status. E: unable to connect to 127.0.0.1:8089 Connection refused

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.23.2Connections: 200Xeon Gold 6346 2PXeon Gold 6338 2PXeon Gold 6342 2PEPYC 7713PEPYC 7543EPYC 7513Xeon Gold 6338EPYC 7343 2PEPYC 7513 2PXeon Gold 6342EPYC 7413 2PEPYC 7413Xeon Gold 634640K80K120K160K200KSE +/- 149.37, N = 3SE +/- 271.76, N = 3SE +/- 512.32, N = 3SE +/- 498.75, N = 3SE +/- 73.04, N = 3SE +/- 142.56, N = 3SE +/- 41.84, N = 3SE +/- 248.07, N = 3SE +/- 704.77, N = 3SE +/- 76.21, N = 3SE +/- 288.51, N = 3SE +/- 83.69, N = 3SE +/- 24.68, N = 3207770.19205570.62205476.78167224.22161270.01160998.23160541.79155325.61151573.48141544.55135890.54129033.29118110.63-std=c99 -O2-std=c99 -O2-std=c99 -O2-std=c99 -O2-std=c99 -O2-std=c99 -O2-std=c99 -O21. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl

Connections: 200

EPYC 7343: The test quit with a non-zero exit status. E: unable to connect to 127.0.0.1:8089 Connection refused

LuxCoreRender

LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: LuxCore Benchmark - Acceleration: CPUEPYC 7513 2PEPYC 7713PXeon Gold 6338 2PXeon Gold 6342 2PEPYC 7413 2PEPYC 7543Xeon Gold 6346 2PEPYC 7513EPYC 7343 2PEPYC 7413Xeon Gold 6338Xeon Gold 6342EPYC 7343Xeon Gold 6346246810SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 15SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 36.756.706.576.165.564.744.684.644.463.683.673.292.722.59MIN: 2.41 / MAX: 8.1MIN: 2.57 / MAX: 7.82MIN: 2.6 / MAX: 7.71MIN: 2.54 / MAX: 7.19MIN: 1.97 / MAX: 6.64MIN: 1.8 / MAX: 5.56MIN: 1.67 / MAX: 5.69MIN: 1.79 / MAX: 5.4MIN: 1.61 / MAX: 5.3MIN: 1.36 / MAX: 4.33MIN: 1.31 / MAX: 4.39MIN: 1.23 / MAX: 3.85MIN: 0.96 / MAX: 3.2MIN: 0.88 / MAX: 3.07

CloudSuite Graph Analytics

CloudSuite Graph Analytics uses Apache GraphX + Spark to perform graph analytics (PageRank) on sample Twitter data. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterCloudSuite Graph Analytics 4.0GraphX Algorithm: Page RankEPYC 7713PEPYC 7543EPYC 7513 2PEPYC 7413EPYC 7343 2PEPYC 7413 2PEPYC 7513Xeon Gold 6342Xeon Gold 6342 2PXeon Gold 6346 2PXeon Gold 6338 2PXeon Gold 6338EPYC 7343Xeon Gold 63463K6K9K12K15KSE +/- 49.21, N = 3SE +/- 79.02, N = 3SE +/- 118.51, N = 3SE +/- 82.57, N = 15SE +/- 190.69, N = 13SE +/- 184.92, N = 15SE +/- 135.36, N = 3SE +/- 106.07, N = 15SE +/- 69.03, N = 14SE +/- 39.28, N = 3SE +/- 108.31, N = 15SE +/- 115.60, N = 15SE +/- 84.93, N = 3SE +/- 97.49, N = 15911292479587981598209831991710340103811059711235112451152513034

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: 1000Xeon Gold 6342 2PXeon Gold 6346 2PXeon Gold 6338 2PEPYC 7543Xeon Gold 6338EPYC 7513Xeon Gold 6342EPYC 7713PEPYC 7343 2PEPYC 7513 2PEPYC 7413Xeon Gold 634640K80K120K160K200KSE +/- 520.06, N = 3SE +/- 140.88, N = 3SE +/- 416.78, N = 3SE +/- 148.74, N = 3SE +/- 234.38, N = 3SE +/- 94.36, N = 3SE +/- 108.10, N = 3SE +/- 323.88, N = 3SE +/- 189.01, N = 3SE +/- 336.74, N = 3SE +/- 1390.17, N = 3SE +/- 58.40, N = 3200467.73199978.55178255.95165810.67164486.94156398.74153700.70151997.72151418.97135921.70129682.72109860.58-std=c99 -O2-std=c99 -O2-std=c99 -O2-std=c99 -O2-std=c99 -O2-std=c99 -O21. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl

Connections: 1000

EPYC 7343: The test quit with a non-zero exit status. E: unable to connect to 127.0.0.1:8089 Connection refused

EPYC 7413 2P: The test quit with a non-zero exit status.

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 7.9.2Test: Read Random Write RandomXeon Gold 6342 2PXeon Gold 6338Xeon Gold 6346 2PEPYC 7713PEPYC 7513EPYC 7543Xeon Gold 6338 2PXeon Gold 6342EPYC 7413Xeon Gold 6346EPYC 7513 2PEPYC 7343 2PEPYC 7413 2P600K1200K1800K2400K3000KSE +/- 14296.96, N = 3SE +/- 2675.18, N = 3SE +/- 37734.79, N = 3SE +/- 27203.96, N = 6SE +/- 1879.76, N = 3SE +/- 17808.71, N = 3SE +/- 17390.98, N = 15SE +/- 4554.38, N = 3SE +/- 2301.51, N = 3SE +/- 2003.10, N = 3SE +/- 5136.66, N = 3SE +/- 3492.11, N = 3SE +/- 6678.29, N = 327798902770547276245427618362750066269029825799262420422236943923112352204871219519121909941. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti

Test: Read Random Write Random

EPYC 7343: The test quit with a non-zero exit status.

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 7.9.2Test: Random Fill SyncXeon Gold 6342 2PXeon Gold 6338 2PXeon Gold 6338Xeon Gold 6346 2PXeon Gold 6342EPYC 7713PEPYC 7513EPYC 7543Xeon Gold 6346EPYC 7413EPYC 7513 2PEPYC 7343 2PEPYC 7413 2P80K160K240K320K400KSE +/- 6251.07, N = 15SE +/- 931.26, N = 3SE +/- 79.36, N = 3SE +/- 2669.53, N = 3SE +/- 194.11, N = 3SE +/- 1530.69, N = 3SE +/- 911.55, N = 3SE +/- 1077.11, N = 3SE +/- 98.97, N = 3SE +/- 831.59, N = 3SE +/- 1581.82, N = 3SE +/- 335.00, N = 3SE +/- 1013.52, N = 33671623071332970292898962775532672822381272337432087131992211972271708281654801. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti

Test: Random Fill Sync

EPYC 7343: The test quit with a non-zero exit status.

CloudSuite In-Memory Analytics

CloudSuite In-Memory Analytics uses Apache Spark and runs a collaborative filtering algorithm in-memory on a dataset of user-movie ratings from Movielens. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterCloudSuite In-Memory Analytics 4.0Training Set Size: SmallXeon Gold 6346EPYC 7343Xeon Gold 6342EPYC 7413Xeon Gold 6338EPYC 7513EPYC 7543Xeon Gold 6346 2PEPYC 7343 2PXeon Gold 6342 2PEPYC 7413 2PEPYC 7713PXeon Gold 6338 2PEPYC 7513 2P40K80K120K160K200KSE +/- 48.64, N = 3SE +/- 13.02, N = 3SE +/- 80.23, N = 3SE +/- 159.06, N = 3SE +/- 84.36, N = 3SE +/- 101.02, N = 3SE +/- 151.00, N = 3SE +/- 203.67, N = 3SE +/- 136.22, N = 3SE +/- 445.33, N = 3SE +/- 1128.62, N = 3SE +/- 820.85, N = 3SE +/- 90.73, N = 3SE +/- 409.71, N = 313855139952196023575366463680837315410964605982287111224136721147653181349

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 2022.3Model: Person Detection FP16 - Device: CPUXeon Gold 6346 2PXeon Gold 6342 2PEPYC 7343 2PXeon Gold 6338 2PEPYC 7413 2PEPYC 7513 2PXeon Gold 6346Xeon Gold 6342EPYC 7343Xeon Gold 6338EPYC 7543EPYC 7413EPYC 7513EPYC 7713P10002000300040005000SE +/- 0.85, N = 3SE +/- 1.46, N = 3SE +/- 0.75, N = 3SE +/- 0.75, N = 3SE +/- 0.56, N = 3SE +/- 2.22, N = 3SE +/- 0.68, N = 3SE +/- 0.81, N = 3SE +/- 10.65, N = 3SE +/- 0.75, N = 3SE +/- 7.16, N = 3SE +/- 4.10, N = 3SE +/- 9.18, N = 3SE +/- 5.09, N = 31043.481198.221445.131467.671688.621803.092047.932358.372790.522962.183186.873275.513561.394538.43MIN: 886.86 / MAX: 1166.18MIN: 911.32 / MAX: 1454.11MIN: 1428.3 / MAX: 1517.31MIN: 1203.01 / MAX: 1562.63MIN: 1420.61 / MAX: 1780.64MIN: 1636.35 / MAX: 1876.9MIN: 1604.74 / MAX: 2166.44MIN: 1772.66 / MAX: 2525.32MIN: 2485.81 / MAX: 2884.12MIN: 2252.85 / MAX: 3160.04MIN: 2866.19 / MAX: 3374.03MIN: 2779.4 / MAX: 3463.81MIN: 3211.28 / MAX: 3765.97MIN: 3564.16 / MAX: 4986.61. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Person Detection FP16 - Device: CPUXeon Gold 6338 2PXeon Gold 6342 2PEPYC 7513 2PXeon Gold 6346 2PEPYC 7413 2PEPYC 7713PEPYC 7343 2PXeon Gold 6338Xeon Gold 6342EPYC 7543EPYC 7513Xeon Gold 6346EPYC 7413EPYC 73433691215SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 310.849.948.827.627.016.925.535.365.034.954.443.873.612.841. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Person Detection FP32 - Device: CPUXeon Gold 6346 2PXeon Gold 6342 2PEPYC 7343 2PXeon Gold 6338 2PEPYC 7413 2PEPYC 7513 2PXeon Gold 6346Xeon Gold 6342EPYC 7343Xeon Gold 6338EPYC 7543EPYC 7413EPYC 7513EPYC 7713P10002000300040005000SE +/- 3.51, N = 3SE +/- 1.27, N = 3SE +/- 1.35, N = 3SE +/- 0.13, N = 3SE +/- 0.39, N = 3SE +/- 2.09, N = 3SE +/- 1.13, N = 3SE +/- 0.31, N = 3SE +/- 1.49, N = 3SE +/- 2.23, N = 3SE +/- 4.08, N = 3SE +/- 7.34, N = 3SE +/- 3.85, N = 3SE +/- 2.29, N = 31072.351217.971447.061495.921689.481804.952081.752400.772813.453023.563217.573280.273537.874533.12MIN: 885.75 / MAX: 1124.15MIN: 940.6 / MAX: 1321.99MIN: 1431.68 / MAX: 1476.13MIN: 1185.61 / MAX: 1589.83MIN: 1404.52 / MAX: 1764.68MIN: 1665.93 / MAX: 1885.89MIN: 951.54 / MAX: 2214.54MIN: 1826.07 / MAX: 2573.73MIN: 2640.81 / MAX: 2908.21MIN: 2431.21 / MAX: 3241.15MIN: 2966.37 / MAX: 3376.92MIN: 1686.07 / MAX: 3445.04MIN: 1864.67 / MAX: 3792.11MIN: 3616.62 / MAX: 4976.851. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Person Detection FP32 - Device: CPUXeon Gold 6338 2PXeon Gold 6342 2PEPYC 7513 2PXeon Gold 6346 2PEPYC 7413 2PEPYC 7713PEPYC 7343 2PXeon Gold 6338Xeon Gold 6342EPYC 7543EPYC 7513Xeon Gold 6346EPYC 7413EPYC 73433691215SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 310.639.788.817.427.016.925.525.264.954.944.453.803.592.821. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

