nnn wed

AMD EPYC 7551 32-Core testing with a GIGABYTE MZ31-AR0-00 v01010101 (F10 BIOS) and ASPEED on Debian 11 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2306076-NE-NNNWED00737
Jump To Table - Results

View

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

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
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

Multi-Way Comparison

Condense Multi-Option Tests 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
AMD EPYC 7551 32-Core
June 07 2023
  37 Minutes
s
June 07 2023
  37 Minutes
c
June 07 2023
  37 Minutes
Invert Hiding All Results Option
  37 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):

AMD EPYC 7551 32-Core

Kernel Notes: Transparent Huge Pages: always
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-Km9U7s/gcc-10-10.2.1/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-Km9U7s/gcc-10-10.2.1/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8001227
Python Notes: Python 3.9.2
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: disabled RSB filling + srbds: Not affected + tsx_async_abort: Not affected

s

c

Processor: AMD EPYC 7551 32-Core @ 2.00GHz (32 Cores / 64 Threads), Motherboard: GIGABYTE MZ31-AR0-00 v01010101 (F10 BIOS), Chipset: AMD 17h, Memory: 8 x 4 GB DDR4-2133MT/s 9ASF51272PZ-2G6E1, Disk: Samsung SSD 960 EVO 500GB, Graphics: ASPEED, Network: Realtek RTL8111/8168/8411 + 2 x Broadcom NetXtreme II BCM57810 10

OS: Debian 11, Kernel: 5.10.0-9-amd64 (x86_64), Compiler: GCC 10.2.1 20210110, File-System: ext4, Screen Resolution: 1024x768

nnn wedOpenBenchmarking.orgPhoronix Test SuiteAMD EPYC 7551 32-Core @ 2.00GHz (32 Cores / 64 Threads)GIGABYTE MZ31-AR0-00 v01010101 (F10 BIOS)AMD 17h8 x 4 GB DDR4-2133MT/s 9ASF51272PZ-2G6E1Samsung SSD 960 EVO 500GBASPEEDRealtek RTL8111/8168/8411 + 2 x Broadcom NetXtreme II BCM57810 10Debian 115.10.0-9-amd64 (x86_64)GCC 10.2.1 20210110ext41024x768ProcessorMotherboardChipsetMemoryDiskGraphicsNetworkOSKernelCompilerFile-SystemScreen ResolutionNnn Wed BenchmarksSystem Logs- Transparent Huge Pages: always- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-Km9U7s/gcc-10-10.2.1/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-Km9U7s/gcc-10-10.2.1/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8001227- Python 3.9.2- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: disabled RSB filling + srbds: Not affected + tsx_async_abort: Not affected

AMD EPYC 7551 32-CorescResult OverviewPhoronix Test Suite100%122%145%167%189%Neural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparsedav1dNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparsedav1ddav1dNeural Magic DeepSparseNeural Magic DeepSparsedav1dN.S.A.8.P.Q.B.B.U - A.M.SN.S.A.8.P.Q.B.B.U - A.M.SN.Q.A.B.b.u.S.1.P - A.M.SN.Q.A.B.b.u.S.1.P - A.M.SN.Q.A.B.b.u.S.1.P - S.S.SN.Q.A.B.b.u.S.1.P - S.S.SC.S.9.P.Y.P - A.M.SC.S.9.P.Y.P - A.M.SC.C.R.5.I - A.M.SC.C.R.5.I - A.M.SN.T.C.D.m - S.S.SN.T.C.D.m - S.S.SN.T.C.B.b.u.c - A.M.SN.D.C.o.b.u.o.I - A.M.SN.T.C.B.b.u.c - A.M.SN.D.C.o.b.u.o.I - A.M.SC.D.Y.C - A.M.SC.D.Y.C - A.M.SN.D.C.o.b.u.o.I - S.S.SN.D.C.o.b.u.o.I - S.S.SC.C.R.5.I - S.S.SC.C.R.5.I - S.S.SN.T.C.B.b.u.c - S.S.SN.T.C.B.b.u.c - S.S.SN.T.C.B.b.u.S - S.S.SN.T.C.B.b.u.S - S.S.SS.N.1C.S.9.P.Y.P - S.S.SC.S.9.P.Y.P - S.S.SN.T.C.B.b.u.S - A.M.SN.T.C.B.b.u.S - A.M.SC.D.Y.C - S.S.SC.D.Y.C - S.S.SN.S.A.8.P.Q.B.B.U - S.S.SN.S.A.8.P.Q.B.B.U - S.S.SC.1.1.bSummer Nature 4KN.T.C.D.m - A.M.SN.T.C.D.m - A.M.SChimera 1080p

