AMD 7950X Linux Memory Tests AMD Ryzen 9 7950X 16-Core testing with a ASUS ROG CROSSHAIR X670E HERO (0604 BIOS) and AMD Radeon RX 6800 XT 16GB on Ubuntu 22.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2209263-NE-AMD7950XL78&rdt&grr .
AMD 7950X Linux Memory Tests Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server OpenGL Vulkan Compiler File-System Screen Resolution GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat AMD Ryzen 9 7950X 16-Core @ 5.88GHz (16 Cores / 32 Threads) ASUS ROG CROSSHAIR X670E HERO (0604 BIOS) AMD Device 14d8 32GB 2000GB Samsung SSD 980 PRO 2TB + 2000GB AMD Radeon RX 6800 XT 16GB (2575/1000MHz) AMD Navi 21 HDMI Audio ASUS VP28U Intel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411 Ubuntu 22.04 6.0.0-060000rc1daily20220820-generic (x86_64) GNOME Shell 42.2 X Server + Wayland 4.6 Mesa 22.3.0-devel (git-4685385 2022-08-23 jammy-oibaf-ppa) (LLVM 14.0.6 DRM 3.48) 1.3.224 GCC 12.0.1 20220319 ext4 3840x2160 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-12-OcsLtf/gcc-12-12-20220319/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-OcsLtf/gcc-12-12-20220319/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-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Processor Details - GSKILL EXPO I: Scaling Governor: amd-pstate performance (Boost: Enabled) - CPU Microcode: 0xa601203 - GSKILL DDR5-6000: Scaling Governor: amd-pstate schedutil (Boost: Enabled) - CPU Microcode: 0xa601203 - Other GSKILL Repeat: Scaling Governor: amd-pstate schedutil (Boost: Enabled) - CPU Microcode: 0xa601203 Graphics Details - BAR1 / Visible vRAM Size: 16368 MB - vBIOS Version: 113-D4120500-101 Python Details - Python 3.10.4 Security Details - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
AMD 7950X Linux Memory Tests nwchem: C240 Buckyball tinymembench: Standard Memset tinymembench: Standard Memcpy build-gem5: Time To Compile hpcg: mbw: Memory Copy, Fixed Block Size - 8192 MiB gpaw: Carbon Nanotube ddnet: 1920 x 1080 - Fullscreen - Vulkan - Default - Multeasymap svt-hevc: 1 - Bosphorus 4K xonotic: 1920 x 1080 - Ultimate gromacs: MPI CPU - water_GMX50_bare openfoam: drivaerFastback, Small Mesh Size - Execution Time openfoam: drivaerFastback, Small Mesh Size - Mesh Time stargate: 192000 - 512 xonotic: 1920 x 1080 - Ultra build-godot: Time To Compile svt-av1: Preset 4 - Bosphorus 4K stargate: 192000 - 1024 unvanquished: 1920 x 1080 - High namd: ATPase Simulation - 327,506 Atoms mbw: Memory Copy - 8192 MiB build-linux-kernel: defconfig unvanquished: 1920 x 1080 - Ultra mbw: Memory Copy, Fixed Block Size - 4096 MiB stargate: 96000 - 512 stargate: 96000 - 1024 svt-vp9: VMAF Optimized - Bosphorus 4K ramspeed: Triad - Integer ramspeed: Average - Floating Point ramspeed: Add - Integer ramspeed: Scale - Floating Point ramspeed: Add - Floating Point ramspeed: Copy - Floating Point ramspeed: Triad - Floating Point ramspeed: Average - Integer ramspeed: Scale - Integer ramspeed: Copy - Integer svt-hevc: 1 - Bosphorus 1080p swet: Average stargate: 480000 - 512 mbw: Memory Copy - 4096 MiB stargate: 44100 - 512 stargate: 480000 - 1024 stargate: 44100 - 1024 compress-7zip: Decompression Rating compress-7zip: Compression Rating svt-av1: Preset 4 - Bosphorus 1080p svt-av1: Preset 8 - Bosphorus 4K sysbench: RAM / Memory svt-hevc: 7 - Bosphorus 4K svt-vp9: Visual Quality Optimized - Bosphorus 4K svt-vp9: PSNR/SSIM Optimized - Bosphorus 4K svt-av1: Preset 10 - Bosphorus 4K svt-hevc: 10 - Bosphorus 4K svt-av1: Preset 12 - Bosphorus 4K svt-vp9: VMAF Optimized - Bosphorus 1080p svt-av1: Preset 8 - Bosphorus 1080p svt-hevc: 7 - Bosphorus 1080p svt-vp9: Visual Quality Optimized - Bosphorus 1080p svt-av1: Preset 10 - Bosphorus 1080p mbw: Memory Copy, Fixed Block Size - 128 MiB svt-vp9: PSNR/SSIM Optimized - Bosphorus 1080p svt-hevc: 10 - Bosphorus 1080p svt-av1: Preset 12 - Bosphorus 1080p yquake2: OpenGL 3.x - On - On - 1920 x 1080 yquake2: Vulkan - On - On - 1920 x 1080 mbw: Memory Copy - 128 MiB