extra tests

benchmarks for a future article.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2309060-NE-EXTRATEST87
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

Limit displaying results to tests within:

AV1 2 Tests
C/C++ Compiler Tests 2 Tests
CPU Massive 5 Tests
Creator Workloads 8 Tests
Database Test Suite 2 Tests
Encoding 3 Tests
Game Development 2 Tests
HPC - High Performance Computing 4 Tests
Machine Learning 2 Tests
Multi-Core 9 Tests
NVIDIA GPU Compute 2 Tests
Intel oneAPI 3 Tests
OpenMPI Tests 5 Tests
Renderers 2 Tests
Server 2 Tests
Server CPU Tests 4 Tests
Video Encoding 3 Tests
Common Workstation Benchmarks 2 Tests

Statistics

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

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Disable Color Branding
Prefer Vertical Bar Graphs

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
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
d
August 25 2023
  3 Hours, 8 Minutes
g
August 30 2023
  4 Hours, 25 Minutes
h
August 30 2023
  4 Hours, 23 Minutes
2 x AMD EPYC 9334 32-Core
September 06 2023
  3 Hours, 9 Minutes
9334 2p
September 06 2023
  3 Hours, 11 Minutes
93334 rep
September 06 2023
  3 Hours, 13 Minutes
Invert Hiding All Results Option
  3 Hours, 35 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):

d

Processor: 2 x AMD EPYC 9124 16-Core @ 3.00GHz (32 Cores / 64 Threads), Motherboard: Supermicro H13DSH (1.5 BIOS), Memory: 24 x 32 GB DDR5-4800MT/s Samsung M321R4GA3BB6-CQKET, Disk: 2 x 1920GB SAMSUNG MZQL21T9HCJR-00A07, Graphics: astdrmfb

OS: AlmaLinux 9.2, Kernel: 5.14.0-284.25.1.el9_2.x86_64 (x86_64), Compiler: GCC 11.3.1 20221121, File-System: ext4, Screen Resolution: 1024x768

Kernel Notes: Transparent Huge Pages: always
Compiler Notes: --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-isl
Processor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa10113e
Java Notes: OpenJDK Runtime Environment (Red_Hat-11.0.20.0.8-1) (build 11.0.20+8-LTS)
Python Notes: Python 3.9.16
Security Notes: 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

g

Kernel Notes: Transparent Huge Pages: always
Compiler Notes: --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-isl
Processor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xaa00116
Java Notes: OpenJDK Runtime Environment (Red_Hat-11.0.20.0.8-1) (build 11.0.20+8-LTS)
Python Notes: Python 3.9.16
Security Notes: 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

h

Changed Processor to 2 x AMD EPYC 9754 128-Core @ 2.25GHz (256 Cores / 512 Threads).

Changed Memory to 23 x 32 GB DDR5-4800MT/s Samsung M321R4GA3BB6-CQKET.

2 x AMD EPYC 9334 32-Core

Kernel Notes: Transparent Huge Pages: always
Compiler Notes: --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-isl
Processor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa10113e
Java Notes: OpenJDK Runtime Environment (Red_Hat-11.0.20.0.8-1) (build 11.0.20+8-LTS)
Python Notes: Python 3.9.16
Security Notes: 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

9334 2p

93334 rep

Changed Processor to 2 x AMD EPYC 9334 32-Core @ 2.70GHz (64 Cores / 128 Threads).

Changed Memory to 21 x 32 GB DDR5-4800MT/s Samsung M321R4GA3BB6-CQKET.

extra testsProcessorMotherboardMemoryDiskGraphicsOSKernelCompilerFile-SystemScreen Resolutiondgh2 x AMD EPYC 9334 32-Core9334 2p93334 rep2 x AMD EPYC 9124 16-Core @ 3.00GHz (32 Cores / 64 Threads)Supermicro H13DSH (1.5 BIOS)24 x 32 GB DDR5-4800MT/s Samsung M321R4GA3BB6-CQKET2 x 1920GB SAMSUNG MZQL21T9HCJR-00A07astdrmfbAlmaLinux 9.25.14.0-284.25.1.el9_2.x86_64 (x86_64)GCC 11.3.1 20221121ext41024x7682 x AMD EPYC 9754 128-Core @ 2.25GHz (256 Cores / 512 Threads)23 x 32 GB DDR5-4800MT/s Samsung M321R4GA3BB6-CQKET2 x AMD EPYC 9334 32-Core @ 2.70GHz (64 Cores / 128 Threads)21 x 32 GB DDR5-4800MT/s Samsung M321R4GA3BB6-CQKETOpenBenchmarking.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-isl Processor Details- d: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa10113e- g: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xaa00116- h: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xaa00116- 2 x AMD EPYC 9334 32-Core: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa10113e- 9334 2p: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa10113e- 93334 rep: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa10113eJava Details- OpenJDK Runtime Environment (Red_Hat-11.0.20.0.8-1) (build 11.0.20+8-LTS)Python Details- Python 3.9.16Security Details- 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

dgh2 x AMD EPYC 9334 32-Core9334 2p93334 repLogarithmic Result OverviewPhoronix Test SuiteBlenderEmbreeStress-NGOSPRayNCNNIntel Open Image DenoiseBRL-CADNeural Magic DeepSparseTimed Linux Kernel CompilationApache CassandraLiquid-DSPSVT-AV1