nnn weddeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Streamdeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO - Asynchronous Multi-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Streamdav1d: Summer Nature 1080pdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Streamdeepsparse: CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamdeepsparse: CV Detection, YOLOv5s COCO - Synchronous Single-Streamdeepsparse: CV Detection, YOLOv5s COCO - Synchronous Single-Streamdeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Synchronous Single-Streamdeepsparse: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Synchronous Single-Streamdav1d: Chimera 1080p 10-bitdav1d: Summer Nature 4Kdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamdav1d: Chimera 1080pAMD EPYC 7551 32-Coresc45.3271352.1131755.828221.0656111.44458.97197.40922114.184124.8284127.874520.804248.05511671.58571748.1899.5038.9595261.875460.93142.4912401.392531.898631.3345400.26632.498298.558710.1448269.31518.05821.930244.5605357.632865.601515.239123.234943.0237150.66102.9987.7551181.8542182.5684.005190.0353603.436726.3622114.50218.73239.40791680.267140.9332113.363818.456954.16651691.44931658.04259.32219.5624237.980867.1132.6621375.628530.230533.0611379.52822.6347101.31379.869256.58508.35551.96744.3266359.730263.711115.691222.819743.8078148.99103.5888.1486181.079183.2385.6915186.522565.623928.1216143.05886.98939.43891666.3261139.3359114.561620.230749.41611526.05231577.395110.3089.8974237.546867.13942.6317379.972930.222133.0712382.29022.615796.10710.4036264.87495.38452.018542.7474372.493263.454915.754622.737543.9648147.83101.8988.0058181.472182.49OpenBenchmarking.org

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-StreamAMD EPYC 7551 32-Corecs2040608010045.3385.6984.01

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-StreamAMD EPYC 7551 32-Corecs80160240320400352.11186.52190.04

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-StreamAMD EPYC 7551 32-Corecs160320480640800755.83565.62603.44

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-StreamAMD EPYC 7551 32-Corecs71421283521.0728.1226.36

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-StreamAMD EPYC 7551 32-Corecs306090120150111.44143.06114.50

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-StreamAMD EPYC 7551 32-Corecs36912158.97196.98938.7323

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-StreamAMD EPYC 7551 32-Corecs36912157.40929.43899.4079

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-StreamAMD EPYC 7551 32-Corecs50010001500200025002114.181666.331680.27

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-StreamAMD EPYC 7551 32-Corecs306090120150124.83139.34140.93

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-StreamAMD EPYC 7551 32-Corecs306090120150127.87114.56113.36

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-StreamAMD EPYC 7551 32-Corecs51015202520.8020.2318.46

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-StreamAMD EPYC 7551 32-Corecs122436486048.0649.4254.17

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-StreamAMD EPYC 7551 32-Corecs4008001200160020001671.591526.051691.45

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-StreamAMD EPYC 7551 32-Corecs4008001200160020001748.191577.401658.04

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-StreamAMD EPYC 7551 32-Corecs36912159.503010.30809.3221

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-StreamAMD EPYC 7551 32-Corecs36912158.95959.89749.5624

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-StreamAMD EPYC 7551 32-Corecs60120180240300261.88237.55237.98

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-StreamAMD EPYC 7551 32-Corecs153045607560.9367.1467.11

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-StreamAMD EPYC 7551 32-Corecs0.5991.1981.7972.3962.9952.49122.63172.6621

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-StreamAMD EPYC 7551 32-Corecs90180270360450401.39379.97375.63

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-StreamAMD EPYC 7551 32-Corecs71421283531.9030.2230.23

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-StreamAMD EPYC 7551 32-Corecs81624324031.3333.0733.06

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-StreamAMD EPYC 7551 32-Corecs90180270360450400.27382.29379.53

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-StreamAMD EPYC 7551 32-Corecs0.59281.18561.77842.37122.9642.49822.61572.6347

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-StreamAMD EPYC 7551 32-Corecs2040608010098.5696.11101.31

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-StreamAMD EPYC 7551 32-Corecs369121510.144810.40369.8690

dav1d

Dav1d is an open-source, speedy AV1 video decoder supporting modern SIMD CPU features. This test profile times how long it takes to decode sample AV1 video content. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is Betterdav1d 1.2.1Video Input: Summer Nature 1080pAMD EPYC 7551 32-Corecs60120180240300269.31264.87256.581. (CC) gcc options: -pthread -lm

Neural Magic DeepSparse

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

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-StreamAMD EPYC 7551 32-Corecs110220330440550518.06495.38508.36

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-StreamAMD EPYC 7551 32-Corecs0.45420.90841.36261.81682.2711.93022.01851.9670