plaidml: No - Inference - Inception V3 - CPU GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 4220.3 31948.3 28635.0 198.038 8.05506 17981.105 150.604 4263.27 5.79 518.2608654 2.497 166.36596 23.359852 4.152298 645.7948044 53.784 3.434 4.500125 665.3 0.83367 19941.335 40.693 669.7 17415.884 6.285946 6.643385 110.78 61570.71 66415.43 61801.87 70644.87 62057.15 70298.20 61354.16 66084.68 70898.08 70544.02 22.81 1419860753 8.430656 20163.909 8.440940 8.814174 8.846218 176029 179543 9.865 81.448 12597.07 101.24 108.06 120.58 145.736 167.72 205.961 435.35 211.350 324.80 383.25 460.305 20753.097 449.74 594.06 718.817 1744.4 1755.6 19400.264 4215.4 31949.9 28518.0 198.616 8.00425 17636.131 150.972 3552.13 5.80 387.4167582 2.491 167.43997 23.157018 3.055673 553.9718980 53.975 2.992 4.427065 409.3 0.83092 19549.766 41.050 415.9 17122.920 6.220335 6.634006 109.96 61005.73 65643.81 61382.59 70396.37 61261.69 70356.91 60927.57 65878.93 70370.60 70078.90 22.86 1424879888 8.439396 19795.484 8.408079 8.808473 8.819321 176501 177787 7.363 75.129 12610.85 100.20 107.86 119.98 130.857 167.26 186.686 418.69 158.343 314.86 372.57 349.152 19354.077 435.43 576.76 453.177 1469.9 1627.5 18913.266 4283.5 31952.6 28522.0 198.397 8.01485 17527.992 150.972 4045.57 5.77 393.4074312 2.491 168.21304 23.302285 4.155233 556.2878549 53.870 3.424 4.532117 595.4 0.83222 19738.292 40.853 586.7 17862.377 6.317154 6.691616 110.19 60886.49 65377.43 60895.67 70123.32 61909.57 69929.36 61317.18 66011.50 69663.60 70096.60 22.76 1427810080 8.471645 19850.560 8.551467 8.802010 8.820758 175835 177626 9.816 81.352 12566.17 100.32 107.19 119.57 144.650 167.25 204.348 433.35 210.803 323.86 382.01 455.224 20803.896 447.30 589.20 709.167 1605.5 1630.3 19642.940 OpenBenchmarking.org
NWChem Input: C240 Buckyball OpenBenchmarking.org Seconds, Fewer Is Better NWChem 7.0.2 Input: C240 Buckyball GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 900 1800 2700 3600 4500 4220.3 4215.4 4283.5 1. (F9X) gfortran options: -lnwctask -lccsd -lmcscf -lselci -lmp2 -lmoints -lstepper -ldriver -loptim -lnwdft -lgradients -lcphf -lesp -lddscf -ldangchang -lguess -lhessian -lvib -lnwcutil -lrimp2 -lproperty -lsolvation -lnwints -lprepar -lnwmd -lnwpw -lofpw -lpaw -lpspw -lband -lnwpwlib -lcafe -lspace -lanalyze -lqhop -lpfft -ldplot -ldrdy -lvscf -lqmmm -lqmd -letrans -ltce -lbq -lmm -lcons -lperfm -ldntmc -lccca -ldimqm -lga -larmci -lpeigs -l64to32 -lopenblas -lpthread -lrt -llapack -lnwcblas -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz -lcomex -m64 -ffast-math -std=legacy -fdefault-integer-8 -finline-functions -O2
Tinymembench Standard Memset OpenBenchmarking.org MB/s, More Is Better Tinymembench 2018-05-28 Standard Memset GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 7K 14K 21K 28K 35K SE +/- 1.92, N = 3 SE +/- 1.90, N = 3 SE +/- 2.07, N = 3 31948.3 31949.9 31952.6 1. (CC) gcc options: -O2 -lm
Tinymembench Standard Memcpy OpenBenchmarking.org MB/s, More Is Better Tinymembench 2018-05-28 Standard Memcpy GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 6K 12K 18K 24K 30K SE +/- 49.79, N = 3 SE +/- 115.71, N = 3 SE +/- 5.83, N = 3 28635.0 28518.0 28522.0 1. (CC) gcc options: -O2 -lm
Timed Gem5 Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Gem5 Compilation 21.2 Time To Compile GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 40 80 120 160 200 SE +/- 0.11, N = 3 SE +/- 0.53, N = 3 SE +/- 1.03, N = 3 198.04 198.62 198.40
High Performance Conjugate Gradient OpenBenchmarking.org GFLOP/s, More Is Better High Performance Conjugate Gradient 3.1 GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 2 4 6 8 10 SE +/- 0.00589, N = 3 SE +/- 0.00167, N = 3 SE +/- 0.00661, N = 3 8.05506 8.00425 8.01485 1. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -lmpi_cxx -lmpi