extra testsstress-ng: Semaphoresstress-ng: Pipedeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: ResNet-50, Baseline - Asynchronous Multi-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: BERT-Large, NLP Question Answering - Asynchronous Multi-Streamdeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamstress-ng: x86_64 RdRandstress-ng: Hashstress-ng: Context Switchingstress-ng: Vector Shuffledeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamncnn: CPU - regnety_400mstress-ng: Floating Pointstress-ng: CPU Stressstress-ng: Function Callstress-ng: Matrix Mathstress-ng: Vector Floating Pointstress-ng: Fused Multiply-Addstress-ng: Zlibdeepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Streamblender: Classroom - CPU-Onlystress-ng: Vector Mathblender: Pabellon Barcelona - CPU-Onlystress-ng: AVX-512 VNNIstress-ng: Memory Copyingstress-ng: Wide Vector Mathstress-ng: Glibc Qsort Data Sortingstress-ng: Mallocstress-ng: Glibc C String Functionsblender: Barbershop - CPU-Onlyblender: BMW27 - CPU-Onlyospray: gravity_spheres_volume/dim_512/scivis/real_timeembree: Pathtracer - Asian Dragonembree: Pathtracer - Asian Dragon Objospray: gravity_spheres_volume/dim_512/ao/real_timedeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Streamembree: Pathtracer - Crownembree: Pathtracer ISPC - Asian Dragonembree: Pathtracer ISPC - Crownstress-ng: Pollblender: Fishy Cat - CPU-Onlyncnn: CPU - blazefaceembree: Pathtracer ISPC - Asian Dragon Objstress-ng: SENDFILEospray: particle_volume/ao/real_timeospray: particle_volume/scivis/real_timestress-ng: Cryptoncnn: CPU - shufflenet-v2stress-ng: Forkingstress-ng: AVL Treestress-ng: CPU Cachestress-ng: MMAPncnn: CPU - efficientnet-b0ncnn: CPU-v3-v3 - mobilenet-v3stress-ng: NUMAncnn: CPU - mnasnetncnn: CPU-v2-v2 - mobilenet-v2ncnn: CPU - FastestDetdeepsparse: CV Detection, YOLOv5s COCO - Synchronous Single-Streamdeepsparse: CV Detection, YOLOv5s COCO - Synchronous Single-Streamdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Streamdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Streamoidn: RT.hdr_alb_nrm.3840x2160 - CPU-Onlyoidn: RT.ldr_alb_nrm.3840x2160 - CPU-Onlyncnn: CPU - squeezenet_ssdospray: gravity_spheres_volume/dim_512/pathtracer/real_timeoidn: RTLightmap.hdr.4096x4096 - CPU-Onlydeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Streamdragonflydb: 20 - 1:100dragonflydb: 10 - 1:100ncnn: CPU - resnet18ncnn: CPU - alexnetdeepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Synchronous Single-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Synchronous Single-Streamdragonflydb: 10 - 1:10deepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Streamncnn: CPU - vgg16ncnn: CPU - resnet50dragonflydb: 20 - 1:10ncnn: CPU - mobilenetncnn: CPU - vision_transformerstress-ng: Socket Activitybrl-cad: VGR Performance Metricstress-ng: MEMFDncnn: CPU - googlenetdeepsparse: ResNet-50, Sparse INT8 - Synchronous Single-Streamdeepsparse: ResNet-50, Sparse INT8 - Synchronous Single-Streamdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Streamdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Streamspecfem3d: Layered Halfspacespecfem3d: Mount St. Helensdeepsparse: ResNet-50, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Streamspecfem3d: Water-layered Halfspacedeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Synchronous Single-Streamdeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Synchronous Single-Streamstress-ng: Futexdeepsparse: BERT-Large, NLP Question Answering - Synchronous Single-Streamdeepsparse: BERT-Large, NLP Question Answering - Synchronous Single-Streamspecfem3d: Homogeneous Halfspacesvt-av1: Preset 13 - Bosphorus 4Kspecfem3d: Tomographic Modeldeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Streamremhos: Sample Remap Examplebuild-linux-kernel: defconfigdeepsparse: ResNet-50, Baseline - Synchronous Single-Streamdeepsparse: ResNet-50, Baseline - Synchronous Single-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamliquid-dsp: 64 - 256 - 512laghos: Sedov Blast Wave, ube_922_hex.meshstress-ng: Matrix 3D Mathcassandra: Writessvt-av1: Preset 13 - Bosphorus 1080pnekrs: Kershawncnn: CPU - yolov4-tinydeepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Streamnekrs: TurboPipe Periodicstress-ng: System V Message Passingdeepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamliquid-dsp: 2 - 256 - 32ospray: particle_volume/pathtracer/real_timesvt-av1: Preset 4 - Bosphorus 1080pliquid-dsp: 2 - 256 - 57stress-ng: Mixed Schedulerstress-ng: Pthreadliquid-dsp: 4 - 256 - 512liquid-dsp: 1 - 256 - 32liquid-dsp: 8 - 256 - 32liquid-dsp: 32 - 256 - 32liquid-dsp: 8 - 256 - 512liquid-dsp: 16 - 256 - 32liquid-dsp: 16 - 256 - 512liquid-dsp: 4 - 256 - 32liquid-dsp: 1 - 256 - 57liquid-dsp: 1 - 256 - 512liquid-dsp: 64 - 256 - 57liquid-dsp: 2 - 256 - 512liquid-dsp: 32 - 256 - 512stress-ng: Mutexliquid-dsp: 64 - 256 - 32svt-av1: Preset 4 - Bosphorus 1080pstress-ng: Atomicliquid-dsp: 8 - 256 - 57deepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamliquid-dsp: 16 - 256 - 57deepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamsvt-av1: Preset 12 - Bosphorus 4Kliquid-dsp: 4 - 256 - 57liquid-dsp: 32 - 256 - 57svt-av1: Preset 4 - Bosphorus 4Ksvt-av1: Preset 13 - Bosphorus 4Ksvt-av1: Preset 4 - Bosphorus 4Kdeepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamdeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Streamdeepsparse: BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Streamdeepsparse: BERT-Large, NLP Question Answering - Asynchronous Multi-Streamsvt-av1: Preset 12 - Bosphorus 4Kdeepsparse: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Streamsvt-av1: Preset 12 - Bosphorus 1080pdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamdeepsparse: ResNet-50, Baseline - Asynchronous Multi-Streamsvt-av1: Preset 12 - Bosphorus 1080psvt-av1: Preset 13 - Bosphorus 1080psvt-av1: Preset 8 - Bosphorus 1080psvt-av1: Preset 8 - Bosphorus 1080pvvenc: Bosphorus 4K - Fastvvenc: Bosphorus 1080p - Faststress-ng: Cloningvvenc: Bosphorus 4K - Fastervvenc: Bosphorus 1080p - Fastersvt-av1: Preset 8 - Bosphorus 4Ksvt-av1: Preset 8 - Bosphorus 4Kkripke: laghos: Triple Point Problemdragonflydb: 50 - 1:100dragonflydb: 50 - 1:10build-linux-kernel: allmodconfigdgh2 x AMD EPYC 9334 32-Core9334 2p93334 rep92019395.1320249488.61373.0279257.4237258.5599757.47724.7153355.8877114.282113.6578168.724785.485419.876319.8112013602.067218607.1217931974.9225006.7336.384933.511939.4188466.5427731.16173878.7106715.8532151217.032944.542661.225594.88234239.6122.73667964.1513428.641543291.91916.74137476652.9340991307.95372.7237.939.8131842.764137.987610.0774106.146737.67748.474639.38414337787.7248.955.6340.5726857324.8910.863410.8453107643.4913.961007.46410.89776708.721131.5514.7611.6418.3510.711.291614.745467.765714.663268.16211.361.3724.2211.90020.6571.3514.013971.836213.919214250093.7111860591.6513.658.134.9317202.501911686474.2640.734524.53628.6926.5315179164.8623.5555.059504.38544648912.6229.031.1189890.944811.086890.075638.48977964914.5056452535.9947150.27634.8222274827.1456139.79344022496.0758.827916.996118.85382887614.87771034620.71448.251220.90435.2837.1102140.45687.1228140.2014504660000263.8510869.492304021152090000035.7519.635650.908974704900006851573.210.081399.1222436.974968834000176.61414.97410563000035640.3670043.7849884000351950002717300001073800000964490005493900001955100001365000005276500012652000177860000024900000387460000438280.162045600000236.99331200000794.0387650410000795.852199.52317428000012345000005.053195.829140.5767139.6127186.648294.619744.914842.8337641.605121.0894419.85361.805362.1006545.195136.0716.76819.1661170.3112.67833.57272.353372072000195.4017583489.3815253621.53800762640.11173499514.942613.0881780.23791778.36165150.4252166.73352405.8755770.5065761.86571128.8846566.7259129.4385129.384978673620.1445298625.91110432440.32154267.34220.9069202.3471782.95523898.45156381.63989553.8604724.84180789739.0816624.0714854.85617.311288008.2622.420133541.1172825.568237581.374846.22719479964.33215429087.6171.977.5149.5123217.591193.050250.4014497.8976183.4023239.4187193.604121346079.310.0226.9193.42973761786.2946.656746.6054462528.7357.6731064.951564.42334039.113664.3447.6735.9614.3829.9231.2444.275.4661182.64175.4478183.37173.403.2858.6628.35211.5030.223533.077931.451931.786529.2615.17.3831135.395520.598148.498956.3453.6241.21108.73110254.19639840497.9457.721.6492605.467213.847372.1848.5843256.16428.7387114.37842951631.9642.038823.7821203.00715.022366.522323.0587.2026138.75847.2111138.59465914000014658.75185134599.57348.0814.415969.32717729966.178.0302124.4072573.358255708000161.16913.5758810900029932.254906.434164100029219000228520000914570000830900004578200001651800001145500004418700010576000207660000020660000331240000364035.5718276000009.831204.44279840000969.2352542300000969.8849189.16415101000010573000004.615191.6654.124167.4236165.5104224.6455113.019153.115648.8841756.6198179.40524.7947490.15471.821471.7619511.795600.23125.22134.8751139.8792.64175.15786069338.66159491222.342633.5921784.35591786.17565175.4863168.75062429.7418774.4054764.73741127.7925569.3208131.5432131.101378690548.4945265797.34110991931.6154293.33222.8586201.5971790.06518600.85158994.25990104.85605340.53181626937.8516625.5713153.495817.121285121.422.3520123210.1472800.748234456.234850.99725705488.15215308424.8171.397.450.0879207.2492172.206850.9618532.4594187.4161225.8305194.274320251576.3310.0223.63184.45373745995.1646.756246.5528461785.3645.2230591.671628.91361173.713749.4748.7637.5614.4629.5530.8942.35.4481183.23655.4268184.09213.533.4658.4128.25371.5430.365132.922630.723132.540629.5617.397.4589134.015919.744650.597558.8554.4744.1493.15113347.776270577115.8355.361.6419608.161112.828677.91699.6974239.19158.6016116.19272880825.1135.850827.8849197.0314.564968.612323.0467.1792139.21457.1163140.440365282000015802.86190955600.76248.8213.96571.56547761412.617.6734130.1929567.85555923000160.8712.9138804200029481.4555328.714105200029200000228090000911870000827490004574200001653900001143900004418300010567000207200000020837000329210000363892.118221000009.901203.49277250000952.8689546690000954.9445194.86315536000010650000004.593177.3634.204166.7561164.6605223.8503113.202752.57748.5107751.7219187.67724.6777485.59371.535571.5815507.017581.067124.695134.381209.5394.83173.25226498215.4439461287.6773.5125519.8211519.99321522.046249.7556718.354233.9079231.4583333.851169.271840.574540.247725697538.815425278.8329340312.9652591.7770.902954.5924103.76176344.3854824.58314789.68198651.8858550931.395876.155651.571151.86430109.2663.376626091.9326146.712804498.361675.93262321226.7872167140.03201.5320.6517.435775.282567.483717.8136204.414969.487686.78572.65149104744.1526.437.272.25531312330.4420.398420.3347156553.5118.631641.77788.211095211.772289.819.7914.8742.3313.7413.9416.448.9324111.8518.8864112.46812.212.2125.5120.34161.0444.304422.567344.739222.347831139658.4925802999.0315.169.393.5591280.781922176931.9826.50637.698136.6529.6231053489.2421.853.7938147.9710125371004.7931.030.87111144.30647.5379132.502221.6690898468.4554735345.6462156.059821.3919205075.3972185.02424717570.3637.142126.917311.61697014127.1369.48714578113.306475.100413.51224.744.809207.71534.8028207.99754210000389.8614005.29255016416.173809563000034.6315.021666.536454411000009268236.48.0098124.7249448.734872597000204.93216.19711132000037887.1470405.47523150003717000028873000011581000001043100005755100002086300001442100005415500013207000224720000025706000413970000457807.79228470000012.06253.6346260000776.9139658580000780.5977163.44218539000012930000005.599162.8554.914137.9127136.595188.743295.739244.487341.3109635.6357158.70520.9994442.5561.457261.4884462.328562.313142.186149.1087.39720.7271245.2113.73236.02589.90577.219391567400198.94212194044.2142013739.43779.2277521.805522.111519.29549.8006719.7723234.1305232.2319334.5256168.338740.550940.446525688067.5215412840.2135971998.9852548.2570.207753.7824101.4176621.2754852.06315324.18198855.7558491170.755885.265626.770552.77430141.5463.456624476.3626144.82802185.771674.65263438850.6477814243.76201.5120.5117.330775.456467.323717.7639204.347769.671586.528872.63629067852.1926.158.1572.77461465208.8120.452620.3981156859.2218.351615793.081135334.92299.2819.9215.1841.4913.6914.0222.298.938111.77868.8725112.64632.202.2028.4720.38911.0344.745722.344744.627922.403929330317.3422585212.5617.4910.73.5922278.179424460221.4826.477237.738436.930.628043162.327.4166.6537674.679943711014.2433.40.86771149.12557.7484128.907721.5373245738.3200918565.6693156.277320.8594721725.3028188.31794644551.2937.297326.805511.643695909155.1129.41908663513.296775.1513.96224.6714.7159211.81054.7942208.3426755970000388.86519828914022.5258638560.785814712000040.1915.086866.247354260300009258853.698.0136124.6687451.054472480000209.60916.29511133000037702.2270476.97524690003712600028843000011587000001051700005795100002078100001448000005562400013357000223160000025885000414060000456942.16229130000012.358254.16336320000779.176674330000781.5381160.62618536000012750000005.643163.4255.012137.4827136.4554189.515895.536444.410641.0198635.6516159.25821.0312442.43661.218461.2502458.518520.167140.171150.3467.44720.882119013.68435.57596.10576.503393276500199.20214488001.2142047609.47777.8507520.3204519.7251521.745149.8729715.5913233.339231.4234334.2742168.63140.379640.286825663966.0215326552.1435280554.4252511.0770.824468.6824129.62176710.8554675.85314753.85198610.9358570424.415875.455618.588951.99430096.5563.716621974.9826129.52802578.871676.27263330738.6372810418.71201.9320.4317.278975.11766.850717.8324204.221169.48586.55572.17499078474.0126.378.3972.84651536517.6520.388220.3139156863.7818.471616.05797.641096840.322287.6919.9615.8742.114.2415.0221.58.9437111.70148.8896112.43152.192.2134.9920.33161.0444.358522.539844.661122.386929280070.9724588214.8116.2210.593.5347282.716523645213.1326.479537.735242.0841.0229580028.0627.9561.2438727.869998931009.4733.680.87041145.23438.1347122.790521.6888129918.486910525.6773156.192821.1513706085.2862188.92434752131.3737.574226.607611.533002652152.5839.37456308213.380174.68413.82524.7844.7957208.31034.8205207.2316753120000387.15078606914009.23268984517.438813095000043.5915.082966.267754372400009251814.097.9992124.8961448.886372532000208.8616.6788624800037534518210003718300029032000011595000001022700005809200002093700001438300005588200013320000219430000026081000415200000457061.39229170000012.25254.23329180000779.8287656510000781.9977161.05318667000013024000005.65160.0785.03137.9731136.8061189.326195.597144.680941.101635.1989161.66620.9984416.14961.49161.4475443.322593.633137.614148.8467.35821.0051188.6413.80334.7694.72677.191375715500197.19OpenBenchmarking.org

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Semaphoresgh2 x AMD EPYC 9334 32-Core93334 rep9334 2pd200M400M600M800M1000M800762640.11786069338.66226498215.44214488001.21212194044.2192019395.131. (CXX) g++ options: -O2 -std=gnu99 -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Pipegh93334 rep9334 2p2 x AMD EPYC 9334 32-Cored40M80M120M160M200M173499514.94159491222.3442047609.4742013739.4339461287.6020249488.611. (CXX) g++ options: -O2 -std=gnu99 -lc

Neural Magic DeepSparse

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Streamhg9334 2p93334 rep2 x AMD EPYC 9334 32-Cored60012001800240030002633.592613.09779.23777.85773.51373.03

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Streamhg9334 2p93334 rep2 x AMD EPYC 9334 32-Cored4008001200160020001784.361780.24521.81520.32519.82257.42

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Streamhg9334 2p2 x AMD EPYC 9334 32-Core93334 repd4008001200160020001786.181778.36522.11519.99519.73258.56

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Streamhg2 x AMD EPYC 9334 32-Core93334 rep9334 2pd110022003300440055005175.495150.431522.051521.751519.30757.48

