EPYC 7502 AOCC 2.3 Compiler Comparison

AMD EPYC 7502 testing of various benchmarks under AMD AOCC 2.3, GCC 10.2, LLVM Clang 11. CFLAGS/CXXFLAGS of "-O3 -march=znver2" throughout. Benchmarks by Michael Larabel for a future article.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2012080-HA-EPYC7502A97
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
Chess Test Suite 2 Tests
C/C++ Compiler Tests 21 Tests
Compression Tests 2 Tests
CPU Massive 19 Tests
Creator Workloads 17 Tests
Cryptography 2 Tests
Database Test Suite 3 Tests
Encoding 7 Tests
Game Development 2 Tests
HPC - High Performance Computing 6 Tests
Imaging 4 Tests
Common Kernel Benchmarks 3 Tests
Machine Learning 4 Tests
Multi-Core 13 Tests
Programmer / Developer System Benchmarks 2 Tests
Renderers 2 Tests
Server 5 Tests
Server CPU Tests 12 Tests
Single-Threaded 6 Tests
Texture Compression 2 Tests
Video Encoding 6 Tests

Statistics

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

Graph Settings

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

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
GCC 10.2
December 07 2020
  3 Hours, 49 Minutes
LLVM Clang 11
December 08 2020
  6 Hours, 56 Minutes
AMD AOCC 2.3
December 07 2020
  3 Hours, 58 Minutes
Invert Hiding All Results Option
  4 Hours, 54 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 AOCC 2.3

Processor: AMD EPYC 7502 32-Core @ 2.50GHz (32 Cores / 64 Threads), Motherboard: ASRockRack EPYCD8 (P2.10 BIOS), Chipset: AMD Starship/Matisse, Memory: 126GB, Disk: 280GB INTEL SSDPED1D280GA, Graphics: ASPEED, Audio: AMD Starship/Matisse, Monitor: VE228, Network: 2 x Intel I350

OS: Ubuntu 20.10, Kernel: 5.8.0-31-generic (x86_64), Desktop: GNOME Shell 3.38.1, Display Server: X Server 1.20.9, Display Driver: modesetting 1.20.9, Compiler: Clang 11.0.0, File-System: ext4, Screen Resolution: 1920x1080

Environment Notes: CXXFLAGS="-O3 -march=znver2" CFLAGS="-O3 -march=znver2"
Compiler Notes: Optimized build with assertions; Default target: x86_64-unknown-linux-gnu; Host CPU: znver2
Processor Notes: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0x830101c
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 IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

GCC 10.2

OS: Ubuntu 20.10, Kernel: 5.8.0-31-generic (x86_64), Desktop: GNOME Shell 3.38.1, Display Server: X Server 1.20.9, Display Driver: modesetting 1.20.9, Compiler: GCC 10.2.0, File-System: ext4, Screen Resolution: 1920x1080

Environment Notes: CXXFLAGS="-O3 -march=znver2" CFLAGS="-O3 -march=znver2"
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-JvwpWM/gcc-10-10.2.0/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-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 ondemand (Boost: Enabled) - CPU Microcode: 0x830101c
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 IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

LLVM Clang 11

OS: Ubuntu 20.10, Kernel: 5.8.0-31-generic (x86_64), Desktop: GNOME Shell 3.38.1, Display Server: X Server 1.20.9, Display Driver: modesetting 1.20.9, Compiler: Clang 11.0.0-2Target:, File-System: ext4, Screen Resolution: 1920x1080

Environment Notes: CXXFLAGS="-O3 -march=znver2" CFLAGS="-O3 -march=znver2"
Processor Notes: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0x830101c
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 IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

EPYC 7502 AOCC 2.3 Compiler ComparisonOpenBenchmarking.orgPhoronix Test SuiteAMD EPYC 7502 32-Core @ 2.50GHz (32 Cores / 64 Threads)ASRockRack EPYCD8 (P2.10 BIOS)AMD Starship/Matisse126GB280GB INTEL SSDPED1D280GAASPEEDAMD Starship/MatisseVE2282 x Intel I350Ubuntu 20.105.8.0-31-generic (x86_64)GNOME Shell 3.38.1X Server 1.20.9modesetting 1.20.9Clang 11.0.0GCC 10.2.0Clang 11.0.0-2Target:ext41920x1080ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverCompilersFile-SystemScreen ResolutionEPYC 7502 AOCC 2.3 Compiler Comparison BenchmarksSystem Logs- CXXFLAGS="-O3 -march=znver2" CFLAGS="-O3 -march=znver2"- AMD AOCC 2.3: Optimized build with assertions; Default target: x86_64-unknown-linux-gnu; Host CPU: znver2 - GCC 10.2: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-JvwpWM/gcc-10-10.2.0/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-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 ondemand (Boost: Enabled) - CPU Microcode: 0x830101c - 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 IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

AMD AOCC 2.3GCC 10.2LLVM Clang 11Result OverviewPhoronix Test Suite100%119%138%157%C-RayLibRawOpenSSLNCNNSVT-AV1oneDNNLAME MP3 EncodingDarmstadt Automotive Parallel Heterogeneous SuiteASTC EncoderAOBenchTSCPGraphicsMagickTNNRedisVP9 libvpx Encodingdav1dStockfishWebP Image EncodeRNNoiseSVT-VP9LZ4 CompressionSciMarkSQLite SpeedtestTimed MrBayes Analysisx264x265Basis Universallibjpeg-turbo tjbenchCrypto++Zstd CompressionNGINX BenchmarkPostgreSQL pgbenchHierarchical INTegration

EPYC 7502 AOCC 2.3 Compiler Comparisondav1d: Chimera 1080pdav1d: Summer Nature 4Kdav1d: Summer Nature 1080pdav1d: Chimera 1080p 10-bitsvt-av1: Enc Mode 0 - 1080psvt-av1: Enc Mode 4 - 1080psvt-av1: Enc Mode 8 - 1080psvt-vp9: VMAF Optimized - Bosphorus 1080psvt-vp9: PSNR/SSIM Optimized - Bosphorus 1080psvt-vp9: Visual Quality Optimized - Bosphorus 1080pvpxenc: Speed 0vpxenc: Speed 5x264: H.264 Video Encodingx265: Bosphorus 4Kx265: Bosphorus 1080pgraphics-magick: Swirlgraphics-magick: Rotategraphics-magick: Sharpengraphics-magick: Enhancedgraphics-magick: Resizingcompress-lz4: 1 - Compression Speedcompress-lz4: 3 - Compression Speedcompress-lz4: 9 - Compression Speedcompress-zstd: 3compress-zstd: 19tjbench: Decompression Throughputscimark2: Compositecryptopp: Unkeyed Algorithmslibraw: Post-Processing Benchmarktscp: AI Chess Performancestockfish: Total Timehint: FLOATredis: LPUSHredis: GETredis: SETnginx: Static Web Page Servingopenssl: RSA 4096-bit Performancedaphne: OpenMP - NDT Mappingdaphne: OpenMP - Points2Imagedaphne: OpenMP - Euclidean Clusterpgbench: 1 - 1 - Read Onlypgbench: 1 - 1 - Read Writepgbench: 1 - 50 - Read Onlypgbench: 1 - 50 - Read Writewebp: Quality 100, Losslesswebp: Quality 100, Highest Compressionwebp: Quality 100, Lossless, Highest Compressiononednn: IP Batch 1D - f32 - CPUonednn: IP Batch 1D - u8s8f32 - CPUonednn: IP Batch All - u8s8f32 - CPUonednn: Deconvolution Batch deconv_1d - f32 - CPUonednn: Deconvolution Batch deconv_3d - f32 - CPUonednn: Deconvolution Batch deconv_1d - u8s8f32 - CPUonednn: Deconvolution Batch deconv_3d - u8s8f32 - CPUonednn: Recurrent Neural Network Training - f32 - CPUonednn: Recurrent Neural Network Inference - f32 - CPUonednn: Matrix Multiply Batch Shapes Transformer - f32 - CPUpgbench: 1 - 1 - Read Only - Average Latencypgbench: 1 - 1 - Read Write - Average Latencypgbench: 1 - 50 - Read Only - Average Latencypgbench: 1 - 50 - Read Write - Average Latencyncnn: CPU - squeezenetncnn: CPU - mobilenetncnn: CPU-v2-v2 - mobilenet-v2ncnn: CPU-v3-v3 - mobilenet-v3ncnn: CPU - shufflenet-v2ncnn: CPU - mnasnetncnn: CPU - efficientnet-b0ncnn: CPU - blazefacencnn: CPU - googlenetncnn: CPU - vgg16ncnn: CPU - resnet18ncnn: CPU - alexnetncnn: CPU - resnet50ncnn: CPU - yolov4-tinytnn: CPU - MobileNet v2tnn: CPU - SqueezeNet v1.1mrbayes: Primate Phylogeny Analysisc-ray: Total Time - 4K, 16 Rays Per Pixelaobench: 2048 x 2048 - Total Timeencode-mp3: WAV To MP3rnnoise: astcenc: Mediumastcenc: Thoroughastcenc: Exhaustivebasis: UASTC Level 2basis: UASTC Level 3basis: UASTC Level 2 + RDO Post-Processingsqlite-speedtest: Timed Time - Size 1,000AMD AOCC 2.3GCC 10.2LLVM Clang 11575.22274.20588.62122.390.1468.65770.698366.61368.17291.226.6520.12151.9223.6950.60136852531652616539780.3948.5245.767937.8114.6176.8737942779.62312.63784038.47113844262375605294314450.617061380024.291874175.911446872.3531368.865413.5923.6813720.155459109678.51296453865541314341320.9047.54642.7041.408791.0092611.92331.667723.660961.991411.87485147.52330.71820.4642350.0340.2590.09214.65514.3817.025.625.206.255.016.942.1916.5132.0311.998.9419.7029.38365.390304.17890.75933.27537.75811.02620.7565.818.1666.0416.31525.210833.53678.067564.96269.72567.42143.020.1036.77555.713354.98348.24279.736.2719.03149.3522.8349.05129553543459020929459.6945.5744.727849.6109.9171.8887972759.35305.90041052.54100728358347386291925951.642101212068.061809976.831369757.1330658.677395.4874.5418452.623694826890.71289193739521332345320.7998.86144.3831.675031.1755613.87931.956953.680732.179571.94380254.61079.24950.5329440.0350.2680.09614.48817.2919.469.378.8810.598.9511.323.9920.8530.8913.129.4623.7029.47324.172305.13494.28418.92235.7838.79821.7237.009.6173.4616.50725.522755.51775.140572.19275.41584.6592.560.1458.59170.229363.72365.57286.245.9618.23146.4322.4450.02132352738462718279838.5448.4044.307866.2111.2174.9910392673.79314.38991436.98114364262434784292874904.537331304842.232122749.431483322.3130676.685412.5945.3211946.566719313674.01289213772530684344320.7197.65542.3771.722471.0313713.46491.693903.723542.055391.98927172.51364.99120.5758640.0350.2650.09414.52815.3517.856.886.877.356.268.772.8418.8836.6013.1910.8322.2330.70392.204311.68293.84130.64641.65510.07821.5406.058.3267.1716.48525.321837.54177.642OpenBenchmarking.org

dav1d

Dav1d is an open-source, speedy AV1 video decoder. 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 0.7.0Video Input: Chimera 1080pLLVM Clang 11GCC 10.2AMD AOCC 2.3120240360480600SE +/- 0.97, N = 3SE +/- 1.05, N = 3SE +/- 0.49, N = 3572.19564.96575.22MIN: 404.8 / MAX: 726.7MIN: 399.64 / MAX: 724.27MIN: 414.12 / MAX: 729.951. (CC) gcc options: -O3 -march=znver2 -pthread
OpenBenchmarking.orgFPS, More Is Betterdav1d 0.7.0Video Input: Chimera 1080pLLVM Clang 11GCC 10.2AMD AOCC 2.3100200300400500Min: 571.07 / Avg: 572.19 / Max: 574.12Min: 563.8 / Avg: 564.96 / Max: 567.06Min: 574.7 / Avg: 575.22 / Max: 576.21. (CC) gcc options: -O3 -march=znver2 -pthread