MBW Test: Memory Copy, Fixed Block Size - Array Size: 8192 MiB OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy, Fixed Block Size - Array Size: 8192 MiB GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 4K 8K 12K 16K 20K SE +/- 129.65, N = 15 SE +/- 189.20, N = 4 SE +/- 123.55, N = 15 17981.11 17636.13 17527.99 1. (CC) gcc options: -O3 -march=native
GPAW Input: Carbon Nanotube OpenBenchmarking.org Seconds, Fewer Is Better GPAW 22.1 Input: Carbon Nanotube GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 30 60 90 120 150 SE +/- 0.12, N = 3 SE +/- 0.28, N = 3 SE +/- 0.13, N = 3 150.60 150.97 150.97 1. (CC) gcc options: -shared -fwrapv -O2 -lxc -lblas -lmpi
DDraceNetwork Resolution: 1920 x 1080 - Mode: Fullscreen - Renderer: Vulkan - Zoom: Default - Demo: Multeasymap OpenBenchmarking.org Frames Per Second, More Is Better DDraceNetwork 16.3.2 Resolution: 1920 x 1080 - Mode: Fullscreen - Renderer: Vulkan - Zoom: Default - Demo: Multeasymap GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 900 1800 2700 3600 4500 SE +/- 34.23, N = 15 SE +/- 35.04, N = 3 SE +/- 54.36, N = 3 4263.27 3552.13 4045.57 1. (CXX) g++ options: -O3 -lrt -ldl -lvulkan -lnotify -lgdk_pixbuf-2.0 -lgio-2.0 -lgobject-2.0 -lglib-2.0 -fuse-ld=gold
SVT-HEVC Tuning: 1 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 1 - Input: Bosphorus 4K GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 1.305 2.61 3.915 5.22 6.525 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 5.79 5.80 5.77 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
Xonotic Resolution: 1920 x 1080 - Effects Quality: Ultimate OpenBenchmarking.org Frames Per Second, More Is Better Xonotic 0.8.5 Resolution: 1920 x 1080 - Effects Quality: Ultimate GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 110 220 330 440 550 SE +/- 5.42, N = 3 SE +/- 0.82, N = 3 SE +/- 0.51, N = 3 518.26 387.42 393.41 MIN: 99 / MAX: 1055 MIN: 40 / MAX: 1000 MIN: 46 / MAX: 1036
GROMACS Implementation: MPI CPU - Input: water_GMX50_bare OpenBenchmarking.org Ns Per Day, More Is Better GROMACS 2022.1 Implementation: MPI CPU - Input: water_GMX50_bare GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 0.5618 1.1236 1.6854 2.2472 2.809 SE +/- 0.001, N = 3 SE +/- 0.001, N = 3 SE +/- 0.003, N = 3 2.497 2.491 2.491 1. (CXX) g++ options: -O3
OpenFOAM Input: drivaerFastback, Small Mesh Size - Execution Time OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 10 Input: drivaerFastback, Small Mesh Size - Execution Time GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 40 80 120 160 200 166.37 167.44 168.21 1. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm
OpenFOAM Input: drivaerFastback, Small Mesh Size - Mesh Time OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 10 Input: drivaerFastback, Small Mesh Size - Mesh Time GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 6 12 18 24 30 23.36 23.16 23.30 1. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm
Stargate Digital Audio Workstation Sample Rate: 192000 - Buffer Size: 512 OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 21.10.9 Sample Rate: 192000 - Buffer Size: 512 GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 0.9349 1.8698 2.8047 3.7396 4.6745 SE +/- 0.018509, N = 3 SE +/- 0.037942, N = 4 SE +/- 0.017846, N = 3 4.152298 3.055673 4.155233 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
Xonotic Resolution: 1920 x 1080 - Effects Quality: Ultra OpenBenchmarking.org Frames Per Second, More Is Better Xonotic 0.8.5 Resolution: 1920 x 1080 - Effects Quality: Ultra GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 140 280 420 560 700 SE +/- 1.87, N = 3 SE +/- 1.48, N = 3 SE +/- 1.34, N = 3 645.79 553.97 556.29 MIN: 413 / MAX: 1128 MIN: 284 / MAX: 1073 MIN: 281 / MAX: 1056
Timed Godot Game Engine Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Godot Game Engine Compilation 3.2.3 Time To Compile GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 12 24 36 48 60 SE +/- 0.17, N = 3 SE +/- 0.05, N = 3 SE +/- 0.09, N = 3 53.78 53.98 53.87