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Streamhg93334 rep9334 2p2 x AMD EPYC 9334 32-Cored4080120160200168.75166.7349.8749.8049.7624.72

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Streamhg9334 2p2 x AMD EPYC 9334 32-Core93334 repd50010001500200025002429.742405.88719.77718.35715.59355.89

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Streamhg9334 2p2 x AMD EPYC 9334 32-Core93334 repd170340510680850774.41770.51234.13233.91233.34114.28

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Streamhg9334 2p2 x AMD EPYC 9334 32-Core93334 repd160320480640800764.74761.87232.23231.46231.42113.66

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamgh9334 2p93334 rep2 x AMD EPYC 9334 32-Cored20040060080010001128.881127.79334.53334.27333.85168.72

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Streamhg2 x AMD EPYC 9334 32-Core93334 rep9334 2pd120240360480600569.32566.73169.27168.63168.3485.49

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Streamhg2 x AMD EPYC 9334 32-Core9334 2p93334 repd306090120150131.54129.4440.5740.5540.3819.88

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Streamhg9334 2p93334 rep2 x AMD EPYC 9334 32-Cored306090120150131.10129.3840.4540.2940.2519.81

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: x86_64 RdRandhg2 x AMD EPYC 9334 32-Core9334 2p93334 repd20M40M60M80M100M78690548.4978673620.1425697538.8025688067.5225663966.0212013602.061. (CXX) g++ options: -O2 -std=gnu99 -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Hashgh2 x AMD EPYC 9334 32-Core9334 2p93334 repd10M20M30M40M50M45298625.9145265797.3415425278.8315412840.2115326552.147218607.121. (CXX) g++ options: -O2 -std=gnu99 -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Context Switchinghg9334 2p93334 rep2 x AMD EPYC 9334 32-Cored20M40M60M80M100M110991931.60110432440.3235971998.9835280554.4229340312.9617931974.921. (CXX) g++ options: -O2 -std=gnu99 -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Vector Shufflehg2 x AMD EPYC 9334 32-Core9334 2p93334 repd30K60K90K120K150K154293.33154267.3452591.7752548.2552511.0725006.731. (CXX) g++ options: -O2 -std=gnu99 -lc

Neural Magic DeepSparse

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamhg2 x AMD EPYC 9334 32-Core93334 rep9334 2pd50100150200250222.86220.9170.9070.8270.2136.38

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: regnety_400md9334 2p2 x AMD EPYC 9334 32-Core93334 rephg408012016020033.5053.7854.5968.68201.59202.34MIN: 33.26 / MAX: 37.92MIN: 53.02 / MAX: 60.41MIN: 50.39 / MAX: 663.91MIN: 53.81 / MAX: 3458.69MIN: 191.08 / MAX: 1525.04MIN: 187.7 / MAX: 1161.841. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Floating Pointhg93334 rep2 x AMD EPYC 9334 32-Core9334 2pd15K30K45K60K75K71790.0671782.9524129.6224103.7624101.4011939.411. (CXX) g++ options: -O2 -std=gnu99 -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: CPU Stressgh93334 rep9334 2p2 x AMD EPYC 9334 32-Cored110K220K330K440K550K523898.45518600.85176710.85176621.27176344.3888466.541. (CXX) g++ options: -O2 -std=gnu99 -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Function Callhg9334 2p2 x AMD EPYC 9334 32-Core93334 repd30K60K90K120K150K158994.25156381.6354852.0654824.5854675.8527731.161. (CXX) g++ options: -O2 -std=gnu99 -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Matrix Mathhg9334 2p2 x AMD EPYC 9334 32-Core93334 repd200K400K600K800K1000K990104.85989553.80315324.18314789.68314753.85173878.701. (CXX) g++ options: -O2 -std=gnu99 -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Vector Floating Pointhg9334 2p2 x AMD EPYC 9334 32-Core93334 repd130K260K390K520K650K605340.53604724.84198855.75198651.88198610.93106715.851. (CXX) g++ options: -O2 -std=gnu99 -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Fused Multiply-Addhg93334 rep2 x AMD EPYC 9334 32-Core9334 2pd40M80M120M160M200M181626937.85180789739.0858570424.4158550931.3958491170.7532151217.031. (CXX) g++ options: -O2 -std=gnu99 -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Zlibhg9334 2p2 x AMD EPYC 9334 32-Core93334 repd4K8K12K16K20K16625.5716624.075885.265876.155875.452944.541. (CXX) g++ options: -O2 -std=gnu99 -lc

Neural Magic DeepSparse

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Streamgh2 x AMD EPYC 9334 32-Core9334 2p93334 repd3K6K9K12K15K14854.8613153.505651.575626.775618.592661.23

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: Classroom - Compute: CPU-Onlyhg2 x AMD EPYC 9334 32-Core93334 rep9334 2pd2040608010017.1217.3151.8651.9952.7794.88

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Vector Mathgh9334 2p2 x AMD EPYC 9334 32-Core93334 repd300K600K900K1200K1500K1288008.261285121.40430141.54430109.26430096.55234239.601. (CXX) g++ options: -O2 -std=gnu99 -lc

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: Pabellon Barcelona - Compute: CPU-Onlyhg2 x AMD EPYC 9334 32-Core9334 2p93334 repd30609012015022.3522.4063.3763.4563.71122.70

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: AVX-512 VNNIgh2 x AMD EPYC 9334 32-Core9334 2p93334 repd4M8M12M16M20M20133541.1120123210.146626091.936624476.366621974.983667964.151. (CXX) g++ options: -O2 -std=gnu99 -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Memory Copyinggh2 x AMD EPYC 9334 32-Core9334 2p93334 repd16K32K48K64K80K72825.5672800.7426146.7126144.8026129.5013428.641. (CXX) g++ options: -O2 -std=gnu99 -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Wide Vector Mathgh2 x AMD EPYC 9334 32-Core93334 rep9334 2pd2M4M6M8M10M8237581.378234456.232804498.362802578.872802185.771543291.911. (CXX) g++ options: -O2 -std=gnu99 -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Glibc Qsort Data Sortinghg93334 rep2 x AMD EPYC 9334 32-Core9334 2pd100020003000400050004850.994846.221676.271675.931674.65916.741. (CXX) g++ options: -O2 -std=gnu99 -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Mallochg9334 2p93334 rep2 x AMD EPYC 9334 32-Cored160M320M480M640M800M725705488.15719479964.33263438850.64263330738.63262321226.78137476652.931. (CXX) g++ options: -O2 -std=gnu99 -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Glibc C String Functionsgh9334 2p93334 rep2 x AMD EPYC 9334 32-Cored50M100M150M200M250M215429087.61215308424.8177814243.7672810418.7172167140.0340991307.951. (CXX) g++ options: -O2 -std=gnu99 -lc

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: Barbershop - Compute: CPU-Onlyhg9334 2p2 x AMD EPYC 9334 32-Core93334 repd8016024032040071.3971.97201.51201.53201.93372.72

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: BMW27 - Compute: CPU-Onlyhg93334 rep9334 2p2 x AMD EPYC 9334 32-Cored9182736457.407.5120.4320.5120.6537.93

OSPRay

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

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.12Benchmark: gravity_spheres_volume/dim_512/scivis/real_timehg2 x AMD EPYC 9334 32-Core9334 2p93334 repd112233445550.0879049.5123017.4357017.3307017.278909.81318

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 4.1Binary: Pathtracer - Model: Asian Dragongh9334 2p2 x AMD EPYC 9334 32-Core93334 repd50100150200250217.59207.2575.4675.2875.1242.76MIN: 211.81 / MAX: 228.26MIN: 203.29 / MAX: 214.14MIN: 73.59 / MAX: 78.22MIN: 73.5 / MAX: 78.24MIN: 73.42 / MAX: 78.19MIN: 42.48 / MAX: 43.18

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.1Binary: Pathtracer - Model: Asian Dragon Objgh2 x AMD EPYC 9334 32-Core9334 2p93334 repd4080120160200193.05172.2167.4867.3266.8537.99MIN: 174.03 / MAX: 205.21MIN: 150.53 / MAX: 183.32MIN: 65.8 / MAX: 70.02MIN: 65.8 / MAX: 70.31MIN: 65.41 / MAX: 70.72MIN: 37.71 / MAX: 38.4

OSPRay

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

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.12Benchmark: gravity_spheres_volume/dim_512/ao/real_timehg93334 rep2 x AMD EPYC 9334 32-Core9334 2pd112233445550.9650.4017.8317.8117.7610.08

Neural Magic DeepSparse

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Streamhg2 x AMD EPYC 9334 32-Core9334 2p93334 repd120240360480600532.46497.90204.41204.35204.22106.15

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 4.1Binary: Pathtracer - Model: Crownhg9334 2p2 x AMD EPYC 9334 32-Core93334 repd4080120160200187.42183.4069.6769.4969.4937.68MIN: 183.21 / MAX: 193.83MIN: 179.05 / MAX: 191.46MIN: 66.25 / MAX: 75.27MIN: 65.97 / MAX: 75.27MIN: 65.87 / MAX: 75.16MIN: 37.26 / MAX: 39.44

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.1Binary: Pathtracer ISPC - Model: Asian Dragongh2 x AMD EPYC 9334 32-Core93334 rep9334 2pd50100150200250239.42225.8386.7986.5686.5348.47MIN: 232.82 / MAX: 253.03MIN: 221.04 / MAX: 232.51MIN: 83.33 / MAX: 93.39MIN: 83.15 / MAX: 93.4MIN: 83.4 / MAX: 92.47MIN: 48.1 / MAX: 49.28

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.1Binary: Pathtracer ISPC - Model: Crownhg2 x AMD EPYC 9334 32-Core9334 2p93334 repd4080120160200194.27193.6072.6572.6472.1739.38MIN: 188.82 / MAX: 203.12MIN: 188.25 / MAX: 201.2MIN: 68.96 / MAX: 77.69MIN: 69.23 / MAX: 79.15MIN: 68.85 / MAX: 77.58MIN: 38.86 / MAX: 40.97

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Pollgh2 x AMD EPYC 9334 32-Core93334 rep9334 2pd5M10M15M20M25M21346079.3020251576.339104744.159078474.019067852.194337787.721. (CXX) g++ options: -O2 -std=gnu99 -lc

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.6Blend File: Fishy Cat - Compute: CPU-Onlygh9334 2p93334 rep2 x AMD EPYC 9334 32-Cored112233445510.0210.0226.1526.3726.4348.95

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: blazefaced2 x AMD EPYC 9334 32-Core9334 2p93334 rephg6121824305.637.208.158.3923.6326.90MIN: 5.53 / MAX: 5.95MIN: 7.05 / MAX: 7.44MIN: 7.89 / MAX: 14.8MIN: 8.09 / MAX: 17.41MIN: 21.98 / MAX: 379.78MIN: 21.88 / MAX: 899.431. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

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 4.1Binary: Pathtracer ISPC - Model: Asian Dragon Objgh93334 rep9334 2p2 x AMD EPYC 9334 32-Cored4080120160200193.43184.4572.8572.7772.2640.57MIN: 170.24 / MAX: 203.63MIN: 159.04 / MAX: 199.2MIN: 70.3 / MAX: 76.96MIN: 70.2 / MAX: 78.62MIN: 69.72 / MAX: 77.54MIN: 40.28 / MAX: 41.19