LuxCoreRender

LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: Danish Mood - Acceleration: CPUEPYC 7513 2PEPYC 7713PXeon Gold 6338 2PXeon Gold 6342 2PEPYC 7413 2PXeon Gold 6346 2PEPYC 7543EPYC 7513EPYC 7343 2PXeon Gold 6338EPYC 7413Xeon Gold 6342EPYC 7343Xeon Gold 6346246810SE +/- 0.07, N = 3SE +/- 0.03, N = 3SE +/- 0.07, N = 5SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 36.436.106.095.845.144.464.364.354.103.473.333.042.482.34MIN: 2.55 / MAX: 7.63MIN: 2.45 / MAX: 7.16MIN: 2.47 / MAX: 7.28MIN: 2.6 / MAX: 6.73MIN: 1.96 / MAX: 6.18MIN: 1.83 / MAX: 5.18MIN: 1.72 / MAX: 5.07MIN: 1.68 / MAX: 5.04MIN: 1.58 / MAX: 4.79MIN: 1.22 / MAX: 4.08MIN: 1.21 / MAX: 3.89MIN: 1.09 / MAX: 3.58MIN: 0.84 / MAX: 2.91MIN: 0.74 / MAX: 2.79

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 2022.3Model: Face Detection FP16 - Device: CPUXeon Gold 6346 2PXeon Gold 6342 2PXeon Gold 6338 2PEPYC 7343 2PEPYC 7413 2PXeon Gold 6346EPYC 7513 2PXeon Gold 6342Xeon Gold 6338EPYC 7343EPYC 7543EPYC 7413EPYC 7513EPYC 7713P7001400210028003500SE +/- 1.08, N = 3SE +/- 0.46, N = 3SE +/- 1.93, N = 3SE +/- 0.58, N = 3SE +/- 1.48, N = 3SE +/- 3.43, N = 3SE +/- 1.75, N = 3SE +/- 7.34, N = 3SE +/- 6.05, N = 3SE +/- 3.34, N = 3SE +/- 9.46, N = 3SE +/- 2.73, N = 3SE +/- 2.40, N = 3SE +/- 4.99, N = 3604.17689.05862.091028.981190.681232.641272.581413.051771.701850.232162.682183.992369.523072.39MIN: 472.25 / MAX: 677.41MIN: 523.39 / MAX: 772.01MIN: 623.51 / MAX: 953.92MIN: 1009.62 / MAX: 1100.65MIN: 1162.02 / MAX: 1273MIN: 935.61 / MAX: 1312.43MIN: 1233.3 / MAX: 1361.68MIN: 686.62 / MAX: 1507.17MIN: 1362.81 / MAX: 1851.05MIN: 1073.49 / MAX: 1950.78MIN: 1785 / MAX: 2247.11MIN: 1919.34 / MAX: 2280.72MIN: 1311.77 / MAX: 2481.25MIN: 2717.45 / MAX: 3200.511. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Face Detection FP16 - Device: CPUXeon Gold 6338 2PXeon Gold 6342 2PXeon Gold 6346 2PEPYC 7513 2PEPYC 7713PEPYC 7413 2PXeon Gold 6338Xeon Gold 6342EPYC 7343 2PEPYC 7543EPYC 7513Xeon Gold 6346EPYC 7413EPYC 7343510152025SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 318.4817.3413.2012.5510.3310.068.968.437.767.326.676.435.444.271. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

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 6.0Encoder: libx265 - Scenario: LiveXeon Gold 6346EPYC 7343Xeon Gold 6342Xeon Gold 6346 2PXeon Gold 6342 2PEPYC 7513EPYC 7413EPYC 7543Xeon Gold 6338Xeon Gold 6338 2PEPYC 7713PEPYC 7343 2PEPYC 7513 2PEPYC 7413 2P306090120150SE +/- 0.44, N = 3SE +/- 0.52, N = 3SE +/- 0.10, N = 3SE +/- 0.19, N = 3SE +/- 0.21, N = 3SE +/- 0.16, N = 3SE +/- 0.19, N = 3SE +/- 0.11, N = 3SE +/- 0.10, N = 3SE +/- 0.13, N = 3SE +/- 0.21, N = 3SE +/- 0.09, N = 3SE +/- 0.48, N = 3SE +/- 0.17, N = 3124.46123.76122.36121.92121.08118.65117.23113.57112.80111.60105.50103.93101.0598.371. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 6.0Encoder: libx265 - Scenario: LiveXeon Gold 6346EPYC 7343Xeon Gold 6342Xeon Gold 6346 2PXeon Gold 6342 2PEPYC 7513EPYC 7413EPYC 7543Xeon Gold 6338Xeon Gold 6338 2PEPYC 7713PEPYC 7343 2PEPYC 7513 2PEPYC 7413 2P1224364860SE +/- 0.14, N = 3SE +/- 0.17, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.07, N = 3SE +/- 0.06, N = 3SE +/- 0.07, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.10, N = 3SE +/- 0.04, N = 3SE +/- 0.24, N = 3SE +/- 0.09, N = 340.5840.8141.2741.4241.7142.5643.0844.4744.7745.2547.8748.5949.9851.341. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl

LuxCoreRender

LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: Orange Juice - Acceleration: CPUEPYC 7513 2PEPYC 7713PXeon Gold 6338 2PEPYC 7413 2PXeon Gold 6342 2PXeon Gold 6346 2PEPYC 7343 2PEPYC 7543EPYC 7513Xeon Gold 6338EPYC 7413Xeon Gold 6342EPYC 7343Xeon Gold 63463691215SE +/- 0.16, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.07, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 313.4012.4412.3011.2411.198.778.598.428.187.016.566.465.055.01MIN: 11.54 / MAX: 15.77MIN: 10.8 / MAX: 14.28MIN: 10.28 / MAX: 14.34MIN: 9.76 / MAX: 12.48MIN: 9.51 / MAX: 13.26MIN: 7.63 / MAX: 9.54MIN: 7.51 / MAX: 9.26MIN: 7.45 / MAX: 9.01MIN: 7.2 / MAX: 8.7MIN: 6.3 / MAX: 7.56MIN: 5.93 / MAX: 6.83MIN: 5.76 / MAX: 7.02MIN: 4.74 / MAX: 5.15MIN: 4.73 / MAX: 5.13

