HPC benchmark- POSSIBLE BAD DATA

Intel Core i7-12700K testing with a MSI PRO Z690-A DDR4(MS-7D25) v1.0 (1.15 BIOS) and Gigabyte AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 6GB on Pop 21.04 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 2112081-TJ-2112076TJ12
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:

Bioinformatics 2 Tests
C/C++ Compiler Tests 3 Tests
CPU Massive 11 Tests
Creator Workloads 2 Tests
Fortran Tests 3 Tests
HPC - High Performance Computing 30 Tests
Machine Learning 15 Tests
Molecular Dynamics 5 Tests
MPI Benchmarks 2 Tests
Multi-Core 3 Tests
NVIDIA GPU Compute 3 Tests
OpenMPI Tests 4 Tests
Python 4 Tests
Scientific Computing 12 Tests
Server CPU Tests 5 Tests
Single-Threaded 3 Tests
Speech 2 Tests
Telephony 2 Tests

Statistics

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

Graph Settings

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

Additional Graphs

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

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
Intel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt
December 05 2021
  12 Hours, 53 Minutes
Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt
December 06 2021
  12 Hours, 28 Minutes
Intel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt
December 06 2021
  14 Hours, 10 Minutes
Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xt
December 08 2021
  6 Hours, 54 Minutes
Invert Hiding All Results Option
  11 Hours, 36 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):


HPC benchmark- POSSIBLE BAD DATAProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLOpenCLVulkanCompilerFile-SystemScreen ResolutionIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700K @ 6.30GHz (8 Cores / 16 Threads)MSI PRO Z690-A DDR4(MS-7D25) v1.0 (1.15 BIOS)Intel Device 7aa732GB500GB Western Digital WDS500G2B0C-00PXH0 + 3 x 10001GB Seagate ST10000DM0004-1Z + 128GB HP SSD S700 ProGigabyte AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 (1650/750MHz)Realtek ALC897LG HDR WQHDIntel I225-VPop 21.045.15.5-76051505-generic (x86_64)GNOME Shell 3.38.4X Server 1.20.114.6 Mesa 21.3.0-devel (LLVM 12.0.1)OpenCL 1.2 Intel FPGA SDK for OpenCL 20.3 + OpenCL 3.0 LINUX + OpenCL 2.2 AMD-APP (3361.0)1.2.182GCC 10.3.0 + Intel oneAPI DPC++/C++ Compiler 2021.4.0 (2021.4.0.20210924) + ICC 2021.4.0 20210910 + CUDA 10.2ext43440x1440Intel Core i7-12700K @ 6.30GHz (12 Cores / 20 Threads)Intel Core i7-12700K @ 6.50GHz (8 Cores / 16 Threads)Gigabyte AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 6GB (1650/750MHz)4.6 Mesa 21.2.2 (LLVM 12.0.0)OpenCL 1.2 Intel FPGA SDK for OpenCL 20.3 + OpenCL 3.0 LINUXGCC 11.1.0 + Intel oneAPI DPC++/C++ Compiler 2021.4.0 (2021.4.0.20210924) + ICC 2021.4.0 20210910OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseEnvironment Details- Intel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt : CXXFLAGS="-O3 -march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect" CFLAGS="-O3 -march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect"- Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt: CXXFLAGS="-O3 -march=native" CFLAGS="-O3 -march=native"- Intel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt: CXXFLAGS="-O3 -march=native" CFLAGS="-O3 -march=native"- Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xt: CXXFLAGS="-O3 -march=sapphirerapids -mno-amx-tile -mno-amx-int8 -mno-amx-bf16" CFLAGS="-O3 -march=sapphirerapids -mno-amx-tile -mno-amx-int8 -mno-amx-bf16"Compiler Details- Intel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt : --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-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/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-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 - Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt: --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-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/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-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 - Intel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt: --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-gDeRY6/gcc-10-10.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-gDeRY6/gcc-10-10.3.0/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-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 - Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xt: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-RPS7jb/gcc-11-11.1.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-RPS7jb/gcc-11-11.1.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Disk Details- Intel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt : NONE / errors=remount-ro,noatime,rw / Block Size: 4096Processor Details- Scaling Governor: intel_pstate powersave - CPU Microcode: 0x15 - Thermald 2.4.3Graphics Details- GLAMOR - BAR1 / Visible vRAM Size: 6128 MBPython Details- Intel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt : Python 3.7.11 :: Intel- Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt: Python 3.7.11 :: Intel- Intel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt: Python 3.7.11 :: Intel- Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xt: Python 3.9.5Security Details- 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 Enhanced IBRS IBPB: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 4096Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt 9K18K27K36K45KSE +/- 301.86, N = 3SE +/- 522.29, N = 9SE +/- 932.44, N = 7SE +/- 293.32, N = 343777433364251640789-mno-amx-tile -mno-amx-int8 -mno-amx-bf16-march=native-march=native-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect1. (CC) gcc options: -pthread -O3 -lm

CloverLeaf

CloverLeaf is a Lagrangian-Eulerian hydrodynamics benchmark. This test profile currently makes use of CloverLeaf's OpenMP version and benchmarked with the clover_bm.in input file (Problem 5). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterCloverLeafLagrangian-Eulerian HydrodynamicsIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt4080120160200SE +/- 0.42, N = 3SE +/- 1.45, N = 3SE +/- 2.66, N = 12SE +/- 18.74, N = 9138.33141.53186.74191.331. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp

PlaidML

This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: ResNet 50 - Device: CPUIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt3691215SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.25, N = 9SE +/- 0.04, N = 39.398.528.418.32

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 0.3Target: CPU - Model: DenseNetIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt9001800270036004500SE +/- 3.06, N = 3SE +/- 2.71, N = 3SE +/- 40.36, N = 3SE +/- 299.40, N = 92623.162719.822854.853987.72-mno-amx-tile -mno-amx-int8 -mno-amx-bf16 - MIN: 2564.18 / MAX: 2757.86-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect - MIN: 2625.5 / MAX: 3184.86-march=native - MIN: 2660.43 / MAX: 3772.17-march=native - MIN: 2619.64 / MAX: 5569.921. (CXX) g++ options: -O3 -fopenmp -pthread -fvisibility=hidden -fvisibility=default -rdynamic -ldl

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.10Model: yolov4 - Device: CPUIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt110220330440550SE +/- 4.64, N = 12SE +/- 0.44, N = 3SE +/- 5.97, N = 12SE +/- 1.48, N = 3520469468460-mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect-mno-amx-tile -mno-amx-int8 -mno-amx-bf161. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -pthread -lpthread

ECP-CANDLE

The CANDLE benchmark codes implement deep learning architectures relevant to problems in cancer. These architectures address problems at different biological scales, specifically problems at the molecular, cellular and population scales. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterECP-CANDLE 0.4Benchmark: P3B1Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt2004006008001000790.26794.26887.14918.20

Mobile Neural Network

MNN is the Mobile Neural Network as a highly efficient, lightweight deep learning framework developed by Alibaba. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: inception-v3Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt612182430SE +/- 0.04, N = 3SE +/- 0.05, N = 15SE +/- 0.55, N = 15SE +/- 0.37, N = 1221.0223.2825.2326.69-mno-amx-tile -mno-amx-int8 -mno-amx-bf16 - MIN: 19.1 / MAX: 37.33-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect - MIN: 20.16 / MAX: 153.62-march=native - MIN: 20.75 / MAX: 242.75-march=native - MIN: 22.92 / MAX: 195.791. (CXX) g++ options: -O3 -std=c++11 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: mobilenet-v1-1.0Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt0.58791.17581.76372.35162.9395SE +/- 0.007, N = 3SE +/- 0.016, N = 15SE +/- 0.066, N = 15SE +/- 0.016, N = 121.5321.7492.0542.613-mno-amx-tile -mno-amx-int8 -mno-amx-bf16 - MIN: 1.46 / MAX: 12.02-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect - MIN: 1.51 / MAX: 60.38-march=native - MIN: 1.55 / MAX: 55.56-march=native - MIN: 2.48 / MAX: 16.011. (CXX) g++ options: -O3 -std=c++11 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: MobileNetV2_224Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt0.57711.15421.73132.30842.8855SE +/- 0.004, N = 3SE +/- 0.021, N = 15SE +/- 0.076, N = 15SE +/- 0.050, N = 121.6161.8922.2172.565-mno-amx-tile -mno-amx-int8 -mno-amx-bf16 - MIN: 1.54 / MAX: 7.39-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect - MIN: 1.59 / MAX: 22.25-march=native - MIN: 1.65 / MAX: 59.17-march=native - MIN: 2.04 / MAX: 63.681. (CXX) g++ options: -O3 -std=c++11 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: SqueezeNetV1.0Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt1.0442.0883.1324.1765.22SE +/- 0.251, N = 3SE +/- 0.051, N = 15SE +/- 0.128, N = 15SE +/- 0.105, N = 123.1653.5904.0604.640-mno-amx-tile -mno-amx-int8 -mno-amx-bf16 - MIN: 2.84 / MAX: 8.57-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect - MIN: 2.83 / MAX: 78.46-march=native - MIN: 2.94 / MAX: 82.76-march=native - MIN: 3.45 / MAX: 47.31. (CXX) g++ options: -O3 -std=c++11 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: resnet-v2-50Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt510152025SE +/- 0.05, N = 3SE +/- 0.06, N = 15SE +/- 0.50, N = 15SE +/- 0.57, N = 1214.7916.6918.4622.62-mno-amx-tile -mno-amx-int8 -mno-amx-bf16 - MIN: 14.1 / MAX: 42.25-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect - MIN: 14.63 / MAX: 104.64-march=native - MIN: 14.88 / MAX: 173.91-march=native - MIN: 19.41 / MAX: 83.451. (CXX) g++ options: -O3 -std=c++11 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: squeezenetv1.1Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt0.64461.28921.93382.57843.223SE +/- 0.010, N = 3SE +/- 0.022, N = 15SE +/- 0.078, N = 15SE +/- 0.110, N = 122.0452.2642.5592.865-mno-amx-tile -mno-amx-int8 -mno-amx-bf16 - MIN: 1.99 / MAX: 8.27-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect - MIN: 1.95 / MAX: 45.84-march=native - MIN: 1.99 / MAX: 49.19-march=native - MIN: 2.23 / MAX: 52.161. (CXX) g++ options: -O3 -std=c++11 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 1.2Model: mobilenetV3Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt0.28370.56740.85111.13481.4185SE +/- 0.001, N = 3SE +/- 0.016, N = 15SE +/- 0.037, N = 15SE +/- 0.017, N = 120.9631.1131.2371.261-mno-amx-tile -mno-amx-int8 -mno-amx-bf16 - MIN: 0.93 / MAX: 4.84-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect - MIN: 0.93 / MAX: 16.19-march=native - MIN: 0.95 / MAX: 40.28-march=native - MIN: 1.08 / MAX: 48.361. (CXX) g++ options: -O3 -std=c++11 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenCV