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: SENDFILEgh93334 rep9334 2p2 x AMD EPYC 9334 32-Cored800K1600K2400K3200K4000K3761786.293745995.161536517.651465208.811312330.44857324.891. (CXX) g++ options: -O2 -std=gnu99 -lc

OSPRay

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

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.12Benchmark: particle_volume/ao/real_timehg9334 2p2 x AMD EPYC 9334 32-Core93334 repd112233445546.7646.6620.4520.4020.3910.86

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.12Benchmark: particle_volume/scivis/real_timegh9334 2p2 x AMD EPYC 9334 32-Core93334 repd112233445546.6146.5520.4020.3320.3110.85

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Cryptogh93334 rep9334 2p2 x AMD EPYC 9334 32-Cored100K200K300K400K500K462528.73461785.36156863.78156859.22156553.51107643.491. (CXX) g++ options: -O2 -std=gnu99 -lc

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: shufflenet-v2d9334 2p93334 rep2 x AMD EPYC 9334 32-Corehg132639526513.9618.3518.4718.6345.2257.67MIN: 13.65 / MAX: 18.71MIN: 17.76 / MAX: 24.49MIN: 18.09 / MAX: 20.53MIN: 18.34 / MAX: 19.34MIN: 40.32 / MAX: 296.92MIN: 40.74 / MAX: 1797.581. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Forkinggh2 x AMD EPYC 9334 32-Core93334 rep9334 2pd7K14K21K28K35K31064.9530591.671641.771616.051615.001007.461. (CXX) g++ options: -O2 -std=gnu99 -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: AVL Treehg93334 rep9334 2p2 x AMD EPYC 9334 32-Cored300600900120015001628.911564.42797.64793.08788.21410.891. (CXX) g++ options: -O2 -std=gnu99 -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: CPU Cache9334 2p93334 rep2 x AMD EPYC 9334 32-Coredhg200K400K600K800K1000K1135334.901096840.321095211.77776708.72361173.71334039.111. (CXX) g++ options: -O2 -std=gnu99 -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: MMAPhg9334 2p2 x AMD EPYC 9334 32-Core93334 repd80016002400320040003749.473664.342299.282289.802287.691131.551. (CXX) g++ options: -O2 -std=gnu99 -lc

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: efficientnet-b0d2 x AMD EPYC 9334 32-Core9334 2p93334 repgh112233445514.7619.7919.9219.9647.6748.76MIN: 14.47 / MAX: 29.12MIN: 18.88 / MAX: 151.97MIN: 19.72 / MAX: 21.08MIN: 19.55 / MAX: 33.09MIN: 47.05 / MAX: 112.46MIN: 47.17 / MAX: 210.731. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v3-v3 - Model: mobilenet-v3d2 x AMD EPYC 9334 32-Core9334 2p93334 repgh91827364511.6414.8715.1815.8735.9637.56MIN: 11.48 / MAX: 15.48MIN: 14.55 / MAX: 15.42MIN: 14.82 / MAX: 21.88MIN: 15.57 / MAX: 16.37MIN: 34.15 / MAX: 266.64MIN: 33.74 / MAX: 351.291. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: NUMA2 x AMD EPYC 9334 32-Core93334 rep9334 2pdhg102030405042.3342.1041.4918.3514.4614.381. (CXX) g++ options: -O2 -std=gnu99 -lc

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: mnasnetd9334 2p2 x AMD EPYC 9334 32-Core93334 rephg71421283510.7013.6913.7414.2429.5529.92MIN: 10.22 / MAX: 14.66MIN: 13.25 / MAX: 14.74MIN: 13.14 / MAX: 22.9MIN: 13.93 / MAX: 14.54MIN: 28.64 / MAX: 97.1MIN: 27.82 / MAX: 234.431. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU-v2-v2 - Model: mobilenet-v2d2 x AMD EPYC 9334 32-Core9334 2p93334 rephg71421283511.2913.9414.0215.0230.8931.24MIN: 10.83 / MAX: 11.91MIN: 13.14 / MAX: 22.71MIN: 13.46 / MAX: 22.99MIN: 14.05 / MAX: 103.51MIN: 29.59 / MAX: 58.99MIN: 30.27 / MAX: 71.71. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: FastestDetd2 x AMD EPYC 9334 32-Core93334 rep9334 2phg102030405016.0016.4421.5022.2942.3044.27MIN: 15.86 / MAX: 20.49MIN: 16.09 / MAX: 32.24MIN: 20.83 / MAX: 30.28MIN: 21.86 / MAX: 23.6MIN: 41.82 / MAX: 83.33MIN: 40.55 / MAX: 822.51. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Streamhg2 x AMD EPYC 9334 32-Core9334 2p93334 repd481216205.44815.46618.93248.93808.943714.7454

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Streamhg2 x AMD EPYC 9334 32-Core9334 2p93334 repd4080120160200183.24182.64111.85111.78111.7067.77

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Streamhg9334 2p2 x AMD EPYC 9334 32-Core93334 repd481216205.42685.44788.87258.88648.889614.6632

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Streamhg9334 2p2 x AMD EPYC 9334 32-Core93334 repd4080120160200184.09183.37112.65112.47112.4368.16

Intel Open Image Denoise

Open Image Denoise is a denoising library for ray-tracing and part of the Intel oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.0Run: RT.hdr_alb_nrm.3840x2160 - Device: CPU-Onlyhg2 x AMD EPYC 9334 32-Core9334 2p93334 repd0.79431.58862.38293.17723.97153.533.402.212.202.191.36

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.0Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-Onlyhg93334 rep2 x AMD EPYC 9334 32-Core9334 2pd0.77851.5572.33553.1143.89253.463.282.212.212.201.37

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: squeezenet_ssdd2 x AMD EPYC 9334 32-Core9334 2p93334 rephg132639526524.2225.5128.4734.9958.4158.66MIN: 23.8 / MAX: 28.97MIN: 23.43 / MAX: 95.27MIN: 28.05 / MAX: 34.83MIN: 28.93 / MAX: 1349.8MIN: 57.55 / MAX: 98.8MIN: 55.23 / MAX: 333.731. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OSPRay

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

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.12Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_timegh9334 2p2 x AMD EPYC 9334 32-Core93334 repd71421283528.3528.2520.3920.3420.3311.90

Intel Open Image Denoise

Open Image Denoise is a denoising library for ray-tracing and part of the Intel oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.0Run: RTLightmap.hdr.4096x4096 - Device: CPU-Onlyhg93334 rep2 x AMD EPYC 9334 32-Core9334 2pd0.34650.6931.03951.3861.73251.541.501.041.041.030.65

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Streamgh2 x AMD EPYC 9334 32-Core93334 rep9334 2pd163248648030.2230.3744.3044.3644.7571.35

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Streamgh2 x AMD EPYC 9334 32-Core93334 rep9334 2pd81624324033.0832.9222.5722.5422.3414.01

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streamhg9334 2p93334 rep2 x AMD EPYC 9334 32-Cored163248648030.7231.4544.6344.6644.7471.84

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Streamhg9334 2p93334 rep2 x AMD EPYC 9334 32-Cored81624324032.5431.7922.4022.3922.3513.92

Dragonflydb

Dragonfly is an open-source database server that is a "modern Redis replacement" that aims to be the fastest memory store while being compliant with the Redis and Memcached protocols. For benchmarking Dragonfly, Memtier_benchmark is used as a NoSQL Redis/Memcache traffic generation plus benchmarking tool developed by Redis Labs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is BetterDragonflydb 1.6.2Clients Per Thread: 20 - Set To Get Ratio: 1:1002 x AMD EPYC 9334 32-Core9334 2p93334 repd7M14M21M28M35M31139658.4929330317.3429280070.9714250093.711. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

Clients Per Thread: 20 - Set To Get Ratio: 1:100

g: The test run did not produce a result. E: Connection error: Connection refused

h: The test run did not produce a result. E: Connection error: Connection refused

OpenBenchmarking.orgOps/sec, More Is BetterDragonflydb 1.6.2Clients Per Thread: 10 - Set To Get Ratio: 1:1002 x AMD EPYC 9334 32-Core93334 rep9334 2pd6M12M18M24M30M25802999.0324588214.8122585212.5611860591.651. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

Clients Per Thread: 10 - Set To Get Ratio: 1:100

g: The test run did not produce a result. E: Connection error: Connection refused

h: The test run did not produce a result. E: Connection error: Connection refused

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: resnet18d2 x AMD EPYC 9334 32-Core93334 rep9334 2pgh71421283513.6515.1616.2217.4929.2629.56MIN: 13.29 / MAX: 15.11MIN: 14.45 / MAX: 22.73MIN: 15.17 / MAX: 57.27MIN: 16.57 / MAX: 24.11MIN: 26.62 / MAX: 124.57MIN: 27.99 / MAX: 114.191. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: alexnetd2 x AMD EPYC 9334 32-Core93334 rep9334 2pgh481216208.139.3910.5910.7015.1017.39MIN: 7.95 / MAX: 8.44MIN: 9 / MAX: 9.79MIN: 9.51 / MAX: 107.87MIN: 10.12 / MAX: 12.2MIN: 14.22 / MAX: 74.43MIN: 14.86 / MAX: 374.111. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream93334 rep2 x AMD EPYC 9334 32-Core9334 2pdgh2468103.53473.55913.59224.93177.38317.4589

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream93334 rep2 x AMD EPYC 9334 32-Core9334 2pdgh60120180240300282.72280.78278.18202.50135.40134.02

Dragonflydb

Dragonfly is an open-source database server that is a "modern Redis replacement" that aims to be the fastest memory store while being compliant with the Redis and Memcached protocols. For benchmarking Dragonfly, Memtier_benchmark is used as a NoSQL Redis/Memcache traffic generation plus benchmarking tool developed by Redis Labs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is BetterDragonflydb 1.6.2Clients Per Thread: 10 - Set To Get Ratio: 1:109334 2p93334 rep2 x AMD EPYC 9334 32-Cored5M10M15M20M25M24460221.4823645213.1322176931.9811686474.261. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

Clients Per Thread: 10 - Set To Get Ratio: 1:10

g: The test run did not produce a result. E: Connection error: Connection refused

h: The test run did not produce a result. E: Connection error: Connection refused

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streamhg9334 2p93334 rep2 x AMD EPYC 9334 32-Cored91827364519.7420.6026.4826.4826.5140.73

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Streamhg9334 2p93334 rep2 x AMD EPYC 9334 32-Cored112233445550.6048.5037.7437.7437.7024.54

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: vgg16d2 x AMD EPYC 9334 32-Core9334 2p93334 repgh132639526528.5736.6536.9042.0856.3458.85MIN: 27.98 / MAX: 32.46MIN: 33.43 / MAX: 47.15MIN: 34.81 / MAX: 49.99MIN: 36.25 / MAX: 590.93MIN: 50.98 / MAX: 172.01MIN: 55.68 / MAX: 98.781. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: resnet50d2 x AMD EPYC 9334 32-Core9334 2p93334 repgh122436486026.5329.6230.6041.0253.6254.47MIN: 26.13 / MAX: 30.95MIN: 27.91 / MAX: 147.23MIN: 30.17 / MAX: 37.09MIN: 30.92 / MAX: 2215.16MIN: 51.72 / MAX: 288.16MIN: 51.64 / MAX: 145.971. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Dragonflydb