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 2022.3Model: Face Detection FP16-INT8 - Device: CPUXeon Gold 6346 2PXeon Gold 6342 2PXeon Gold 6338 2PXeon Gold 6346Xeon Gold 6342EPYC 7343 2PXeon Gold 6338EPYC 7413 2PEPYC 7513 2PEPYC 7343EPYC 7543EPYC 7413EPYC 7513EPYC 7713P30060090012001500SE +/- 0.03, N = 3SE +/- 0.08, N = 3SE +/- 0.07, N = 3SE +/- 0.12, N = 3SE +/- 0.25, N = 3SE +/- 0.12, N = 3SE +/- 0.13, N = 3SE +/- 0.04, N = 3SE +/- 0.49, N = 3SE +/- 0.21, N = 3SE +/- 1.20, N = 3SE +/- 0.56, N = 3SE +/- 0.48, N = 3SE +/- 0.66, N = 3155.15177.69217.18313.14360.49423.55450.58483.37507.62854.22961.41979.211038.361279.15MIN: 141.05 / MAX: 204.41MIN: 164.55 / MAX: 257.56MIN: 185.19 / MAX: 336.95MIN: 257.91 / MAX: 392.73MIN: 415.99 / MAX: 455.1MIN: 338.75 / MAX: 484.67MIN: 438.12 / MAX: 515.6MIN: 474.68 / MAX: 549.27MIN: 777.98 / MAX: 878.94MIN: 831.19 / MAX: 978.3MIN: 861.53 / MAX: 1015.88MIN: 906.21 / MAX: 1056.67MIN: 1018.37 / MAX: 1317.051. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Face Detection FP16-INT8 - Device: CPUXeon Gold 6338 2PXeon Gold 6342 2PXeon Gold 6346 2PXeon Gold 6338Xeon Gold 6342EPYC 7513 2PXeon Gold 6346EPYC 7713PEPYC 7413 2PEPYC 7343 2PEPYC 7543EPYC 7513EPYC 7413EPYC 73431632486480SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 373.5867.4451.5135.4333.2231.4325.5224.8124.7218.8516.5615.2912.179.361. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Machine Translation EN To DE FP16 - Device: CPUXeon Gold 6346 2PXeon Gold 6342 2PXeon Gold 6338 2PEPYC 7343 2PEPYC 7413 2PXeon Gold 6346EPYC 7513 2PXeon Gold 6342Xeon Gold 6338EPYC 7343EPYC 7543EPYC 7413EPYC 7513EPYC 7713P60120180240300SE +/- 0.07, N = 3SE +/- 0.14, N = 3SE +/- 0.13, N = 3SE +/- 0.16, N = 3SE +/- 0.14, N = 3SE +/- 0.09, N = 3SE +/- 0.13, N = 3SE +/- 0.26, N = 3SE +/- 0.16, N = 3SE +/- 0.41, N = 3SE +/- 1.43, N = 3SE +/- 0.94, N = 3SE +/- 0.84, N = 3SE +/- 0.24, N = 355.4965.8178.1684.87100.17102.51105.07116.82142.53162.40190.87197.58212.22274.66MIN: 48.46 / MAX: 70.39MIN: 58.3 / MAX: 79.61MIN: 70.17 / MAX: 99.06MIN: 79.52 / MAX: 104.17MIN: 87.19 / MAX: 120.18MIN: 56.14 / MAX: 121.15MIN: 87.23 / MAX: 132.74MIN: 63.95 / MAX: 139.61MIN: 52.25 / MAX: 172.52MIN: 81.47 / MAX: 190.75MIN: 91.92 / MAX: 221.58MIN: 108.45 / MAX: 224.88MIN: 102.13 / MAX: 251.51MIN: 113.93 / MAX: 346.091. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Machine Translation EN To DE FP16 - Device: CPUXeon Gold 6338 2PXeon Gold 6342 2PEPYC 7513 2PXeon Gold 6346 2PEPYC 7413 2PEPYC 7713PXeon Gold 6338Xeon Gold 6342EPYC 7343 2PEPYC 7543Xeon Gold 6346EPYC 7513EPYC 7413EPYC 73434080120160200SE +/- 0.33, N = 3SE +/- 0.38, N = 3SE +/- 0.21, N = 3SE +/- 0.18, N = 3SE +/- 0.17, N = 3SE +/- 0.13, N = 3SE +/- 0.11, N = 3SE +/- 0.24, N = 3SE +/- 0.19, N = 3SE +/- 0.65, N = 3SE +/- 0.06, N = 3SE +/- 0.31, N = 3SE +/- 0.29, N = 3SE +/- 0.13, N = 3204.17181.98152.10144.01119.68116.30112.12102.6794.1883.7377.9975.2860.6749.201. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Person Vehicle Bike Detection FP16 - Device: CPUEPYC 7343 2PXeon Gold 6346 2PXeon Gold 6342 2PEPYC 7413 2PEPYC 7513 2PXeon Gold 6338 2PEPYC 7343Xeon Gold 6346EPYC 7543Xeon Gold 6342EPYC 7413EPYC 7513Xeon Gold 6338EPYC 7713P510152025SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 37.057.418.659.129.329.8512.3712.9314.3714.7815.5716.1817.7720.72MIN: 6.43 / MAX: 17.91MIN: 6.33 / MAX: 18.13MIN: 7.32 / MAX: 20.32MIN: 7.26 / MAX: 24.13MIN: 7.86 / MAX: 22.87MIN: 8.63 / MAX: 22.81MIN: 7.65 / MAX: 28.74MIN: 7.44 / MAX: 25.18MIN: 8.67 / MAX: 30.82MIN: 8.27 / MAX: 28.31MIN: 8.87 / MAX: 31.65MIN: 8.55 / MAX: 33.46MIN: 9.82 / MAX: 36.18MIN: 16.73 / MAX: 74.021. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Person Vehicle Bike Detection FP16 - Device: CPUEPYC 7513 2PXeon Gold 6338 2PEPYC 7713PXeon Gold 6342 2PEPYC 7413 2PEPYC 7343 2PEPYC 7543Xeon Gold 6346 2PEPYC 7513Xeon Gold 6338Xeon Gold 6342EPYC 7413EPYC 7343Xeon Gold 6346400800120016002000SE +/- 3.83, N = 3SE +/- 2.61, N = 3SE +/- 1.02, N = 3SE +/- 1.68, N = 3SE +/- 0.70, N = 3SE +/- 1.01, N = 3SE +/- 3.78, N = 3SE +/- 1.01, N = 3SE +/- 0.76, N = 3SE +/- 0.64, N = 3SE +/- 1.01, N = 3SE +/- 0.50, N = 3SE +/- 2.63, N = 3SE +/- 0.53, N = 31713.901619.831542.731382.221313.761132.271112.621076.16987.77899.05810.68769.91646.15617.711. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Vehicle Detection FP16-INT8 - Device: CPUXeon Gold 6346 2PXeon Gold 6342 2PXeon Gold 6338 2PEPYC 7343 2PXeon Gold 6346EPYC 7513 2PEPYC 7413 2PXeon Gold 6342Xeon Gold 6338EPYC 7343EPYC 7543EPYC 7413EPYC 7513EPYC 7713P510152025SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 33.413.984.696.426.797.627.637.759.6112.2213.7014.3814.8618.42MIN: 2.97 / MAX: 14.93MIN: 3.28 / MAX: 15.38MIN: 4.17 / MAX: 21.97MIN: 6.15 / MAX: 15.78MIN: 3.7 / MAX: 21.83MIN: 7.15 / MAX: 31.91MIN: 6.86 / MAX: 22.57MIN: 4.25 / MAX: 40.39MIN: 5.23 / MAX: 31.29MIN: 8.5 / MAX: 28.01MIN: 7.41 / MAX: 31.1MIN: 8.17 / MAX: 28.75MIN: 8.08 / MAX: 33.72MIN: 9.93 / MAX: 52.041. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Vehicle Detection FP16-INT8 - Device: CPUXeon Gold 6338 2PXeon Gold 6342 2PXeon Gold 6346 2PEPYC 7513 2PEPYC 7713PXeon Gold 6338EPYC 7413 2PXeon Gold 6342EPYC 7343 2PXeon Gold 6346EPYC 7543EPYC 7513EPYC 7413EPYC 73437001400210028003500SE +/- 1.96, N = 3SE +/- 5.21, N = 3SE +/- 1.91, N = 3SE +/- 0.29, N = 3SE +/- 1.60, N = 3SE +/- 1.15, N = 3SE +/- 7.85, N = 3SE +/- 1.94, N = 3SE +/- 0.73, N = 3SE +/- 0.17, N = 3SE +/- 0.71, N = 3SE +/- 0.12, N = 3SE +/- 1.37, N = 3SE +/- 0.19, N = 33402.823005.722339.162097.591735.571661.481570.381544.951243.241175.721166.691076.30833.99654.141. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Weld Porosity Detection FP16 - Device: CPUEPYC 7343 2PEPYC 7413 2PEPYC 7513 2PEPYC 7343EPYC 7543EPYC 7413EPYC 7513Xeon Gold 6346 2PXeon Gold 6346Xeon Gold 6342Xeon Gold 6342 2PEPYC 7713PXeon Gold 6338 2PXeon Gold 6338816243240SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.06, N = 310.1311.7013.3219.7622.3023.1824.5524.6124.9328.0928.7330.9535.1235.34MIN: 9.28 / MAX: 20.91MIN: 10.76 / MAX: 20.03MIN: 10.8 / MAX: 27.29MIN: 10.1 / MAX: 35.55MIN: 11.46 / MAX: 38.87MIN: 12.53 / MAX: 39.62MIN: 13.09 / MAX: 41.71MIN: 21.31 / MAX: 35.8MIN: 12.1 / MAX: 57.1MIN: 13.13 / MAX: 55.07MIN: 25.35 / MAX: 48.34MIN: 16.7 / MAX: 61.98MIN: 31.16 / MAX: 58.07MIN: 17.29 / MAX: 68.721. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Weld Porosity Detection FP16 - Device: CPUXeon Gold 6338 2PXeon Gold 6342 2PXeon Gold 6346 2PEPYC 7513 2PEPYC 7713PEPYC 7413 2PXeon Gold 6338Xeon Gold 6342EPYC 7343 2PEPYC 7543EPYC 7513Xeon Gold 6346EPYC 7413EPYC 7343400800120016002000SE +/- 2.62, N = 3SE +/- 1.17, N = 3SE +/- 1.02, N = 3SE +/- 1.42, N = 3SE +/- 0.61, N = 3SE +/- 0.89, N = 3SE +/- 1.35, N = 3SE +/- 0.30, N = 3SE +/- 0.57, N = 3SE +/- 0.47, N = 3SE +/- 0.67, N = 3SE +/- 1.16, N = 3SE +/- 0.42, N = 3SE +/- 0.27, N = 31813.341664.201296.571196.031033.391024.68904.01853.15788.14716.95651.20640.88517.32404.561. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUXeon Gold 6346 2PXeon Gold 6346Xeon Gold 6342 2PXeon Gold 6342EPYC 7343EPYC 7343 2PXeon Gold 6338 2PXeon Gold 6338EPYC 7413EPYC 7543EPYC 7413 2PEPYC 7513EPYC 7513 2PEPYC 7713P0.39150.7831.17451.5661.9575SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.860.920.991.051.111.141.161.231.271.271.301.371.391.74MIN: 0.67 / MAX: 13.21MIN: 0.52 / MAX: 14.11MIN: 0.73 / MAX: 14.31MIN: 0.49 / MAX: 15.59MIN: 0.62 / MAX: 14.15MIN: 0.96 / MAX: 12.95MIN: 0.91 / MAX: 14.56MIN: 0.58 / MAX: 21.43MIN: 0.72 / MAX: 14.84MIN: 0.71 / MAX: 14.55MIN: 1.07 / MAX: 14.22MIN: 0.85 / MAX: 19.76MIN: 1.14 / MAX: 14.4MIN: 0.91 / MAX: 22.451. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUXeon Gold 6338 2PXeon Gold 6342 2PEPYC 7513 2PXeon Gold 6346 2PEPYC 7413 2PEPYC 7713PEPYC 7343 2PXeon Gold 6338EPYC 7543EPYC 7513Xeon Gold 6342EPYC 7413Xeon Gold 6346EPYC 734312K24K36K48K60KSE +/- 28.36, N = 3SE +/- 11.43, N = 3SE +/- 31.93, N = 3SE +/- 51.11, N = 3SE +/- 96.63, N = 3SE +/- 463.83, N = 3SE +/- 47.15, N = 3SE +/- 22.82, N = 3SE +/- 28.61, N = 3SE +/- 36.34, N = 3SE +/- 19.47, N = 3SE +/- 25.63, N = 3SE +/- 12.78, N = 3SE +/- 3.86, N = 354275.4247664.1745746.2736784.8336411.0134339.2127742.3425216.3825079.4123116.8222510.5818711.9217148.8914256.401. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Weld Porosity Detection FP16-INT8 - Device: CPUXeon Gold 6346 2PXeon Gold 6346Xeon Gold 6342 2PXeon Gold 6342Xeon Gold 6338 2PXeon Gold 6338EPYC 7343 2PEPYC 7343EPYC 7413 2PEPYC 7543EPYC 7513 2PEPYC 7413EPYC 7513EPYC 7713P612182430SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 36.416.807.307.758.869.5516.5317.5018.6619.6319.6419.8021.0325.83MIN: 5.31 / MAX: 19.26MIN: 4.77 / MAX: 21.69MIN: 6.03 / MAX: 21.33MIN: 4.53 / MAX: 25.85MIN: 7.46 / MAX: 22.29MIN: 5.64 / MAX: 161.27MIN: 15.85 / MAX: 27.79MIN: 9.9 / MAX: 31.67MIN: 17.49 / MAX: 31.43MIN: 10.05 / MAX: 32.68MIN: 17.9 / MAX: 30.08MIN: 9.47 / MAX: 32.84MIN: 10.07 / MAX: 37.02MIN: 12.36 / MAX: 42.41. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Weld Porosity Detection FP16-INT8 - Device: CPUXeon Gold 6338 2PXeon Gold 6342 2PXeon Gold 6346 2PXeon Gold 6338EPYC 7513 2PXeon Gold 6342EPYC 7413 2PEPYC 7713PXeon Gold 6346EPYC 7343 2PEPYC 7543EPYC 7513EPYC 7413EPYC 734315003000450060007500SE +/- 0.75, N = 3SE +/- 3.20, N = 3SE +/- 2.46, N = 3SE +/- 1.10, N = 3SE +/- 1.61, N = 3SE +/- 0.53, N = 3SE +/- 0.28, N = 3SE +/- 1.30, N = 3SE +/- 0.48, N = 3SE +/- 0.17, N = 3SE +/- 0.33, N = 3SE +/- 0.26, N = 3SE +/- 0.09, N = 3SE +/- 0.17, N = 37209.166564.474979.273345.713255.753090.282570.672475.952347.831934.071628.991520.461211.31913.751. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Vehicle Detection FP16 - Device: CPUEPYC 7343 2PXeon Gold 6346 2PEPYC 7513 2PEPYC 7413 2PXeon Gold 6342 2PXeon Gold 6338 2PEPYC 7343Xeon Gold 6346EPYC 7543EPYC 7413EPYC 7513Xeon Gold 6342Xeon Gold 6338EPYC 7713P816243240SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.10, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 310.8811.4913.6214.0714.1917.0120.5121.7223.6625.0326.5026.6833.1934.00MIN: 9.85 / MAX: 18.79MIN: 9.55 / MAX: 23.06MIN: 11.93 / MAX: 37.05MIN: 11.6 / MAX: 34.29MIN: 10.82 / MAX: 27.29MIN: 12.34 / MAX: 32.47MIN: 10.96 / MAX: 31.38MIN: 10.48 / MAX: 36.43MIN: 13.21 / MAX: 47.37MIN: 17.49 / MAX: 46.59MIN: 15.94 / MAX: 62.11MIN: 13.7 / MAX: 43.32MIN: 14.88 / MAX: 64.4MIN: 20.86 / MAX: 90.261. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Vehicle Detection FP16 - Device: CPUEPYC 7513 2PEPYC 7713PXeon Gold 6338 2PEPYC 7413 2PXeon Gold 6342 2PEPYC 7343 2PXeon Gold 6346 2PEPYC 7543EPYC 7513Xeon Gold 6338EPYC 7413Xeon Gold 6342EPYC 7343Xeon Gold 634630060090012001500SE +/- 0.46, N = 3SE +/- 0.33, N = 3SE +/- 0.97, N = 3SE +/- 1.28, N = 3SE +/- 0.67, N = 3SE +/- 1.53, N = 3SE +/- 1.91, N = 3SE +/- 0.75, N = 3SE +/- 2.26, N = 3SE +/- 0.77, N = 3SE +/- 0.91, N = 3SE +/- 0.55, N = 3SE +/- 0.47, N = 3SE +/- 0.43, N = 31173.42940.29939.07852.08844.38734.99695.06675.88603.36481.60479.00449.39389.71368.021. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Age Gender Recognition Retail 0013 FP16 - Device: CPUXeon Gold 6346 2PXeon Gold 6346Xeon Gold 6342 2PXeon Gold 6342EPYC 7343EPYC 7343 2PXeon Gold 6338 2PEPYC 7543Xeon Gold 6338EPYC 7413EPYC 7413 2PEPYC 7513EPYC 7513 2PEPYC 7713P0.42750.8551.28251.712.1375SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.991.041.141.191.211.231.321.371.381.391.401.491.501.90MIN: 0.73 / MAX: 12.92MIN: 0.63 / MAX: 14.02MIN: 0.85 / MAX: 14.64MIN: 0.57 / MAX: 16.29MIN: 0.71 / MAX: 41.75MIN: 1.03 / MAX: 14.15MIN: 1.02 / MAX: 14.4MIN: 0.75 / MAX: 14.85MIN: 0.61 / MAX: 20.84MIN: 0.77 / MAX: 14.54MIN: 1.13 / MAX: 14.36MIN: 0.7 / MAX: 73.62MIN: 1.19 / MAX: 14.26MIN: 0.99 / MAX: 27.381. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Age Gender Recognition Retail 0013 FP16 - Device: CPUXeon Gold 6338 2PEPYC 7513 2PXeon Gold 6342 2PEPYC 7413 2PEPYC 7713PXeon Gold 6346 2PEPYC 7343 2PEPYC 7543Xeon Gold 6338EPYC 7513Xeon Gold 6342EPYC 7413Xeon Gold 6346EPYC 734310K20K30K40K50KSE +/- 9.04, N = 3SE +/- 39.42, N = 3SE +/- 46.35, N = 3SE +/- 25.78, N = 3SE +/- 113.09, N = 3SE +/- 51.77, N = 3SE +/- 47.98, N = 3SE +/- 8.38, N = 3SE +/- 9.27, N = 3SE +/- 9.24, N = 3SE +/- 22.59, N = 3SE +/- 2.86, N = 3SE +/- 6.67, N = 3SE +/- 16.19, N = 347801.0742487.4941669.5034019.2133271.1732137.1325795.5823118.2722808.1421308.5120000.7617211.2815262.3613149.711. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl