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.7.0Video Input: Summer Nature 4KLLVM Clang 11GCC 10.2AMD AOCC 2.360120180240300SE +/- 1.08, N = 3SE +/- 0.57, N = 3SE +/- 1.22, N = 3275.41269.72274.20MIN: 155.99 / MAX: 295.35MIN: 160.12 / MAX: 288.9MIN: 151.98 / MAX: 293.441. (CC) gcc options: -O3 -march=znver2 -pthread
OpenBenchmarking.orgFPS, More Is Betterdav1d 0.7.0Video Input: Summer Nature 4KLLVM Clang 11GCC 10.2AMD AOCC 2.350100150200250Min: 273.55 / Avg: 275.41 / Max: 277.29Min: 269.12 / Avg: 269.72 / Max: 270.87Min: 271.78 / Avg: 274.2 / Max: 275.661. (CC) gcc options: -O3 -march=znver2 -pthread

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.7.0Video Input: Summer Nature 1080pLLVM Clang 11GCC 10.2AMD AOCC 2.3130260390520650SE +/- 0.95, N = 3SE +/- 0.36, N = 3SE +/- 2.09, N = 3584.65567.42588.62MIN: 337.56 / MAX: 641.35MIN: 337.19 / MAX: 625.71MIN: 345.64 / MAX: 651.081. (CC) gcc options: -O3 -march=znver2 -pthread
OpenBenchmarking.orgFPS, More Is Betterdav1d 0.7.0Video Input: Summer Nature 1080pLLVM Clang 11GCC 10.2AMD AOCC 2.3100200300400500Min: 582.87 / Avg: 584.65 / Max: 586.12Min: 566.97 / Avg: 567.42 / Max: 568.14Min: 586.15 / Avg: 588.62 / Max: 592.771. (CC) gcc options: -O3 -march=znver2 -pthread

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.7.0Video Input: Chimera 1080p 10-bitLLVM Clang 11GCC 10.2AMD AOCC 2.3306090120150SE +/- 0.26, N = 3SE +/- 0.18, N = 3SE +/- 0.34, N = 392.56143.02122.39MIN: 61.05 / MAX: 158.66MIN: 98.76 / MAX: 246.17MIN: 85.78 / MAX: 202.391. (CC) gcc options: -O3 -march=znver2 -pthread
OpenBenchmarking.orgFPS, More Is Betterdav1d 0.7.0Video Input: Chimera 1080p 10-bitLLVM Clang 11GCC 10.2AMD AOCC 2.3306090120150Min: 92.04 / Avg: 92.56 / Max: 92.85Min: 142.67 / Avg: 143.02 / Max: 143.27Min: 121.74 / Avg: 122.39 / Max: 122.911. (CC) gcc options: -O3 -march=znver2 -pthread

SVT-AV1

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-AV1 CPU-based multi-threaded video encoder for the AV1 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 0 - Input: 1080pLLVM Clang 11GCC 10.2AMD AOCC 2.30.03290.06580.09870.13160.1645SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 30.1450.1030.1461. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 0 - Input: 1080pLLVM Clang 11GCC 10.2AMD AOCC 2.312345Min: 0.15 / Avg: 0.15 / Max: 0.15Min: 0.1 / Avg: 0.1 / Max: 0.1Min: 0.15 / Avg: 0.15 / Max: 0.151. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 4 - Input: 1080pLLVM Clang 11GCC 10.2AMD AOCC 2.3246810SE +/- 0.026, N = 3SE +/- 0.025, N = 3SE +/- 0.042, N = 38.5916.7758.6571. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 4 - Input: 1080pLLVM Clang 11GCC 10.2AMD AOCC 2.33691215Min: 8.54 / Avg: 8.59 / Max: 8.62Min: 6.73 / Avg: 6.78 / Max: 6.82Min: 8.57 / Avg: 8.66 / Max: 8.71. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 8 - Input: 1080pLLVM Clang 11GCC 10.2AMD AOCC 2.31632486480SE +/- 0.30, N = 3SE +/- 0.29, N = 3SE +/- 0.46, N = 370.2355.7170.701. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 8 - Input: 1080pLLVM Clang 11GCC 10.2AMD AOCC 2.31428425670Min: 69.79 / Avg: 70.23 / Max: 70.8Min: 55.14 / Avg: 55.71 / Max: 56.08Min: 69.81 / Avg: 70.7 / Max: 71.371. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie

SVT-VP9

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.1Tuning: VMAF Optimized - Input: Bosphorus 1080pLLVM Clang 11GCC 10.2AMD AOCC 2.380160240320400SE +/- 1.70, N = 3SE +/- 2.15, N = 3SE +/- 1.39, N = 3363.72354.98366.611. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.1Tuning: VMAF Optimized - Input: Bosphorus 1080pLLVM Clang 11GCC 10.2AMD AOCC 2.370140210280350Min: 360.36 / Avg: 363.72 / Max: 365.85Min: 352.73 / Avg: 354.98 / Max: 359.28Min: 363.86 / Avg: 366.61 / Max: 368.321. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.1Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080pLLVM Clang 11GCC 10.2AMD AOCC 2.380160240320400SE +/- 1.74, N = 3SE +/- 1.42, N = 3SE +/- 0.54, N = 3365.57348.24368.171. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.1Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080pLLVM Clang 11GCC 10.2AMD AOCC 2.370140210280350Min: 362.1 / Avg: 365.57 / Max: 367.42Min: 346.02 / Avg: 348.24 / Max: 350.88Min: 367.42 / Avg: 368.17 / Max: 369.231. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.1Tuning: Visual Quality Optimized - Input: Bosphorus 1080pLLVM Clang 11GCC 10.2AMD AOCC 2.360120180240300SE +/- 1.68, N = 3SE +/- 1.18, N = 3SE +/- 0.90, N = 3286.24279.73291.221. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.1Tuning: Visual Quality Optimized - Input: Bosphorus 1080pLLVM Clang 11GCC 10.2AMD AOCC 2.350100150200250Min: 282.89 / Avg: 286.24 / Max: 288.05Min: 277.52 / Avg: 279.73 / Max: 281.56Min: 289.72 / Avg: 291.22 / Max: 292.831. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm

VP9 libvpx Encoding

This is a standard video encoding performance test of Google's libvpx library and the vpxenc command for the VP9/WebM format using a sample 1080p video. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.8.2Speed: Speed 0LLVM Clang 11GCC 10.2AMD AOCC 2.3246810SE +/- 0.09, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 35.966.276.651. (CXX) g++ options: -m64 -lm -lpthread -O3 -march=znver2 -fPIC -U_FORTIFY_SOURCE -std=c++11
OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.8.2Speed: Speed 0LLVM Clang 11GCC 10.2AMD AOCC 2.33691215Min: 5.86 / Avg: 5.96 / Max: 6.13Min: 6.24 / Avg: 6.27 / Max: 6.3Min: 6.64 / Avg: 6.65 / Max: 6.651. (CXX) g++ options: -m64 -lm -lpthread -O3 -march=znver2 -fPIC -U_FORTIFY_SOURCE -std=c++11

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.8.2Speed: Speed 5LLVM Clang 11GCC 10.2AMD AOCC 2.3510152025SE +/- 0.07, N = 3SE +/- 0.04, N = 3SE +/- 0.10, N = 318.2319.0320.121. (CXX) g++ options: -m64 -lm -lpthread -O3 -march=znver2 -fPIC -U_FORTIFY_SOURCE -std=c++11
OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.8.2Speed: Speed 5LLVM Clang 11GCC 10.2AMD AOCC 2.3510152025Min: 18.1 / Avg: 18.23 / Max: 18.32Min: 18.97 / Avg: 19.03 / Max: 19.1Min: 20.02 / Avg: 20.12 / Max: 20.311. (CXX) g++ options: -m64 -lm -lpthread -O3 -march=znver2 -fPIC -U_FORTIFY_SOURCE -std=c++11

x264

This is a simple test of the x264 encoder run on the CPU (OpenCL support disabled) with a sample video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterx264 2019-12-17H.264 Video EncodingLLVM Clang 11GCC 10.2AMD AOCC 2.3306090120150SE +/- 0.59, N = 3SE +/- 1.24, N = 3SE +/- 0.67, N = 3146.43149.35151.92-mstack-alignment=64-mstack-alignment=641. (CC) gcc options: -ldl -m64 -lm -lpthread -O3 -ffast-math -march=znver2 -std=gnu99 -fPIC -fomit-frame-pointer -fno-tree-vectorize
OpenBenchmarking.orgFrames Per Second, More Is Betterx264 2019-12-17H.264 Video EncodingLLVM Clang 11GCC 10.2AMD AOCC 2.3306090120150Min: 145.54 / Avg: 146.43 / Max: 147.54Min: 147.47 / Avg: 149.35 / Max: 151.7Min: 150.66 / Avg: 151.92 / Max: 152.941. (CC) gcc options: -ldl -m64 -lm -lpthread -O3 -ffast-math -march=znver2 -std=gnu99 -fPIC -fomit-frame-pointer -fno-tree-vectorize

x265

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

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 4KLLVM Clang 11GCC 10.2AMD AOCC 2.3612182430SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.05, N = 322.4422.8323.691. (CXX) g++ options: -O3 -march=znver2 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 4KLLVM Clang 11GCC 10.2AMD AOCC 2.3612182430Min: 22.4 / Avg: 22.44 / Max: 22.49Min: 22.74 / Avg: 22.83 / Max: 22.95Min: 23.6 / Avg: 23.69 / Max: 23.771. (CXX) g++ options: -O3 -march=znver2 -rdynamic -lpthread -lrt -ldl -lnuma