Dragonfly is an open-source database server that is a "modern Redis replacement" that aims to be the fastest memory store while being compliant with the Redis and Memcached protocols. For benchmarking Dragonfly, Memtier_benchmark is used as a NoSQL Redis/Memcache traffic generation plus benchmarking tool developed by Redis Labs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is BetterDragonflydb 1.6.2Clients Per Thread: 20 - Set To Get Ratio: 1:102 x AMD EPYC 9334 32-Core93334 rep9334 2pd7M14M21M28M35M31053489.2429580028.0628043162.3015179164.861. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

Clients Per Thread: 20 - Set To Get Ratio: 1:10

g: The test run did not produce a result. E: Connection error: Connection refused

h: The test run did not produce a result. E: Connection error: Connection refused

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: mobilenet2 x AMD EPYC 9334 32-Cored9334 2p93334 repgh102030405021.8023.5527.4127.9541.2144.14MIN: 21.41 / MAX: 29.57MIN: 23.18 / MAX: 27.8MIN: 26.74 / MAX: 33.85MIN: 27.34 / MAX: 34.73MIN: 40.54 / MAX: 69.23MIN: 42.79 / MAX: 118.071. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: vision_transformer2 x AMD EPYC 9334 32-Cored93334 rep9334 2phg2040608010053.7955.0561.2466.6593.15108.73MIN: 52.29 / MAX: 122.53MIN: 54.24 / MAX: 72.37MIN: 59.18 / MAX: 264.24MIN: 59.07 / MAX: 626.24MIN: 88.26 / MAX: 206.51MIN: 94.5 / MAX: 1869.821. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Socket Activityhg93334 rep2 x AMD EPYC 9334 32-Core9334 2pd20K40K60K80K100K113347.77110254.1938727.8638147.9737674.679504.381. (CXX) g++ options: -O2 -std=gnu99 -lc

BRL-CAD

BRL-CAD is a cross-platform, open-source solid modeling system with built-in benchmark mode. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgVGR Performance Metric, More Is BetterBRL-CAD 7.36VGR Performance Metricgh2 x AMD EPYC 9334 32-Core93334 rep9334 2pd1.4M2.8M4.2M5.6M7M6398404627057710125379998939943715446481. (CXX) g++ options: -std=c++14 -pipe -fvisibility=hidden -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -ltcl8.6 -lregex_brl -lz_brl -lnetpbm -ldl -lm -ltk8.6

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: MEMFD9334 2p93334 rep2 x AMD EPYC 9334 32-Coredhg20040060080010001014.241009.471004.79912.62115.8397.941. (CXX) g++ options: -O2 -std=gnu99 -lc

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: googlenetd2 x AMD EPYC 9334 32-Core9334 2p93334 rephg132639526529.0331.0333.4033.6855.3657.72MIN: 27.97 / MAX: 36.49MIN: 30.4 / MAX: 40.18MIN: 32.92 / MAX: 35.55MIN: 32.93 / MAX: 40.38MIN: 54.42 / MAX: 115.96MIN: 52.79 / MAX: 429.121. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream9334 2p93334 rep2 x AMD EPYC 9334 32-Coredhg0.37110.74221.11331.48441.85550.86770.87040.87111.11891.64191.6492

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream9334 2p93334 rep2 x AMD EPYC 9334 32-Coredhg20040060080010001149.131145.231144.31890.94608.16605.47

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream2 x AMD EPYC 9334 32-Core9334 2p93334 repdhg481216207.53797.74848.134711.086812.828613.8473

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream2 x AMD EPYC 9334 32-Core9334 2p93334 repdhg306090120150132.50128.91122.7990.0877.9272.18

SPECFEM3D

simulates acoustic (fluid), elastic (solid), coupled acoustic/elastic, poroelastic or seismic wave propagation in any type of conforming mesh of hexahedra. This test profile currently relies on CPU-based execution for SPECFEM3D and using a variety of their built-in examples/models for benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Layered Halfspace9334 2p2 x AMD EPYC 9334 32-Core93334 repd91827364521.5421.6721.6938.491. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi

Model: Layered Halfspace

g: The test quit with a non-zero exit status. E: [amd-test-01.local:1787630] pml_ucx.c:419 Error: ucp_ep_create(proc=111) failed: Input/output error

h: The test quit with a non-zero exit status. E: [amd-test-01.local:1416584] pml_ucx.c:419 Error: ucp_ep_create(proc=154) failed: Input/output error

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Mount St. Helens9334 2p2 x AMD EPYC 9334 32-Core93334 repd481216208.3200918568.4554735348.48691052014.5056452531. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi

Model: Mount St. Helens

g: The test quit with a non-zero exit status. E: [amd-test-01.local:1786040] pml_ucx.c:419 Error: ucp_ep_create(proc=17) failed: Input/output error

h: The test quit with a non-zero exit status. E: [amd-test-01.local:1415047] pml_ucx.c:419 Error: ucp_ep_create(proc=80) failed: Endpoint timeout

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream2 x AMD EPYC 9334 32-Core9334 2p93334 repdgh36912155.64625.66935.67735.99478.58439.6974

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Streamd2 x AMD EPYC 9334 32-Core93334 rep9334 2phg60120180240300150.28156.06156.19156.28239.19256.16

SPECFEM3D

simulates acoustic (fluid), elastic (solid), coupled acoustic/elastic, poroelastic or seismic wave propagation in any type of conforming mesh of hexahedra. This test profile currently relies on CPU-based execution for SPECFEM3D and using a variety of their built-in examples/models for benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Water-layered Halfspace9334 2p93334 rep2 x AMD EPYC 9334 32-Cored81624324020.8621.1521.3934.821. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi

Model: Water-layered Halfspace

g: The test quit with a non-zero exit status. E: [amd-test-01.local:1791559] pml_ucx.c:419 Error: ucp_ep_create(proc=100) failed: Input/output error

h: The test quit with a non-zero exit status. E: [amd-test-01.local:1420136] pml_ucx.c:419 Error: ucp_ep_create(proc=93) failed: Destination is unreachable

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream93334 rep9334 2p2 x AMD EPYC 9334 32-Coredhg2468105.28625.30285.39727.14568.60168.7387

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream93334 rep9334 2p2 x AMD EPYC 9334 32-Coredhg4080120160200188.92188.32185.02139.79116.19114.38

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Futex93334 rep2 x AMD EPYC 9334 32-Core9334 2pdgh1000K2000K3000K4000K5000K4752131.374717570.364644551.294022496.072951631.962880825.111. (CXX) g++ options: -O2 -std=gnu99 -lc

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Streamh2 x AMD EPYC 9334 32-Core9334 2p93334 repgd132639526535.8537.1437.3037.5742.0458.83

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Streamh2 x AMD EPYC 9334 32-Core9334 2p93334 repgd71421283527.8826.9226.8126.6123.7817.00

SPECFEM3D

simulates acoustic (fluid), elastic (solid), coupled acoustic/elastic, poroelastic or seismic wave propagation in any type of conforming mesh of hexahedra. This test profile currently relies on CPU-based execution for SPECFEM3D and using a variety of their built-in examples/models for benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Homogeneous Halfspace93334 rep2 x AMD EPYC 9334 32-Core9334 2pd51015202511.5311.6211.6418.851. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi

Model: Homogeneous Halfspace

g: The test quit with a non-zero exit status. E: [amd-test-01.local:1790169] pml_ucx.c:419 Error: ucp_ep_create(proc=60) failed: Destination is unreachable

h: The test quit with a non-zero exit status. E: [amd-test-01.local:1419043] pml_ucx.c:419 Error: ucp_ep_create(proc=43) failed: Destination is unreachable

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.7Encoder Mode: Preset 13 - Input: Bosphorus 4Kgh9334 2p93334 rep2 x AMD EPYC 9334 32-Core4080120160200203.01197.03155.11152.58127.141. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

SPECFEM3D

simulates acoustic (fluid), elastic (solid), coupled acoustic/elastic, poroelastic or seismic wave propagation in any type of conforming mesh of hexahedra. This test profile currently relies on CPU-based execution for SPECFEM3D and using a variety of their built-in examples/models for benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Tomographic Model93334 rep9334 2p2 x AMD EPYC 9334 32-Cored481216209.3745630829.4190866359.48714578114.8777103461. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi

Model: Tomographic Model

g: The test quit with a non-zero exit status. E: Par_file_faults not found: assuming that there are no faults

h: The test quit with a non-zero exit status. E: [amd-test-01.local:1417740] pml_ucx.c:419 Error: ucp_ep_create(proc=82) failed: Input/output error

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream9334 2p2 x AMD EPYC 9334 32-Core93334 rephgd51015202513.3013.3113.3814.5615.0220.71

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream9334 2p2 x AMD EPYC 9334 32-Core93334 rephgd2040608010075.1575.1074.6868.6166.5248.25

Remhos

Remhos (REMap High-Order Solver) is a miniapp that solves the pure advection equations that are used to perform monotonic and conservative discontinuous field interpolation (remap) as part of the Eulerian phase in Arbitrary Lagrangian Eulerian (ALE) simulations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRemhos 1.0Test: Sample Remap Example2 x AMD EPYC 9334 32-Core93334 rep9334 2pd51015202513.5113.8313.9620.901. (CXX) g++ options: -O3 -std=c++11 -lmfem -lHYPRE -lmetis -lrt -lmpi_cxx -lmpi

Test: Sample Remap Example

g: The test quit with a non-zero exit status. E: [amd-test-01.local:1784682] 3 more processes have sent help message help-mpi-errors.txt / mpi_errors_are_fatal unknown handle

h: The test quit with a non-zero exit status. E: [amd-test-01.local:1413726] pml_ucx.c:419 Error: ucp_ep_create(proc=79) failed: Endpoint timeout

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: defconfighg9334 2p2 x AMD EPYC 9334 32-Core93334 repd81624324023.0523.0624.6724.7424.7835.28

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream9334 2p93334 rep2 x AMD EPYC 9334 32-Coredhg2468104.71594.79574.80907.11027.17927.2026

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream9334 2p93334 rep2 x AMD EPYC 9334 32-Coredhg50100150200250211.81208.31207.72140.46139.21138.76

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream9334 2p2 x AMD EPYC 9334 32-Core93334 rephdg2468104.79424.80284.82057.11637.12287.2111

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream9334 2p2 x AMD EPYC 9334 32-Core93334 rephdg50100150200250208.34207.99207.23140.44140.20138.59

Liquid-DSP

LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 64 - Buffer Length: 256 - Filter Length: 5129334 2p2 x AMD EPYC 9334 32-Core93334 repghd160M320M480M640M800M7559700007542100007531200006591400006528200005046600001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Laghos

Laghos (LAGrangian High-Order Solver) is a miniapp that solves the time-dependent Euler equations of compressible gas dynamics in a moving Lagrangian frame using unstructured high-order finite element spatial discretization and explicit high-order time-stepping. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMajor Kernels Total Rate, More Is BetterLaghos 3.1Test: Sedov Blast Wave, ube_922_hex.mesh2 x AMD EPYC 9334 32-Core9334 2p93334 repd80160240320400389.86388.87387.15263.851. (CXX) g++ options: -O3 -std=c++11 -lmfem -lHYPRE -lmetis -lrt -lmpi_cxx -lmpi

Test: Sedov Blast Wave, ube_922_hex.mesh

g: The test quit with a non-zero exit status. E: [amd-test-01.local:1783809] pml_ucx.c:419 Error: ucp_ep_create(proc=153) failed: Input/output error

h: The test quit with a non-zero exit status. E: [amd-test-01.local:1412464] pml_ucx.c:419 Error: ucp_ep_create(proc=82) failed: Destination is unreachable