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 3.0Algorithm: RSA4096EPYC 7513 2PXeon Gold 6338 2PEPYC 7713PXeon Gold 6342 2PEPYC 7413 2PXeon Gold 6346 2PEPYC 7343 2PEPYC 7543EPYC 7513Xeon Gold 6338Xeon Gold 6342EPYC 7413EPYC 7343Xeon Gold 6346200K400K600K800K1000KSE +/- 55.88, N = 3SE +/- 40.84, N = 3SE +/- 53.07, N = 3SE +/- 292.45, N = 3SE +/- 52.75, N = 3SE +/- 232.08, N = 3SE +/- 36.78, N = 3SE +/- 34.51, N = 3SE +/- 556.85, N = 3SE +/- 41.22, N = 3SE +/- 54.53, N = 3SE +/- 51.25, N = 3SE +/- 27.40, N = 3SE +/- 83.11, N = 31003089.4838351.8823388.7798077.1778483.0580306.3574456.9522787.3501938.9419447.9398769.3390326.3287549.0286703.71. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

OpenBenchmarking.orgsign/s, More Is BetterOpenSSL 3.0Algorithm: RSA4096EPYC 7513 2PXeon Gold 6338 2PEPYC 7713PXeon Gold 6342 2PEPYC 7413 2PXeon Gold 6346 2PEPYC 7343 2PEPYC 7543EPYC 7513Xeon Gold 6338Xeon Gold 6342EPYC 7413EPYC 7343Xeon Gold 63463K6K9K12K15KSE +/- 12.10, N = 3SE +/- 0.24, N = 3SE +/- 10.29, N = 3SE +/- 5.32, N = 3SE +/- 9.47, N = 3SE +/- 0.90, N = 3SE +/- 5.12, N = 3SE +/- 7.21, N = 3SE +/- 5.98, N = 3SE +/- 0.27, N = 3SE +/- 13.25, N = 3SE +/- 0.09, N = 3SE +/- 3.48, N = 3SE +/- 0.18, N = 315222.312874.912568.112235.111846.88906.18794.67963.17637.86442.76109.75947.94398.64397.21. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

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 1.3.2Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-StreamXeon Gold 6346Xeon Gold 6346 2PXeon Gold 6342Xeon Gold 6342 2PEPYC 7343Xeon Gold 6338EPYC 7343 2PXeon Gold 6338 2PEPYC 7543EPYC 7413EPYC 7413 2PEPYC 7513EPYC 7513 2PEPYC 7713P150300450600750SE +/- 0.27, N = 3SE +/- 0.17, N = 3SE +/- 0.38, N = 3SE +/- 0.45, N = 3SE +/- 0.07, N = 3SE +/- 0.21, N = 3SE +/- 0.14, N = 3SE +/- 0.50, N = 3SE +/- 0.07, N = 3SE +/- 0.16, N = 3SE +/- 0.27, N = 3SE +/- 0.12, N = 3SE +/- 0.03, N = 3SE +/- 0.64, N = 3338.98350.63386.88399.33450.60471.63475.87488.41507.66515.06544.62546.28575.37684.85

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-StreamXeon Gold 6338 2PXeon Gold 6342 2PEPYC 7513 2PEPYC 7713PXeon Gold 6346 2PEPYC 7413 2PXeon Gold 6338EPYC 7343 2PEPYC 7543Xeon Gold 6342EPYC 7513Xeon Gold 6346EPYC 7413EPYC 73431530456075SE +/- 0.15, N = 3SE +/- 0.18, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 365.2159.9755.4746.6845.5543.9133.9033.4231.3931.0129.2723.5923.2917.74

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-StreamXeon Gold 6346Xeon Gold 6346 2PXeon Gold 6342Xeon Gold 6342 2PEPYC 7343EPYC 7343 2PXeon Gold 6338EPYC 7543EPYC 7413Xeon Gold 6338 2PEPYC 7413 2PEPYC 7513EPYC 7513 2PEPYC 7713P50100150200250SE +/- 0.99, N = 3SE +/- 0.32, N = 3SE +/- 0.70, N = 3SE +/- 0.98, N = 3SE +/- 0.33, N = 3SE +/- 0.07, N = 3SE +/- 0.38, N = 3SE +/- 0.50, N = 3SE +/- 0.15, N = 3SE +/- 0.95, N = 3SE +/- 0.16, N = 3SE +/- 0.21, N = 3SE +/- 1.13, N = 3SE +/- 0.17, N = 3126.16127.16144.31151.86152.83164.14173.20174.36178.21179.89187.68193.47204.23241.33

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-StreamXeon Gold 6338 2PXeon Gold 6342 2PEPYC 7513 2PEPYC 7713PEPYC 7413 2PXeon Gold 6346 2PEPYC 7343 2PXeon Gold 6338EPYC 7543Xeon Gold 6342EPYC 7513EPYC 7413Xeon Gold 6346EPYC 73434080120160200SE +/- 0.99, N = 3SE +/- 1.12, N = 3SE +/- 0.85, N = 3SE +/- 0.05, N = 3SE +/- 0.12, N = 3SE +/- 0.30, N = 3SE +/- 0.06, N = 3SE +/- 0.15, N = 3SE +/- 0.28, N = 3SE +/- 0.41, N = 3SE +/- 0.11, N = 3SE +/- 0.05, N = 3SE +/- 0.53, N = 3SE +/- 0.12, N = 3177.59157.81156.24132.30127.54125.6097.2092.2791.5783.0382.5567.2063.3552.26

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 7.9.2Test: Random ReadEPYC 7513 2PEPYC 7713PEPYC 7413 2PXeon Gold 6338 2PXeon Gold 6342 2PEPYC 7343 2PEPYC 7543Xeon Gold 6346 2PEPYC 7513EPYC 7413Xeon Gold 6338Xeon Gold 6342Xeon Gold 634660M120M180M240M300MSE +/- 716630.49, N = 3SE +/- 795243.99, N = 3SE +/- 885950.65, N = 3SE +/- 2092706.33, N = 3SE +/- 1248520.83, N = 3SE +/- 286135.95, N = 3SE +/- 275956.06, N = 3SE +/- 779454.00, N = 3SE +/- 207267.91, N = 3SE +/- 547389.34, N = 3SE +/- 260236.87, N = 3SE +/- 594128.06, N = 3SE +/- 427323.28, N = 3299129297246464521238439429226944746210724462181223940161712224154099244150974278120400741113495056104010467773910481. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti

Test: Random Read

EPYC 7343: The test quit with a non-zero exit status.

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 1.3.2Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-StreamXeon Gold 6346 2PXeon Gold 6346EPYC 7343EPYC 7343 2PXeon Gold 6342 2PXeon Gold 6342EPYC 7543EPYC 7413EPYC 7413 2PEPYC 7513EPYC 7513 2PXeon Gold 6338 2PXeon Gold 6338EPYC 7713P2004006008001000SE +/- 0.43, N = 3SE +/- 0.43, N = 3SE +/- 0.72, N = 3SE +/- 0.41, N = 3SE +/- 0.92, N = 3SE +/- 0.47, N = 3SE +/- 0.25, N = 3SE +/- 0.56, N = 3SE +/- 0.21, N = 3SE +/- 0.05, N = 3SE +/- 0.46, N = 3SE +/- 0.23, N = 3SE +/- 0.28, N = 3SE +/- 0.92, N = 3599.81605.67629.19636.28685.96689.68716.02729.31738.78791.97803.45847.38856.001010.00

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-StreamEPYC 7513 2PXeon Gold 6338 2PXeon Gold 6342 2PEPYC 7413 2PEPYC 7713PXeon Gold 6346 2PEPYC 7343 2PEPYC 7543EPYC 7513Xeon Gold 6338Xeon Gold 6342EPYC 7413Xeon Gold 6346EPYC 7343918273645SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.09, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 339.5937.7034.7932.2531.4526.5424.9222.0719.9018.6717.3916.3213.2112.65

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-StreamXeon Gold 6346Xeon Gold 6346 2PXeon Gold 6342Xeon Gold 6342 2PXeon Gold 6338Xeon Gold 6338 2PEPYC 7343EPYC 7413EPYC 7543EPYC 7513EPYC 7343 2PEPYC 7413 2PEPYC 7513 2PEPYC 7713P1632486480SE +/- 0.03, N = 3SE +/- 0.09, N = 3SE +/- 0.07, N = 3SE +/- 0.29, N = 3SE +/- 0.15, N = 3SE +/- 0.10, N = 3SE +/- 0.01, N = 3SE +/- 0.07, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.10, N = 3SE +/- 0.09, N = 3SE +/- 0.11, N = 3SE +/- 0.06, N = 333.0333.1140.6840.7044.1345.3648.8653.0354.3256.3356.9862.3665.3970.21

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-StreamXeon Gold 6338 2PXeon Gold 6342 2PEPYC 7513 2PXeon Gold 6346 2PEPYC 7713PEPYC 7413 2PXeon Gold 6338Xeon Gold 6342EPYC 7543EPYC 7513EPYC 7343 2PXeon Gold 6346EPYC 7413EPYC 7343150300450600750SE +/- 1.61, N = 3SE +/- 4.23, N = 3SE +/- 0.82, N = 3SE +/- 1.35, N = 3SE +/- 0.43, N = 3SE +/- 0.51, N = 3SE +/- 1.30, N = 3SE +/- 0.55, N = 3SE +/- 0.08, N = 3SE +/- 0.19, N = 3SE +/- 0.45, N = 3SE +/- 0.24, N = 3SE +/- 0.29, N = 3SE +/- 0.06, N = 3704.95589.28488.63482.92455.12384.29362.29294.76294.21283.71280.43242.04226.05163.56

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-StreamXeon Gold 6346 2PXeon Gold 6346EPYC 7343EPYC 7343 2PXeon Gold 6342 2PXeon Gold 6342EPYC 7543EPYC 7413EPYC 7413 2PEPYC 7513EPYC 7513 2PXeon Gold 6338 2PXeon Gold 6338EPYC 7713P2004006008001000SE +/- 0.72, N = 3SE +/- 0.26, N = 3SE +/- 0.24, N = 3SE +/- 0.25, N = 3SE +/- 0.49, N = 3SE +/- 0.32, N = 3SE +/- 0.33, N = 3SE +/- 0.30, N = 3SE +/- 0.75, N = 3SE +/- 0.93, N = 3SE +/- 0.61, N = 3SE +/- 0.68, N = 3SE +/- 0.54, N = 3SE +/- 0.83, N = 3600.72605.57627.69634.73686.45690.24716.12729.06739.76792.46802.16848.91855.781010.58

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-StreamEPYC 7513 2PXeon Gold 6338 2PXeon Gold 6342 2PEPYC 7413 2PEPYC 7713PXeon Gold 6346 2PEPYC 7343 2PEPYC 7543EPYC 7513Xeon Gold 6338Xeon Gold 6342EPYC 7413Xeon Gold 6346EPYC 7343918273645SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.10, N = 3SE +/- 0.02, N = 3SE +/- 0.07, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.07, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 339.6637.6334.8632.2531.4026.5225.0222.1219.9818.6917.3816.3713.2112.62

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 7513 2PXeon Gold 6338 2PEPYC 7713PXeon Gold 6342 2PEPYC 7413 2PEPYC 7343 2PXeon Gold 6346 2PEPYC 7543EPYC 7513Xeon Gold 6338EPYC 7413Xeon Gold 6342EPYC 7343Xeon Gold 63461530456075SE +/- 0.32, N = 5SE +/- 0.37, N = 5SE +/- 0.34, N = 6SE +/- 0.34, N = 5SE +/- 0.36, N = 5SE +/- 0.47, N = 3SE +/- 0.54, N = 3SE +/- 0.50, N = 3SE +/- 0.51, N = 3SE +/- 0.61, N = 3SE +/- 0.50, N = 3SE +/- 0.56, N = 3SE +/- 0.47, N = 3SE +/- 0.52, N = 329.7833.0433.7533.7933.8238.9740.4042.0944.7551.8452.7255.4963.4967.65

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 1.3.2Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-StreamXeon Gold 6346 2PXeon Gold 6346EPYC 7343EPYC 7343 2PXeon Gold 6342Xeon Gold 6342 2PEPYC 7543EPYC 7413EPYC 7413 2PEPYC 7513EPYC 7513 2PXeon Gold 6338 2PXeon Gold 6338EPYC 7713P50100150200250SE +/- 0.10, N = 3SE +/- 0.56, N = 3SE +/- 0.09, N = 3SE +/- 0.17, N = 3SE +/- 0.13, N = 3SE +/- 0.51, N = 3SE +/- 0.12, N = 3SE +/- 0.15, N = 3SE +/- 0.11, N = 3SE +/- 0.41, N = 3SE +/- 0.11, N = 3SE +/- 0.33, N = 3SE +/- 0.18, N = 3SE +/- 0.59, N = 3141.36143.49148.96152.15158.56159.75169.93170.16174.62183.72187.52190.84191.31230.92