This is a benchmark of the OpenCV (Computer Vision) library's built-in performance tests. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenCV 4.5.4Test: DNN - Deep Neural NetworkIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt20K40K60K80K100KSE +/- 245.00, N = 15SE +/- 713.19, N = 15SE +/- 1166.72, N = 15SE +/- 3031.05, N = 127537522476663791035-march=native -ldl -lm -lpthread -lrt-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect -ldl -lm -lpthread -lrt-march=native -ldl -lm -lpthread -lrt1. (CXX) g++ options: -O3 -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -fvisibility=hidden

I'll need to retest the other setups here, something seems VERY wrong

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 20210720Target: CPU - Model: regnety_400mIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt246810SE +/- 0.01, N = 3SE +/- 0.01, N = 15SE +/- 0.20, N = 15SE +/- 0.55, N = 154.715.556.807.44-mno-amx-tile -mno-amx-int8 -mno-amx-bf16 - MIN: 4.58 / MAX: 6.32-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect - MIN: 4.92 / MAX: 31.26-march=native - MIN: 6.23 / MAX: 15.86-march=native - MIN: 5.34 / MAX: 398.21. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: squeezenet_ssdIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt48121620SE +/- 0.02, N = 3SE +/- 0.02, N = 15SE +/- 0.52, N = 15SE +/- 0.72, N = 1512.0613.4114.8515.89-mno-amx-tile -mno-amx-int8 -mno-amx-bf16 - MIN: 11.82 / MAX: 17.26-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect - MIN: 12.41 / MAX: 45.1-march=native - MIN: 13.57 / MAX: 63.1-march=native - MIN: 12.62 / MAX: 489.071. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: yolov4-tinyIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt48121620SE +/- 0.20, N = 3SE +/- 0.13, N = 15SE +/- 0.43, N = 15SE +/- 0.44, N = 1514.0515.3417.3317.62-mno-amx-tile -mno-amx-int8 -mno-amx-bf16 - MIN: 13.36 / MAX: 28.81-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect - MIN: 13.6 / MAX: 60.85-march=native - MIN: 14.49 / MAX: 220.15-march=native - MIN: 15.29 / MAX: 370.581. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: resnet50Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt510152025SE +/- 0.23, N = 3SE +/- 0.11, N = 15SE +/- 0.58, N = 15SE +/- 0.32, N = 1515.2216.3819.4120.01-mno-amx-tile -mno-amx-int8 -mno-amx-bf16 - MIN: 14.63 / MAX: 21.4-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect - MIN: 14.75 / MAX: 169.63-march=native - MIN: 15.46 / MAX: 404.54-march=native - MIN: 18.29 / MAX: 72.61. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: alexnetIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt3691215SE +/- 0.01, N = 3SE +/- 0.05, N = 15SE +/- 0.31, N = 15SE +/- 0.06, N = 158.389.2910.6411.23-mno-amx-tile -mno-amx-int8 -mno-amx-bf16 - MIN: 8.27 / MAX: 14.31-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect - MIN: 8.58 / MAX: 188.45-march=native - MIN: 8.84 / MAX: 348.67-march=native - MIN: 10.78 / MAX: 35.581. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: resnet18Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt3691215SE +/- 0.03, N = 3SE +/- 0.05, N = 15SE +/- 0.21, N = 15SE +/- 0.65, N = 159.2310.3711.7413.24-mno-amx-tile -mno-amx-int8 -mno-amx-bf16 - MIN: 9.03 / MAX: 29.68-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect - MIN: 9.43 / MAX: 107.77-march=native - MIN: 10.66 / MAX: 43.48-march=native - MIN: 9.67 / MAX: 377.981. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: vgg16Intel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt1020304050SE +/- 0.15, N = 15SE +/- 0.31, N = 3SE +/- 0.40, N = 15SE +/- 1.09, N = 1537.7337.9140.6143.97-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect - MIN: 35.14 / MAX: 288.51-mno-amx-tile -mno-amx-int8 -mno-amx-bf16 - MIN: 37.18 / MAX: 80.66-march=native - MIN: 38.83 / MAX: 98.35-march=native - MIN: 36.31 / MAX: 485.441. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: googlenetIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt3691215SE +/- 0.04, N = 3SE +/- 0.15, N = 15SE +/- 0.27, N = 15SE +/- 0.39, N = 157.639.0010.3410.43-mno-amx-tile -mno-amx-int8 -mno-amx-bf16 - MIN: 7.41 / MAX: 17.97-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect - MIN: 7.77 / MAX: 212.02-march=native - MIN: 9.1 / MAX: 35.14-march=native - MIN: 8.03 / MAX: 223.751. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: blazefaceIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt0.27230.54460.81691.08921.3615SE +/- 0.01, N = 3SE +/- 0.00, N = 15SE +/- 0.04, N = 15SE +/- 0.04, N = 150.911.021.211.21-mno-amx-tile -mno-amx-int8 -mno-amx-bf16 - MIN: 0.88 / MAX: 4.07-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect - MIN: 0.93 / MAX: 3.99-march=native - MIN: 0.93 / MAX: 35.68-march=native - MIN: 1.05 / MAX: 6.941. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: efficientnet-b0Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt1.00582.01163.01744.02325.029SE +/- 0.01, N = 3SE +/- 0.02, N = 15SE +/- 0.20, N = 15SE +/- 0.12, N = 152.903.374.354.47-mno-amx-tile -mno-amx-int8 -mno-amx-bf16 - MIN: 2.83 / MAX: 3.97-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect - MIN: 2.95 / MAX: 16.3-march=native - MIN: 3.03 / MAX: 261.53-march=native - MIN: 3.96 / MAX: 34.651. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: mnasnetIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt0.6481.2961.9442.5923.24SE +/- 0.01, N = 3SE +/- 0.01, N = 14SE +/- 0.12, N = 14SE +/- 0.12, N = 151.852.122.722.88-mno-amx-tile -mno-amx-int8 -mno-amx-bf16 - MIN: 1.79 / MAX: 2.88-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect - MIN: 1.86 / MAX: 5.63-march=native - MIN: 1.95 / MAX: 218.37-march=native - MIN: 2.43 / MAX: 186.851. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: shufflenet-v2Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt0.7111.4222.1332.8443.555SE +/- 0.00, N = 3SE +/- 0.01, N = 14SE +/- 0.07, N = 14SE +/- 0.31, N = 152.182.392.673.16-mno-amx-tile -mno-amx-int8 -mno-amx-bf16 - MIN: 2.1 / MAX: 6.91-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect - MIN: 2.14 / MAX: 6.73-march=native - MIN: 2.45 / MAX: 10.63-march=native - MIN: 2.17 / MAX: 324.421. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU-v3-v3 - Model: mobilenet-v3Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt0.61881.23761.85642.47523.094SE +/- 0.01, N = 3SE +/- 0.01, N = 15SE +/- 0.12, N = 15SE +/- 0.09, N = 151.892.172.742.75-mno-amx-tile -mno-amx-int8 -mno-amx-bf16 - MIN: 1.83 / MAX: 2.92-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect - MIN: 1.87 / MAX: 11.1-march=native - MIN: 1.97 / MAX: 173.37-march=native - MIN: 2.43 / MAX: 270.921. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU-v2-v2 - Model: mobilenet-v2Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt0.69751.3952.09252.793.4875SE +/- 0.01, N = 3SE +/- 0.01, N = 15SE +/- 0.12, N = 15SE +/- 0.15, N = 152.152.382.983.10-mno-amx-tile -mno-amx-int8 -mno-amx-bf16 - MIN: 2.08 / MAX: 5.56-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect - MIN: 2.09 / MAX: 19.16-march=native - MIN: 2.18 / MAX: 280.99-march=native - MIN: 2.73 / MAX: 4101. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: mobilenetIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt3691215SE +/- 0.10, N = 3SE +/- 0.12, N = 15SE +/- 0.34, N = 15SE +/- 0.31, N = 158.639.0710.7411.06-mno-amx-tile -mno-amx-int8 -mno-amx-bf16 - MIN: 8.28 / MAX: 13.76-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect - MIN: 7.88 / MAX: 149.11-march=native - MIN: 8.38 / MAX: 272.88-march=native - MIN: 9.8 / MAX: 493.361. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.10Model: shufflenet-v2-10 - Device: CPUIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xt10K20K30K40K50KSE +/- 46.94, N = 3SE +/- 105.96, N = 3SE +/- 181.26, N = 3SE +/- 620.08, N = 1145034428974068839909-mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect-mno-amx-tile -mno-amx-int8 -mno-amx-bf161. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -pthread -lpthread