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 1080pLLVM Clang 11GCC 10.2AMD AOCC 2.31122334455SE +/- 0.09, N = 3SE +/- 0.13, N = 3SE +/- 0.14, N = 350.0249.0550.601. (CXX) g++ options: -O3 -march=znver2 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 1080pLLVM Clang 11GCC 10.2AMD AOCC 2.31020304050Min: 49.87 / Avg: 50.02 / Max: 50.19Min: 48.81 / Avg: 49.05 / Max: 49.25Min: 50.37 / Avg: 50.6 / Max: 50.841. (CXX) g++ options: -O3 -march=znver2 -rdynamic -lpthread -lrt -ldl -lnuma

GraphicsMagick

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample 6000x4000 pixel JPEG image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: SwirlLLVM Clang 11GCC 10.2AMD AOCC 2.330060090012001500SE +/- 2.40, N = 3SE +/- 1.00, N = 3SE +/- 4.26, N = 31323129513681. (CC) gcc options: -fopenmp -O3 -march=znver2 -pthread -ljpeg -lX11 -lz -lm -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: SwirlLLVM Clang 11GCC 10.2AMD AOCC 2.32004006008001000Min: 1318 / Avg: 1322.67 / Max: 1326Min: 1293 / Avg: 1295 / Max: 1296Min: 1360 / Avg: 1368.33 / Max: 13741. (CC) gcc options: -fopenmp -O3 -march=znver2 -pthread -ljpeg -lX11 -lz -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: RotateLLVM Clang 11GCC 10.2AMD AOCC 2.3120240360480600SE +/- 5.24, N = 3SE +/- 1.00, N = 35275355251. (CC) gcc options: -fopenmp -O3 -march=znver2 -pthread -ljpeg -lX11 -lz -lm -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: RotateLLVM Clang 11GCC 10.2AMD AOCC 2.390180270360450Min: 528 / Avg: 534.67 / Max: 545Min: 524 / Avg: 525 / Max: 5271. (CC) gcc options: -fopenmp -O3 -march=znver2 -pthread -ljpeg -lX11 -lz -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: SharpenLLVM Clang 11GCC 10.2AMD AOCC 2.3901802703604503844343161. (CC) gcc options: -fopenmp -O3 -march=znver2 -pthread -ljpeg -lX11 -lz -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: EnhancedLLVM Clang 11GCC 10.2AMD AOCC 2.31402804205607006275905261. (CC) gcc options: -fopenmp -O3 -march=znver2 -pthread -ljpeg -lX11 -lz -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: ResizingLLVM Clang 11GCC 10.2AMD AOCC 2.3400800120016002000SE +/- 10.17, N = 3SE +/- 17.89, N = 3SE +/- 22.27, N = 31827209216531. (CC) gcc options: -fopenmp -O3 -march=znver2 -pthread -ljpeg -lX11 -lz -lm -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: ResizingLLVM Clang 11GCC 10.2AMD AOCC 2.3400800120016002000Min: 1807 / Avg: 1827.33 / Max: 1838Min: 2056 / Avg: 2091.67 / Max: 2112Min: 1609 / Avg: 1653 / Max: 16811. (CC) gcc options: -fopenmp -O3 -march=znver2 -pthread -ljpeg -lX11 -lz -lm -lpthread

LZ4 Compression

This test measures the time needed to compress/decompress a sample file (an Ubuntu ISO) using LZ4 compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 1 - Compression SpeedLLVM Clang 11GCC 10.2AMD AOCC 2.32K4K6K8K10KSE +/- 55.02, N = 3SE +/- 56.41, N = 3SE +/- 45.16, N = 39838.549459.699780.391. (CC) gcc options: -O3
OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 1 - Compression SpeedLLVM Clang 11GCC 10.2AMD AOCC 2.32K4K6K8K10KMin: 9748.47 / Avg: 9838.54 / Max: 9938.32Min: 9379.7 / Avg: 9459.69 / Max: 9568.59Min: 9697.45 / Avg: 9780.39 / Max: 9852.821. (CC) gcc options: -O3

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 3 - Compression SpeedLLVM Clang 11GCC 10.2AMD AOCC 2.31122334455SE +/- 0.04, N = 3SE +/- 0.66, N = 3SE +/- 0.00, N = 348.4045.5748.521. (CC) gcc options: -O3
OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 3 - Compression SpeedLLVM Clang 11GCC 10.2AMD AOCC 2.31020304050Min: 48.32 / Avg: 48.4 / Max: 48.45Min: 44.86 / Avg: 45.57 / Max: 46.9Min: 48.52 / Avg: 48.52 / Max: 48.521. (CC) gcc options: -O3

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 9 - Compression SpeedLLVM Clang 11GCC 10.2AMD AOCC 2.31020304050SE +/- 0.02, N = 3SE +/- 0.60, N = 3SE +/- 0.03, N = 344.3044.7245.761. (CC) gcc options: -O3
OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 9 - Compression SpeedLLVM Clang 11GCC 10.2AMD AOCC 2.3918273645Min: 44.26 / Avg: 44.3 / Max: 44.33Min: 43.72 / Avg: 44.72 / Max: 45.79Min: 45.71 / Avg: 45.76 / Max: 45.821. (CC) gcc options: -O3

Zstd Compression

This test measures the time needed to compress a sample file (an Ubuntu ISO) using Zstd compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.5Compression Level: 3LLVM Clang 11GCC 10.2AMD AOCC 2.32K4K6K8K10KSE +/- 30.93, N = 3SE +/- 6.11, N = 3SE +/- 3.73, N = 37866.27849.67937.81. (CC) gcc options: -O3 -march=znver2 -pthread -lz
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.5Compression Level: 3LLVM Clang 11GCC 10.2AMD AOCC 2.314002800420056007000Min: 7828.4 / Avg: 7866.2 / Max: 7927.5Min: 7838.2 / Avg: 7849.6 / Max: 7859.1Min: 7933.6 / Avg: 7937.77 / Max: 7945.21. (CC) gcc options: -O3 -march=znver2 -pthread -lz

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.5Compression Level: 19LLVM Clang 11GCC 10.2AMD AOCC 2.3306090120150SE +/- 0.30, N = 3SE +/- 0.23, N = 3SE +/- 0.26, N = 3111.2109.9114.61. (CC) gcc options: -O3 -march=znver2 -pthread -lz
OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.4.5Compression Level: 19LLVM Clang 11GCC 10.2AMD AOCC 2.320406080100Min: 110.8 / Avg: 111.23 / Max: 111.8Min: 109.7 / Avg: 109.93 / Max: 110.4Min: 114.1 / Avg: 114.57 / Max: 1151. (CC) gcc options: -O3 -march=znver2 -pthread -lz

libjpeg-turbo tjbench

tjbench is a JPEG decompression/compression benchmark part of libjpeg-turbo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMegapixels/sec, More Is Betterlibjpeg-turbo tjbench 2.0.2Test: Decompression ThroughputLLVM Clang 11GCC 10.2AMD AOCC 2.34080120160200SE +/- 0.21, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3174.99171.89176.871. (CC) gcc options: -O3 -march=znver2 -rdynamic
OpenBenchmarking.orgMegapixels/sec, More Is Betterlibjpeg-turbo tjbench 2.0.2Test: Decompression ThroughputLLVM Clang 11GCC 10.2AMD AOCC 2.3306090120150Min: 174.59 / Avg: 174.99 / Max: 175.31Min: 171.81 / Avg: 171.89 / Max: 171.94Min: 176.84 / Avg: 176.87 / Max: 176.891. (CC) gcc options: -O3 -march=znver2 -rdynamic

SciMark

This test runs the ANSI C version of SciMark 2.0, which is a benchmark for scientific and numerical computing developed by programmers at the National Institute of Standards and Technology. This test is made up of Fast Foruier Transform, Jacobi Successive Over-relaxation, Monte Carlo, Sparse Matrix Multiply, and dense LU matrix factorization benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: CompositeLLVM Clang 11GCC 10.2AMD AOCC 2.36001200180024003000SE +/- 7.04, N = 3SE +/- 14.97, N = 3SE +/- 43.99, N = 32673.792759.352779.621. (CC) gcc options: -O3 -march=znver2 -lm
OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: CompositeLLVM Clang 11GCC 10.2AMD AOCC 2.35001000150020002500Min: 2661.26 / Avg: 2673.79 / Max: 2685.6Min: 2737.01 / Avg: 2759.35 / Max: 2787.78Min: 2734.21 / Avg: 2779.62 / Max: 2867.581. (CC) gcc options: -O3 -march=znver2 -lm

Crypto++

Crypto++ is a C++ class library of cryptographic algorithms. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/second, More Is BetterCrypto++ 8.2Test: Unkeyed AlgorithmsLLVM Clang 11GCC 10.2AMD AOCC 2.370140210280350SE +/- 0.20, N = 3SE +/- 0.09, N = 3SE +/- 0.16, N = 3314.39305.90312.641. (CXX) g++ options: -O3 -march=znver2 -fPIC -pthread -pipe
OpenBenchmarking.orgMiB/second, More Is BetterCrypto++ 8.2Test: Unkeyed AlgorithmsLLVM Clang 11GCC 10.2AMD AOCC 2.360120180240300Min: 314.03 / Avg: 314.39 / Max: 314.74Min: 305.76 / Avg: 305.9 / Max: 306.06Min: 312.33 / Avg: 312.64 / Max: 312.811. (CXX) g++ options: -O3 -march=znver2 -fPIC -pthread -pipe

LibRaw

LibRaw is a RAW image decoder for digital camera photos. This test profile runs LibRaw's post-processing benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMpix/sec, More Is BetterLibRaw 0.20Post-Processing BenchmarkLLVM Clang 11GCC 10.2AMD AOCC 2.31224364860SE +/- 0.13, N = 3SE +/- 0.16, N = 3SE +/- 0.10, N = 336.9852.5438.471. (CXX) g++ options: -O3 -march=znver2 -fopenmp -ljpeg -lz -lm
OpenBenchmarking.orgMpix/sec, More Is BetterLibRaw 0.20Post-Processing BenchmarkLLVM Clang 11GCC 10.2AMD AOCC 2.31122334455Min: 36.77 / Avg: 36.98 / Max: 37.23Min: 52.28 / Avg: 52.54 / Max: 52.82Min: 38.31 / Avg: 38.47 / Max: 38.641. (CXX) g++ options: -O3 -march=znver2 -fopenmp -ljpeg -lz -lm

TSCP

This is a performance test of TSCP, Tom Kerrigan's Simple Chess Program, which has a built-in performance benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterTSCP 1.81AI Chess PerformanceLLVM Clang 11GCC 10.2AMD AOCC 2.3200K400K600K800K1000KSE +/- 582.00, N = 5SE +/- 1467.20, N = 5SE +/- 471.20, N = 51143642100728311384421. (CC) gcc options: -O3 -march=znver2 -march=native
OpenBenchmarking.orgNodes Per Second, More Is BetterTSCP 1.81AI Chess PerformanceLLVM Clang 11GCC 10.2AMD AOCC 2.3200K400K600K800K1000KMin: 1142692 / Avg: 1143642.4 / Max: 1145068Min: 1001414 / Avg: 1007282.8 / Max: 1008750Min: 1137971 / Avg: 1138442.2 / Max: 11403271. (CC) gcc options: -O3 -march=znver2 -march=native