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-StreamEPYC 7513 2PXeon Gold 6338 2PXeon Gold 6342 2PEPYC 7713PEPYC 7413 2PXeon Gold 6346 2PEPYC 7343 2PEPYC 7543EPYC 7513Xeon Gold 6338Xeon Gold 6342EPYC 7413Xeon Gold 6346EPYC 73434080120160200SE +/- 0.08, N = 3SE +/- 0.37, N = 3SE +/- 0.50, N = 3SE +/- 0.30, N = 3SE +/- 0.10, N = 3SE +/- 0.13, N = 3SE +/- 0.08, N = 3SE +/- 0.06, N = 3SE +/- 0.21, N = 3SE +/- 0.08, N = 3SE +/- 0.06, N = 3SE +/- 0.06, N = 3SE +/- 0.22, N = 3SE +/- 0.02, N = 3170.26167.38150.09138.14137.04113.07104.8993.9786.9483.6275.6770.4155.7553.60

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: SlowEPYC 7513 2PEPYC 7413 2PEPYC 7343 2PXeon Gold 6342 2PEPYC 7543EPYC 7713PXeon Gold 6346 2PEPYC 7513Xeon Gold 6338 2PEPYC 7413Xeon Gold 6338Xeon Gold 6342EPYC 7343Xeon Gold 634648121620SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 317.2616.0014.8914.2214.0013.9913.4513.4312.5610.549.769.379.268.18

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 3.4Blend File: BMW27 - Compute: CPU-OnlyEPYC 7513 2PXeon Gold 6338 2PEPYC 7713PEPYC 7413 2PXeon Gold 6342 2PEPYC 7343 2PXeon Gold 6346 2PEPYC 7543EPYC 7513Xeon Gold 6338EPYC 7413Xeon Gold 6342EPYC 7343Xeon Gold 634620406080100SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.12, N = 3SE +/- 0.06, N = 3SE +/- 0.04, N = 3SE +/- 0.12, N = 3SE +/- 0.10, N = 3SE +/- 0.09, N = 3SE +/- 0.07, N = 3SE +/- 0.13, N = 3SE +/- 0.08, N = 3SE +/- 0.10, N = 3SE +/- 0.05, N = 325.4629.6630.3631.8032.2541.3042.3546.2449.2459.5562.0364.9082.6086.38

GROMACS

The GROMACS (GROningen MAchine for Chemical Simulations) molecular dynamics package testing with the water_GMX50 data. This test profile allows selecting between CPU and GPU-based GROMACS builds. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2023Implementation: MPI CPU - Input: water_GMX50_bareXeon Gold 6338 2PXeon Gold 6342 2PEPYC 7513 2PXeon Gold 6346 2PEPYC 7713PEPYC 7413 2PEPYC 7343 2PEPYC 7543Xeon Gold 6338EPYC 7513Xeon Gold 6342EPYC 7413Xeon Gold 6346246810SE +/- 0.011, N = 3SE +/- 0.019, N = 3SE +/- 0.019, N = 3SE +/- 0.018, N = 3SE +/- 0.008, N = 3SE +/- 0.015, N = 3SE +/- 0.009, N = 3SE +/- 0.013, N = 3SE +/- 0.025, N = 3SE +/- 0.006, N = 3SE +/- 0.004, N = 3SE +/- 0.003, N = 3SE +/- 0.001, N = 37.3796.7615.5895.3915.0984.8204.0834.0013.7173.5473.3763.0052.6191. (CXX) g++ options: -O3

Implementation: MPI CPU - Input: water_GMX50_bare

EPYC 7343: The test quit with a non-zero exit status. E: mpirun noticed that process rank 9 with PID 0 on node amd-test-02 exited on signal 4 (Illegal instruction).

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: MediumEPYC 7513 2PEPYC 7413 2PEPYC 7343 2PXeon Gold 6342 2PEPYC 7543EPYC 7713PEPYC 7513Xeon Gold 6346 2PXeon Gold 6338 2PEPYC 7413Xeon Gold 6338Xeon Gold 6342EPYC 7343Xeon Gold 6346510152025SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 319.5918.0616.7816.0015.7715.7115.1015.0514.1211.8710.8810.5110.429.16

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.orgSeconds, Fewer Is BetterFFmpeg 6.0Encoder: libx264 - Scenario: LiveEPYC 7343EPYC 7343 2PEPYC 7543EPYC 7713PEPYC 7513EPYC 7513 2PEPYC 7413Xeon Gold 6346EPYC 7413 2PXeon Gold 6346 2PXeon Gold 6342Xeon Gold 6342 2PXeon Gold 6338Xeon Gold 6338 2P714212835SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.08, N = 323.1823.4123.8624.2024.3524.4624.8824.9925.2426.0426.0727.0928.2429.141. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl

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 1.3.2Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-StreamXeon Gold 6346 2PXeon Gold 6346EPYC 7343Xeon Gold 6342Xeon Gold 6342 2PEPYC 7343 2PEPYC 7543EPYC 7413EPYC 7413 2PXeon Gold 6338EPYC 7513Xeon Gold 6338 2PEPYC 7513 2PEPYC 7713P306090120150SE +/- 0.09, N = 3SE +/- 0.14, N = 3SE +/- 0.12, N = 3SE +/- 0.29, N = 3SE +/- 0.09, N = 3SE +/- 0.02, N = 3SE +/- 0.07, N = 3SE +/- 0.03, N = 3SE +/- 0.10, N = 3SE +/- 0.20, N = 3SE +/- 0.13, N = 3SE +/- 0.15, N = 3SE +/- 0.06, N = 3SE +/- 0.36, N = 369.0469.1975.4176.1276.5677.3485.8786.0888.6392.0592.5492.6495.08117.48

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-StreamXeon Gold 6338 2PEPYC 7513 2PXeon Gold 6342 2PEPYC 7713PEPYC 7413 2PXeon Gold 6346 2PEPYC 7343 2PEPYC 7543Xeon Gold 6338EPYC 7513Xeon Gold 6342EPYC 7413Xeon Gold 6346EPYC 734380160240320400SE +/- 0.54, N = 3SE +/- 0.20, N = 3SE +/- 0.35, N = 3SE +/- 0.86, N = 3SE +/- 0.27, N = 3SE +/- 0.29, N = 3SE +/- 0.11, N = 3SE +/- 0.11, N = 3SE +/- 0.37, N = 3SE +/- 0.28, N = 3SE +/- 0.61, N = 3SE +/- 0.06, N = 3SE +/- 0.23, N = 3SE +/- 0.16, N = 3345.18335.99313.14271.88270.27231.51206.53186.09173.77172.73157.60139.27115.60105.96

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 DirectionXeon Gold 6338 2PEPYC 7413 2PEPYC 7513 2PXeon Gold 6342 2PEPYC 7343 2PXeon Gold 6346 2PEPYC 7713PEPYC 7543EPYC 7513EPYC 7413Xeon Gold 6338Xeon Gold 6342EPYC 7343Xeon Gold 6346918273645SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.28, N = 15SE +/- 0.19, N = 4SE +/- 0.07, N = 3SE +/- 0.44, N = 15SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.07, N = 3SE +/- 0.12, N = 3SE +/- 0.04, N = 3SE +/- 0.42, N = 3SE +/- 0.14, N = 3SE +/- 0.08, N = 314.6915.6915.8116.5118.0221.2223.0924.1130.7432.4033.0033.3035.5640.551. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -lmpi_usempif08 -lmpi_mpifh -lmpi

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 1.3.2Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-StreamXeon Gold 6346 2PXeon Gold 6346Xeon Gold 6342 2PXeon Gold 6342Xeon Gold 6338Xeon Gold 6338 2PEPYC 7343EPYC 7343 2PEPYC 7413EPYC 7543EPYC 7413 2PEPYC 7513EPYC 7513 2PEPYC 7713P20406080100SE +/- 0.00, N = 3SE +/- 0.04, N = 3SE +/- 0.16, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.11, N = 3SE +/- 0.03, N = 3SE +/- 0.16, N = 3SE +/- 0.09, N = 3SE +/- 0.21, N = 3SE +/- 0.17, N = 3SE +/- 0.07, N = 3SE +/- 0.12, N = 336.3837.0441.4641.8149.9649.9755.4155.6062.2062.2964.7266.4768.1286.46

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.3.2Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-StreamXeon Gold 6338 2PXeon Gold 6342 2PEPYC 7513 2PXeon Gold 6346 2PEPYC 7413 2PEPYC 7713PXeon Gold 6338EPYC 7343 2PXeon Gold 6342EPYC 7543EPYC 7513Xeon Gold 6346EPYC 7413EPYC 7343140280420560700SE +/- 0.15, N = 3SE +/- 2.27, N = 3SE +/- 0.50, N = 3SE +/- 0.08, N = 3SE +/- 1.20, N = 3SE +/- 0.55, N = 3SE +/- 0.07, N = 3SE +/- 0.20, N = 3SE +/- 0.25, N = 3SE +/- 0.36, N = 3SE +/- 0.61, N = 3SE +/- 0.23, N = 3SE +/- 0.51, N = 3SE +/- 0.25, N = 3639.77578.25468.93439.33370.19369.54320.01287.18286.88256.52240.41215.84192.68144.23

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 AtomsXeon Gold 6338 2PEPYC 7513 2PXeon Gold 6342 2PEPYC 7713PEPYC 7413 2PXeon Gold 6346 2PEPYC 7343 2PEPYC 7543Xeon Gold 6338EPYC 7513Xeon Gold 6342EPYC 7413Xeon Gold 6346EPYC 73430.25730.51460.77191.02921.2865SE +/- 0.00053, N = 3SE +/- 0.00049, N = 3SE +/- 0.00083, N = 3SE +/- 0.00061, N = 3SE +/- 0.00231, N = 3SE +/- 0.00067, N = 3SE +/- 0.00060, N = 3SE +/- 0.00115, N = 3SE +/- 0.00160, N = 3SE +/- 0.00039, N = 3SE +/- 0.00023, N = 3SE +/- 0.00216, N = 3SE +/- 0.00172, N = 3SE +/- 0.00059, N = 30.355020.367160.380910.455910.470530.493540.592600.655540.702150.715850.751730.886770.987421.14340

Kvazaar

This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: MediumEPYC 7513 2PEPYC 7413 2PEPYC 7343 2PEPYC 7543EPYC 7513Xeon Gold 6342 2PEPYC 7713PXeon Gold 6346 2PXeon Gold 6338 2PEPYC 7413EPYC 7343Xeon Gold 6338Xeon Gold 6342Xeon Gold 6346612182430SE +/- 0.04, N = 3SE +/- 0.26, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.08, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 325.0223.2022.5021.0420.3319.2719.0318.3917.6316.1014.9413.6913.1712.211. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

LuxCoreRender

LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: Rainbow Colors and Prism - Acceleration: CPUEPYC 7713PEPYC 7513 2PEPYC 7513EPYC 7543EPYC 7413 2PEPYC 7413Xeon Gold 6342Xeon Gold 6338EPYC 7343 2PXeon Gold 6342 2PEPYC 7343Xeon Gold 6346 2PXeon Gold 6346Xeon Gold 6338 2P510152025SE +/- 0.13, N = 5SE +/- 0.18, N = 6SE +/- 0.05, N = 5SE +/- 0.18, N = 4SE +/- 0.09, N = 4SE +/- 0.12, N = 5SE +/- 0.13, N = 5SE +/- 0.11, N = 9SE +/- 0.12, N = 4SE +/- 0.24, N = 15SE +/- 0.08, N = 4SE +/- 0.20, N = 15SE +/- 0.07, N = 4SE +/- 0.23, N = 1518.7317.4417.4416.6915.7315.1113.7713.2013.0312.6012.1212.0511.4511.33MIN: 18.24 / MAX: 19.11MIN: 15.46 / MAX: 18.02MIN: 15.75 / MAX: 17.95MIN: 15.03 / MAX: 17.36MIN: 14.3 / MAX: 16.13MIN: 13.66 / MAX: 15.57MIN: 12.72 / MAX: 14.53MIN: 11.71 / MAX: 14.29MIN: 11.85 / MAX: 13.27MIN: 10.6 / MAX: 13.91MIN: 11.11 / MAX: 12.32MIN: 10.43 / MAX: 13.24MIN: 10.45 / MAX: 11.99MIN: 9.36 / MAX: 12.19