SVT-AV1 Encoder Mode: Preset 4 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.2 Encoder Mode: Preset 4 - Input: Bosphorus 4K GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 0.7727 1.5454 2.3181 3.0908 3.8635 SE +/- 0.004, N = 3 SE +/- 0.004, N = 3 SE +/- 0.008, N = 3 3.434 2.992 3.424 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Stargate Digital Audio Workstation Sample Rate: 192000 - Buffer Size: 1024 OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 21.10.9 Sample Rate: 192000 - Buffer Size: 1024 GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 1.0197 2.0394 3.0591 4.0788 5.0985 SE +/- 0.003512, N = 3 SE +/- 0.023836, N = 3 SE +/- 0.004427, N = 3 4.500125 4.427065 4.532117 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
Unvanquished Resolution: 1920 x 1080 - Effects Quality: High OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.53 Resolution: 1920 x 1080 - Effects Quality: High GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 140 280 420 560 700 SE +/- 2.47, N = 3 SE +/- 10.53, N = 15 SE +/- 1.59, N = 3 665.3 409.3 595.4
NAMD ATPase Simulation - 327,506 Atoms OpenBenchmarking.org days/ns, Fewer Is Better NAMD 2.14 ATPase Simulation - 327,506 Atoms GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 0.1876 0.3752 0.5628 0.7504 0.938 SE +/- 0.00096, N = 3 SE +/- 0.00089, N = 3 SE +/- 0.00109, N = 3 0.83367 0.83092 0.83222
MBW Test: Memory Copy - Array Size: 8192 MiB OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy - Array Size: 8192 MiB GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 4K 8K 12K 16K 20K SE +/- 36.90, N = 3 SE +/- 35.88, N = 3 SE +/- 120.52, N = 3 19941.34 19549.77 19738.29 1. (CC) gcc options: -O3 -march=native
Timed Linux Kernel Compilation Build: defconfig OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 5.18 Build: defconfig GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 9 18 27 36 45 SE +/- 0.26, N = 3 SE +/- 0.26, N = 3 SE +/- 0.27, N = 3 40.69 41.05 40.85
Unvanquished Resolution: 1920 x 1080 - Effects Quality: Ultra OpenBenchmarking.org Frames Per Second, More Is Better Unvanquished 0.53 Resolution: 1920 x 1080 - Effects Quality: Ultra GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 140 280 420 560 700 SE +/- 0.51, N = 3 SE +/- 10.51, N = 12 SE +/- 3.40, N = 3 669.7 415.9 586.7
MBW Test: Memory Copy, Fixed Block Size - Array Size: 4096 MiB OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy, Fixed Block Size - Array Size: 4096 MiB GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 4K 8K 12K 16K 20K SE +/- 147.28, N = 3 SE +/- 190.78, N = 5 SE +/- 213.97, N = 4 17415.88 17122.92 17862.38 1. (CC) gcc options: -O3 -march=native
Stargate Digital Audio Workstation Sample Rate: 96000 - Buffer Size: 512 OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 21.10.9 Sample Rate: 96000 - Buffer Size: 512 GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 2 4 6 8 10 SE +/- 0.008072, N = 3 SE +/- 0.047856, N = 3 SE +/- 0.014432, N = 3 6.285946 6.220335 6.317154 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
Stargate Digital Audio Workstation Sample Rate: 96000 - Buffer Size: 1024 OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 21.10.9 Sample Rate: 96000 - Buffer Size: 1024 GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 2 4 6 8 10 SE +/- 0.032029, N = 3 SE +/- 0.015894, N = 3 SE +/- 0.011127, N = 3 6.643385 6.634006 6.691616 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
SVT-VP9 Tuning: VMAF Optimized - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: VMAF Optimized - Input: Bosphorus 4K GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 20 40 60 80 100 SE +/- 0.75, N = 15 SE +/- 0.74, N = 15 SE +/- 0.91, N = 12 110.78 109.96 110.19 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
RAMspeed SMP Type: Triad - Benchmark: Integer OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Triad - Benchmark: Integer GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 13K 26K 39K 52K 65K SE +/- 127.26, N = 3 SE +/- 74.72, N = 3 SE +/- 51.04, N = 3 61570.71 61005.73 60886.49 1. (CC) gcc options: -O3 -march=native