Stockfish

This is a test of Stockfish, an advanced C++11 chess benchmark that can scale up to 128 CPU cores. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 12Total TimeLLVM Clang 11GCC 10.2AMD AOCC 2.313M26M39M52M65MSE +/- 877956.02, N = 4SE +/- 872585.44, N = 3SE +/- 379890.17, N = 3624347845834738662375605-flto=thin-flto -flto=jobserver-flto=thin1. (CXX) g++ options: -m64 -lpthread -O3 -march=znver2 -fno-exceptions -std=c++17 -pedantic -msse -msse3 -mpopcnt -msse4.1 -mssse3 -msse2
OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 12Total TimeLLVM Clang 11GCC 10.2AMD AOCC 2.311M22M33M44M55MMin: 60541799 / Avg: 62434784 / Max: 64327675Min: 56935236 / Avg: 58347385.67 / Max: 59941487Min: 61935820 / Avg: 62375605.33 / Max: 631320531. (CXX) g++ options: -m64 -lpthread -O3 -march=znver2 -fno-exceptions -std=c++17 -pedantic -msse -msse3 -mpopcnt -msse4.1 -mssse3 -msse2

Hierarchical INTegration

This test runs the U.S. Department of Energy's Ames Laboratory Hierarchical INTegration (HINT) benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQUIPs, More Is BetterHierarchical INTegration 1.0Test: FLOATLLVM Clang 11GCC 10.2AMD AOCC 2.360M120M180M240M300MSE +/- 170353.62, N = 3SE +/- 15707.07, N = 3SE +/- 30193.74, N = 3292874904.54291925951.64294314450.621. (CC) gcc options: -O3 -march=znver2 -march=native -lm
OpenBenchmarking.orgQUIPs, More Is BetterHierarchical INTegration 1.0Test: FLOATLLVM Clang 11GCC 10.2AMD AOCC 2.350M100M150M200M250MMin: 292551021.97 / Avg: 292874904.54 / Max: 293128421.65Min: 291898211.16 / Avg: 291925951.64 / Max: 291952588.45Min: 294258623.56 / Avg: 294314450.62 / Max: 294362301.321. (CC) gcc options: -O3 -march=znver2 -march=native -lm

Redis

Redis is an open-source data structure server. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: LPUSHLLVM Clang 11GCC 10.2AMD AOCC 2.3300K600K900K1200K1500KSE +/- 22719.73, N = 15SE +/- 21030.89, N = 15SE +/- 18763.42, N = 31304842.231212068.061380024.291. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3 -march=znver2
OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: LPUSHLLVM Clang 11GCC 10.2AMD AOCC 2.3200K400K600K800K1000KMin: 1199155.88 / Avg: 1304842.23 / Max: 1460134.25Min: 1117318.5 / Avg: 1212068.06 / Max: 1346153.5Min: 1347752 / Avg: 1380024.29 / Max: 1412745.751. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3 -march=znver2

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: GETLLVM Clang 11GCC 10.2AMD AOCC 2.3500K1000K1500K2000K2500KSE +/- 49885.99, N = 15SE +/- 18838.90, N = 3SE +/- 30693.11, N = 152122749.431809976.831874175.911. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3 -march=znver2
OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: GETLLVM Clang 11GCC 10.2AMD AOCC 2.3400K800K1200K1600K2000KMin: 1733435 / Avg: 2122749.43 / Max: 2364822.75Min: 1773049.62 / Avg: 1809976.83 / Max: 1834921Min: 1666879.88 / Avg: 1874175.91 / Max: 2066512.381. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3 -march=znver2

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: SETLLVM Clang 11GCC 10.2AMD AOCC 2.3300K600K900K1200K1500KSE +/- 22282.05, N = 15SE +/- 24810.19, N = 15SE +/- 27170.26, N = 151483322.311369757.131446872.351. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3 -march=znver2
OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: SETLLVM Clang 11GCC 10.2AMD AOCC 2.3300K600K900K1200K1500KMin: 1394878.62 / Avg: 1483322.31 / Max: 1669716.25Min: 1239474.62 / Avg: 1369757.13 / Max: 1546139.12Min: 1285676.12 / Avg: 1446872.35 / Max: 1608077.251. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3 -march=znver2

NGINX Benchmark

This is a test of ab, which is the Apache Benchmark program running against nginx. This test profile measures how many requests per second a given system can sustain when carrying out 2,000,000 requests with 500 requests being carried out concurrently. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterNGINX Benchmark 1.9.9Static Web Page ServingLLVM Clang 11GCC 10.2AMD AOCC 2.37K14K21K28K35KSE +/- 159.74, N = 3SE +/- 381.73, N = 4SE +/- 254.59, N = 1530676.6830658.6731368.861. (CC) gcc options: -lpthread -lcrypt -lcrypto -lz -O3 -march=native -march=znver2
OpenBenchmarking.orgRequests Per Second, More Is BetterNGINX Benchmark 1.9.9Static Web Page ServingLLVM Clang 11GCC 10.2AMD AOCC 2.35K10K15K20K25KMin: 30454.56 / Avg: 30676.68 / Max: 30986.62Min: 30130.16 / Avg: 30658.67 / Max: 31758.42Min: 29477.09 / Avg: 31368.86 / Max: 33105.191. (CC) gcc options: -lpthread -lcrypt -lcrypto -lz -O3 -march=native -march=znver2

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test measures the RSA 4096-bit performance of OpenSSL. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSigns Per Second, More Is BetterOpenSSL 1.1.1RSA 4096-bit PerformanceLLVM Clang 11GCC 10.2AMD AOCC 2.316003200480064008000SE +/- 1.37, N = 3SE +/- 0.73, N = 3SE +/- 0.64, N = 35412.57395.45413.5-Qunused-arguments-Qunused-arguments1. (CC) gcc options: -pthread -m64 -O3 -march=znver2 -lssl -lcrypto -ldl
OpenBenchmarking.orgSigns Per Second, More Is BetterOpenSSL 1.1.1RSA 4096-bit PerformanceLLVM Clang 11GCC 10.2AMD AOCC 2.313002600390052006500Min: 5409.8 / Avg: 5412.5 / Max: 5414.2Min: 7394 / Avg: 7395.37 / Max: 7396.5Min: 5412.3 / Avg: 5413.5 / Max: 5414.51. (CC) gcc options: -pthread -m64 -O3 -march=znver2 -lssl -lcrypto -ldl

Darmstadt Automotive Parallel Heterogeneous Suite

DAPHNE is the Darmstadt Automotive Parallel HeterogeNEous Benchmark Suite with OpenCL / CUDA / OpenMP test cases for these automotive benchmarks for evaluating programming models in context to vehicle autonomous driving capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTest Cases Per Minute, More Is BetterDarmstadt Automotive Parallel Heterogeneous SuiteBackend: OpenMP - Kernel: NDT MappingLLVM Clang 11GCC 10.2AMD AOCC 2.32004006008001000SE +/- 2.29, N = 3SE +/- 2.97, N = 3SE +/- 1.07, N = 3945.32874.54923.681. (CXX) g++ options: -O3 -std=c++11 -fopenmp
OpenBenchmarking.orgTest Cases Per Minute, More Is BetterDarmstadt Automotive Parallel Heterogeneous SuiteBackend: OpenMP - Kernel: NDT MappingLLVM Clang 11GCC 10.2AMD AOCC 2.3170340510680850Min: 941.53 / Avg: 945.32 / Max: 949.46Min: 871.13 / Avg: 874.54 / Max: 880.45Min: 921.91 / Avg: 923.68 / Max: 925.611. (CXX) g++ options: -O3 -std=c++11 -fopenmp

OpenBenchmarking.orgTest Cases Per Minute, More Is BetterDarmstadt Automotive Parallel Heterogeneous SuiteBackend: OpenMP - Kernel: Points2ImageLLVM Clang 11GCC 10.2AMD AOCC 2.34K8K12K16K20KSE +/- 96.60, N = 3SE +/- 140.90, N = 3SE +/- 163.63, N = 611946.5718452.6213720.161. (CXX) g++ options: -O3 -std=c++11 -fopenmp
OpenBenchmarking.orgTest Cases Per Minute, More Is BetterDarmstadt Automotive Parallel Heterogeneous SuiteBackend: OpenMP - Kernel: Points2ImageLLVM Clang 11GCC 10.2AMD AOCC 2.33K6K9K12K15KMin: 11809.19 / Avg: 11946.57 / Max: 12132.9Min: 18280.53 / Avg: 18452.62 / Max: 18731.91Min: 13297.72 / Avg: 13720.16 / Max: 14488.591. (CXX) g++ options: -O3 -std=c++11 -fopenmp

OpenBenchmarking.orgTest Cases Per Minute, More Is BetterDarmstadt Automotive Parallel Heterogeneous SuiteBackend: OpenMP - Kernel: Euclidean ClusterLLVM Clang 11GCC 10.2AMD AOCC 2.32004006008001000SE +/- 2.53, N = 3SE +/- 0.77, N = 3SE +/- 0.47, N = 3674.01890.71678.511. (CXX) g++ options: -O3 -std=c++11 -fopenmp
OpenBenchmarking.orgTest Cases Per Minute, More Is BetterDarmstadt Automotive Parallel Heterogeneous SuiteBackend: OpenMP - Kernel: Euclidean ClusterLLVM Clang 11GCC 10.2AMD AOCC 2.3160320480640800Min: 670.12 / Avg: 674.01 / Max: 678.74Min: 889.31 / Avg: 890.71 / Max: 891.94Min: 678.03 / Avg: 678.51 / Max: 679.451. (CXX) g++ options: -O3 -std=c++11 -fopenmp