PHPBench

PHPBench is a benchmark suite for PHP. It performs a large number of simple tests in order to bench various aspects of the PHP interpreter. PHPBench can be used to compare hardware, operating systems, PHP versions, PHP accelerators and caches, compiler options, etc. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterPHPBench 0.8.1PHP Benchmark SuiteXeon Gold 6346Xeon Gold 6346 2PXeon Gold 6342 2PXeon Gold 6342EPYC 7343 2PEPYC 7343Xeon Gold 6338 2PXeon Gold 6338EPYC 7543EPYC 7513 2PEPYC 7413 2PEPYC 7713PEPYC 7513EPYC 7413200K400K600K800K1000KSE +/- 678.65, N = 3SE +/- 1806.45, N = 3SE +/- 580.18, N = 3SE +/- 581.13, N = 3SE +/- 2797.29, N = 3SE +/- 1077.87, N = 3SE +/- 340.03, N = 3SE +/- 1918.32, N = 3SE +/- 1437.74, N = 3SE +/- 1938.22, N = 3SE +/- 4937.26, N = 3SE +/- 3010.31, N = 3SE +/- 4086.10, N = 3SE +/- 1332.81, N = 3812732809727789297788731735624732752722240719675687000686597680136678966678084670928

SVT-VP9

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample YUV input video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: VMAF Optimized - Input: Bosphorus 4KEPYC 7713PEPYC 7543EPYC 7513 2PEPYC 7513EPYC 7413 2PEPYC 7343 2PXeon Gold 6338Xeon Gold 6342Xeon Gold 6346 2PEPYC 7413Xeon Gold 6342 2PXeon Gold 6338 2PEPYC 7343Xeon Gold 63464080120160200SE +/- 1.46, N = 15SE +/- 1.40, N = 15SE +/- 1.60, N = 15SE +/- 0.92, N = 15SE +/- 4.20, N = 15SE +/- 1.45, N = 15SE +/- 1.38, N = 15SE +/- 1.09, N = 15SE +/- 1.32, N = 6SE +/- 1.16, N = 8SE +/- 1.39, N = 15SE +/- 1.44, N = 15SE +/- 0.79, N = 6SE +/- 0.57, N = 6172.24171.65163.58161.26154.60152.31143.42141.68141.50140.28139.88137.47111.82109.471. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

Kvazaar

This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Super FastEPYC 7513 2PEPYC 7413 2PEPYC 7343 2PEPYC 7543EPYC 7513EPYC 7713PXeon Gold 6342 2PXeon Gold 6346 2PEPYC 7413Xeon Gold 6338 2PEPYC 7343Xeon Gold 6342Xeon Gold 6346Xeon Gold 63381428425670SE +/- 0.55, N = 5SE +/- 0.24, N = 5SE +/- 0.18, N = 5SE +/- 0.09, N = 5SE +/- 0.17, N = 5SE +/- 0.39, N = 15SE +/- 0.39, N = 4SE +/- 0.05, N = 4SE +/- 0.04, N = 4SE +/- 0.40, N = 15SE +/- 0.03, N = 4SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.09, N = 363.5361.7557.1354.2752.8150.6747.4945.1743.0241.4441.2434.3533.9333.711. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

Pennant

Pennant is an application focused on hydrodynamics on general unstructured meshes in 2D. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: sedovbigEPYC 7513 2PEPYC 7413 2PEPYC 7713PEPYC 7343 2PEPYC 7543EPYC 7513Xeon Gold 6342 2PXeon Gold 6338 2PEPYC 7413Xeon Gold 6346 2PEPYC 7343Xeon Gold 6338Xeon Gold 6342Xeon Gold 63461020304050SE +/- 0.049248, N = 5SE +/- 0.029276, N = 4SE +/- 0.083702, N = 4SE +/- 0.078086, N = 4SE +/- 0.049389, N = 3SE +/- 0.031210, N = 3SE +/- 0.015004, N = 3SE +/- 0.024622, N = 3SE +/- 0.083410, N = 3SE +/- 0.016802, N = 3SE +/- 0.053422, N = 3SE +/- 0.015982, N = 3SE +/- 0.024301, N = 3SE +/- 0.018190, N = 38.76146210.79851011.31944013.47434015.39717017.88689018.26646019.64620021.41936022.14267026.92807030.86947031.83193041.9676201. (CXX) g++ options: -fopenmp -lmpi_cxx -lmpi

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 4.0Binary: Pathtracer ISPC - Model: CrownXeon Gold 6338 2PXeon Gold 6342 2PEPYC 7513 2PEPYC 7713PEPYC 7413 2PXeon Gold 6346 2PXeon Gold 6338EPYC 7343 2PEPYC 7543EPYC 7513Xeon Gold 6342EPYC 7413Xeon Gold 6346EPYC 73431530456075SE +/- 0.07, N = 5SE +/- 0.33, N = 5SE +/- 0.07, N = 5SE +/- 0.10, N = 4SE +/- 0.08, N = 4SE +/- 0.05, N = 4SE +/- 0.07, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.11, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.08, N = 3SE +/- 0.02, N = 369.5961.1858.9051.6846.6046.2735.8435.4935.1233.1429.1725.8323.1720.01MIN: 67.34 / MAX: 73.46MIN: 57.63 / MAX: 66.74MIN: 57.6 / MAX: 61.52MIN: 48.53 / MAX: 56.01MIN: 45.29 / MAX: 47.9MIN: 45.19 / MAX: 48.79MIN: 34.73 / MAX: 37.86MIN: 35 / MAX: 36.16MIN: 34.38 / MAX: 36.15MIN: 32.13 / MAX: 34.24MIN: 28.31 / MAX: 34.1MIN: 25.36 / MAX: 26.62MIN: 22.47 / MAX: 25.37MIN: 19.68 / MAX: 20.39

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.0Binary: Pathtracer - Model: CrownEPYC 7513 2PXeon Gold 6338 2PEPYC 7713PXeon Gold 6342 2PEPYC 7413 2PXeon Gold 6346 2PEPYC 7343 2PEPYC 7543EPYC 7513Xeon Gold 6338EPYC 7413Xeon Gold 6342EPYC 7343Xeon Gold 63461428425670SE +/- 0.22, N = 5SE +/- 0.05, N = 4SE +/- 0.16, N = 4SE +/- 0.06, N = 4SE +/- 0.05, N = 4SE +/- 0.18, N = 3SE +/- 0.07, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.08, N = 3SE +/- 0.13, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 362.3658.3352.7551.3949.9538.9037.7537.2834.1829.8427.4225.3521.2219.76MIN: 60.41 / MAX: 65.16MIN: 56.72 / MAX: 61.53MIN: 51.1 / MAX: 58.19MIN: 49.55 / MAX: 55.56MIN: 48.86 / MAX: 51.27MIN: 38.2 / MAX: 40.63MIN: 37.14 / MAX: 38.79MIN: 36.31 / MAX: 38.34MIN: 33.8 / MAX: 34.89MIN: 29.02 / MAX: 31.34MIN: 26.84 / MAX: 28.27MIN: 24.68 / MAX: 28.35MIN: 20.8 / MAX: 21.59MIN: 19.56 / MAX: 20.64

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.0Binary: Pathtracer - Model: Asian DragonXeon Gold 6338 2PEPYC 7713PXeon Gold 6342 2PEPYC 7513 2PEPYC 7413 2PXeon Gold 6346 2PEPYC 7543EPYC 7513EPYC 7343 2PXeon Gold 6338EPYC 7413Xeon Gold 6342EPYC 7343Xeon Gold 63461530456075SE +/- 0.05, N = 5SE +/- 0.03, N = 5SE +/- 0.06, N = 5SE +/- 0.09, N = 4SE +/- 0.06, N = 4SE +/- 0.05, N = 4SE +/- 0.05, N = 4SE +/- 0.04, N = 4SE +/- 0.05, N = 3SE +/- 0.09, N = 3SE +/- 0.13, N = 3SE +/- 0.04, N = 3SE +/- 0.14, N = 3SE +/- 0.02, N = 367.1362.5759.6853.8148.3543.5141.9540.2138.9735.9131.9031.0123.7623.39MIN: 65.98 / MAX: 70.89MIN: 61.2 / MAX: 64.08MIN: 58.54 / MAX: 62.25MIN: 52.99 / MAX: 56.35MIN: 47.63 / MAX: 49.46MIN: 43 / MAX: 44.91MIN: 41.57 / MAX: 42.56MIN: 39.78 / MAX: 40.88MIN: 38.53 / MAX: 40.01MIN: 34.65 / MAX: 37.75MIN: 31.52 / MAX: 32.65MIN: 29.86 / MAX: 33.48MIN: 23.41 / MAX: 24.11MIN: 23.25 / MAX: 24.1

Kvazaar

This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Very FastEPYC 7513 2PEPYC 7413 2PEPYC 7343 2PEPYC 7543EPYC 7513EPYC 7713PXeon Gold 6342 2PXeon Gold 6346 2PXeon Gold 6338 2PEPYC 7413EPYC 7343Xeon Gold 6338Xeon Gold 6342Xeon Gold 63461224364860SE +/- 0.06, N = 5SE +/- 0.08, N = 4SE +/- 0.09, N = 4SE +/- 0.09, N = 4SE +/- 0.07, N = 4SE +/- 0.05, N = 4SE +/- 0.04, N = 4SE +/- 0.03, N = 4SE +/- 0.14, N = 4SE +/- 0.05, N = 3SE +/- 0.07, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 354.1348.9345.8643.2542.3241.5939.2536.8436.4733.4132.3527.4727.0326.641. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

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 7513 2PEPYC 7413 2PEPYC 7713PEPYC 7343 2PEPYC 7543EPYC 7513Xeon Gold 6342 2PXeon Gold 6338 2PXeon Gold 6346 2PEPYC 7413EPYC 7343Xeon Gold 6338Xeon Gold 6342Xeon Gold 63461224364860SE +/- 0.15, N = 4SE +/- 0.11, N = 4SE +/- 0.08, N = 4SE +/- 0.13, N = 4SE +/- 0.03, N = 4SE +/- 0.07, N = 4SE +/- 0.04, N = 4SE +/- 0.11, N = 3SE +/- 0.02, N = 3SE +/- 0.08, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 351.0545.9842.5641.2040.6739.5239.0336.0135.8931.3028.9426.7926.6524.70

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Super FastEPYC 7513 2PEPYC 7413 2PEPYC 7713PEPYC 7343 2PEPYC 7543Xeon Gold 6342 2PEPYC 7513Xeon Gold 6346 2PXeon Gold 6338 2PEPYC 7413EPYC 7343Xeon Gold 6342Xeon Gold 6338Xeon Gold 63461224364860SE +/- 0.22, N = 4SE +/- 0.11, N = 4SE +/- 0.28, N = 4SE +/- 0.12, N = 4SE +/- 0.09, N = 4SE +/- 0.06, N = 4SE +/- 0.01, N = 4SE +/- 0.05, N = 4SE +/- 0.38, N = 4SE +/- 0.15, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 351.4648.0745.4942.9542.8141.7341.4638.4637.2233.1030.0028.8228.5026.26

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 4.0Binary: Pathtracer ISPC - Model: Asian DragonXeon Gold 6338 2PXeon Gold 6342 2PEPYC 7713PXeon Gold 6346 2PEPYC 7513 2PEPYC 7413 2PXeon Gold 6338Xeon Gold 6342EPYC 7543EPYC 7513EPYC 7343 2PEPYC 7413Xeon Gold 6346EPYC 734320406080100SE +/- 0.09, N = 6SE +/- 0.02, N = 5SE +/- 0.04, N = 5SE +/- 0.03, N = 4SE +/- 0.13, N = 4SE +/- 0.07, N = 4SE +/- 0.04, N = 4SE +/- 0.06, N = 4SE +/- 0.03, N = 4SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 384.8675.2560.1055.4151.9446.2945.7940.9840.5138.3538.0130.4529.3123.06MIN: 82.99 / MAX: 89.58MIN: 73.81 / MAX: 79.52MIN: 59.02 / MAX: 61.86MIN: 54.58 / MAX: 57.85MIN: 50.91 / MAX: 54.47MIN: 45.68 / MAX: 47.36MIN: 45.07 / MAX: 48.58MIN: 39.96 / MAX: 43MIN: 40.15 / MAX: 41.05MIN: 37.95 / MAX: 38.96MIN: 37.62 / MAX: 38.66MIN: 30.17 / MAX: 30.93MIN: 28.56 / MAX: 31.49MIN: 22.91 / MAX: 23.57

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 1080p - Video Preset: SlowEPYC 7513 2PEPYC 7413 2PEPYC 7713PXeon Gold 6342 2PXeon Gold 6338 2PEPYC 7343 2PEPYC 7543EPYC 7513EPYC 7343EPYC 7413Xeon Gold 6346 2PXeon Gold 6346Xeon Gold 6342Xeon Gold 63381428425670SE +/- 0.11, N = 5SE +/- 0.15, N = 5SE +/- 0.13, N = 5SE +/- 0.13, N = 4SE +/- 0.15, N = 4SE +/- 0.09, N = 4SE +/- 0.05, N = 4SE +/- 0.05, N = 4SE +/- 0.05, N = 4SE +/- 0.03, N = 4SE +/- 0.06, N = 4SE +/- 0.04, N = 3SE +/- 0.07, N = 3SE +/- 0.04, N = 363.0059.5256.0751.7444.4843.9241.0940.5238.5238.4538.4333.0533.0228.13