RAMspeed SMP Type: Average - Benchmark: Floating Point OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Average - Benchmark: Floating Point GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 14K 28K 42K 56K 70K SE +/- 48.56, N = 3 SE +/- 240.54, N = 3 SE +/- 187.42, N = 3 66415.43 65643.81 65377.43 1. (CC) gcc options: -O3 -march=native
RAMspeed SMP Type: Add - Benchmark: Integer OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Add - Benchmark: Integer GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 13K 26K 39K 52K 65K SE +/- 249.37, N = 3 SE +/- 320.16, N = 3 SE +/- 73.80, N = 3 61801.87 61382.59 60895.67 1. (CC) gcc options: -O3 -march=native
RAMspeed SMP Type: Scale - Benchmark: Floating Point OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Scale - Benchmark: Floating Point GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 15K 30K 45K 60K 75K SE +/- 262.17, N = 3 SE +/- 534.82, N = 3 SE +/- 281.15, N = 3 70644.87 70396.37 70123.32 1. (CC) gcc options: -O3 -march=native
RAMspeed SMP Type: Add - Benchmark: Floating Point OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Add - Benchmark: Floating Point GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 13K 26K 39K 52K 65K SE +/- 392.69, N = 3 SE +/- 206.96, N = 3 SE +/- 191.79, N = 3 62057.15 61261.69 61909.57 1. (CC) gcc options: -O3 -march=native
RAMspeed SMP Type: Copy - Benchmark: Floating Point OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Copy - Benchmark: Floating Point GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 15K 30K 45K 60K 75K SE +/- 481.32, N = 3 SE +/- 199.54, N = 3 SE +/- 216.25, N = 3 70298.20 70356.91 69929.36 1. (CC) gcc options: -O3 -march=native
RAMspeed SMP Type: Triad - Benchmark: Floating Point OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Triad - Benchmark: Floating Point GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 13K 26K 39K 52K 65K SE +/- 218.68, N = 3 SE +/- 302.53, N = 3 SE +/- 202.59, N = 3 61354.16 60927.57 61317.18 1. (CC) gcc options: -O3 -march=native
RAMspeed SMP Type: Average - Benchmark: Integer OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Average - Benchmark: Integer GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 14K 28K 42K 56K 70K SE +/- 294.47, N = 3 SE +/- 453.58, N = 3 SE +/- 213.65, N = 3 66084.68 65878.93 66011.50 1. (CC) gcc options: -O3 -march=native
RAMspeed SMP Type: Scale - Benchmark: Integer OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Scale - Benchmark: Integer GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 15K 30K 45K 60K 75K SE +/- 188.29, N = 3 SE +/- 241.04, N = 3 SE +/- 336.46, N = 3 70898.08 70370.60 69663.60 1. (CC) gcc options: -O3 -march=native
RAMspeed SMP Type: Copy - Benchmark: Integer OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Copy - Benchmark: Integer GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 15K 30K 45K 60K 75K SE +/- 185.95, N = 3 SE +/- 478.63, N = 3 SE +/- 101.89, N = 3 70544.02 70078.90 70096.60 1. (CC) gcc options: -O3 -march=native
SVT-HEVC Tuning: 1 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 1 - Input: Bosphorus 1080p GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 5 10 15 20 25 SE +/- 0.05, N = 3 SE +/- 0.07, N = 3 SE +/- 0.03, N = 3 22.81 22.86 22.76 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
Swet Average OpenBenchmarking.org Operations Per Second, More Is Better Swet 1.5.16 Average GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 300M 600M 900M 1200M 1500M SE +/- 12600421.30, N = 3 SE +/- 4979292.84, N = 3 SE +/- 14557964.15, N = 6 1419860753 1424879888 1427810080 1. (CC) gcc options: -lm -lpthread -lcurses -lrt
Stargate Digital Audio Workstation Sample Rate: 480000 - Buffer Size: 512 OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 21.10.9 Sample Rate: 480000 - Buffer Size: 512 GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 2 4 6 8 10 SE +/- 0.028325, N = 3 SE +/- 0.047751, N = 3 SE +/- 0.038401, N = 3 8.430656 8.439396 8.471645 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