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Matrix 3D Mathhg9334 2p93334 rep2 x AMD EPYC 9334 32-Cored3K6K9K12K15K15802.8614658.7514022.5014009.2314005.2910869.491. (CXX) g++ options: -O2 -std=gnu99 -lc

Apache Cassandra

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

OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 4.1.3Test: Writes93334 rep9334 2p2 x AMD EPYC 9334 32-Coredhg60K120K180K240K300K268984258638255016230402190955185134

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.7Encoder Mode: Preset 13 - Input: Bosphorus 1080phg9334 2p93334 rep2 x AMD EPYC 9334 32-Core130260390520650600.76599.57560.79517.44416.171. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

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 on smaller systems. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgflops/rank, More Is BetternekRS 23.0Input: Kershawd9334 2p93334 rep2 x AMD EPYC 9334 32-Core2000M4000M6000M8000M10000M115209000008147120000813095000080956300001. (CXX) g++ options: -fopenmp -O2 -march=native -mtune=native -ftree-vectorize -rdynamic -lmpi_cxx -lmpi

Input: Kershaw

g: The test quit with a non-zero exit status. E: [amd-test-01.local:1792976] pml_ucx.c:419 Error: ucp_ep_create(proc=131) failed: Destination is unreachable

h: The test quit with a non-zero exit status. E: [amd-test-01.local:1421720] pml_ucx.c:419 Error: ucp_ep_create(proc=97) failed: Endpoint timeout

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20230517Target: CPU - Model: yolov4-tiny2 x AMD EPYC 9334 32-Cored9334 2p93334 repgh112233445534.6335.7540.1943.5948.0848.82MIN: 32.71 / MAX: 43.98MIN: 34.32 / MAX: 45.5MIN: 39.2 / MAX: 49.85MIN: 35.28 / MAX: 640.68MIN: 42.94 / MAX: 393.57MIN: 45.36 / MAX: 93.881. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Streamhg2 x AMD EPYC 9334 32-Core93334 rep9334 2pd51015202513.9714.4215.0215.0815.0919.64

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Streamhg2 x AMD EPYC 9334 32-Core93334 rep9334 2pd163248648071.5769.3366.5466.2766.2550.91

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 on smaller systems. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgflops/rank, More Is BetternekRS 23.0Input: TurboPipe Periodicd2 x AMD EPYC 9334 32-Core93334 rep9334 2p1600M3200M4800M6400M8000M74704900005441100000543724000054260300001. (CXX) g++ options: -fopenmp -O2 -march=native -mtune=native -ftree-vectorize -rdynamic -lmpi_cxx -lmpi

Input: TurboPipe Periodic

g: The test quit with a non-zero exit status. E: [amd-test-01.local:1794008] pml_ucx.c:419 Error: ucp_ep_create(proc=37) failed: Input/output error

h: The test quit with a non-zero exit status. E: mpi_errors_are_fatal unknown handle

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: System V Message Passing2 x AMD EPYC 9334 32-Core9334 2p93334 rephgd2M4M6M8M10M9268236.409258853.699251814.097761412.617729966.176851573.201. (CXX) g++ options: -O2 -std=gnu99 -lc

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streamh93334 rep2 x AMD EPYC 9334 32-Core9334 2pgd36912157.67347.99928.00988.01368.030210.0813

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Streamh93334 rep2 x AMD EPYC 9334 32-Core9334 2pgd306090120150130.19124.90124.72124.67124.4199.12

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Streamd2 x AMD EPYC 9334 32-Core93334 rep9334 2phg120240360480600436.97448.73448.89451.05567.86573.36

Liquid-DSP

LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 2 - Buffer Length: 256 - Filter Length: 322 x AMD EPYC 9334 32-Core93334 rep9334 2pdhg16M32M48M64M80M7259700072532000724800006883400055923000557080001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OSPRay

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

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.12Benchmark: particle_volume/pathtracer/real_time9334 2p93334 rep2 x AMD EPYC 9334 32-Coredgh50100150200250209.61208.86204.93176.61161.17160.87

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 1.6Encoder Mode: Preset 4 - Input: Bosphorus 1080p93334 rep9334 2p2 x AMD EPYC 9334 32-Coredgh4812162016.6816.3016.2014.9713.5812.911. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Liquid-DSP

LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 2 - Buffer Length: 256 - Filter Length: 579334 2p2 x AMD EPYC 9334 32-Coredgh93334 rep20M40M60M80M100M1113300001113200001056300008810900088042000862480001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Mixed Scheduler2 x AMD EPYC 9334 32-Core9334 2p93334 repdgh8K16K24K32K40K37887.1437702.2237534.0035640.3629932.2029481.451. (CXX) g++ options: -O2 -std=gnu99 -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Pthread9334 2p2 x AMD EPYC 9334 32-Coredhg15K30K45K60K75K70476.9770405.4770043.7855328.7154906.431. (CXX) g++ options: -O2 -std=gnu99 -lc

Test: Pthread

93334 rep: The test quit with a non-zero exit status.

Liquid-DSP

LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 4 - Buffer Length: 256 - Filter Length: 5129334 2p2 x AMD EPYC 9334 32-Core93334 repdgh11M22M33M44M55M5246900052315000518210004988400041641000410520001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 1 - Buffer Length: 256 - Filter Length: 3293334 rep2 x AMD EPYC 9334 32-Core9334 2pdgh8M16M24M32M40M3718300037170000371260003519500029219000292000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 8 - Buffer Length: 256 - Filter Length: 3293334 rep2 x AMD EPYC 9334 32-Core9334 2pdgh60M120M180M240M300M2903200002887300002884300002717300002285200002280900001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 32 - Buffer Length: 256 - Filter Length: 3293334 rep9334 2p2 x AMD EPYC 9334 32-Coredgh200M400M600M800M1000M11595000001158700000115810000010738000009145700009118700001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 8 - Buffer Length: 256 - Filter Length: 5129334 2p2 x AMD EPYC 9334 32-Core93334 repdgh20M40M60M80M100M1051700001043100001022700009644900083090000827490001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 16 - Buffer Length: 256 - Filter Length: 3293334 rep9334 2p2 x AMD EPYC 9334 32-Coredgh120M240M360M480M600M5809200005795100005755100005493900004578200004574200001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 16 - Buffer Length: 256 - Filter Length: 51293334 rep2 x AMD EPYC 9334 32-Core9334 2pdhg40M80M120M160M200M2093700002086300002078100001955100001653900001651800001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 4 - Buffer Length: 256 - Filter Length: 329334 2p2 x AMD EPYC 9334 32-Core93334 repdgh30M60M90M120M150M1448000001442100001438300001365000001145500001143900001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 1 - Buffer Length: 256 - Filter Length: 5793334 rep9334 2p2 x AMD EPYC 9334 32-Coredgh12M24M36M48M60M5588200055624000541550005276500044187000441830001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 1 - Buffer Length: 256 - Filter Length: 5129334 2p93334 rep2 x AMD EPYC 9334 32-Coredgh3M6M9M12M15M1335700013320000132070001265200010576000105670001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 64 - Buffer Length: 256 - Filter Length: 572 x AMD EPYC 9334 32-Core9334 2p93334 repghd500M1000M1500M2000M2500M2247200000223160000021943000002076600000207200000017786000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 2 - Buffer Length: 256 - Filter Length: 51293334 rep9334 2p2 x AMD EPYC 9334 32-Coredhg6M12M18M24M30M2608100025885000257060002490000020837000206600001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 32 - Buffer Length: 256 - Filter Length: 51293334 rep9334 2p2 x AMD EPYC 9334 32-Coredgh90M180M270M360M450M4152000004140600004139700003874600003312400003292100001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Mutex2 x AMD EPYC 9334 32-Core93334 rep9334 2pdgh100K200K300K400K500K457807.79457061.39456942.16438280.16364035.57363892.101. (CXX) g++ options: -O2 -std=gnu99 -lc

Liquid-DSP

LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 64 - Buffer Length: 256 - Filter Length: 3293334 rep9334 2p2 x AMD EPYC 9334 32-Coredgh500M1000M1500M2000M2500M2291700000229130000022847000002045600000182760000018221000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.7Encoder Mode: Preset 4 - Input: Bosphorus 1080p9334 2p93334 rep2 x AMD EPYC 9334 32-Corehg369121512.35812.25012.0609.9019.8311. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Atomic93334 rep9334 2p2 x AMD EPYC 9334 32-Coredgh60120180240300254.23254.16253.60236.99204.44203.491. (CXX) g++ options: -O2 -std=gnu99 -lc

Liquid-DSP

LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 8 - Buffer Length: 256 - Filter Length: 572 x AMD EPYC 9334 32-Core9334 2pd93334 repgh70M140M210M280M350M3462600003363200003312000003291800002798400002772500001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream2 x AMD EPYC 9334 32-Core9334 2p93334 repdhg2004006008001000776.91779.18779.83794.04952.87969.24

Liquid-DSP

LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 16 - Buffer Length: 256 - Filter Length: 579334 2p2 x AMD EPYC 9334 32-Core93334 repdhg140M280M420M560M700M6743300006585800006565100006504100005466900005423000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream2 x AMD EPYC 9334 32-Core9334 2p93334 repdhg2004006008001000780.60781.54782.00795.85954.94969.88

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 1.6Encoder Mode: Preset 12 - Input: Bosphorus 4Kdhg2 x AMD EPYC 9334 32-Core93334 rep9334 2p4080120160200199.52194.86189.16163.44161.05160.631. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Liquid-DSP

LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 4 - Buffer Length: 256 - Filter Length: 5793334 rep2 x AMD EPYC 9334 32-Core9334 2pdhg40M80M120M160M200M1866700001853900001853600001742800001553600001510100001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 32 - Buffer Length: 256 - Filter Length: 5793334 rep2 x AMD EPYC 9334 32-Core9334 2pdhg300M600M900M1200M1500M1302400000129300000012750000001234500000106500000010573000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

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 1.6Encoder Mode: Preset 4 - Input: Bosphorus 4K93334 rep9334 2p2 x AMD EPYC 9334 32-Coredgh1.27132.54263.81395.08526.35655.6505.6435.5995.0534.6154.5931. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.6Encoder Mode: Preset 13 - Input: Bosphorus 4Kdgh9334 2p2 x AMD EPYC 9334 32-Core93334 rep4080120160200195.83191.67177.36163.43162.86160.081. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.7Encoder Mode: Preset 4 - Input: Bosphorus 4K93334 rep9334 2p2 x AMD EPYC 9334 32-Corehg1.13182.26363.39544.52725.6595.0305.0124.9144.2044.1241. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream9334 2p2 x AMD EPYC 9334 32-Core93334 repdhg4080120160200137.48137.91137.97140.58166.76167.42

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream9334 2p2 x AMD EPYC 9334 32-Core93334 repdhg4080120160200136.46136.60136.81139.61164.66165.51

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Streamd2 x AMD EPYC 9334 32-Core93334 rep9334 2phg50100150200250186.65188.74189.33189.52223.85224.65

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Streamd9334 2p93334 rep2 x AMD EPYC 9334 32-Coregh30609012015094.6295.5495.6095.74113.02113.20

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream9334 2p2 x AMD EPYC 9334 32-Core93334 repdhg122436486044.4144.4944.6844.9152.5853.12

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream9334 2p93334 rep2 x AMD EPYC 9334 32-Coredhg112233445541.0241.1041.3142.8348.5148.88