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Ultra FastEPYC 7513 2PEPYC 7413 2PEPYC 7713PEPYC 7543EPYC 7343 2PEPYC 7513Xeon Gold 6342 2PXeon Gold 6346 2PXeon Gold 6338 2PEPYC 7413EPYC 7343Xeon Gold 6342Xeon Gold 6338Xeon Gold 63461224364860SE +/- 0.28, N = 5SE +/- 0.34, N = 4SE +/- 0.27, N = 4SE +/- 0.10, N = 4SE +/- 0.07, N = 4SE +/- 0.06, N = 4SE +/- 0.18, N = 4SE +/- 0.03, N = 4SE +/- 0.48, N = 4SE +/- 0.08, N = 4SE +/- 0.07, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 353.2149.7748.3147.2446.6546.0744.2442.0838.9238.8835.2833.3031.6731.03

LULESH

LULESH is the Livermore Unstructured Lagrangian Explicit Shock Hydrodynamics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgz/s, More Is BetterLULESH 2.0.3Xeon Gold 6338 2PEPYC 7513 2PEPYC 7343 2PXeon Gold 6342 2PEPYC 7413 2PEPYC 7713PXeon Gold 6346 2PEPYC 7543Xeon Gold 6338EPYC 7513EPYC 7343Xeon Gold 6346Xeon Gold 6342EPYC 74139K18K27K36K45KSE +/- 13.51, N = 4SE +/- 90.00, N = 4SE +/- 149.46, N = 6SE +/- 38.77, N = 6SE +/- 276.03, N = 15SE +/- 29.51, N = 3SE +/- 40.17, N = 5SE +/- 138.07, N = 5SE +/- 85.02, N = 5SE +/- 101.13, N = 5SE +/- 24.59, N = 6SE +/- 11.87, N = 6SE +/- 26.68, N = 6SE +/- 25.11, N = 639798.6937170.8627713.9426940.9825716.7722242.5322099.3221129.4118868.7218098.8010323.1810152.769964.419682.801. (CXX) g++ options: -O3 -fopenmp -lm -lmpi_cxx -lmpi

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 7513 2PXeon Gold 6338 2PEPYC 7713PEPYC 7413 2PXeon Gold 6342 2PEPYC 7343 2PXeon Gold 6346 2PEPYC 7543EPYC 7513Xeon Gold 6338EPYC 7413Xeon Gold 6342Xeon Gold 634620406080100SE +/- 0.16, N = 5SE +/- 0.17, N = 5SE +/- 0.15, N = 5SE +/- 0.13, N = 4SE +/- 0.31, N = 4SE +/- 0.48, N = 4SE +/- 0.03, N = 4SE +/- 0.04, N = 4SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.05, N = 393.3580.3976.5168.7668.5155.9454.9250.4647.1040.4136.0735.5627.621. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm

Implementation: OpenMP - Input Deck: BM1

EPYC 7343: The test quit with a non-zero exit status.

OpenBenchmarking.orgGFInst/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM1EPYC 7513 2PXeon Gold 6338 2PEPYC 7713PEPYC 7413 2PXeon Gold 6342 2PEPYC 7343 2PXeon Gold 6346 2PEPYC 7543EPYC 7513Xeon Gold 6338EPYC 7413Xeon Gold 6342Xeon Gold 63465001000150020002500SE +/- 4.00, N = 5SE +/- 4.35, N = 5SE +/- 3.71, N = 5SE +/- 3.16, N = 4SE +/- 7.83, N = 4SE +/- 11.90, N = 4SE +/- 0.78, N = 4SE +/- 1.10, N = 4SE +/- 0.14, N = 3SE +/- 0.83, N = 3SE +/- 0.56, N = 3SE +/- 1.48, N = 3SE +/- 1.38, N = 32333.762009.721912.741718.941712.721398.411372.931261.441177.571010.28901.85889.01690.471. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm

Implementation: OpenMP - Input Deck: BM1

EPYC 7343: The test quit with a non-zero exit status.

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 1080p - Video Preset: MediumEPYC 7513 2PEPYC 7413 2PEPYC 7713PXeon Gold 6342 2PXeon Gold 6338 2PEPYC 7343 2PEPYC 7543EPYC 7513EPYC 7413EPYC 7343Xeon Gold 6346 2PXeon Gold 6342Xeon Gold 6346Xeon Gold 63381632486480SE +/- 0.19, N = 5SE +/- 0.08, N = 5SE +/- 0.19, N = 5SE +/- 0.14, N = 5SE +/- 0.08, N = 4SE +/- 0.08, N = 4SE +/- 0.10, N = 4SE +/- 0.04, N = 4SE +/- 0.09, N = 4SE +/- 0.16, N = 4SE +/- 0.09, N = 4SE +/- 0.02, N = 4SE +/- 0.04, N = 4SE +/- 0.02, N = 370.7566.4761.6657.7049.3949.1546.1445.6043.2743.1143.0437.0837.0031.35

Pennant

Pennant is an application focused on hydrodynamics on general unstructured meshes in 2D. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: leblancbigEPYC 7513 2PEPYC 7413 2PEPYC 7713PXeon Gold 6338 2PXeon Gold 6342 2PEPYC 7343 2PEPYC 7543Xeon Gold 6346 2PEPYC 7513EPYC 7413Xeon Gold 6338Xeon Gold 6342EPYC 7343Xeon Gold 6346510152025SE +/- 0.022993, N = 6SE +/- 0.020399, N = 6SE +/- 0.054440, N = 6SE +/- 0.011875, N = 5SE +/- 0.022667, N = 5SE +/- 0.016342, N = 5SE +/- 0.028009, N = 5SE +/- 0.008469, N = 5SE +/- 0.065044, N = 4SE +/- 0.066993, N = 4SE +/- 0.017732, N = 4SE +/- 0.025498, N = 3SE +/- 0.027516, N = 3SE +/- 0.006168, N = 34.8276485.9766536.2467047.3473797.5238247.6180468.5755969.73306510.83575012.95789014.44702015.69182016.69242019.4932801. (CXX) g++ options: -fopenmp -lmpi_cxx -lmpi

SVT-VP9

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample YUV input video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: PSNR/SSIM Optimized - Input: Bosphorus 4KEPYC 7713PEPYC 7543EPYC 7513 2PEPYC 7513EPYC 7413 2PEPYC 7343 2PXeon Gold 6346 2PXeon Gold 6338Xeon Gold 6342 2PXeon Gold 6342Xeon Gold 6338 2PEPYC 7413EPYC 7343Xeon Gold 63464080120160200SE +/- 0.20, N = 7SE +/- 0.17, N = 7SE +/- 2.12, N = 15SE +/- 0.48, N = 7SE +/- 0.94, N = 6SE +/- 0.22, N = 7SE +/- 0.27, N = 7SE +/- 0.14, N = 7SE +/- 0.52, N = 6SE +/- 0.26, N = 7SE +/- 0.19, N = 5SE +/- 0.24, N = 7SE +/- 0.17, N = 7SE +/- 0.11, N = 6179.74175.18165.46164.17161.19158.14150.48148.73148.45148.12144.22143.85115.80115.371. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUEPYC 7513 2PEPYC 7713PEPYC 7413 2PEPYC 7343 2PEPYC 7543Xeon Gold 6338Xeon Gold 6342Xeon Gold 6346EPYC 7513EPYC 7413Xeon Gold 6338 2PXeon Gold 6342 2PXeon Gold 6346 2P0.75181.50362.25543.00723.759SE +/- 0.004296, N = 7SE +/- 0.000877, N = 7SE +/- 0.001690, N = 7SE +/- 0.003169, N = 7SE +/- 0.001763, N = 7SE +/- 0.007172, N = 7SE +/- 0.009698, N = 7SE +/- 0.003371, N = 7SE +/- 0.002206, N = 7SE +/- 0.003897, N = 7SE +/- 0.018972, N = 10SE +/- 0.026790, N = 7SE +/- 0.028591, N = 150.7868030.9379180.9404551.1884001.3013801.7112901.8219001.9420001.9501602.1373102.4662702.9934003.341250MIN: 0.68MIN: 0.87MIN: 0.75MIN: 0.94MIN: 1.15MIN: 1.58MIN: 1.68MIN: 1.73MIN: 1.75MIN: 1.86MIN: 2.29MIN: 2.81MIN: 3.071. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU

EPYC 7343: The test quit with a non-zero exit status.

SVT-VP9

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample YUV input video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.3Tuning: Visual Quality Optimized - Input: Bosphorus 4KEPYC 7513 2PEPYC 7713PEPYC 7413 2PXeon Gold 6342 2PEPYC 7543Xeon Gold 6338 2PXeon Gold 6346 2PEPYC 7343 2PEPYC 7513Xeon Gold 6338Xeon Gold 6342EPYC 7413EPYC 7343Xeon Gold 6346306090120150SE +/- 0.59, N = 6SE +/- 0.28, N = 6SE +/- 0.32, N = 6SE +/- 0.33, N = 6SE +/- 0.25, N = 7SE +/- 0.88, N = 5SE +/- 0.17, N = 6SE +/- 0.49, N = 6SE +/- 0.14, N = 7SE +/- 0.18, N = 6SE +/- 0.23, N = 6SE +/- 0.18, N = 6SE +/- 0.08, N = 6SE +/- 0.07, N = 6148.84146.48145.30138.19137.52131.90130.49130.23129.22111.92109.31107.7783.7383.381. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

SVT-HEVC

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 7 - Input: Bosphorus 4KEPYC 7513 2PEPYC 7713PEPYC 7413 2PXeon Gold 6342 2PXeon Gold 6338 2PEPYC 7543Xeon Gold 6346 2PEPYC 7343 2PEPYC 7513Xeon Gold 6338EPYC 7413Xeon Gold 6342EPYC 7343Xeon Gold 6346306090120150SE +/- 0.43, N = 7SE +/- 0.16, N = 7SE +/- 0.12, N = 7SE +/- 0.32, N = 7SE +/- 0.31, N = 7SE +/- 0.19, N = 7SE +/- 0.06, N = 7SE +/- 0.14, N = 7SE +/- 0.12, N = 7SE +/- 0.05, N = 6SE +/- 0.04, N = 6SE +/- 0.10, N = 6SE +/- 0.07, N = 5SE +/- 0.06, N = 5149.01138.52136.95136.71128.72119.84117.26116.56111.9591.7085.6785.6671.4165.821. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.5.0Tuning: 10 - Input: Bosphorus 4KEPYC 7713PEPYC 7543EPYC 7413 2PEPYC 7513EPYC 7513 2PEPYC 7343 2PEPYC 7413Xeon Gold 6346 2PXeon Gold 6338 2PXeon Gold 6342 2PXeon Gold 6342Xeon Gold 6338EPYC 7343Xeon Gold 634650100150200250SE +/- 0.70, N = 9SE +/- 0.23, N = 9SE +/- 1.90, N = 15SE +/- 0.27, N = 8SE +/- 2.94, N = 15SE +/- 1.02, N = 8SE +/- 0.39, N = 8SE +/- 1.19, N = 15SE +/- 0.96, N = 8SE +/- 1.35, N = 15SE +/- 0.23, N = 8SE +/- 0.18, N = 8SE +/- 0.23, N = 8SE +/- 0.06, N = 7224.80219.43208.59207.54201.76191.99181.39176.86176.67176.18173.16171.63143.45134.341. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

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 1.4Encoder Mode: Preset 12 - Input: Bosphorus 4KEPYC 7543EPYC 7713PEPYC 7513EPYC 7513 2PEPYC 7413 2PXeon Gold 6342 2PXeon Gold 6346 2PEPYC 7413Xeon Gold 6342EPYC 7343 2PXeon Gold 6338 2PXeon Gold 6338EPYC 7343Xeon Gold 634650100150200250SE +/- 0.47, N = 8SE +/- 1.31, N = 8SE +/- 0.86, N = 8SE +/- 1.43, N = 7SE +/- 0.76, N = 7SE +/- 1.23, N = 7SE +/- 0.70, N = 7SE +/- 0.80, N = 8SE +/- 0.50, N = 7SE +/- 0.36, N = 7SE +/- 0.71, N = 7SE +/- 0.49, N = 7SE +/- 0.47, N = 8SE +/- 0.44, N = 8237.13232.00231.54217.70217.43213.42211.63210.55206.81204.55201.07194.14179.07173.291. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