MBW Test: Memory Copy - Array Size: 4096 MiB OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy - Array Size: 4096 MiB GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 4K 8K 12K 16K 20K SE +/- 209.93, N = 3 SE +/- 23.61, N = 3 SE +/- 109.32, N = 3 20163.91 19795.48 19850.56 1. (CC) gcc options: -O3 -march=native
Stargate Digital Audio Workstation Sample Rate: 44100 - Buffer Size: 512 OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 21.10.9 Sample Rate: 44100 - Buffer Size: 512 GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 2 4 6 8 10 SE +/- 0.095903, N = 3 SE +/- 0.040947, N = 3 SE +/- 0.024271, N = 3 8.440940 8.408079 8.551467 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
Stargate Digital Audio Workstation Sample Rate: 480000 - Buffer Size: 1024 OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 21.10.9 Sample Rate: 480000 - Buffer Size: 1024 GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 2 4 6 8 10 SE +/- 0.012564, N = 3 SE +/- 0.063982, N = 3 SE +/- 0.059475, N = 3 8.814174 8.808473 8.802010 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
Stargate Digital Audio Workstation Sample Rate: 44100 - Buffer Size: 1024 OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 21.10.9 Sample Rate: 44100 - Buffer Size: 1024 GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 2 4 6 8 10 SE +/- 0.042656, N = 3 SE +/- 0.024044, N = 3 SE +/- 0.026760, N = 3 8.846218 8.819321 8.820758 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
7-Zip Compression Test: Decompression Rating OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 22.01 Test: Decompression Rating GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 40K 80K 120K 160K 200K SE +/- 291.97, N = 3 SE +/- 595.12, N = 3 SE +/- 586.04, N = 3 176029 176501 175835 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
7-Zip Compression Test: Compression Rating OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 22.01 Test: Compression Rating GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 40K 80K 120K 160K 200K SE +/- 37.62, N = 3 SE +/- 436.38, N = 3 SE +/- 230.76, N = 3 179543 177787 177626 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
SVT-AV1 Encoder Mode: Preset 4 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.2 Encoder Mode: Preset 4 - Input: Bosphorus 1080p GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 3 6 9 12 15 SE +/- 0.034, N = 3 SE +/- 0.013, N = 3 SE +/- 0.056, N = 3 9.865 7.363 9.816 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
SVT-AV1 Encoder Mode: Preset 8 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.2 Encoder Mode: Preset 8 - Input: Bosphorus 4K GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 20 40 60 80 100 SE +/- 0.28, N = 3 SE +/- 0.08, N = 3 SE +/- 0.29, N = 3 81.45 75.13 81.35 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Sysbench Test: RAM / Memory OpenBenchmarking.org MiB/sec, More Is Better Sysbench 1.0.20 Test: RAM / Memory GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 3K 6K 9K 12K 15K SE +/- 20.00, N = 3 SE +/- 34.63, N = 3 SE +/- 16.15, N = 3 12597.07 12610.85 12566.17 1. (CC) gcc options: -O2 -funroll-loops -rdynamic -ldl -laio -lm
SVT-HEVC Tuning: 7 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 7 - Input: Bosphorus 4K GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 20 40 60 80 100 SE +/- 0.15, N = 3 SE +/- 0.17, N = 3 SE +/- 0.14, N = 3 101.24 100.20 100.32 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
SVT-VP9 Tuning: Visual Quality Optimized - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: Visual Quality Optimized - Input: Bosphorus 4K GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 20 40 60 80 100 SE +/- 0.16, N = 3 SE +/- 0.08, N = 3 SE +/- 0.06, N = 3 108.06 107.86 107.19 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