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream93334 rep2 x AMD EPYC 9334 32-Core9334 2pdhg160320480640800635.20635.64635.65641.61751.72756.62

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.7Encoder Mode: Preset 12 - Input: Bosphorus 4Khg93334 rep9334 2p2 x AMD EPYC 9334 32-Core4080120160200187.68179.41161.67159.26158.711. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream93334 rep2 x AMD EPYC 9334 32-Core9334 2pdhg61218243021.0021.0021.0321.0924.6824.79

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 1.6Encoder Mode: Preset 12 - Input: Bosphorus 1080pgh2 x AMD EPYC 9334 32-Core9334 2pd93334 rep110220330440550490.15485.59442.55442.44419.85416.151. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream9334 2p2 x AMD EPYC 9334 32-Core93334 repdhg163248648061.2261.4661.4961.8171.5471.82

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream9334 2p93334 rep2 x AMD EPYC 9334 32-Coredhg163248648061.2561.4561.4962.1071.5871.76

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.7Encoder Mode: Preset 12 - Input: Bosphorus 1080pgh2 x AMD EPYC 9334 32-Core9334 2p93334 rep110220330440550511.80507.02462.33458.52443.321. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.6Encoder Mode: Preset 13 - Input: Bosphorus 1080pg93334 reph2 x AMD EPYC 9334 32-Cored9334 2p130260390520650600.23593.63581.07562.31545.20520.171. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.7Encoder Mode: Preset 8 - Input: Bosphorus 1080p2 x AMD EPYC 9334 32-Core9334 2p93334 repgh306090120150142.19140.17137.61125.22124.701. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.6Encoder Mode: Preset 8 - Input: Bosphorus 1080p9334 2p2 x AMD EPYC 9334 32-Core93334 repdgh306090120150150.35149.11148.85136.07134.88134.381. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

VVenC

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

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.9Video Input: Bosphorus 4K - Video Preset: Fast9334 2p2 x AMD EPYC 9334 32-Core93334 repd2468107.4477.3977.3586.7681. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto

Video Input: Bosphorus 4K - Video Preset: Fast

g: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1

h: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.9Video Input: Bosphorus 1080p - Video Preset: Fast93334 rep9334 2p2 x AMD EPYC 9334 32-Cored51015202521.0120.8820.7319.171. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto

Video Input: Bosphorus 1080p - Video Preset: Fast

g: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1

h: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.16.04Test: Cloning2 x AMD EPYC 9334 32-Coreh9334 2p93334 repdg300600900120015001245.211209.531190.001188.641170.311139.871. (CXX) g++ options: -O2 -std=gnu99 -lc

VVenC

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

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.9Video Input: Bosphorus 4K - Video Preset: Faster93334 rep2 x AMD EPYC 9334 32-Core9334 2pd4812162013.8013.7313.6812.681. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto

Video Input: Bosphorus 4K - Video Preset: Faster

g: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1

h: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.9Video Input: Bosphorus 1080p - Video Preset: Faster2 x AMD EPYC 9334 32-Core9334 2p93334 repd81624324036.0335.5834.7633.571. (CXX) g++ options: -O3 -flto -fno-fat-lto-objects -flto=auto

Video Input: Bosphorus 1080p - Video Preset: Faster

g: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1

h: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1

SVT-AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.7Encoder Mode: Preset 8 - Input: Bosphorus 4K9334 2ph93334 repg2 x AMD EPYC 9334 32-Core2040608010096.1194.8394.7392.6489.911. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.6Encoder Mode: Preset 8 - Input: Bosphorus 4K2 x AMD EPYC 9334 32-Core93334 rep9334 2pghd2040608010077.2277.1976.5075.1573.2572.351. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq

Kripke

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

OpenBenchmarking.orgThroughput FoM, More Is BetterKripke 1.2.69334 2p2 x AMD EPYC 9334 32-Core93334 repd80M160M240M320M400M3932765003915674003757155003720720001. (CXX) g++ options: -O3 -fopenmp -ldl

g: The test quit with a non-zero exit status. E: [1693403940.471431] [amd-test-01:1342351:0] sock.c:325 UCX ERROR connect(fd=48, dest_addr=127.0.0.1:44899) failed: Connection refused

h: The test quit with a non-zero exit status. E: 7.469567] [amd-test-01:928103:0] sock.c:325 UCX ERROR connect(fd=44, dest_addr=127.0.0.1:45965) failed: Connection refused

Laghos

Laghos (LAGrangian High-Order Solver) is a miniapp that solves the time-dependent Euler equations of compressible gas dynamics in a moving Lagrangian frame using unstructured high-order finite element spatial discretization and explicit high-order time-stepping. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMajor Kernels Total Rate, More Is BetterLaghos 3.1Test: Triple Point Problem9334 2p2 x AMD EPYC 9334 32-Core93334 repd4080120160200199.20198.94197.19195.401. (CXX) g++ options: -O3 -std=c++11 -lmfem -lHYPRE -lmetis -lrt -lmpi_cxx -lmpi

Test: Triple Point Problem

g: The test quit with a non-zero exit status. E: [amd-test-01.local:1782157] pml_ucx.c:419 Error: ucp_ep_create(proc=13) failed: Destination is unreachable

h: The test quit with a non-zero exit status. E: [amd-test-01.local:1411089] pml_ucx.c:419 Error: ucp_ep_create(proc=62) failed: Endpoint timeout

Dragonflydb

Dragonfly is an open-source database server that is a "modern Redis replacement" that aims to be the fastest memory store while being compliant with the Redis and Memcached protocols. For benchmarking Dragonfly, Memtier_benchmark is used as a NoSQL Redis/Memcache traffic generation plus benchmarking tool developed by Redis Labs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is BetterDragonflydb 1.6.2Clients Per Thread: 50 - Set To Get Ratio: 1:100d4M8M12M16M20M17583489.381. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

Clients Per Thread: 50 - Set To Get Ratio: 1:100

g: The test run did not produce a result. E: Connection error: Connection refused

h: The test run did not produce a result. E: Connection error: Connection refused

2 x AMD EPYC 9334 32-Core: The test run did not produce a result. E: Connection error: Connection refused

9334 2p: The test run did not produce a result. E: Connection error: Connection refused

93334 rep: The test run did not produce a result. E: Connection error: Connection refused

OpenBenchmarking.orgOps/sec, More Is BetterDragonflydb 1.6.2Clients Per Thread: 50 - Set To Get Ratio: 1:10d3M6M9M12M15M15253621.531. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

Clients Per Thread: 50 - Set To Get Ratio: 1:10

g: The test run did not produce a result. E: Connection error: Connection refused

h: The test run did not produce a result. E: Connection error: Connection refused

2 x AMD EPYC 9334 32-Core: The test run did not produce a result. E: Connection error: Connection refused

9334 2p: The test run did not produce a result. E: Connection error: Connection refused

93334 rep: The test run did not produce a result. E: Connection error: Connection refused

AOM AV1

This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google as the AV1 Codec Library. Learn more via the OpenBenchmarking.org test page.

Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4K

2 x AMD EPYC 9334 32-Core: The test run did not produce a result.

9334 2p: The test run did not produce a result.

93334 rep: The test run did not produce a result.

Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 1080p

2 x AMD EPYC 9334 32-Core: The test run did not produce a result.

9334 2p: The test run did not produce a result.

93334 rep: The test run did not produce a result.

Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4K

2 x AMD EPYC 9334 32-Core: The test run did not produce a result.

9334 2p: The test run did not produce a result.

93334 rep: The test run did not produce a result.

Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 1080p

2 x AMD EPYC 9334 32-Core: The test run did not produce a result.

9334 2p: The test run did not produce a result.

93334 rep: The test run did not produce a result.

Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4K

2 x AMD EPYC 9334 32-Core: The test run did not produce a result.

9334 2p: The test run did not produce a result.

93334 rep: The test run did not produce a result.

Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 1080p

2 x AMD EPYC 9334 32-Core: The test run did not produce a result.

9334 2p: The test run did not produce a result.

93334 rep: The test run did not produce a result.

Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4K

2 x AMD EPYC 9334 32-Core: The test run did not produce a result.

9334 2p: The test run did not produce a result.

93334 rep: The test run did not produce a result.

Encoder Mode: Speed 6 Realtime - Input: Bosphorus 1080p

2 x AMD EPYC 9334 32-Core: The test run did not produce a result.

9334 2p: The test run did not produce a result.

93334 rep: The test run did not produce a result.

Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K

2 x AMD EPYC 9334 32-Core: The test run did not produce a result.

9334 2p: The test run did not produce a result.

93334 rep: The test run did not produce a result.

Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080p

2 x AMD EPYC 9334 32-Core: The test run did not produce a result.

9334 2p: The test run did not produce a result.

93334 rep: The test run did not produce a result.

Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K

2 x AMD EPYC 9334 32-Core: The test run did not produce a result.

9334 2p: The test run did not produce a result.

93334 rep: The test run did not produce a result.

Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080p

2 x AMD EPYC 9334 32-Core: The test run did not produce a result.

9334 2p: The test run did not produce a result.

93334 rep: The test run did not produce a result.

Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4K

2 x AMD EPYC 9334 32-Core: The test run did not produce a result.

9334 2p: The test run did not produce a result.

93334 rep: The test run did not produce a result.

Encoder Mode: Speed 10 Realtime - Input: Bosphorus 1080p

2 x AMD EPYC 9334 32-Core: The test run did not produce a result.

9334 2p: The test run did not produce a result.

93334 rep: The test run did not produce a result.

Encoder Mode: Speed 11 Realtime - Input: Bosphorus 4K

2 x AMD EPYC 9334 32-Core: The test run did not produce a result.

9334 2p: The test run did not produce a result.

93334 rep: The test run did not produce a result.

Encoder Mode: Speed 11 Realtime - Input: Bosphorus 1080p

2 x AMD EPYC 9334 32-Core: The test run did not produce a result.

9334 2p: The test run did not produce a result.

93334 rep: The test run did not produce a result.

Stress-NG

Stress-NG is a Linux stress tool developed by Colin Ian King. Learn more via the OpenBenchmarking.org test page.

Test: IO_uring

d: The test run did not produce a result.

g: The test run did not produce a result.

h: The test run did not produce a result.

2 x AMD EPYC 9334 32-Core: The test run did not produce a result.

9334 2p: The test run did not produce a result.

93334 rep: The test run did not produce a result.

Dragonflydb

Dragonfly is an open-source database server that is a "modern Redis replacement" that aims to be the fastest memory store while being compliant with the Redis and Memcached protocols. For benchmarking Dragonfly, Memtier_benchmark is used as a NoSQL Redis/Memcache traffic generation plus benchmarking tool developed by Redis Labs. Learn more via the OpenBenchmarking.org test page.

Clients Per Thread: 60 - Set To Get Ratio: 1:100

d: The test run did not produce a result. E: Connection error: Connection reset by peer

g: The test run did not produce a result. E: Connection error: Connection refused

h: The test run did not produce a result. E: Connection error: Connection refused

2 x AMD EPYC 9334 32-Core: The test run did not produce a result. E: Connection error: Connection refused

9334 2p: The test run did not produce a result. E: Connection error: Connection refused

93334 rep: The test run did not produce a result. E: Connection error: Connection refused

Clients Per Thread: 60 - Set To Get Ratio: 1:10

d: The test run did not produce a result. E: Connection error: Connection reset by peer

g: The test run did not produce a result. E: Connection error: Connection refused

h: The test run did not produce a result. E: Connection error: Connection refused

2 x AMD EPYC 9334 32-Core: The test run did not produce a result. E: Connection error: Connection refused

9334 2p: The test run did not produce a result. E: Connection error: Connection refused

93334 rep: The test run did not produce a result. E: Connection error: Connection refused

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.