PyHPC Benchmarks

PyHPC-Benchmarks is a suite of Python high performance computing benchmarks for execution on CPUs and GPUs using various popular Python HPC libraries. The PyHPC CPU-based benchmarks focus on sequential CPU performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Numpy - Project Size: 4194304 - Benchmark: Isoneutral MixingIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt0.47950.9591.43851.9182.3975SE +/- 0.001, N = 3SE +/- 0.001, N = 3SE +/- 0.004, N = 3SE +/- 0.100, N = 151.8471.8612.0212.131

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: NASNet MobileIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt30K60K90K120K150KSE +/- 609.47, N = 3SE +/- 95.70, N = 3SE +/- 2986.13, N = 15SE +/- 6529.38, N = 1289096.6126721.0130527.0154285.0

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 4096Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt 3K6K9K12K15KSE +/- 54.22, N = 3SE +/- 25.36, N = 3SE +/- 24.06, N = 3SE +/- 108.98, N = 814069135681349412945-mno-amx-tile -mno-amx-int8 -mno-amx-bf16-march=native-march=native-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect1. (CC) gcc options: -pthread -O3 -lm

SHOC Scalable HeterOgeneous Computing

The CUDA and OpenCL version of Vetter's Scalable HeterOgeneous Computing benchmark suite. SHOC provides a number of different benchmark programs for evaluating the performance and stability of compute devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Max SP FlopsIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt400K800K1200K1600K2000KSE +/- 44470.87, N = 12SE +/- 76015.19, N = 12SE +/- 38770.78, N = 15SE +/- 87626.15, N = 151723333166723215815431542874-mno-amx-tile -mno-amx-int8 -mno-amx-bf16-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect-march=native-march=native1. (CXX) g++ options: -O3 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -Xlinker --enable-new-dtags -rpath -lmpicxx -lmpifort -lmpi -lpthread -ldl

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.10Model: fcn-resnet101-11 - Device: CPUIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt20406080100SE +/- 0.67, N = 3SE +/- 0.17, N = 3SE +/- 0.00, N = 3SE +/- 0.75, N = 580747468-mno-amx-tile -mno-amx-int8 -mno-amx-bf16-mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -pthread -lpthread

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: Points2ImageIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt7K14K21K28K35KSE +/- 638.53, N = 12SE +/- 274.39, N = 3SE +/- 100.69, N = 3SE +/- 1308.12, N = 1333183.1232570.1626580.0925089.991. (CXX) g++ options: -O3 -std=c++11 -fopenmp

Numpy Benchmark

This is a test to obtain the general Numpy performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterNumpy BenchmarkIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt130260390520650SE +/- 1.67, N = 3SE +/- 1.21, N = 3SE +/- 2.34, N = 3SE +/- 2.53, N = 3615.24565.28558.72422.78

ECP-CANDLE

The CANDLE benchmark codes implement deep learning architectures relevant to problems in cancer. These architectures address problems at different biological scales, specifically problems at the molecular, cellular and population scales. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterECP-CANDLE 0.4Benchmark: P3B2Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt90180270360450353.81401.56403.48409.43

PyHPC Benchmarks

PyHPC-Benchmarks is a suite of Python high performance computing benchmarks for execution on CPUs and GPUs using various popular Python HPC libraries. The PyHPC CPU-based benchmarks focus on sequential CPU performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: PyTorch - Project Size: 4194304 - Benchmark: Isoneutral MixingIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt0.49770.99541.49311.99082.4885SE +/- 0.005, N = 3SE +/- 0.001, N = 3SE +/- 0.016, N = 3SE +/- 0.018, N = 91.3251.3321.3362.212

CP2K Molecular Dynamics

CP2K is an open-source molecular dynamics software package focused on quantum chemistry and solid-state physics. This test profile currently uses the SSMP (OpenMP) version of cp2k. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterCP2K Molecular Dynamics 8.2Input: Fayalite-FISTIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt90180270360450368.13382.83398.30403.73

PlaidML

This test profile uses PlaidML deep learning framework developed by Intel for offering up various benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: VGG16 - Device: CPUIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt612182430SE +/- 0.08, N = 3SE +/- 0.07, N = 3SE +/- 0.24, N = 4SE +/- 0.22, N = 423.0822.2919.5719.23

PyHPC Benchmarks

PyHPC-Benchmarks is a suite of Python high performance computing benchmarks for execution on CPUs and GPUs using various popular Python HPC libraries. The PyHPC CPU-based benchmarks focus on sequential CPU performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: JAX - Project Size: 65536 - Benchmark: Isoneutral MixingIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt0.00290.00580.00870.01160.0145SE +/- 0.000, N = 15SE +/- 0.000, N = 15SE +/- 0.000, N = 15SE +/- 0.001, N = 120.0100.0110.0110.013

Mlpack Benchmark

Mlpack benchmark scripts for machine learning libraries Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_qdaIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt20406080100SE +/- 0.12, N = 3SE +/- 0.33, N = 3SE +/- 0.15, N = 3SE +/- 0.88, N = 346.6095.9796.46109.65

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: SqueezeNetIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt30K60K90K120K150KSE +/- 195.44, N = 3SE +/- 86.06, N = 3SE +/- 1142.56, N = 15SE +/- 701.15, N = 3109893141138143667159253

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.10Model: super-resolution-10 - Device: CPUIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt10002000300040005000SE +/- 24.67, N = 3SE +/- 10.54, N = 3SE +/- 7.52, N = 3SE +/- 5.07, N = 34662459345794417-mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect-mno-amx-tile -mno-amx-int8 -mno-amx-bf161. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto -fno-fat-lto-objects -ldl -lrt -pthread -lpthread

Mlpack Benchmark

Mlpack benchmark scripts for machine learning libraries Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_linearridgeregressionIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xt0.69981.39962.09942.79923.499SE +/- 0.02, N = 15SE +/- 0.02, N = 15SE +/- 0.02, N = 3SE +/- 0.03, N = 31.531.642.293.11

PyHPC Benchmarks

PyHPC-Benchmarks is a suite of Python high performance computing benchmarks for execution on CPUs and GPUs using various popular Python HPC libraries. The PyHPC CPU-based benchmarks focus on sequential CPU performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: PyTorch - Project Size: 1048576 - Benchmark: Equation of StateIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt0.01240.02480.03720.04960.062SE +/- 0.000, N = 3SE +/- 0.000, N = 15SE +/- 0.000, N = 15SE +/- 0.000, N = 30.0150.0210.0210.055

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: OpenCL - Kernel: Points2ImageIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt4K8K12K16K20KSE +/- 145.81, N = 3SE +/- 375.06, N = 12SE +/- 177.47, N = 3SE +/- 137.15, N = 316397.2815539.0715525.6615404.281. (CXX) g++ options: -O3 -std=c++11 -fopenmp

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V4Intel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt500K1000K1500K2000K2500KSE +/- 2696.20, N = 3SE +/- 10245.31, N = 3SE +/- 1345.60, N = 3SE +/- 8085.58, N = 31564193202247720246802213513

NAMD

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

OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 AtomsIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt 0.28420.56840.85261.13681.421SE +/- 0.00925, N = 3SE +/- 0.00123, N = 3SE +/- 0.00934, N = 10SE +/- 0.01507, N = 30.949571.143641.189101.26329