PostgreSQL pgbench

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

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 1 - Mode: Read OnlyLLVM Clang 11GCC 10.2AMD AOCC 2.36K12K18K24K30KSE +/- 252.07, N = 3SE +/- 137.51, N = 3SE +/- 73.04, N = 32892128919296451. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=znver2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 1 - Mode: Read OnlyLLVM Clang 11GCC 10.2AMD AOCC 2.35K10K15K20K25KMin: 28553.04 / Avg: 28921.21 / Max: 29403.54Min: 28675.43 / Avg: 28919.49 / Max: 29151.33Min: 29533.33 / Avg: 29644.87 / Max: 29782.331. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=znver2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 1 - Mode: Read WriteLLVM Clang 11GCC 10.2AMD AOCC 2.38001600240032004000SE +/- 3.59, N = 3SE +/- 46.08, N = 5SE +/- 18.01, N = 33772373938651. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=znver2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 1 - Mode: Read WriteLLVM Clang 11GCC 10.2AMD AOCC 2.37001400210028003500Min: 3765.64 / Avg: 3772.39 / Max: 3777.89Min: 3661.95 / Avg: 3738.93 / Max: 3912.47Min: 3841.6 / Avg: 3865.19 / Max: 3900.571. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=znver2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 50 - Mode: Read OnlyLLVM Clang 11GCC 10.2AMD AOCC 2.3120K240K360K480K600KSE +/- 4278.21, N = 3SE +/- 4440.25, N = 3SE +/- 798.75, N = 35306845213325413141. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=znver2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 50 - Mode: Read OnlyLLVM Clang 11GCC 10.2AMD AOCC 2.390K180K270K360K450KMin: 522660.49 / Avg: 530683.67 / Max: 537270.27Min: 513644.91 / Avg: 521332.12 / Max: 529026.4Min: 539787.52 / Avg: 541313.86 / Max: 542485.311. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=znver2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 50 - Mode: Read WriteLLVM Clang 11GCC 10.2AMD AOCC 2.37001400210028003500SE +/- 4.43, N = 3SE +/- 5.86, N = 3SE +/- 5.71, N = 33443345334131. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=znver2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 50 - Mode: Read WriteLLVM Clang 11GCC 10.2AMD AOCC 2.36001200180024003000Min: 3434.2 / Avg: 3443.05 / Max: 3447.87Min: 3440.84 / Avg: 3452.55 / Max: 3458.53Min: 3403.04 / Avg: 3413.22 / Max: 3422.811. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=znver2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

WebP Image Encode

This is a test of Google's libwebp with the cwebp image encode utility and using a sample 6000x4000 pixel JPEG image as the input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, LosslessLLVM Clang 11GCC 10.2AMD AOCC 2.3510152025SE +/- 0.02, N = 3SE +/- 0.08, N = 3SE +/- 0.03, N = 320.7220.8020.901. (CC) gcc options: -fvisibility=hidden -O3 -march=znver2 -pthread -lm -ljpeg
OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, LosslessLLVM Clang 11GCC 10.2AMD AOCC 2.3510152025Min: 20.69 / Avg: 20.72 / Max: 20.75Min: 20.71 / Avg: 20.8 / Max: 20.97Min: 20.85 / Avg: 20.9 / Max: 20.951. (CC) gcc options: -fvisibility=hidden -O3 -march=znver2 -pthread -lm -ljpeg

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Highest CompressionLLVM Clang 11GCC 10.2AMD AOCC 2.3246810SE +/- 0.008, N = 3SE +/- 0.003, N = 3SE +/- 0.008, N = 37.6558.8617.5461. (CC) gcc options: -fvisibility=hidden -O3 -march=znver2 -pthread -lm -ljpeg
OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Highest CompressionLLVM Clang 11GCC 10.2AMD AOCC 2.33691215Min: 7.65 / Avg: 7.66 / Max: 7.67Min: 8.86 / Avg: 8.86 / Max: 8.87Min: 7.53 / Avg: 7.55 / Max: 7.561. (CC) gcc options: -fvisibility=hidden -O3 -march=znver2 -pthread -lm -ljpeg

OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Lossless, Highest CompressionLLVM Clang 11GCC 10.2AMD AOCC 2.31020304050SE +/- 0.12, N = 3SE +/- 0.12, N = 3SE +/- 0.01, N = 342.3844.3842.701. (CC) gcc options: -fvisibility=hidden -O3 -march=znver2 -pthread -lm -ljpeg
OpenBenchmarking.orgEncode Time - Seconds, Fewer Is BetterWebP Image Encode 1.1Encode Settings: Quality 100, Lossless, Highest CompressionLLVM Clang 11GCC 10.2AMD AOCC 2.3918273645Min: 42.26 / Avg: 42.38 / Max: 42.61Min: 44.17 / Avg: 44.38 / Max: 44.58Min: 42.7 / Avg: 42.7 / Max: 42.721. (CC) gcc options: -fvisibility=hidden -O3 -march=znver2 -pthread -lm -ljpeg

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: IP Batch 1D - Data Type: f32 - Engine: CPULLVM Clang 11GCC 10.2AMD AOCC 2.30.38760.77521.16281.55041.938SE +/- 0.00256, N = 3SE +/- 0.00519, N = 3SE +/- 0.00432, N = 31.722471.675031.40879-fopenmp=libomp - MIN: 1.62-fopenmp - MIN: 1.59-fopenmp=libomp - MIN: 1.361. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: IP Batch 1D - Data Type: f32 - Engine: CPULLVM Clang 11GCC 10.2AMD AOCC 2.3246810Min: 1.72 / Avg: 1.72 / Max: 1.73Min: 1.67 / Avg: 1.68 / Max: 1.69Min: 1.4 / Avg: 1.41 / Max: 1.421. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: IP Batch 1D - Data Type: u8s8f32 - Engine: CPULLVM Clang 11GCC 10.2AMD AOCC 2.30.26450.5290.79351.0581.3225SE +/- 0.00137, N = 3SE +/- 0.00350, N = 3SE +/- 0.00275, N = 31.031371.175561.00926-fopenmp=libomp - MIN: 0.97-fopenmp - MIN: 1.13-fopenmp=libomp - MIN: 0.951. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: IP Batch 1D - Data Type: u8s8f32 - Engine: CPULLVM Clang 11GCC 10.2AMD AOCC 2.3246810Min: 1.03 / Avg: 1.03 / Max: 1.03Min: 1.17 / Avg: 1.18 / Max: 1.18Min: 1 / Avg: 1.01 / Max: 1.011. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: IP Batch All - Data Type: u8s8f32 - Engine: CPULLVM Clang 11GCC 10.2AMD AOCC 2.348121620SE +/- 0.04, N = 3SE +/- 0.06, N = 3SE +/- 0.02, N = 313.4613.8811.92-fopenmp=libomp - MIN: 13.14-fopenmp - MIN: 13.35-fopenmp=libomp - MIN: 11.651. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: IP Batch All - Data Type: u8s8f32 - Engine: CPULLVM Clang 11GCC 10.2AMD AOCC 2.348121620Min: 13.39 / Avg: 13.46 / Max: 13.52Min: 13.77 / Avg: 13.88 / Max: 13.97Min: 11.9 / Avg: 11.92 / Max: 11.951. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Deconvolution Batch deconv_1d - Data Type: f32 - Engine: CPULLVM Clang 11GCC 10.2AMD AOCC 2.30.44030.88061.32091.76122.2015SE +/- 0.01023, N = 3SE +/- 0.01336, N = 3SE +/- 0.00186, N = 31.693901.956951.66772-fopenmp=libomp - MIN: 1.63-fopenmp - MIN: 1.87-fopenmp=libomp - MIN: 1.611. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Deconvolution Batch deconv_1d - Data Type: f32 - Engine: CPULLVM Clang 11GCC 10.2AMD AOCC 2.3246810Min: 1.68 / Avg: 1.69 / Max: 1.71Min: 1.94 / Avg: 1.96 / Max: 1.98Min: 1.67 / Avg: 1.67 / Max: 1.671. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Deconvolution Batch deconv_3d - Data Type: f32 - Engine: CPULLVM Clang 11GCC 10.2AMD AOCC 2.30.83781.67562.51343.35124.189SE +/- 0.00775, N = 3SE +/- 0.01624, N = 3SE +/- 0.01101, N = 33.723543.680733.66096-fopenmp=libomp - MIN: 3.57-fopenmp - MIN: 3.53-fopenmp=libomp - MIN: 3.491. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Deconvolution Batch deconv_3d - Data Type: f32 - Engine: CPULLVM Clang 11GCC 10.2AMD AOCC 2.3246810Min: 3.71 / Avg: 3.72 / Max: 3.74Min: 3.66 / Avg: 3.68 / Max: 3.71Min: 3.65 / Avg: 3.66 / Max: 3.681. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Deconvolution Batch deconv_1d - Data Type: u8s8f32 - Engine: CPULLVM Clang 11GCC 10.2AMD AOCC 2.30.49040.98081.47121.96162.452SE +/- 0.00233, N = 3SE +/- 0.00145, N = 3SE +/- 0.00112, N = 32.055392.179571.99141-fopenmp=libomp - MIN: 1.96-fopenmp - MIN: 2.05-fopenmp=libomp - MIN: 1.921. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Deconvolution Batch deconv_1d - Data Type: u8s8f32 - Engine: CPULLVM Clang 11GCC 10.2AMD AOCC 2.3246810Min: 2.05 / Avg: 2.06 / Max: 2.06Min: 2.18 / Avg: 2.18 / Max: 2.18Min: 1.99 / Avg: 1.99 / Max: 1.991. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Deconvolution Batch deconv_3d - Data Type: u8s8f32 - Engine: CPULLVM Clang 11GCC 10.2AMD AOCC 2.30.44760.89521.34281.79042.238SE +/- 0.00691, N = 3SE +/- 0.00392, N = 3SE +/- 0.00189, N = 31.989271.943801.87485-fopenmp=libomp - MIN: 1.9-fopenmp - MIN: 1.82-fopenmp=libomp - MIN: 1.821. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Deconvolution Batch deconv_3d - Data Type: u8s8f32 - Engine: CPULLVM Clang 11GCC 10.2AMD AOCC 2.3246810Min: 1.98 / Avg: 1.99 / Max: 2Min: 1.94 / Avg: 1.94 / Max: 1.95Min: 1.87 / Avg: 1.87 / Max: 1.881. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPULLVM Clang 11GCC 10.2AMD AOCC 2.360120180240300SE +/- 1.10, N = 3SE +/- 0.73, N = 3SE +/- 0.06, N = 3172.51254.61147.52-fopenmp=libomp - MIN: 169.54-fopenmp - MIN: 251.67-fopenmp=libomp - MIN: 146.311. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPULLVM Clang 11GCC 10.2AMD AOCC 2.350100150200250Min: 170.32 / Avg: 172.51 / Max: 173.7Min: 253.81 / Avg: 254.61 / Max: 256.06Min: 147.45 / Avg: 147.52 / Max: 147.651. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPULLVM Clang 11GCC 10.2AMD AOCC 2.320406080100SE +/- 2.37, N = 15SE +/- 0.80, N = 3SE +/- 0.32, N = 364.9979.2530.72-fopenmp=libomp - MIN: 50.95-fopenmp - MIN: 77.35-fopenmp=libomp - MIN: 29.351. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPULLVM Clang 11GCC 10.2AMD AOCC 2.31530456075Min: 51.43 / Avg: 64.99 / Max: 74.8Min: 77.95 / Avg: 79.25 / Max: 80.7Min: 30.09 / Avg: 30.72 / Max: 31.161. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPULLVM Clang 11GCC 10.2AMD AOCC 2.30.12960.25920.38880.51840.648SE +/- 0.001767, N = 3SE +/- 0.001691, N = 3SE +/- 0.000544, N = 30.5758640.5329440.464235-fopenmp=libomp - MIN: 0.55-fopenmp - MIN: 0.51-fopenmp=libomp - MIN: 0.451. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPULLVM Clang 11GCC 10.2AMD AOCC 2.3246810Min: 0.57 / Avg: 0.58 / Max: 0.58Min: 0.53 / Avg: 0.53 / Max: 0.54Min: 0.46 / Avg: 0.46 / Max: 0.471. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -pie -lpthread -ldl