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-StreamAMD EPYC 7551 32-Corecs102030405044.5642.7544.33

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-StreamAMD EPYC 7551 32-Corecs80160240320400357.63372.49359.73

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-StreamAMD EPYC 7551 32-Corecs153045607565.6063.4563.71

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-StreamAMD EPYC 7551 32-Corecs4812162015.2415.7515.69

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-StreamAMD EPYC 7551 32-Corecs61218243023.2322.7422.82

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-StreamAMD EPYC 7551 32-Corecs102030405043.0243.9643.81

dav1d

Dav1d is an open-source, speedy AV1 video decoder supporting modern SIMD CPU features. This test profile times how long it takes to decode sample AV1 video content. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is Betterdav1d 1.2.1Video Input: Chimera 1080p 10-bitAMD EPYC 7551 32-Corecs306090120150150.66147.83148.991. (CC) gcc options: -pthread -lm

OpenBenchmarking.orgFPS, More Is Betterdav1d 1.2.1Video Input: Summer Nature 4KAMD EPYC 7551 32-Corecs20406080100102.99101.89103.581. (CC) gcc options: -pthread -lm

Neural Magic DeepSparse

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

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-StreamAMD EPYC 7551 32-Corecs2040608010087.7688.0188.15

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.5Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-StreamAMD EPYC 7551 32-Corecs4080120160200181.85181.47181.08

dav1d

Dav1d is an open-source, speedy AV1 video decoder supporting modern SIMD CPU features. This test profile times how long it takes to decode sample AV1 video content. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is Betterdav1d 1.2.1Video Input: Chimera 1080pAMD EPYC 7551 32-Corecs4080120160200182.56182.49183.231. (CC) gcc options: -pthread -lm

40 Results Shown

Neural Magic DeepSparse:
  NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Stream:
    ms/batch
    items/sec
  CV Segmentation, 90% Pruned YOLACT Pruned - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  NLP Text Classification, DistilBERT mnli - Synchronous Single-Stream:
    items/sec
    ms/batch
  NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream:
    ms/batch
  NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream:
    ms/batch
  NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Stream:
    items/sec
  NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Stream:
    items/sec
  CV Detection, YOLOv5s COCO - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Stream:
    items/sec
    ms/batch
  CV Classification, ResNet-50 ImageNet - Synchronous Single-Stream:
    ms/batch
    items/sec
  NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Stream:
    ms/batch
    items/sec
  NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Stream:
    ms/batch
    items/sec
dav1d
Neural Magic DeepSparse:
  CV Segmentation, 90% Pruned YOLACT Pruned - Synchronous Single-Stream:
    ms/batch
    items/sec
  NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  CV Detection, YOLOv5s COCO - Synchronous Single-Stream:
    ms/batch
    items/sec
  NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Synchronous Single-Stream:
    items/sec
    ms/batch
dav1d:
  Chimera 1080p 10-bit
  Summer Nature 4K
Neural Magic DeepSparse:
  NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream:
    items/sec
    ms/batch
dav1d

AMD EPYC 7551 32-Core

Kernel Notes: Transparent Huge Pages: always
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-Km9U7s/gcc-10-10.2.1/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-Km9U7s/gcc-10-10.2.1/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8001227
Python Notes: Python 3.9.2
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: disabled RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 7 June 2023 15:14 by user root.

s

Kernel Notes: Transparent Huge Pages: always
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-Km9U7s/gcc-10-10.2.1/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-Km9U7s/gcc-10-10.2.1/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8001227
Python Notes: Python 3.9.2
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: disabled RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 7 June 2023 15:38 by user root.

c

Processor: AMD EPYC 7551 32-Core @ 2.00GHz (32 Cores / 64 Threads), Motherboard: GIGABYTE MZ31-AR0-00 v01010101 (F10 BIOS), Chipset: AMD 17h, Memory: 8 x 4 GB DDR4-2133MT/s 9ASF51272PZ-2G6E1, Disk: Samsung SSD 960 EVO 500GB, Graphics: ASPEED, Network: Realtek RTL8111/8168/8411 + 2 x Broadcom NetXtreme II BCM57810 10

OS: Debian 11, Kernel: 5.10.0-9-amd64 (x86_64), Compiler: GCC 10.2.1 20210110, File-System: ext4, Screen Resolution: 1024x768

Kernel Notes: Transparent Huge Pages: always
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-Km9U7s/gcc-10-10.2.1/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-Km9U7s/gcc-10-10.2.1/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8001227
Python Notes: Python 3.9.2
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: disabled RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 7 June 2023 16:03 by user root.