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 20210720Target: Vulkan GPU - Model: regnety_400mIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt1.31182.62363.93545.24726.559SE +/- 0.02, N = 3SE +/- 0.05, N = 9SE +/- 0.09, N = 15SE +/- 1.34, N = 33.463.714.285.83-mno-amx-tile -mno-amx-int8 -mno-amx-bf16 - MIN: 3.39 / MAX: 9.61-march=native - MIN: 3.44 / MAX: 27.73-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect - MIN: 3.49 / MAX: 28.51-march=native - MIN: 3.47 / MAX: 39.091. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: squeezenet_ssdIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt1.06432.12863.19294.25725.3215SE +/- 0.01, N = 3SE +/- 0.06, N = 9SE +/- 0.04, N = 15SE +/- 0.35, N = 33.744.304.634.73-mno-amx-tile -mno-amx-int8 -mno-amx-bf16 - MIN: 3.67 / MAX: 6.02-march=native - MIN: 3.76 / MAX: 18.02-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect - MIN: 3.77 / MAX: 53.14-march=native - MIN: 3.77 / MAX: 44.231. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: yolov4-tinyIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt3691215SE +/- 0.03, N = 3SE +/- 0.02, N = 9SE +/- 0.03, N = 15SE +/- 1.16, N = 37.638.148.1610.03-mno-amx-tile -mno-amx-int8 -mno-amx-bf16 - MIN: 7.42 / MAX: 9.29-march=native - MIN: 7.82 / MAX: 19.98-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect - MIN: 7.45 / MAX: 57.64-march=native - MIN: 7.85 / MAX: 80.221. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: resnet50Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt246810SE +/- 0.01, N = 3SE +/- 0.04, N = 9SE +/- 0.08, N = 15SE +/- 1.23, N = 35.636.116.647.46-mno-amx-tile -mno-amx-int8 -mno-amx-bf16 - MIN: 5.55 / MAX: 11.35-march=native - MIN: 5.6 / MAX: 31.19-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect - MIN: 5.66 / MAX: 49.12-march=native - MIN: 5.65 / MAX: 33.991. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: alexnetIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt246810SE +/- 0.01, N = 3SE +/- 0.14, N = 9SE +/- 0.06, N = 15SE +/- 0.55, N = 35.756.416.696.84-mno-amx-tile -mno-amx-int8 -mno-amx-bf16 - MIN: 5.49 / MAX: 12.08-march=native - MIN: 5.54 / MAX: 27.79-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect - MIN: 5.55 / MAX: 48.95-march=native - MIN: 5.56 / MAX: 36.91. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: resnet18Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt0.8911.7822.6733.5644.455SE +/- 0.04, N = 3SE +/- 0.09, N = 7SE +/- 0.05, N = 15SE +/- 1.09, N = 31.962.343.043.96-mno-amx-tile -mno-amx-int8 -mno-amx-bf16 - MIN: 1.89 / MAX: 9.21-march=native - MIN: 1.95 / MAX: 34.31-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect - MIN: 2.03 / MAX: 39.18-march=native - MIN: 2.04 / MAX: 34.371. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: vgg16Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt510152025SE +/- 0.07, N = 3SE +/- 0.08, N = 9SE +/- 0.12, N = 15SE +/- 2.77, N = 316.4316.9617.5819.80-mno-amx-tile -mno-amx-int8 -mno-amx-bf16 - MIN: 15.67 / MAX: 43.35-march=native - MIN: 15.75 / MAX: 62.69-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect - MIN: 15.73 / MAX: 64.58-march=native - MIN: 15.66 / MAX: 57.671. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: googlenetIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt246810SE +/- 0.01, N = 3SE +/- 0.06, N = 9SE +/- 0.07, N = 15SE +/- 1.19, N = 34.695.105.417.09-mno-amx-tile -mno-amx-int8 -mno-amx-bf16 - MIN: 4.63 / MAX: 7.03-march=native - MIN: 4.68 / MAX: 29.19-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect - MIN: 4.74 / MAX: 36.71-march=native - MIN: 4.73 / MAX: 34.541. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: blazefaceIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt0.60981.21961.82942.43923.049SE +/- 0.04, N = 3SE +/- 0.02, N = 9SE +/- 0.03, N = 15SE +/- 0.30, N = 31.031.431.692.71-mno-amx-tile -mno-amx-int8 -mno-amx-bf16 - MIN: 0.85 / MAX: 22.57-march=native - MIN: 1.17 / MAX: 22.73-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect - MIN: 1.29 / MAX: 28.85-march=native - MIN: 1.3 / MAX: 55.081. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: efficientnet-b0Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt3691215SE +/- 0.01, N = 3SE +/- 0.05, N = 9SE +/- 0.04, N = 15SE +/- 1.47, N = 37.207.657.729.34-mno-amx-tile -mno-amx-int8 -mno-amx-bf16 - MIN: 7.08 / MAX: 11.54-march=native - MIN: 7.2 / MAX: 28.56-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect - MIN: 7.18 / MAX: 34.33-march=native - MIN: 7.17 / MAX: 38.241. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: mnasnetIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt0.96081.92162.88243.84324.804SE +/- 0.01, N = 3SE +/- 0.06, N = 9SE +/- 0.09, N = 15SE +/- 1.10, N = 32.482.723.404.27-mno-amx-tile -mno-amx-int8 -mno-amx-bf16 - MIN: 2.4 / MAX: 6.71-march=native - MIN: 2.46 / MAX: 25.53-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect - MIN: 2.5 / MAX: 33.07-march=native - MIN: 2.5 / MAX: 32.541. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: shufflenet-v2Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt0.82131.64262.46393.28524.1065SE +/- 0.00, N = 3SE +/- 0.02, N = 9SE +/- 0.04, N = 15SE +/- 0.97, N = 31.802.072.683.65-mno-amx-tile -mno-amx-int8 -mno-amx-bf16 - MIN: 1.77 / MAX: 3.92-march=native - MIN: 1.82 / MAX: 24.55-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect - MIN: 1.86 / MAX: 25.24-march=native - MIN: 1.88 / MAX: 35.31. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt1.0712.1423.2134.2845.355SE +/- 0.05, N = 3SE +/- 0.05, N = 9SE +/- 0.05, N = 15SE +/- 0.44, N = 33.333.644.024.76-mno-amx-tile -mno-amx-int8 -mno-amx-bf16 - MIN: 3.22 / MAX: 15.12-march=native - MIN: 3.28 / MAX: 24.44-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect - MIN: 3.28 / MAX: 27.17-march=native - MIN: 3.33 / MAX: 28.561. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt0.91131.82262.73393.64524.5565SE +/- 0.01, N = 3SE +/- 0.04, N = 9SE +/- 0.04, N = 15SE +/- 0.50, N = 32.412.613.194.05-mno-amx-tile -mno-amx-int8 -mno-amx-bf16 - MIN: 2.33 / MAX: 6.88-march=native - MIN: 2.38 / MAX: 19.16-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect - MIN: 2.43 / MAX: 25.75-march=native - MIN: 2.44 / MAX: 30.191. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: Vulkan GPU - Model: mobilenetIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt246810SE +/- 0.05, N = 3SE +/- 0.06, N = 9SE +/- 0.07, N = 15SE +/- 0.10, N = 36.176.726.867.40-mno-amx-tile -mno-amx-int8 -mno-amx-bf16 - MIN: 5.85 / MAX: 8.17-march=native - MIN: 6.36 / MAX: 35.89-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect - MIN: 6.23 / MAX: 45.95-march=native - MIN: 6.41 / MAX: 52.121. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V2Intel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt 400K800K1200K1600K2000KSE +/- 972.87, N = 3SE +/- 2059.01, N = 3SE +/- 380.18, N = 3SE +/- 2113.91, N = 31413363178385718015201837950

PyHPC Benchmarks

PyHPC-Benchmarks is a suite of Python high performance computing benchmarks for execution on CPUs and GPUs using various popular Python HPC libraries. The PyHPC CPU-based benchmarks focus on sequential CPU performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: TensorFlow - Project Size: 1048576 - Benchmark: Equation of StateIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xt0.00470.00940.01410.01880.0235SE +/- 0.000, N = 4SE +/- 0.000, N = 15SE +/- 0.000, N = 3SE +/- 0.000, N = 150.0200.0200.0200.021

SHOC Scalable HeterOgeneous Computing

The CUDA and OpenCL version of Vetter's Scalable HeterOgeneous Computing benchmark suite. SHOC provides a number of different benchmark programs for evaluating the performance and stability of compute devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: S3DIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt 48121620SE +/- 0.12, N = 15SE +/- 0.11, N = 10SE +/- 0.12, N = 15SE +/- 0.18, N = 1513.9613.7013.6612.24-march=native-mno-amx-tile -mno-amx-int8 -mno-amx-bf16-march=native-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect1. (CXX) g++ options: -O3 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -Xlinker --enable-new-dtags -rpath -lmpicxx -lmpifort -lmpi -lpthread -ldl

ASKAP

ASKAP is a set of benchmarks from the Australian SKA Pathfinder. The principal ASKAP benchmarks are the Hogbom Clean Benchmark (tHogbomClean) and Convolutional Resamping Benchmark (tConvolve) as well as some previous ASKAP benchmarks being included as well for OpenCL and CUDA execution of tConvolve. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve MT - DegriddingIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt400800120016002000SE +/- 0.85, N = 3SE +/- 2.06, N = 3SE +/- 1.70, N = 3SE +/- 15.85, N = 32023.162004.441970.571966.151. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve MT - GriddingIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt30060090012001500SE +/- 0.74, N = 3SE +/- 0.45, N = 3SE +/- 2.99, N = 3SE +/- 0.43, N = 31256.301255.801231.731171.041. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet FloatIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt 20K40K60K80K100KSE +/- 1007.74, N = 3SE +/- 1032.89, N = 5SE +/- 153.26, N = 3SE +/- 70.47, N = 374706.993377.493959.495569.3