PostgreSQL pgbench

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

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 1 - Mode: Read Only - Average LatencyLLVM Clang 11GCC 10.2AMD AOCC 2.30.00790.01580.02370.03160.0395SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 30.0350.0350.0341. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=znver2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 1 - Mode: Read Only - Average LatencyLLVM Clang 11GCC 10.2AMD AOCC 2.312345Min: 0.03 / Avg: 0.03 / Max: 0.04Min: 0.03 / Avg: 0.03 / Max: 0.04Min: 0.03 / Avg: 0.03 / Max: 0.031. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=znver2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 1 - Mode: Read Write - Average LatencyLLVM Clang 11GCC 10.2AMD AOCC 2.30.06030.12060.18090.24120.3015SE +/- 0.000, N = 3SE +/- 0.003, N = 5SE +/- 0.001, N = 30.2650.2680.2591. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=znver2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 1 - Mode: Read Write - Average LatencyLLVM Clang 11GCC 10.2AMD AOCC 2.312345Min: 0.27 / Avg: 0.27 / Max: 0.27Min: 0.26 / Avg: 0.27 / Max: 0.27Min: 0.26 / Avg: 0.26 / Max: 0.261. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=znver2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 50 - Mode: Read Only - Average LatencyLLVM Clang 11GCC 10.2AMD AOCC 2.30.02160.04320.06480.08640.108SE +/- 0.001, N = 3SE +/- 0.001, N = 3SE +/- 0.000, N = 30.0940.0960.0921. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=znver2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 50 - Mode: Read Only - Average LatencyLLVM Clang 11GCC 10.2AMD AOCC 2.312345Min: 0.09 / Avg: 0.09 / Max: 0.1Min: 0.1 / Avg: 0.1 / Max: 0.1Min: 0.09 / Avg: 0.09 / Max: 0.091. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=znver2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 50 - Mode: Read Write - Average LatencyLLVM Clang 11GCC 10.2AMD AOCC 2.348121620SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 314.5314.4914.661. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=znver2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL pgbench 13.0Scaling Factor: 1 - Clients: 50 - Mode: Read Write - Average LatencyLLVM Clang 11GCC 10.2AMD AOCC 2.348121620Min: 14.51 / Avg: 14.53 / Max: 14.57Min: 14.46 / Avg: 14.49 / Max: 14.54Min: 14.62 / Avg: 14.66 / Max: 14.71. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=znver2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm

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 20200916Target: CPU - Model: squeezenetLLVM Clang 11GCC 10.2AMD AOCC 2.348121620SE +/- 0.14, N = 15SE +/- 0.12, N = 3SE +/- 0.10, N = 315.3517.2914.38-lomp - MIN: 14.29 / MAX: 18.88-lgomp - MIN: 16.89 / MAX: 19.32-lomp - MIN: 13.96 / MAX: 16.871. (CXX) g++ options: -O3 -march=znver2 -rdynamic -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: squeezenetLLVM Clang 11GCC 10.2AMD AOCC 2.348121620Min: 14.45 / Avg: 15.35 / Max: 16.29Min: 17.12 / Avg: 17.29 / Max: 17.51Min: 14.21 / Avg: 14.38 / Max: 14.561. (CXX) g++ options: -O3 -march=znver2 -rdynamic -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: mobilenetLLVM Clang 11GCC 10.2AMD AOCC 2.3510152025SE +/- 0.13, N = 15SE +/- 0.12, N = 3SE +/- 0.34, N = 317.8519.4617.02-lomp - MIN: 16.89 / MAX: 21.04-lgomp - MIN: 18.87 / MAX: 31.76-lomp - MIN: 16.39 / MAX: 20.111. (CXX) g++ options: -O3 -march=znver2 -rdynamic -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: mobilenetLLVM Clang 11GCC 10.2AMD AOCC 2.3510152025Min: 17.06 / Avg: 17.85 / Max: 18.52Min: 19.22 / Avg: 19.46 / Max: 19.61Min: 16.63 / Avg: 17.02 / Max: 17.691. (CXX) g++ options: -O3 -march=znver2 -rdynamic -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU-v2-v2 - Model: mobilenet-v2LLVM Clang 11GCC 10.2AMD AOCC 2.33691215SE +/- 0.06, N = 15SE +/- 0.24, N = 3SE +/- 0.08, N = 36.889.375.62-lomp - MIN: 6.35 / MAX: 16.49-lgomp - MIN: 8.62 / MAX: 11-lomp - MIN: 5.35 / MAX: 7.491. (CXX) g++ options: -O3 -march=znver2 -rdynamic -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU-v2-v2 - Model: mobilenet-v2LLVM Clang 11GCC 10.2AMD AOCC 2.33691215Min: 6.5 / Avg: 6.88 / Max: 7.25Min: 8.89 / Avg: 9.37 / Max: 9.64Min: 5.46 / Avg: 5.62 / Max: 5.721. (CXX) g++ options: -O3 -march=znver2 -rdynamic -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU-v3-v3 - Model: mobilenet-v3LLVM Clang 11GCC 10.2AMD AOCC 2.3246810SE +/- 0.06, N = 15SE +/- 0.11, N = 3SE +/- 0.04, N = 36.878.885.20-lomp - MIN: 6.16 / MAX: 8.64-lgomp - MIN: 8.58 / MAX: 10.83-lomp - MIN: 5.05 / MAX: 7.611. (CXX) g++ options: -O3 -march=znver2 -rdynamic -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU-v3-v3 - Model: mobilenet-v3LLVM Clang 11GCC 10.2AMD AOCC 2.33691215Min: 6.38 / Avg: 6.87 / Max: 7.2Min: 8.69 / Avg: 8.88 / Max: 9.08Min: 5.15 / Avg: 5.2 / Max: 5.281. (CXX) g++ options: -O3 -march=znver2 -rdynamic -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: shufflenet-v2LLVM Clang 11GCC 10.2AMD AOCC 2.33691215SE +/- 0.02, N = 15SE +/- 0.68, N = 3SE +/- 0.12, N = 37.3510.596.25-lomp - MIN: 7.09 / MAX: 11.01-lgomp - MIN: 9.42 / MAX: 13.72-lomp - MIN: 5.96 / MAX: 6.531. (CXX) g++ options: -O3 -march=znver2 -rdynamic -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: shufflenet-v2LLVM Clang 11GCC 10.2AMD AOCC 2.33691215Min: 7.18 / Avg: 7.35 / Max: 7.49Min: 9.78 / Avg: 10.59 / Max: 11.94Min: 6.02 / Avg: 6.25 / Max: 6.381. (CXX) g++ options: -O3 -march=znver2 -rdynamic -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: mnasnetLLVM Clang 11GCC 10.2AMD AOCC 2.33691215SE +/- 0.09, N = 15SE +/- 0.29, N = 3SE +/- 0.03, N = 36.268.955.01-lomp - MIN: 5.63 / MAX: 8.5-lgomp - MIN: 8.26 / MAX: 11.03-lomp - MIN: 4.87 / MAX: 5.391. (CXX) g++ options: -O3 -march=znver2 -rdynamic -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: mnasnetLLVM Clang 11GCC 10.2AMD AOCC 2.33691215Min: 5.72 / Avg: 6.26 / Max: 6.85Min: 8.39 / Avg: 8.95 / Max: 9.39Min: 4.96 / Avg: 5.01 / Max: 5.071. (CXX) g++ options: -O3 -march=znver2 -rdynamic -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: efficientnet-b0LLVM Clang 11GCC 10.2AMD AOCC 2.33691215SE +/- 0.09, N = 15SE +/- 0.09, N = 3SE +/- 0.05, N = 38.7711.326.94-lomp - MIN: 7.99 / MAX: 13.6-lgomp - MIN: 11.03 / MAX: 13.16-lomp - MIN: 6.72 / MAX: 91. (CXX) g++ options: -O3 -march=znver2 -rdynamic -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: efficientnet-b0LLVM Clang 11GCC 10.2AMD AOCC 2.33691215Min: 8.15 / Avg: 8.77 / Max: 9.27Min: 11.15 / Avg: 11.32 / Max: 11.47Min: 6.89 / Avg: 6.94 / Max: 7.041. (CXX) g++ options: -O3 -march=znver2 -rdynamic -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: blazefaceLLVM Clang 11GCC 10.2AMD AOCC 2.30.89781.79562.69343.59124.489SE +/- 0.02, N = 15SE +/- 0.10, N = 3SE +/- 0.03, N = 32.843.992.19-lomp - MIN: 2.67 / MAX: 4.67-lgomp - MIN: 3.77 / MAX: 4.73-lomp - MIN: 2.1 / MAX: 2.431. (CXX) g++ options: -O3 -march=znver2 -rdynamic -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: blazefaceLLVM Clang 11GCC 10.2AMD AOCC 2.3246810Min: 2.75 / Avg: 2.84 / Max: 2.96Min: 3.86 / Avg: 3.99 / Max: 4.2Min: 2.14 / Avg: 2.19 / Max: 2.251. (CXX) g++ options: -O3 -march=znver2 -rdynamic -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: googlenetLLVM Clang 11GCC 10.2AMD AOCC 2.3510152025SE +/- 0.27, N = 15SE +/- 0.10, N = 3SE +/- 0.05, N = 318.8820.8516.51-lomp - MIN: 16.91 / MAX: 23.31-lgomp - MIN: 19.8 / MAX: 22.84-lomp - MIN: 16.26 / MAX: 18.751. (CXX) g++ options: -O3 -march=znver2 -rdynamic -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: googlenetLLVM Clang 11GCC 10.2AMD AOCC 2.3510152025Min: 17.74 / Avg: 18.88 / Max: 20.85Min: 20.66 / Avg: 20.85 / Max: 20.96Min: 16.44 / Avg: 16.51 / Max: 16.611. (CXX) g++ options: -O3 -march=znver2 -rdynamic -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: vgg16LLVM Clang 11GCC 10.2AMD AOCC 2.3816243240SE +/- 0.42, N = 15SE +/- 0.30, N = 3SE +/- 0.31, N = 336.6030.8932.03-lomp - MIN: 32.93 / MAX: 48.08-lgomp - MIN: 30.04 / MAX: 50.21-lomp - MIN: 30.86 / MAX: 35.21. (CXX) g++ options: -O3 -march=znver2 -rdynamic -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: vgg16LLVM Clang 11GCC 10.2AMD AOCC 2.3816243240Min: 33.89 / Avg: 36.6 / Max: 38.77Min: 30.55 / Avg: 30.89 / Max: 31.49Min: 31.4 / Avg: 32.03 / Max: 32.341. (CXX) g++ options: -O3 -march=znver2 -rdynamic -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: resnet18LLVM Clang 11GCC 10.2AMD AOCC 2.33691215SE +/- 0.12, N = 15SE +/- 0.09, N = 3SE +/- 0.15, N = 313.1913.1211.99-lomp - MIN: 12.17 / MAX: 23.53-lgomp - MIN: 12.79 / MAX: 15.11-lomp - MIN: 11.71 / MAX: 14.271. (CXX) g++ options: -O3 -march=znver2 -rdynamic -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: resnet18LLVM Clang 11GCC 10.2AMD AOCC 2.348121620Min: 12.3 / Avg: 13.19 / Max: 13.86Min: 13.03 / Avg: 13.12 / Max: 13.31Min: 11.82 / Avg: 11.99 / Max: 12.281. (CXX) g++ options: -O3 -march=znver2 -rdynamic -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: alexnetLLVM Clang 11GCC 10.2AMD AOCC 2.33691215SE +/- 0.18, N = 15SE +/- 0.14, N = 3SE +/- 0.01, N = 310.839.468.94-lomp - MIN: 9.15 / MAX: 60.4-lgomp - MIN: 9.17 / MAX: 11.49-lomp - MIN: 8.81 / MAX: 13.491. (CXX) g++ options: -O3 -march=znver2 -rdynamic -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: alexnetLLVM Clang 11GCC 10.2AMD AOCC 2.33691215Min: 9.41 / Avg: 10.83 / Max: 11.62Min: 9.28 / Avg: 9.46 / Max: 9.73Min: 8.92 / Avg: 8.94 / Max: 8.961. (CXX) g++ options: -O3 -march=znver2 -rdynamic -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: resnet50LLVM Clang 11GCC 10.2AMD AOCC 2.3612182430SE +/- 0.20, N = 15SE +/- 0.16, N = 3SE +/- 0.18, N = 322.2323.7019.70-lomp - MIN: 20.63 / MAX: 31.79-lgomp - MIN: 23.21 / MAX: 25.68-lomp - MIN: 19.16 / MAX: 22.411. (CXX) g++ options: -O3 -march=znver2 -rdynamic -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: resnet50LLVM Clang 11GCC 10.2AMD AOCC 2.3612182430Min: 20.8 / Avg: 22.23 / Max: 23.38Min: 23.39 / Avg: 23.7 / Max: 23.93Min: 19.37 / Avg: 19.7 / Max: 201. (CXX) g++ options: -O3 -march=znver2 -rdynamic -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: yolov4-tinyLLVM Clang 11GCC 10.2AMD AOCC 2.3714212835SE +/- 0.19, N = 15SE +/- 0.12, N = 3SE +/- 0.15, N = 330.7029.4729.38-lomp - MIN: 29.08 / MAX: 40.6-lgomp - MIN: 28.89 / MAX: 31.49-lomp - MIN: 28.77 / MAX: 31.681. (CXX) g++ options: -O3 -march=znver2 -rdynamic -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20200916Target: CPU - Model: yolov4-tinyLLVM Clang 11GCC 10.2AMD AOCC 2.3714212835Min: 29.41 / Avg: 30.7 / Max: 31.89Min: 29.25 / Avg: 29.47 / Max: 29.65Min: 29.08 / Avg: 29.38 / Max: 29.541. (CXX) g++ options: -O3 -march=znver2 -rdynamic -lpthread