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 1080p - Video Preset: Super FastEPYC 7713PEPYC 7513 2PEPYC 7413 2PXeon Gold 6342 2PEPYC 7343 2PEPYC 7543EPYC 7513Xeon Gold 6338 2PXeon Gold 6346 2PEPYC 7413EPYC 7343Xeon Gold 6342Xeon Gold 6346Xeon Gold 63384080120160200SE +/- 1.30, N = 15SE +/- 0.59, N = 9SE +/- 0.48, N = 9SE +/- 0.61, N = 8SE +/- 0.15, N = 8SE +/- 0.17, N = 8SE +/- 0.09, N = 8SE +/- 0.62, N = 8SE +/- 0.15, N = 8SE +/- 0.15, N = 8SE +/- 0.23, N = 7SE +/- 0.06, N = 7SE +/- 0.08, N = 7SE +/- 0.13, N = 6180.55173.74163.18152.28142.78139.65138.95133.13127.62125.26116.79106.29100.8794.98

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 1080p - Video Preset: Very FastEPYC 7513 2PEPYC 7713PEPYC 7413 2PXeon Gold 6342 2PEPYC 7343 2PXeon Gold 6338 2PEPYC 7543EPYC 7513EPYC 7413Xeon Gold 6346 2PEPYC 7343Xeon Gold 6342Xeon Gold 6346Xeon Gold 63384080120160200SE +/- 0.87, N = 9SE +/- 0.24, N = 9SE +/- 0.70, N = 9SE +/- 0.51, N = 8SE +/- 0.22, N = 8SE +/- 0.79, N = 8SE +/- 0.17, N = 8SE +/- 0.17, N = 8SE +/- 0.17, N = 7SE +/- 0.07, N = 7SE +/- 0.15, N = 7SE +/- 0.07, N = 7SE +/- 0.10, N = 6SE +/- 0.05, N = 6173.58168.38164.25150.71134.43131.93130.26129.79118.56116.97110.9898.1393.1787.55

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 1.4Encoder Mode: Preset 13 - Input: Bosphorus 4KEPYC 7543EPYC 7513EPYC 7713PXeon Gold 6346 2PXeon Gold 6342 2PEPYC 7413EPYC 7413 2PEPYC 7513 2PEPYC 7343 2PXeon Gold 6342Xeon Gold 6338 2PXeon Gold 6338EPYC 7343Xeon Gold 634650100150200250SE +/- 0.51, N = 8SE +/- 0.62, N = 8SE +/- 0.85, N = 8SE +/- 1.08, N = 8SE +/- 1.17, N = 8SE +/- 0.31, N = 8SE +/- 0.58, N = 8SE +/- 1.18, N = 8SE +/- 0.41, N = 8SE +/- 0.47, N = 8SE +/- 1.06, N = 7SE +/- 0.37, N = 8SE +/- 0.40, N = 8SE +/- 0.40, N = 8214.39210.24203.19200.42200.38195.80193.78193.15191.02190.74180.92176.04172.16166.791. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

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 1080p - Video Preset: Ultra FastEPYC 7713PEPYC 7513 2PEPYC 7413 2PXeon Gold 6342 2PEPYC 7343 2PEPYC 7543EPYC 7513Xeon Gold 6346 2PEPYC 7413Xeon Gold 6338 2PEPYC 7343Xeon Gold 6342Xeon Gold 6346Xeon Gold 63384080120160200SE +/- 1.44, N = 9SE +/- 0.58, N = 9SE +/- 0.88, N = 9SE +/- 0.69, N = 8SE +/- 0.28, N = 8SE +/- 0.15, N = 8SE +/- 0.24, N = 8SE +/- 0.20, N = 8SE +/- 0.17, N = 8SE +/- 0.92, N = 8SE +/- 0.10, N = 8SE +/- 0.25, N = 7SE +/- 0.07, N = 7SE +/- 0.15, N = 7196.33175.35165.33155.38155.33154.38153.97139.86138.79136.60130.30118.47113.18105.96

System Power Consumption Monitor

OpenBenchmarking.orgWattsSystem Power Consumption MonitorPhoronix Test Suite System MonitoringEPYC 7413EPYC 7343EPYC 7513EPYC 7543EPYC 7713PXeon Gold 6346Xeon Gold 6338Xeon Gold 6342EPYC 7343 2PEPYC 7413 2PEPYC 7513 2PXeon Gold 6346 2PXeon Gold 6338 2PXeon Gold 6342 2P2004006008001000Min: 8 / Avg: 209.56 / Max: 1269Min: 45 / Avg: 221.93 / Max: 327Min: 7 / Avg: 222.77 / Max: 1265Min: 45 / Avg: 243.81 / Max: 793Min: 12 / Avg: 247.7 / Max: 769Min: 117 / Avg: 279.8 / Max: 378Min: 120 / Avg: 280.3 / Max: 395Min: 119 / Avg: 299.04 / Max: 441Min: 8 / Avg: 335.19 / Max: 1229Min: 5 / Avg: 341.73 / Max: 815Min: 4 / Avg: 354.08 / Max: 1296Min: 215 / Avg: 470.82 / Max: 772Min: 236 / Avg: 471.28 / Max: 775Min: 213 / Avg: 501.51 / Max: 1250

CPU Power Consumption Monitor

OpenBenchmarking.orgWattsCPU Power Consumption MonitorPhoronix Test Suite System MonitoringEPYC 7413EPYC 7513EPYC 7343EPYC 7713PEPYC 7543Xeon Gold 6338Xeon Gold 6346Xeon Gold 6342EPYC 7413 2PEPYC 7343 2PEPYC 7513 2PXeon Gold 6338 2PXeon Gold 6346 2PXeon Gold 6342 2P150300450600750Min: 29.1 / Avg: 127 / Max: 324.96Min: 26.89 / Avg: 134.88 / Max: 396.04Min: 23.99 / Avg: 140.71 / Max: 328.9Min: 43.09 / Avg: 150.11 / Max: 386.67Min: 36.25 / Avg: 150.53 / Max: 430.76Min: 53.56 / Avg: 168.73 / Max: 425.54Min: 47.76 / Avg: 187.84 / Max: 408.81Min: 45.82 / Avg: 188.97 / Max: 461.29Min: 68.53 / Avg: 227.74 / Max: 566.42Min: 58.82 / Avg: 232.68 / Max: 664.7Min: 65.82 / Avg: 239.48 / Max: 696.69Min: 113.87 / Avg: 305.61 / Max: 595.53Min: 102.44 / Avg: 316.34 / Max: 856.39Min: 98.17 / Avg: 321.64 / Max: 832.85

CPU Peak Freq (Highest CPU Core Frequency) Monitor

OpenBenchmarking.orgMegahertzCPU Peak Freq (Highest CPU Core Frequency) MonitorPhoronix Test Suite System MonitoringXeon Gold 6338Xeon Gold 6338 2PEPYC 7713PEPYC 7513EPYC 7413Xeon Gold 6342EPYC 7543EPYC 7513 2PEPYC 7413 2PXeon Gold 6342 2PXeon Gold 6346Xeon Gold 6346 2PEPYC 7343EPYC 7343 2P8001600240032004000Min: 1768 / Avg: 2871.72 / Max: 3251Min: 2063 / Avg: 2933.33 / Max: 3303Min: 1880 / Avg: 3063.29 / Max: 3719Min: 2158 / Avg: 3299.38 / Max: 3938Min: 2161 / Avg: 3329.22 / Max: 3766Min: 2406 / Avg: 3359.04 / Max: 3553Min: 2196 / Avg: 3362.09 / Max: 3799Min: 2133 / Avg: 3391.15 / Max: 3882Min: 2276 / Avg: 3393.65 / Max: 3908Min: 2702 / Avg: 3399.67 / Max: 4321Min: 2730 / Avg: 3569.74 / Max: 3842Min: 3077 / Avg: 3589.28 / Max: 4011Min: 2145 / Avg: 3603.76 / Max: 3954Min: 2157 / Avg: 3667.94 / Max: 4327

146 Results Shown

TensorFlow:
  CPU - 512 - ResNet-50
  CPU - 256 - ResNet-50
Xcompact3d Incompact3d
Blender
PostgreSQL:
  1000 - 800 - Read Only - Average Latency
  1000 - 800 - Read Only
  1000 - 1000 - Read Only - Average Latency
  1000 - 1000 - Read Only
CloudSuite Web Serving
CloudSuite Graph Analytics
Graph500:
  26:
    bfs max_TEPS
    sssp max_TEPS
    sssp median_TEPS
    bfs median_TEPS
PostgreSQL:
  1000 - 1000 - Read Write - Average Latency
  1000 - 1000 - Read Write
  1000 - 800 - Read Write - Average Latency
  1000 - 800 - Read Write
Timed LLVM Compilation
CloudSuite Web Serving
ClickHouse:
  100M Rows Hits Dataset, Third Run
  100M Rows Hits Dataset, Second Run
  100M Rows Hits Dataset, First Run / Cold Cache
Timed Node.js Compilation
Timed LLVM Compilation
CloudSuite In-Memory Analytics
FFmpeg:
  libx265 - Video On Demand:
    FPS
    Seconds
  libx265 - Platform:
    FPS
    Seconds
  libx265 - Upload:
    FPS
    Seconds
OpenSSL
High Performance Conjugate Gradient
nekRS
Memcached
RocksDB
OSPRay Studio
RocksDB
OSPRay Studio:
  3 - 4K - 1 - Path Tracer
  1 - 4K - 32 - Path Tracer
Blender
OSPRay Studio
Memcached
Apache Cassandra
Memcached
CloudSuite Web Serving
CloudSuite Graph Analytics
SVT-HEVC
RocksDB
nginx:
  500
  200
LuxCoreRender
CloudSuite Graph Analytics
nginx
RocksDB:
  Read Rand Write Rand
  Rand Fill Sync
CloudSuite In-Memory Analytics
OpenVINO:
  Person Detection FP16 - CPU:
    ms
    FPS
  Person Detection FP32 - CPU:
    ms
    FPS
LuxCoreRender
OpenVINO:
  Face Detection FP16 - CPU:
    ms
    FPS
FFmpeg:
  libx265 - Live:
    FPS
    Seconds
LuxCoreRender
OpenVINO:
  Face Detection FP16-INT8 - CPU:
    ms
    FPS
  Machine Translation EN To DE FP16 - CPU:
    ms
    FPS
  Person Vehicle Bike Detection FP16 - CPU:
    ms
    FPS
  Vehicle Detection FP16-INT8 - CPU:
    ms
    FPS
  Weld Porosity Detection FP16 - CPU:
    ms
    FPS
  Age Gender Recognition Retail 0013 FP16-INT8 - CPU:
    ms
    FPS
  Weld Porosity Detection FP16-INT8 - CPU:
    ms
    FPS
  Vehicle Detection FP16 - CPU:
    ms
    FPS
  Age Gender Recognition Retail 0013 FP16 - CPU:
    ms
    FPS
OpenSSL:
  RSA4096:
    verify/s
    sign/s
Neural Magic DeepSparse:
  CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Stream:
    ms/batch
    items/sec
RocksDB
Neural Magic DeepSparse:
  NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream:
    ms/batch
    items/sec
Timed Linux Kernel Compilation
Neural Magic DeepSparse:
  NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Stream:
    ms/batch
    items/sec
uvg266
Blender
GROMACS
uvg266
FFmpeg
Neural Magic DeepSparse:
  NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream:
    ms/batch
    items/sec
Xcompact3d Incompact3d
Neural Magic DeepSparse:
  CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream:
    ms/batch
    items/sec
NAMD
Kvazaar
LuxCoreRender
PHPBench
SVT-VP9
Kvazaar
Pennant
Embree:
  Pathtracer ISPC - Crown
  Pathtracer - Crown
  Pathtracer - Asian Dragon
Kvazaar
uvg266:
  Bosphorus 4K - Very Fast
  Bosphorus 4K - Super Fast
Embree
uvg266:
  Bosphorus 1080p - Slow
  Bosphorus 4K - Ultra Fast
LULESH
miniBUDE:
  OpenMP - BM1:
    Billion Interactions/s
    GFInst/s
uvg266
Pennant
SVT-VP9
oneDNN
SVT-VP9
SVT-HEVC:
  7 - Bosphorus 4K
  10 - Bosphorus 4K
SVT-AV1
uvg266:
  Bosphorus 1080p - Super Fast
  Bosphorus 1080p - Very Fast
SVT-AV1
uvg266
System Power Consumption Monitor:
  Phoronix Test Suite System Monitoring:
    Watts
    Watts
    Megahertz