PyHPC Benchmarks

PyHPC-Benchmarks is a suite of Python high performance computing benchmarks for execution on CPUs and GPUs using various popular Python HPC libraries. The PyHPC CPU-based benchmarks focus on sequential CPU performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Aesara - Project Size: 4194304 - Benchmark: Isoneutral MixingIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt0.29270.58540.87811.17081.4635SE +/- 0.003, N = 3SE +/- 0.001, N = 3SE +/- 0.004, N = 3SE +/- 0.003, N = 31.2561.2991.2991.301

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet QuantIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt 20K40K60K80K100KSE +/- 254.55, N = 3SE +/- 147.61, N = 3SE +/- 995.15, N = 3SE +/- 477.30, N = 378810.597487.498208.899378.6

PyHPC Benchmarks

PyHPC-Benchmarks is a suite of Python high performance computing benchmarks for execution on CPUs and GPUs using various popular Python HPC libraries. The PyHPC CPU-based benchmarks focus on sequential CPU performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: JAX - Project Size: 4194304 - Benchmark: Isoneutral MixingIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt0.17530.35060.52590.70120.8765SE +/- 0.001, N = 3SE +/- 0.000, N = 3SE +/- 0.001, N = 3SE +/- 0.001, N = 30.6350.6370.6440.779

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: JAX - Project Size: 262144 - Benchmark: Isoneutral MixingIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt0.00770.01540.02310.03080.0385SE +/- 0.000, N = 15SE +/- 0.000, N = 15SE +/- 0.000, N = 15SE +/- 0.001, N = 120.0270.0280.0280.034

Himeno Benchmark

The Himeno benchmark is a linear solver of pressure Poisson using a point-Jacobi method. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMFLOPS, More Is BetterHimeno Benchmark 3.0Poisson Pressure SolverIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt2K4K6K8K10KSE +/- 6.21, N = 3SE +/- 5.76, N = 3SE +/- 67.32, N = 3SE +/- 32.30, N = 310224.569558.669209.759116.46-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect-mno-amx-tile -mno-amx-int8 -mno-amx-bf16-march=native-march=native1. (CC) gcc options: -O3 -mavx2

Nebular Empirical Analysis Tool

NEAT is the Nebular Empirical Analysis Tool for empirical analysis of ionised nebulae, with uncertainty propagation. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterNebular Empirical Analysis Tool 2.3Intel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt 612182430SE +/- 0.66, N = 15SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 325.6826.1726.6826.981. (F9X) gfortran options: -O3 -cpp -ffree-line-length-0 -Jsource/ -fopenmp -fno-backtrace -lcfitsio

Mlpack Benchmark

Mlpack benchmark scripts for machine learning libraries Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_icaIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xt816243240SE +/- 0.07, N = 3SE +/- 0.02, N = 3SE +/- 0.26, N = 12SE +/- 0.29, N = 912.0212.3914.5836.43

PyHPC Benchmarks

PyHPC-Benchmarks is a suite of Python high performance computing benchmarks for execution on CPUs and GPUs using various popular Python HPC libraries. The PyHPC CPU-based benchmarks focus on sequential CPU performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: PyTorch - Project Size: 4194304 - Benchmark: Equation of StateIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt0.05020.10040.15060.20080.251SE +/- 0.002, N = 15SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 30.0690.0880.0900.223

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Numba - Project Size: 4194304 - Benchmark: Isoneutral MixingIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt 0.19060.38120.57180.76240.953SE +/- 0.003, N = 3SE +/- 0.005, N = 3SE +/- 0.001, N = 3SE +/- 0.001, N = 30.8150.8370.8450.847

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: TensorFlow - Project Size: 65536 - Benchmark: Equation of StateIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xt0.00050.0010.00150.0020.0025SE +/- 0.000, N = 3SE +/- 0.000, N = 15SE +/- 0.000, N = 3SE +/- 0.000, N = 30.0010.0010.0020.002

ACES DGEMM

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

OpenBenchmarking.orgGFLOP/s, More Is BetterACES DGEMM 1.0Sustained Floating-Point RateIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt 1.17112.34223.51334.68445.8555SE +/- 0.005750, N = 3SE +/- 0.019734, N = 3SE +/- 0.027431, N = 3SE +/- 0.007819, N = 35.2050184.9653314.9095974.723792-mno-amx-tile -mno-amx-int8 -mno-amx-bf16-mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect1. (CC) gcc options: -O3 -march=native -fopenmp

miniFE

MiniFE Finite Element is an application for unstructured implicit finite element codes. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgCG Mflops, More Is BetterminiFE 2.2Problem Size: SmallIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt 14002800420056007000SE +/- 9.91, N = 3SE +/- 26.31, N = 3SE +/- 4.26, N = 3SE +/- 73.38, N = 36321.616218.415932.115458.441. (CXX) g++ options: -O3 -fopenmp -Xlinker --enable-new-dtags -rpath -lmpicxx -lmpifort -lmpi -lrt -lpthread -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: Euclidean ClusterIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt400800120016002000SE +/- 12.05, N = 3SE +/- 3.29, N = 3SE +/- 27.64, N = 15SE +/- 12.00, N = 151649.841615.651439.631355.371. (CXX) g++ options: -O3 -std=c++11 -fopenmp

PyHPC Benchmarks

PyHPC-Benchmarks is a suite of Python high performance computing benchmarks for execution on CPUs and GPUs using various popular Python HPC libraries. The PyHPC CPU-based benchmarks focus on sequential CPU performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Aesara - Project Size: 65536 - Benchmark: Isoneutral MixingIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt 0.00380.00760.01140.01520.019SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 150.0160.0160.0160.017

Kripke

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

OpenBenchmarking.orgThroughput FoM, More Is BetterKripke 1.2.4Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt17M34M51M68M85MSE +/- 37071.05, N = 3SE +/- 132255.44, N = 3SE +/- 396295.91, N = 3SE +/- 688051.71, N = 377469363768686937619500072234187-mno-amx-tile -mno-amx-int8 -mno-amx-bf16-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect-march=native-march=native1. (CXX) g++ options: -O3 -fopenmp

PyHPC Benchmarks

PyHPC-Benchmarks is a suite of Python high performance computing benchmarks for execution on CPUs and GPUs using various popular Python HPC libraries. The PyHPC CPU-based benchmarks focus on sequential CPU performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Numpy - Project Size: 4194304 - Benchmark: Equation of StateIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt0.30220.60440.90661.20881.511SE +/- 0.002, N = 3SE +/- 0.001, N = 3SE +/- 0.004, N = 3SE +/- 0.003, N = 31.3131.3251.3271.343

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 MappingIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt2004006008001000SE +/- 4.87, N = 3SE +/- 4.83, N = 3SE +/- 10.71, N = 5SE +/- 26.57, N = 151099.431008.65993.75821.381. (CXX) g++ options: -O3 -std=c++11 -fopenmp

PyHPC Benchmarks

PyHPC-Benchmarks is a suite of Python high performance computing benchmarks for execution on CPUs and GPUs using various popular Python HPC libraries. The PyHPC CPU-based benchmarks focus on sequential CPU performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: PyTorch - Project Size: 65536 - Benchmark: Isoneutral MixingIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt0.0070.0140.0210.0280.035SE +/- 0.000, N = 3SE +/- 0.000, N = 15SE +/- 0.000, N = 3SE +/- 0.000, N = 30.0130.0130.0130.031

DeepSpeech

Mozilla DeepSpeech is a speech-to-text engine powered by TensorFlow for machine learning and derived from Baidu's Deep Speech research paper. This test profile times the speech-to-text process for a roughly three minute audio recording. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDeepSpeech 0.6Acceleration: CPUIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt1530456075SE +/- 0.28, N = 3SE +/- 0.29, N = 3SE +/- 0.25, N = 3SE +/- 0.20, N = 348.7849.0854.5565.96

SHOC Scalable HeterOgeneous Computing

The CUDA and OpenCL version of Vetter's Scalable HeterOgeneous Computing benchmark suite. SHOC provides a number of different benchmark programs for evaluating the performance and stability of compute devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: GEMM SGEMM_NIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt60120180240300SE +/- 1.08, N = 3SE +/- 0.87, N = 3SE +/- 4.42, N = 12SE +/- 3.17, N = 15284.99263.16254.60228.41-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect-mno-amx-tile -mno-amx-int8 -mno-amx-bf16-march=native-march=native1. (CXX) g++ options: -O3 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -Xlinker --enable-new-dtags -rpath -lmpicxx -lmpifort -lmpi -lpthread -ldl

ASKAP

ASKAP is a set of benchmarks from the Australian SKA Pathfinder. The principal ASKAP benchmarks are the Hogbom Clean Benchmark (tHogbomClean) and Convolutional Resamping Benchmark (tConvolve) as well as some previous ASKAP benchmarks being included as well for OpenCL and CUDA execution of tConvolve. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Second, More Is BetterASKAP 1.0Test: Hogbom Clean OpenMPIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt60120180240300SE +/- 0.23, N = 3SE +/- 0.58, N = 3SE +/- 1.70, N = 15SE +/- 4.49, N = 15264.78255.32253.55243.801. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