TNN

TNN is an open-source deep learning reasoning framework developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.2.3Target: CPU - Model: MobileNet v2LLVM Clang 11GCC 10.2AMD AOCC 2.390180270360450SE +/- 0.45, N = 3SE +/- 0.62, N = 3SE +/- 0.24, N = 3392.20324.17365.39-fopenmp=libomp - MIN: 390.71 / MAX: 393.87-fopenmp - MIN: 311.9 / MAX: 354.48-fopenmp=libomp - MIN: 364.57 / MAX: 366.341. (CXX) g++ options: -O3 -march=znver2 -pthread -fvisibility=hidden -rdynamic -ldl
OpenBenchmarking.orgms, Fewer Is BetterTNN 0.2.3Target: CPU - Model: MobileNet v2LLVM Clang 11GCC 10.2AMD AOCC 2.370140210280350Min: 391.41 / Avg: 392.2 / Max: 392.99Min: 323.06 / Avg: 324.17 / Max: 325.19Min: 364.94 / Avg: 365.39 / Max: 365.781. (CXX) g++ options: -O3 -march=znver2 -pthread -fvisibility=hidden -rdynamic -ldl

OpenBenchmarking.orgms, Fewer Is BetterTNN 0.2.3Target: CPU - Model: SqueezeNet v1.1LLVM Clang 11GCC 10.2AMD AOCC 2.370140210280350SE +/- 1.92, N = 3SE +/- 0.20, N = 3SE +/- 0.66, N = 3311.68305.13304.18-fopenmp=libomp - MIN: 306.99 / MAX: 314.32-fopenmp - MIN: 304.36 / MAX: 306.06-fopenmp=libomp - MIN: 302.78 / MAX: 315.911. (CXX) g++ options: -O3 -march=znver2 -pthread -fvisibility=hidden -rdynamic -ldl
OpenBenchmarking.orgms, Fewer Is BetterTNN 0.2.3Target: CPU - Model: SqueezeNet v1.1LLVM Clang 11GCC 10.2AMD AOCC 2.360120180240300Min: 307.85 / Avg: 311.68 / Max: 313.86Min: 304.92 / Avg: 305.13 / Max: 305.53Min: 303.33 / Avg: 304.18 / Max: 305.471. (CXX) g++ options: -O3 -march=znver2 -pthread -fvisibility=hidden -rdynamic -ldl

Timed MrBayes Analysis

This test performs a bayesian analysis of a set of primate genome sequences in order to estimate their phylogeny. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MrBayes Analysis 3.2.7Primate Phylogeny AnalysisLLVM Clang 11GCC 10.2AMD AOCC 2.320406080100SE +/- 0.04, N = 3SE +/- 0.17, N = 3SE +/- 0.04, N = 393.8494.2890.76-mabm1. (CC) gcc options: -mmmx -msse -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -msha -maes -mavx -mfma -mavx2 -mrdrnd -mbmi -mbmi2 -madx -O3 -std=c99 -pedantic -march=znver2 -lm
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MrBayes Analysis 3.2.7Primate Phylogeny AnalysisLLVM Clang 11GCC 10.2AMD AOCC 2.320406080100Min: 93.76 / Avg: 93.84 / Max: 93.89Min: 94.02 / Avg: 94.28 / Max: 94.61Min: 90.71 / Avg: 90.76 / Max: 90.841. (CC) gcc options: -mmmx -msse -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -msha -maes -mavx -mfma -mavx2 -mrdrnd -mbmi -mbmi2 -madx -O3 -std=c99 -pedantic -march=znver2 -lm

C-Ray

This is a test of C-Ray, a simple raytracer designed to test the floating-point CPU performance. This test is multi-threaded (16 threads per core), will shoot 8 rays per pixel for anti-aliasing, and will generate a 1600 x 1200 image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per PixelLLVM Clang 11GCC 10.2AMD AOCC 2.3816243240SE +/- 0.08, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 330.6518.9233.281. (CC) gcc options: -lm -lpthread -O3 -march=znver2
OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per PixelLLVM Clang 11GCC 10.2AMD AOCC 2.3714212835Min: 30.52 / Avg: 30.65 / Max: 30.8Min: 18.88 / Avg: 18.92 / Max: 18.94Min: 33.2 / Avg: 33.27 / Max: 33.391. (CC) gcc options: -lm -lpthread -O3 -march=znver2

AOBench

AOBench is a lightweight ambient occlusion renderer, written in C. The test profile is using a size of 2048 x 2048. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterAOBenchSize: 2048 x 2048 - Total TimeLLVM Clang 11GCC 10.2AMD AOCC 2.31020304050SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 341.6635.7837.761. (CC) gcc options: -lm -O3 -march=znver2
OpenBenchmarking.orgSeconds, Fewer Is BetterAOBenchSize: 2048 x 2048 - Total TimeLLVM Clang 11GCC 10.2AMD AOCC 2.3918273645Min: 41.61 / Avg: 41.66 / Max: 41.68Min: 35.76 / Avg: 35.78 / Max: 35.82Min: 37.72 / Avg: 37.76 / Max: 37.831. (CC) gcc options: -lm -O3 -march=znver2

LAME MP3 Encoding

LAME is an MP3 encoder licensed under the LGPL. This test measures the time required to encode a WAV file to MP3 format. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterLAME MP3 Encoding 3.100WAV To MP3LLVM Clang 11GCC 10.2AMD AOCC 2.33691215SE +/- 0.003, N = 3SE +/- 0.004, N = 3SE +/- 0.004, N = 310.0788.79811.026-ffast-math -funroll-loops -fschedule-insns2 -fbranch-count-reg -fforce-addr1. (CC) gcc options: -O3 -pipe -march=znver2 -lncurses -lm
OpenBenchmarking.orgSeconds, Fewer Is BetterLAME MP3 Encoding 3.100WAV To MP3LLVM Clang 11GCC 10.2AMD AOCC 2.33691215Min: 10.07 / Avg: 10.08 / Max: 10.09Min: 8.79 / Avg: 8.8 / Max: 8.8Min: 11.02 / Avg: 11.03 / Max: 11.031. (CC) gcc options: -O3 -pipe -march=znver2 -lncurses -lm

RNNoise

RNNoise is a recurrent neural network for audio noise reduction developed by Mozilla and Xiph.Org. This test profile is a single-threaded test measuring the time to denoise a sample 26 minute long 16-bit RAW audio file using this recurrent neural network noise suppression library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRNNoise 2020-06-28LLVM Clang 11GCC 10.2AMD AOCC 2.3510152025SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 321.5421.7220.761. (CC) gcc options: -O3 -march=znver2 -pedantic -fvisibility=hidden
OpenBenchmarking.orgSeconds, Fewer Is BetterRNNoise 2020-06-28LLVM Clang 11GCC 10.2AMD AOCC 2.3510152025Min: 21.54 / Avg: 21.54 / Max: 21.55Min: 21.68 / Avg: 21.72 / Max: 21.76Min: 20.73 / Avg: 20.76 / Max: 20.771. (CC) gcc options: -O3 -march=znver2 -pedantic -fvisibility=hidden