Build: allmodconfig

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

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

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

2 x AMD EPYC 9334 32-Core: The test quit with a non-zero exit status.

9334 2p: The test quit with a non-zero exit status.

93334 rep: The test quit with a non-zero exit status.

196 Results Shown

Stress-NG:
  Semaphores
  Pipe
Neural Magic DeepSparse:
  BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Stream
  ResNet-50, Baseline - Asynchronous Multi-Stream
  CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream
  NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Asynchronous Multi-Stream
  BERT-Large, NLP Question Answering - Asynchronous Multi-Stream
  NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Stream
  CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Stream
  CV Detection, YOLOv5s COCO - Asynchronous Multi-Stream
  NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream
  NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Stream
  NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream
  NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream
Stress-NG:
  x86_64 RdRand
  Hash
  Context Switching
  Vector Shuffle
Neural Magic DeepSparse
NCNN
Stress-NG:
  Floating Point
  CPU Stress
  Function Call
  Matrix Math
  Vector Floating Point
  Fused Multiply-Add
  Zlib
Neural Magic DeepSparse
Blender
Stress-NG
Blender
Stress-NG:
  AVX-512 VNNI
  Memory Copying
  Wide Vector Math
  Glibc Qsort Data Sorting
  Malloc
  Glibc C String Functions
Blender:
  Barbershop - CPU-Only
  BMW27 - CPU-Only
OSPRay
Embree:
  Pathtracer - Asian Dragon
  Pathtracer - Asian Dragon Obj
OSPRay
Neural Magic DeepSparse
Embree:
  Pathtracer - Crown
  Pathtracer ISPC - Asian Dragon
  Pathtracer ISPC - Crown
Stress-NG
Blender
NCNN
Embree
Stress-NG
OSPRay:
  particle_volume/ao/real_time
  particle_volume/scivis/real_time
Stress-NG
NCNN
Stress-NG:
  Forking
  AVL Tree
  CPU Cache
  MMAP
NCNN:
  CPU - efficientnet-b0
  CPU-v3-v3 - mobilenet-v3
Stress-NG
NCNN:
  CPU - mnasnet
  CPU-v2-v2 - mobilenet-v2
  CPU - FastestDet
Neural Magic DeepSparse:
  CV Detection, YOLOv5s COCO - Synchronous Single-Stream:
    ms/batch
    items/sec
  CV Detection, YOLOv5s COCO, Sparse INT8 - Synchronous Single-Stream:
    ms/batch
    items/sec
Intel Open Image Denoise:
  RT.hdr_alb_nrm.3840x2160 - CPU-Only
  RT.ldr_alb_nrm.3840x2160 - CPU-Only
NCNN
OSPRay
Intel Open Image Denoise
Neural Magic DeepSparse:
  NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Stream:
    ms/batch
    items/sec
  NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Stream:
    ms/batch
    items/sec
Dragonflydb:
  20 - 1:100
  10 - 1:100
NCNN:
  CPU - resnet18
  CPU - alexnet
Neural Magic DeepSparse:
  NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Synchronous Single-Stream:
    ms/batch
    items/sec
Dragonflydb
Neural Magic DeepSparse:
  CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Stream:
    ms/batch
    items/sec
NCNN:
  CPU - vgg16
  CPU - resnet50
Dragonflydb
NCNN:
  CPU - mobilenet
  CPU - vision_transformer
Stress-NG
BRL-CAD
Stress-NG
NCNN
Neural Magic DeepSparse:
  ResNet-50, Sparse INT8 - Synchronous Single-Stream:
    ms/batch
    items/sec
  BERT-Large, NLP Question Answering, Sparse INT8 - Synchronous Single-Stream:
    ms/batch
    items/sec
SPECFEM3D:
  Layered Halfspace
  Mount St. Helens
Neural Magic DeepSparse:
  ResNet-50, Sparse INT8 - Asynchronous Multi-Stream
  NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Stream
SPECFEM3D
Neural Magic DeepSparse:
  NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Synchronous Single-Stream:
    ms/batch
    items/sec
Stress-NG
Neural Magic DeepSparse:
  BERT-Large, NLP Question Answering - Synchronous Single-Stream:
    ms/batch
    items/sec
SPECFEM3D
SVT-AV1
SPECFEM3D
Neural Magic DeepSparse:
  NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Stream:
    ms/batch
    items/sec
Remhos
Timed Linux Kernel Compilation
Neural Magic DeepSparse:
  ResNet-50, Baseline - Synchronous Single-Stream:
    ms/batch
    items/sec
  CV Classification, ResNet-50 ImageNet - Synchronous Single-Stream:
    ms/batch
    items/sec
Liquid-DSP
Laghos
Stress-NG
Apache Cassandra
SVT-AV1
nekRS
NCNN
Neural Magic DeepSparse:
  NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Stream:
    ms/batch
    items/sec
nekRS
Stress-NG
Neural Magic DeepSparse:
  NLP Text Classification, DistilBERT mnli - Synchronous Single-Stream:
    ms/batch
    items/sec
  CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Stream:
    ms/batch
Liquid-DSP
OSPRay
SVT-AV1
Liquid-DSP
Stress-NG:
  Mixed Scheduler
  Pthread
Liquid-DSP:
  4 - 256 - 512
  1 - 256 - 32
  8 - 256 - 32
  32 - 256 - 32
  8 - 256 - 512
  16 - 256 - 32
  16 - 256 - 512
  4 - 256 - 32
  1 - 256 - 57
  1 - 256 - 512
  64 - 256 - 57
  2 - 256 - 512
  32 - 256 - 512
Stress-NG
Liquid-DSP
SVT-AV1
Stress-NG
Liquid-DSP
Neural Magic DeepSparse
Liquid-DSP
Neural Magic DeepSparse
SVT-AV1
Liquid-DSP:
  4 - 256 - 57
  32 - 256 - 57
SVT-AV1:
  Preset 4 - Bosphorus 4K
  Preset 13 - Bosphorus 4K
SVT-AV1
Neural Magic DeepSparse:
  CV Detection, YOLOv5s COCO - Asynchronous Multi-Stream
  CV Detection, YOLOv5s COCO, Sparse INT8 - Asynchronous Multi-Stream
  NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Stream
  NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream
  NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Stream
  BERT-Large, NLP Question Answering, Sparse INT8 - Asynchronous Multi-Stream
  BERT-Large, NLP Question Answering - Asynchronous Multi-Stream
SVT-AV1
Neural Magic DeepSparse
SVT-AV1
Neural Magic DeepSparse:
  CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream
  ResNet-50, Baseline - Asynchronous Multi-Stream
SVT-AV1
SVT-AV1
SVT-AV1
SVT-AV1
VVenC:
  Bosphorus 4K - Fast
  Bosphorus 1080p - Fast
Stress-NG
VVenC:
  Bosphorus 4K - Faster
  Bosphorus 1080p - Faster
SVT-AV1
SVT-AV1
Kripke
Laghos
Dragonflydb:
  50 - 1:100
  50 - 1:10

d

Processor: 2 x AMD EPYC 9124 16-Core @ 3.00GHz (32 Cores / 64 Threads), Motherboard: Supermicro H13DSH (1.5 BIOS), Memory: 24 x 32 GB DDR5-4800MT/s Samsung M321R4GA3BB6-CQKET, Disk: 2 x 1920GB SAMSUNG MZQL21T9HCJR-00A07, Graphics: astdrmfb

OS: AlmaLinux 9.2, Kernel: 5.14.0-284.25.1.el9_2.x86_64 (x86_64), Compiler: GCC 11.3.1 20221121, File-System: ext4, Screen Resolution: 1024x768

Kernel Notes: Transparent Huge Pages: always
Compiler Notes: --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-isl
Processor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa10113e
Java Notes: OpenJDK Runtime Environment (Red_Hat-11.0.20.0.8-1) (build 11.0.20+8-LTS)
Python Notes: Python 3.9.16
Security Notes: 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

Testing initiated at 25 August 2023 16:37 by user .

g

Kernel Notes: Transparent Huge Pages: always
Compiler Notes: --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-isl
Processor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xaa00116
Java Notes: OpenJDK Runtime Environment (Red_Hat-11.0.20.0.8-1) (build 11.0.20+8-LTS)
Python Notes: Python 3.9.16
Security Notes: 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

Testing initiated at 30 August 2023 15:00 by user .

h

Processor: 2 x AMD EPYC 9754 128-Core @ 2.25GHz (256 Cores / 512 Threads), Motherboard: Supermicro H13DSH (1.5 BIOS), Memory: 23 x 32 GB DDR5-4800MT/s Samsung M321R4GA3BB6-CQKET, Disk: 2 x 1920GB SAMSUNG MZQL21T9HCJR-00A07, Graphics: astdrmfb

OS: AlmaLinux 9.2, Kernel: 5.14.0-284.25.1.el9_2.x86_64 (x86_64), Compiler: GCC 11.3.1 20221121, File-System: ext4, Screen Resolution: 1024x768

Kernel Notes: Transparent Huge Pages: always
Compiler Notes: --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-isl
Processor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xaa00116
Java Notes: OpenJDK Runtime Environment (Red_Hat-11.0.20.0.8-1) (build 11.0.20+8-LTS)
Python Notes: Python 3.9.16
Security Notes: 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

Testing initiated at 30 August 2023 19:26 by user .

2 x AMD EPYC 9334 32-Core

Kernel Notes: Transparent Huge Pages: always
Compiler Notes: --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-isl
Processor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa10113e
Java Notes: OpenJDK Runtime Environment (Red_Hat-11.0.20.0.8-1) (build 11.0.20+8-LTS)
Python Notes: Python 3.9.16
Security Notes: 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

Testing initiated at 6 September 2023 16:34 by user .

9334 2p

Kernel Notes: Transparent Huge Pages: always
Compiler Notes: --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-isl
Processor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa10113e
Java Notes: OpenJDK Runtime Environment (Red_Hat-11.0.20.0.8-1) (build 11.0.20+8-LTS)
Python Notes: Python 3.9.16
Security Notes: 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

Testing initiated at 6 September 2023 19:43 by user .

93334 rep

Processor: 2 x AMD EPYC 9334 32-Core @ 2.70GHz (64 Cores / 128 Threads), Motherboard: Supermicro H13DSH (1.5 BIOS), Memory: 21 x 32 GB DDR5-4800MT/s Samsung M321R4GA3BB6-CQKET, Disk: 2 x 1920GB SAMSUNG MZQL21T9HCJR-00A07, Graphics: astdrmfb

OS: AlmaLinux 9.2, Kernel: 5.14.0-284.25.1.el9_2.x86_64 (x86_64), Compiler: GCC 11.3.1 20221121, File-System: ext4, Screen Resolution: 1024x768

Kernel Notes: Transparent Huge Pages: always
Compiler Notes: --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-isl
Processor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa10113e
Java Notes: OpenJDK Runtime Environment (Red_Hat-11.0.20.0.8-1) (build 11.0.20+8-LTS)
Python Notes: Python 3.9.16
Security Notes: 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

Testing initiated at 6 September 2023 22:11 by user .