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 0.3Target: CPU - Model: MobileNet v2Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt110220330440550SE +/- 0.22, N = 3SE +/- 1.06, N = 3SE +/- 2.18, N = 15SE +/- 0.45, N = 3216.87224.71262.51486.56-mno-amx-tile -mno-amx-int8 -mno-amx-bf16 - MIN: 214.9 / MAX: 226.18-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect - MIN: 219.21 / MAX: 248.29-march=native - MIN: 221.83 / MAX: 377.5-march=native - MIN: 479.58 / MAX: 559.421. (CXX) g++ options: -O3 -fopenmp -pthread -fvisibility=hidden -fvisibility=default -rdynamic -ldl

Mlpack Benchmark

Mlpack benchmark scripts for machine learning libraries Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_svmIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt3691215SE +/- 0.05, N = 15SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.54, N = 126.957.1910.8313.06

PyHPC Benchmarks

PyHPC-Benchmarks is a suite of Python high performance computing benchmarks for execution on CPUs and GPUs using various popular Python HPC libraries. The PyHPC CPU-based benchmarks focus on sequential CPU performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: TensorFlow - Project Size: 262144 - Benchmark: Equation of StateIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xt0.00110.00220.00330.00440.0055SE +/- 0.000, N = 15SE +/- 0.000, N = 15SE +/- 0.000, N = 3SE +/- 0.000, N = 150.0040.0040.0050.005

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Numba - Project Size: 65536 - Benchmark: Equation of StateIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xt0.00050.0010.00150.0020.0025SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 30.0020.0020.0020.002

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Aesara - Project Size: 4194304 - Benchmark: Equation of StateIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt0.04030.08060.12090.16120.2015SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 30.1680.1750.1780.179

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Numpy - Project Size: 1048576 - Benchmark: Equation of StateIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt0.05110.10220.15330.20440.2555SE +/- 0.000, N = 3SE +/- 0.001, N = 3SE +/- 0.000, N = 3SE +/- 0.002, N = 30.2190.2220.2220.227

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: JAX - Project Size: 1048576 - Benchmark: Isoneutral MixingIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt0.03830.07660.11490.15320.1915SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.001, N = 3SE +/- 0.004, N = 120.1330.1340.1340.170

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Numpy - Project Size: 65536 - Benchmark: Equation of StateIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt0.00320.00640.00960.01280.016SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.001, N = 150.0120.0130.0130.014

R Benchmark

This test is a quick-running survey of general R performance Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterR BenchmarkIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt0.02470.04940.07410.09880.1235SE +/- 0.0004, N = 3SE +/- 0.0004, N = 3SE +/- 0.0013, N = 3SE +/- 0.0057, N = 120.10380.10700.10960.10971. R scripting front-end version 4.0.4 (2021-02-15)

PyHPC Benchmarks

PyHPC-Benchmarks is a suite of Python high performance computing benchmarks for execution on CPUs and GPUs using various popular Python HPC libraries. The PyHPC CPU-based benchmarks focus on sequential CPU performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Numba - Project Size: 262144 - Benchmark: Equation of StateIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt0.0020.0040.0060.0080.01SE +/- 0.000, N = 3SE +/- 0.000, N = 15SE +/- 0.000, N = 3SE +/- 0.000, N = 30.0080.0090.0090.009

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Numba - Project Size: 4194304 - Benchmark: Equation of StateIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt0.03240.06480.09720.12960.162SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.001, N = 3SE +/- 0.001, N = 30.1370.1430.1440.144

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: PyTorch - Project Size: 65536 - Benchmark: Equation of StateIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt0.00090.00180.00270.00360.0045SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 30.0010.0020.0020.004

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Numpy - Project Size: 16384 - Benchmark: Isoneutral MixingIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xt0.00110.00220.00330.00440.0055SE +/- 0.000, N = 15SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 150.0040.0050.0050.005

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Numba - Project Size: 65536 - Benchmark: Isoneutral MixingIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt 0.00270.00540.00810.01080.0135SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 30.0110.0110.0110.012

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: JAX - Project Size: 1048576 - Benchmark: Equation of StateIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt0.0020.0040.0060.0080.01SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 30.0070.0080.0080.009

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: TensorFlow - Project Size: 4194304 - Benchmark: Equation of StateIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt 0.02140.04280.06420.08560.107SE +/- 0.000, N = 3SE +/- 0.001, N = 3SE +/- 0.000, N = 3SE +/- 0.001, N = 30.0930.0930.0940.095

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Numpy - Project Size: 1048576 - Benchmark: Isoneutral MixingIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt0.10330.20660.30990.41320.5165SE +/- 0.001, N = 3SE +/- 0.002, N = 3SE +/- 0.001, N = 3SE +/- 0.001, N = 30.4090.4160.4540.459

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: PyTorch - Project Size: 1048576 - Benchmark: Isoneutral MixingIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt0.11230.22460.33690.44920.5615SE +/- 0.003, N = 3SE +/- 0.001, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 30.2800.2810.2850.499

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Aesara - Project Size: 1048576 - Benchmark: Isoneutral MixingIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt 0.06590.13180.19770.26360.3295SE +/- 0.000, N = 3SE +/- 0.002, N = 3SE +/- 0.001, N = 3SE +/- 0.002, N = 30.2850.2900.2900.293

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Aesara - Project Size: 16384 - Benchmark: Isoneutral MixingIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xt0.00090.00180.00270.00360.0045SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 30.0030.0040.0040.004

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Numba - Project Size: 16384 - Benchmark: Isoneutral MixingIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt 0.00070.00140.00210.00280.0035SE +/- 0.000, N = 15SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 150.0020.0020.0020.003

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 2020-06-28Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt 48121620SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.09, N = 3SE +/- 0.01, N = 316.1016.5216.7917.51-mno-amx-tile -mno-amx-int8 -mno-amx-bf16-march=native-march=native-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect1. (CC) gcc options: -O3 -pedantic -fvisibility=hidden

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 0.3Target: CPU - Model: SqueezeNet v1.1Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt50100150200250SE +/- 0.04, N = 3SE +/- 0.11, N = 3SE +/- 0.06, N = 3SE +/- 1.05, N = 3225.76230.46235.53237.60-mno-amx-tile -mno-amx-int8 -mno-amx-bf16 - MIN: 225.47 / MAX: 226.77-march=native - MIN: 230.05 / MAX: 230.91-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect - MIN: 235.23 / MAX: 237-march=native - MIN: 235.29 / MAX: 265.951. (CXX) g++ options: -O3 -fopenmp -pthread -fvisibility=hidden -fvisibility=default -rdynamic -ldl

PyHPC Benchmarks

PyHPC-Benchmarks is a suite of Python high performance computing benchmarks for execution on CPUs and GPUs using various popular Python HPC libraries. The PyHPC CPU-based benchmarks focus on sequential CPU performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Numpy - Project Size: 262144 - Benchmark: Isoneutral MixingIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt0.02270.04540.06810.09080.1135SE +/- 0.000, N = 3SE +/- 0.001, N = 3SE +/- 0.001, N = 3SE +/- 0.000, N = 30.0890.0900.0970.101

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Aesara - Project Size: 262144 - Benchmark: Isoneutral MixingIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt0.01370.02740.04110.05480.0685SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.001, N = 30.0600.0600.0610.061

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Aesara - Project Size: 262144 - Benchmark: Equation of StateIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt0.00250.0050.00750.010.0125SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 30.0100.0110.0110.011

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: PyTorch - Project Size: 262144 - Benchmark: Isoneutral MixingIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt0.0250.050.0750.10.125SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 30.0520.0520.0540.111

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: PyTorch - Project Size: 262144 - Benchmark: Equation of StateIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt0.00290.00580.00870.01160.0145SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 30.0040.0050.0050.013

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: JAX - Project Size: 4194304 - Benchmark: Equation of StateIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt0.00830.01660.02490.03320.0415SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 30.0280.0290.0300.037

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 4096Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt20K40K60K80K100KSE +/- 950.48, N = 3SE +/- 688.36, N = 15SE +/- 367.77, N = 3SE +/- 827.63, N = 41023331001558066778573-mno-amx-tile -mno-amx-int8 -mno-amx-bf16-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect-march=native-march=native1. (CC) gcc options: -pthread -O3 -lm

PyHPC Benchmarks

PyHPC-Benchmarks is a suite of Python high performance computing benchmarks for execution on CPUs and GPUs using various popular Python HPC libraries. The PyHPC CPU-based benchmarks focus on sequential CPU performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Numba - Project Size: 1048576 - Benchmark: Isoneutral MixingIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt 0.04550.0910.13650.1820.2275SE +/- 0.001, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 30.1940.2010.2010.202

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Aesara - Project Size: 16384 - Benchmark: Equation of StateIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xt0.00020.00040.00060.00080.001SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 30.0010.0010.0010.001

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: JAX - Project Size: 262144 - Benchmark: Equation of StateIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xt0.00020.00040.00060.00080.001SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 15SE +/- 0.000, N = 30.0010.0010.0010.001

Dolfyn

Dolfyn is a Computational Fluid Dynamics (CFD) code of modern numerical simulation techniques. The Dolfyn test profile measures the execution time of the bundled computational fluid dynamics demos that are bundled with Dolfyn. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDolfyn 0.527Computational Fluid DynamicsIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt 3691215SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 310.6911.0411.0611.16