ASTC Encoder

ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.0Preset: MediumLLVM Clang 11GCC 10.2AMD AOCC 2.3246810SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 36.057.005.811. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.0Preset: MediumLLVM Clang 11GCC 10.2AMD AOCC 2.33691215Min: 6.02 / Avg: 6.05 / Max: 6.06Min: 6.99 / Avg: 7 / Max: 7.02Min: 5.8 / Avg: 5.81 / Max: 5.821. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.0Preset: ThoroughLLVM Clang 11GCC 10.2AMD AOCC 2.33691215SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 38.329.618.161. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.0Preset: ThoroughLLVM Clang 11GCC 10.2AMD AOCC 2.33691215Min: 8.32 / Avg: 8.32 / Max: 8.32Min: 9.6 / Avg: 9.61 / Max: 9.61Min: 8.16 / Avg: 8.16 / Max: 8.161. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread

OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.0Preset: ExhaustiveLLVM Clang 11GCC 10.2AMD AOCC 2.31632486480SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 367.1773.4666.041. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterASTC Encoder 2.0Preset: ExhaustiveLLVM Clang 11GCC 10.2AMD AOCC 2.31428425670Min: 67.16 / Avg: 67.17 / Max: 67.19Min: 73.42 / Avg: 73.46 / Max: 73.48Min: 65.98 / Avg: 66.04 / Max: 66.131. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread

Basis Universal

Basis Universal is a GPU texture codoec. This test times how long it takes to convert sRGB PNGs into Basis Univeral assets with various settings. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.12Settings: UASTC Level 2LLVM Clang 11GCC 10.2AMD AOCC 2.348121620SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 316.4916.5116.321. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.12Settings: UASTC Level 2LLVM Clang 11GCC 10.2AMD AOCC 2.348121620Min: 16.47 / Avg: 16.49 / Max: 16.5Min: 16.48 / Avg: 16.51 / Max: 16.54Min: 16.29 / Avg: 16.31 / Max: 16.331. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.12Settings: UASTC Level 3LLVM Clang 11GCC 10.2AMD AOCC 2.3612182430SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 325.3225.5225.211. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.12Settings: UASTC Level 3LLVM Clang 11GCC 10.2AMD AOCC 2.3612182430Min: 25.31 / Avg: 25.32 / Max: 25.33Min: 25.51 / Avg: 25.52 / Max: 25.53Min: 25.2 / Avg: 25.21 / Max: 25.221. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.12Settings: UASTC Level 2 + RDO Post-ProcessingLLVM Clang 11GCC 10.2AMD AOCC 2.32004006008001000SE +/- 0.24, N = 3SE +/- 0.14, N = 3SE +/- 0.04, N = 3837.54755.52833.541. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterBasis Universal 1.12Settings: UASTC Level 2 + RDO Post-ProcessingLLVM Clang 11GCC 10.2AMD AOCC 2.3150300450600750Min: 837.07 / Avg: 837.54 / Max: 837.8Min: 755.36 / Avg: 755.52 / Max: 755.81Min: 833.47 / Avg: 833.54 / Max: 833.611. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread

SQLite Speedtest

This is a benchmark of SQLite's speedtest1 benchmark program with an increased problem size of 1,000. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite Speedtest 3.30Timed Time - Size 1,000LLVM Clang 11GCC 10.2AMD AOCC 2.320406080100SE +/- 0.18, N = 3SE +/- 0.13, N = 3SE +/- 0.09, N = 377.6475.1478.071. (CC) gcc options: -O3 -march=znver2 -ldl -lz -lpthread
OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite Speedtest 3.30Timed Time - Size 1,000LLVM Clang 11GCC 10.2AMD AOCC 2.31530456075Min: 77.44 / Avg: 77.64 / Max: 78Min: 74.96 / Avg: 75.14 / Max: 75.4Min: 77.88 / Avg: 78.07 / Max: 78.191. (CC) gcc options: -O3 -march=znver2 -ldl -lz -lpthread

Geometric Mean Of All Test Results

OpenBenchmarking.orgGeometric Mean, More Is BetterGeometric Mean Of All Test ResultsResult Composite - EPYC 7502 AOCC 2.3 Compiler ComparisonLLVM Clang 11GCC 10.2AMD AOCC 2.3306090120150115.39113.07121.37

Number Of First Place Finishes

LLVM Clang 1111 [12.4%]GCC 10.217 [19.1%]AMD AOCC 2.361 [68.5%]Number Of First Place FinishesWins - 89 TestsOpenBenchmarking.org

Number Of Last Place Finishes

LLVM Clang 1123 [25.8%]GCC 10.256 [62.9%]AMD AOCC 2.310 [11.2%]Number Of Last Place FinishesLosses - 89 TestsOpenBenchmarking.org

92 Results Shown

dav1d:
  Chimera 1080p
  Summer Nature 4K
  Summer Nature 1080p
  Chimera 1080p 10-bit
SVT-AV1:
  Enc Mode 0 - 1080p
  Enc Mode 4 - 1080p
  Enc Mode 8 - 1080p
SVT-VP9:
  VMAF Optimized - Bosphorus 1080p
  PSNR/SSIM Optimized - Bosphorus 1080p
  Visual Quality Optimized - Bosphorus 1080p
VP9 libvpx Encoding:
  Speed 0
  Speed 5
x264
x265:
  Bosphorus 4K
  Bosphorus 1080p
GraphicsMagick:
  Swirl
  Rotate
  Sharpen
  Enhanced
  Resizing
LZ4 Compression:
  1 - Compression Speed
  3 - Compression Speed
  9 - Compression Speed
Zstd Compression:
  3
  19
libjpeg-turbo tjbench
SciMark
Crypto++
LibRaw
TSCP
Stockfish
Hierarchical INTegration
Redis:
  LPUSH
  GET
  SET
NGINX Benchmark
OpenSSL
Darmstadt Automotive Parallel Heterogeneous Suite:
  OpenMP - NDT Mapping
  OpenMP - Points2Image
  OpenMP - Euclidean Cluster
PostgreSQL pgbench:
  1 - 1 - Read Only
  1 - 1 - Read Write
  1 - 50 - Read Only
  1 - 50 - Read Write
WebP Image Encode:
  Quality 100, Lossless
  Quality 100, Highest Compression
  Quality 100, Lossless, Highest Compression
oneDNN:
  IP Batch 1D - f32 - CPU
  IP Batch 1D - u8s8f32 - CPU
  IP Batch All - u8s8f32 - CPU
  Deconvolution Batch deconv_1d - f32 - CPU
  Deconvolution Batch deconv_3d - f32 - CPU
  Deconvolution Batch deconv_1d - u8s8f32 - CPU
  Deconvolution Batch deconv_3d - u8s8f32 - CPU
  Recurrent Neural Network Training - f32 - CPU
  Recurrent Neural Network Inference - f32 - CPU
  Matrix Multiply Batch Shapes Transformer - f32 - CPU
PostgreSQL pgbench:
  1 - 1 - Read Only - Average Latency
  1 - 1 - Read Write - Average Latency
  1 - 50 - Read Only - Average Latency
  1 - 50 - Read Write - Average Latency
NCNN:
  CPU - squeezenet
  CPU - mobilenet
  CPU-v2-v2 - mobilenet-v2
  CPU-v3-v3 - mobilenet-v3
  CPU - shufflenet-v2
  CPU - mnasnet
  CPU - efficientnet-b0
  CPU - blazeface
  CPU - googlenet
  CPU - vgg16
  CPU - resnet18
  CPU - alexnet
  CPU - resnet50
  CPU - yolov4-tiny
TNN:
  CPU - MobileNet v2
  CPU - SqueezeNet v1.1
Timed MrBayes Analysis
C-Ray
AOBench
LAME MP3 Encoding
RNNoise
ASTC Encoder:
  Medium
  Thorough
  Exhaustive
Basis Universal:
  UASTC Level 2
  UASTC Level 3
  UASTC Level 2 + RDO Post-Processing
SQLite Speedtest
Geometric Mean Of All Test Results:
  Result Composite - EPYC 7502 AOCC 2.3 Compiler Comparison
  Wins - 89 Tests
  Losses - 89 Tests

AMD AOCC 2.3

Processor: AMD EPYC 7502 32-Core @ 2.50GHz (32 Cores / 64 Threads), Motherboard: ASRockRack EPYCD8 (P2.10 BIOS), Chipset: AMD Starship/Matisse, Memory: 126GB, Disk: 280GB INTEL SSDPED1D280GA, Graphics: ASPEED, Audio: AMD Starship/Matisse, Monitor: VE228, Network: 2 x Intel I350

OS: Ubuntu 20.10, Kernel: 5.8.0-31-generic (x86_64), Desktop: GNOME Shell 3.38.1, Display Server: X Server 1.20.9, Display Driver: modesetting 1.20.9, Compiler: Clang 11.0.0, File-System: ext4, Screen Resolution: 1920x1080

Environment Notes: CXXFLAGS="-O3 -march=znver2" CFLAGS="-O3 -march=znver2"
Compiler Notes: Optimized build with assertions; Default target: x86_64-unknown-linux-gnu; Host CPU: znver2
Processor Notes: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0x830101c
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 IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 7 December 2020 10:27 by user phoronix.

GCC 10.2

Processor: AMD EPYC 7502 32-Core @ 2.50GHz (32 Cores / 64 Threads), Motherboard: ASRockRack EPYCD8 (P2.10 BIOS), Chipset: AMD Starship/Matisse, Memory: 126GB, Disk: 280GB INTEL SSDPED1D280GA, Graphics: ASPEED, Audio: AMD Starship/Matisse, Monitor: VE228, Network: 2 x Intel I350

OS: Ubuntu 20.10, Kernel: 5.8.0-31-generic (x86_64), Desktop: GNOME Shell 3.38.1, Display Server: X Server 1.20.9, Display Driver: modesetting 1.20.9, Compiler: GCC 10.2.0, File-System: ext4, Screen Resolution: 1920x1080

Environment Notes: CXXFLAGS="-O3 -march=znver2" CFLAGS="-O3 -march=znver2"
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-JvwpWM/gcc-10-10.2.0/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-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 ondemand (Boost: Enabled) - CPU Microcode: 0x830101c
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 IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 7 December 2020 16:58 by user phoronix.

LLVM Clang 11

Processor: AMD EPYC 7502 32-Core @ 2.50GHz (32 Cores / 64 Threads), Motherboard: ASRockRack EPYCD8 (P2.10 BIOS), Chipset: AMD Starship/Matisse, Memory: 126GB, Disk: 280GB INTEL SSDPED1D280GA, Graphics: ASPEED, Audio: AMD Starship/Matisse, Monitor: VE228, Network: 2 x Intel I350

OS: Ubuntu 20.10, Kernel: 5.8.0-31-generic (x86_64), Desktop: GNOME Shell 3.38.1, Display Server: X Server 1.20.9, Display Driver: modesetting 1.20.9, Compiler: Clang 11.0.0-2Target:, File-System: ext4, Screen Resolution: 1920x1080

Environment Notes: CXXFLAGS="-O3 -march=znver2" CFLAGS="-O3 -march=znver2"
Processor Notes: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0x830101c
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 IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 8 December 2020 06:09 by user phoronix.