ASKAP

ASKAP is a set of benchmarks from the Australian SKA Pathfinder. The principal ASKAP benchmarks are the Hogbom Clean Benchmark (tHogbomClean) and Convolutional Resamping Benchmark (tConvolve) as well as some previous ASKAP benchmarks being included as well for OpenCL and CUDA execution of tConvolve. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve OpenMP - DegriddingIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt 8001600240032004000SE +/- 0.00, N = 3SE +/- 25.80, N = 5SE +/- 10.37, N = 3SE +/- 9.94, N = 33550.083423.092873.342812.631. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve OpenMP - GriddingIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt 400800120016002000SE +/- 4.31, N = 3SE +/- 18.90, N = 5SE +/- 9.49, N = 3SE +/- 10.00, N = 31853.311826.951584.971484.831. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

PyHPC Benchmarks

PyHPC-Benchmarks is a suite of Python high performance computing benchmarks for execution on CPUs and GPUs using various popular Python HPC libraries. The PyHPC CPU-based benchmarks focus on sequential CPU performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Numba - Project Size: 262144 - Benchmark: Isoneutral MixingIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt0.00970.01940.02910.03880.0485SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 30.0420.0430.0430.043

SHOC Scalable HeterOgeneous Computing

The CUDA and OpenCL version of Vetter's Scalable HeterOgeneous Computing benchmark suite. SHOC provides a number of different benchmark programs for evaluating the performance and stability of compute devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: ReductionIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt510152025SE +/- 0.10, N = 3SE +/- 0.29, N = 3SE +/- 0.08, N = 3SE +/- 0.15, N = 321.8821.2117.9116.81-mno-amx-tile -mno-amx-int8 -mno-amx-bf16-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect-march=native-march=native1. (CXX) g++ options: -O3 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -Xlinker --enable-new-dtags -rpath -lmpicxx -lmpifort -lmpi -lpthread -ldl

ECP-CANDLE

The CANDLE benchmark codes implement deep learning architectures relevant to problems in cancer. These architectures address problems at different biological scales, specifically problems at the molecular, cellular and population scales. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterECP-CANDLE 0.4Benchmark: P1B2Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt 71421283526.1528.4128.6931.79

PyHPC Benchmarks

PyHPC-Benchmarks is a suite of Python high performance computing benchmarks for execution on CPUs and GPUs using various popular Python HPC libraries. The PyHPC CPU-based benchmarks focus on sequential CPU performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: PyTorch - Project Size: 16384 - Benchmark: Isoneutral MixingIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt0.0020.0040.0060.0080.01SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 30.0030.0030.0030.009

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 4096Intel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt4K8K12K16K20KSE +/- 141.46, N = 14SE +/- 33.69, N = 3SE +/- 117.70, N = 3SE +/- 29.78, N = 318379183031827917876-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect-mno-amx-tile -mno-amx-int8 -mno-amx-bf16-march=native-march=native1. (CC) gcc options: -pthread -O3 -lm

GNU Octave Benchmark

This test profile measures how long it takes to complete several reference GNU Octave files via octave-benchmark. GNU Octave is used for numerical computations and is an open-source alternative to MATLAB. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGNU Octave Benchmark 6.1.1~hg.2021.01.26Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt 1.16242.32483.48724.64965.812SE +/- 0.017, N = 5SE +/- 0.025, N = 5SE +/- 0.039, N = 5SE +/- 0.024, N = 54.9505.0695.1085.166

PyHPC Benchmarks

PyHPC-Benchmarks is a suite of Python high performance computing benchmarks for execution on CPUs and GPUs using various popular Python HPC libraries. The PyHPC CPU-based benchmarks focus on sequential CPU performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Aesara - Project Size: 1048576 - Benchmark: Equation of StateIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt0.00990.01980.02970.03960.0495SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 30.0420.0440.0440.044

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: JAX - Project Size: 16384 - Benchmark: Isoneutral MixingIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xt0.00050.0010.00150.0020.0025SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 30.0020.0020.0020.002

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Numba - Project Size: 16384 - Benchmark: Equation of StateIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xt0.00020.00040.00060.00080.001SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 30.0010.0010.0010.001

Timed MAFFT Alignment

This test performs an alignment of 100 pyruvate decarboxylase sequences. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MAFFT Alignment 7.471Multiple Sequence Alignment - LSU RNAIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt246810SE +/- 0.031, N = 3SE +/- 0.051, N = 3SE +/- 0.009, N = 3SE +/- 0.069, N = 37.6677.9158.0138.1831. (CC) gcc options: -std=c99 -O3 -lm -lpthread

SHOC Scalable HeterOgeneous Computing

The CUDA and OpenCL version of Vetter's Scalable HeterOgeneous Computing benchmark suite. SHOC provides a number of different benchmark programs for evaluating the performance and stability of compute devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: TriadIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt 510152025SE +/- 0.20, N = 4SE +/- 0.16, N = 15SE +/- 0.20, N = 15SE +/- 0.29, N = 1518.4318.3817.5015.63-march=native-march=native-mno-amx-tile -mno-amx-int8 -mno-amx-bf16-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect1. (CXX) g++ options: -O3 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -Xlinker --enable-new-dtags -rpath -lmpicxx -lmpifort -lmpi -lpthread -ldl

PyHPC Benchmarks

PyHPC-Benchmarks is a suite of Python high performance computing benchmarks for execution on CPUs and GPUs using various popular Python HPC libraries. The PyHPC CPU-based benchmarks focus on sequential CPU performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Numpy - Project Size: 65536 - Benchmark: Isoneutral MixingIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt0.00540.01080.01620.02160.027SE +/- 0.000, N = 3SE +/- 0.000, N = 13SE +/- 0.000, N = 3SE +/- 0.000, N = 30.0210.0210.0240.024

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 32Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt20K40K60K80K100KSE +/- 650.31, N = 3SE +/- 1461.14, N = 15SE +/- 618.46, N = 15SE +/- 820.18, N = 383426796687588675032-mno-amx-tile -mno-amx-int8 -mno-amx-bf16-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect-march=native-march=native1. (CC) gcc options: -pthread -O3 -lm

PyHPC Benchmarks

PyHPC-Benchmarks is a suite of Python high performance computing benchmarks for execution on CPUs and GPUs using various popular Python HPC libraries. The PyHPC CPU-based benchmarks focus on sequential CPU performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Numpy - Project Size: 262144 - Benchmark: Equation of StateIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt0.01190.02380.03570.04760.0595SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 30.0510.0520.0530.053

SHOC Scalable HeterOgeneous Computing

The CUDA and OpenCL version of Vetter's Scalable HeterOgeneous Computing benchmark suite. SHOC provides a number of different benchmark programs for evaluating the performance and stability of compute devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Bus Speed ReadbackIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt 918273645SE +/- 1.55, N = 15SE +/- 1.52, N = 12SE +/- 1.03, N = 14SE +/- 1.21, N = 1538.4337.1936.0431.31-march=native-mno-amx-tile -mno-amx-int8 -mno-amx-bf16-march=native-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect1. (CXX) g++ options: -O3 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -Xlinker --enable-new-dtags -rpath -lmpicxx -lmpifort -lmpi -lpthread -ldl

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Bus Speed DownloadIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt 918273645SE +/- 1.64, N = 15SE +/- 1.47, N = 15SE +/- 1.31, N = 15SE +/- 1.01, N = 1238.5338.2335.1930.54-march=native-mno-amx-tile -mno-amx-int8 -mno-amx-bf16-march=native-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect1. (CXX) g++ options: -O3 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -Xlinker --enable-new-dtags -rpath -lmpicxx -lmpifort -lmpi -lpthread -ldl

PyHPC Benchmarks

PyHPC-Benchmarks is a suite of Python high performance computing benchmarks for execution on CPUs and GPUs using various popular Python HPC libraries. The PyHPC CPU-based benchmarks focus on sequential CPU performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Numba - Project Size: 1048576 - Benchmark: Equation of StateIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt0.00810.01620.02430.03240.0405SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 30.0340.0350.0360.036

Scikit-Learn

Scikit-learn is a Python module for machine learning Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 0.22.1Intel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt246810SE +/- 0.009, N = 3SE +/- 0.045, N = 3SE +/- 0.019, N = 3SE +/- 0.002, N = 34.8835.0696.1678.193

Another strange result, merits more testing

PyHPC Benchmarks

PyHPC-Benchmarks is a suite of Python high performance computing benchmarks for execution on CPUs and GPUs using various popular Python HPC libraries. The PyHPC CPU-based benchmarks focus on sequential CPU performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Aesara - Project Size: 65536 - Benchmark: Equation of StateIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xt0.00070.00140.00210.00280.0035SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 30.0030.0030.0030.003

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 32Intel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt 5K10K15K20K25KSE +/- 13.78, N = 3SE +/- 122.88, N = 3SE +/- 20.34, N = 3SE +/- 1.86, N = 323240231172274722739-march=native-march=native-mno-amx-tile -mno-amx-int8 -mno-amx-bf16-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect1. (CC) gcc options: -pthread -O3 -lm

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 32Intel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt 5K10K15K20K25KSE +/- 102.46, N = 3SE +/- 178.70, N = 3SE +/- 54.44, N = 3SE +/- 214.39, N = 323622234772286122796-march=native-march=native-mno-amx-tile -mno-amx-int8 -mno-amx-bf16-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect1. (CC) gcc options: -pthread -O3 -lm

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 0.3Target: CPU - Model: SqueezeNet v2Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt1122334455SE +/- 0.05, N = 3SE +/- 0.08, N = 3SE +/- 0.32, N = 3SE +/- 0.22, N = 344.7445.5045.9046.59-mno-amx-tile -mno-amx-int8 -mno-amx-bf16 - MIN: 44.37 / MAX: 45.8-march=native - MIN: 45.08 / MAX: 45.93-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect - MIN: 45.05 / MAX: 46.7-march=native - MIN: 45.39 / MAX: 53.211. (CXX) g++ options: -O3 -fopenmp -pthread -fvisibility=hidden -fvisibility=default -rdynamic -ldl

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 32Intel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xt7K14K21K28K35KSE +/- 25.36, N = 3SE +/- 235.28, N = 3SE +/- 192.25, N = 3SE +/- 6.89, N = 332202300593004729780-mno-amx-tile -mno-amx-int8 -mno-amx-bf16-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect-march=native-march=native1. (CC) gcc options: -pthread -O3 -lm

PyHPC Benchmarks

PyHPC-Benchmarks is a suite of Python high performance computing benchmarks for execution on CPUs and GPUs using various popular Python HPC libraries. The PyHPC CPU-based benchmarks focus on sequential CPU performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPyHPC Benchmarks 3.0Device: CPU - Backend: Numpy - Project Size: 16384 - Benchmark: Equation of StateIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt Intel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xt0.00050.0010.00150.0020.0025SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 3SE +/- 0.000, N = 30.0020.0020.0020.002

SHOC Scalable HeterOgeneous Computing

The CUDA and OpenCL version of Vetter's Scalable HeterOgeneous Computing benchmark suite. SHOC provides a number of different benchmark programs for evaluating the performance and stability of compute devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: FFT SPIntel Core i7-12700k Golden Cove Pcore + Gracemont Ecore DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Pcore AVX512-SAPPHIRE RAPIDS COMPILER SHENANIGANS- DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore ONLY no AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xtIntel Core i7-12700k Golden Cove Pcore AVX512 DDR4 3200 CL 15 16 16 36 RX 5600xt 20406080100SE +/- 0.08, N = 3SE +/- 0.58, N = 3SE +/- 0.45, N = 3SE +/- 1.24, N = 3101.1299.8898.1487.62-march=native-mno-amx-tile -mno-amx-int8 -mno-amx-bf16-march=native-march=native -mavx512f -mavx512dq -mavx512ifma -mavx512cd -mavx512bw -mavx512vl -mavx512bf16 -mavx512vbmi -mavx512vbmi2 -mavx512vnni -mavx512bitalg -mavx512vpopcntdq -mavx512vp2intersect1. (CXX) g++ options: -O3 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -Xlinker --enable-new-dtags -rpath -lmpicxx -lmpifort -lmpi -lpthread -ldl

153 Results Shown

FFTW
CloverLeaf
PlaidML
TNN
ONNX Runtime
ECP-CANDLE
Mobile Neural Network:
  inception-v3
  mobilenet-v1-1.0
  MobileNetV2_224
  SqueezeNetV1.0
  resnet-v2-50
  squeezenetv1.1
  mobilenetV3
OpenCV
NCNN:
  CPU - regnety_400m
  CPU - squeezenet_ssd
  CPU - yolov4-tiny
  CPU - resnet50
  CPU - alexnet
  CPU - resnet18
  CPU - vgg16
  CPU - googlenet
  CPU - blazeface
  CPU - efficientnet-b0
  CPU - mnasnet
  CPU - shufflenet-v2
  CPU-v3-v3 - mobilenet-v3
  CPU-v2-v2 - mobilenet-v2
  CPU - mobilenet
ONNX Runtime
PyHPC Benchmarks
TensorFlow Lite
FFTW
SHOC Scalable HeterOgeneous Computing
ONNX Runtime
Darmstadt Automotive Parallel Heterogeneous Suite
Numpy Benchmark
ECP-CANDLE
PyHPC Benchmarks
CP2K Molecular Dynamics
PlaidML
PyHPC Benchmarks
Mlpack Benchmark
TensorFlow Lite
ONNX Runtime
Mlpack Benchmark
PyHPC Benchmarks
Darmstadt Automotive Parallel Heterogeneous Suite
TensorFlow Lite
NAMD
NCNN:
  Vulkan GPU - regnety_400m
  Vulkan GPU - squeezenet_ssd
  Vulkan GPU - yolov4-tiny
  Vulkan GPU - resnet50
  Vulkan GPU - alexnet
  Vulkan GPU - resnet18
  Vulkan GPU - vgg16
  Vulkan GPU - googlenet
  Vulkan GPU - blazeface
  Vulkan GPU - efficientnet-b0
  Vulkan GPU - mnasnet
  Vulkan GPU - shufflenet-v2
  Vulkan GPU-v3-v3 - mobilenet-v3
  Vulkan GPU-v2-v2 - mobilenet-v2
  Vulkan GPU - mobilenet
TensorFlow Lite
PyHPC Benchmarks
SHOC Scalable HeterOgeneous Computing
ASKAP:
  tConvolve MT - Degridding
  tConvolve MT - Gridding
TensorFlow Lite
PyHPC Benchmarks
TensorFlow Lite
PyHPC Benchmarks:
  CPU - JAX - 4194304 - Isoneutral Mixing
  CPU - JAX - 262144 - Isoneutral Mixing
Himeno Benchmark
Nebular Empirical Analysis Tool
Mlpack Benchmark
PyHPC Benchmarks:
  CPU - PyTorch - 4194304 - Equation of State
  CPU - Numba - 4194304 - Isoneutral Mixing
  CPU - TensorFlow - 65536 - Equation of State
ACES DGEMM
miniFE
Darmstadt Automotive Parallel Heterogeneous Suite
PyHPC Benchmarks
Kripke
PyHPC Benchmarks
Darmstadt Automotive Parallel Heterogeneous Suite
PyHPC Benchmarks
DeepSpeech
SHOC Scalable HeterOgeneous Computing
ASKAP
TNN
Mlpack Benchmark
PyHPC Benchmarks:
  CPU - TensorFlow - 262144 - Equation of State
  CPU - Numba - 65536 - Equation of State
  CPU - Aesara - 4194304 - Equation of State
  CPU - Numpy - 1048576 - Equation of State
  CPU - JAX - 1048576 - Isoneutral Mixing
  CPU - Numpy - 65536 - Equation of State
R Benchmark
PyHPC Benchmarks:
  CPU - Numba - 262144 - Equation of State
  CPU - Numba - 4194304 - Equation of State
  CPU - PyTorch - 65536 - Equation of State
  CPU - Numpy - 16384 - Isoneutral Mixing
  CPU - Numba - 65536 - Isoneutral Mixing
  CPU - JAX - 1048576 - Equation of State
  CPU - TensorFlow - 4194304 - Equation of State
  CPU - Numpy - 1048576 - Isoneutral Mixing
  CPU - PyTorch - 1048576 - Isoneutral Mixing
  CPU - Aesara - 1048576 - Isoneutral Mixing
  CPU - Aesara - 16384 - Isoneutral Mixing
  CPU - Numba - 16384 - Isoneutral Mixing
RNNoise
TNN
PyHPC Benchmarks:
  CPU - Numpy - 262144 - Isoneutral Mixing
  CPU - Aesara - 262144 - Isoneutral Mixing
  CPU - Aesara - 262144 - Equation of State
  CPU - PyTorch - 262144 - Isoneutral Mixing
  CPU - PyTorch - 262144 - Equation of State
  CPU - JAX - 4194304 - Equation of State
FFTW
PyHPC Benchmarks:
  CPU - Numba - 1048576 - Isoneutral Mixing
  CPU - Aesara - 16384 - Equation of State
  CPU - JAX - 262144 - Equation of State
Dolfyn
ASKAP:
  tConvolve OpenMP - Degridding
  tConvolve OpenMP - Gridding
PyHPC Benchmarks
SHOC Scalable HeterOgeneous Computing
ECP-CANDLE
PyHPC Benchmarks
FFTW
GNU Octave Benchmark
PyHPC Benchmarks:
  CPU - Aesara - 1048576 - Equation of State
  CPU - JAX - 16384 - Isoneutral Mixing
  CPU - Numba - 16384 - Equation of State
Timed MAFFT Alignment
SHOC Scalable HeterOgeneous Computing
PyHPC Benchmarks
FFTW
PyHPC Benchmarks
SHOC Scalable HeterOgeneous Computing:
  OpenCL - Bus Speed Readback
  OpenCL - Bus Speed Download
PyHPC Benchmarks
Scikit-Learn
PyHPC Benchmarks
FFTW:
  Stock - 1D FFT Size 32
  Stock - 2D FFT Size 32
TNN
FFTW
PyHPC Benchmarks
SHOC Scalable HeterOgeneous Computing