SVT-VP9 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 4K GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 30 60 90 120 150 SE +/- 0.04, N = 3 SE +/- 0.18, N = 3 SE +/- 0.16, N = 3 120.58 119.98 119.57 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
SVT-AV1 Encoder Mode: Preset 10 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.2 Encoder Mode: Preset 10 - Input: Bosphorus 4K GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 30 60 90 120 150 SE +/- 0.19, N = 3 SE +/- 0.34, N = 3 SE +/- 0.14, N = 3 145.74 130.86 144.65 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
SVT-HEVC Tuning: 10 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 10 - Input: Bosphorus 4K GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 40 80 120 160 200 SE +/- 0.24, N = 3 SE +/- 0.44, N = 3 SE +/- 0.31, N = 3 167.72 167.26 167.25 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
SVT-AV1 Encoder Mode: Preset 12 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.2 Encoder Mode: Preset 12 - Input: Bosphorus 4K GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 50 100 150 200 250 SE +/- 0.73, N = 3 SE +/- 0.69, N = 3 SE +/- 1.08, N = 3 205.96 186.69 204.35 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
SVT-VP9 Tuning: VMAF Optimized - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: VMAF Optimized - Input: Bosphorus 1080p GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 90 180 270 360 450 SE +/- 4.04, N = 7 SE +/- 4.73, N = 4 SE +/- 3.79, N = 8 435.35 418.69 433.35 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
SVT-AV1 Encoder Mode: Preset 8 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.2 Encoder Mode: Preset 8 - Input: Bosphorus 1080p GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 50 100 150 200 250 SE +/- 1.16, N = 3 SE +/- 0.46, N = 3 SE +/- 0.48, N = 3 211.35 158.34 210.80 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
SVT-HEVC Tuning: 7 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 7 - Input: Bosphorus 1080p GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 70 140 210 280 350 SE +/- 0.86, N = 3 SE +/- 0.56, N = 3 SE +/- 0.46, N = 3 324.80 314.86 323.86 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
SVT-VP9 Tuning: Visual Quality Optimized - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: Visual Quality Optimized - Input: Bosphorus 1080p GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 80 160 240 320 400 SE +/- 0.63, N = 3 SE +/- 0.69, N = 3 SE +/- 0.78, N = 3 383.25 372.57 382.01 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
SVT-AV1 Encoder Mode: Preset 10 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.2 Encoder Mode: Preset 10 - Input: Bosphorus 1080p GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 100 200 300 400 500 SE +/- 3.72, N = 3 SE +/- 4.08, N = 3 SE +/- 2.24, N = 3 460.31 349.15 455.22 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
MBW Test: Memory Copy, Fixed Block Size - Array Size: 128 MiB OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy, Fixed Block Size - Array Size: 128 MiB GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 4K 8K 12K 16K 20K SE +/- 67.09, N = 3 SE +/- 355.38, N = 15 SE +/- 28.47, N = 3 20753.10 19354.08 20803.90 1. (CC) gcc options: -O3 -march=native
SVT-VP9 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 100 200 300 400 500 SE +/- 1.42, N = 3 SE +/- 1.19, N = 3 SE +/- 0.48, N = 3 449.74 435.43 447.30 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
SVT-HEVC Tuning: 10 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 10 - Input: Bosphorus 1080p GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 130 260 390 520 650 SE +/- 0.90, N = 3 SE +/- 2.27, N = 3 SE +/- 1.17, N = 3 594.06 576.76 589.20 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
SVT-AV1 Encoder Mode: Preset 12 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.2 Encoder Mode: Preset 12 - Input: Bosphorus 1080p GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 160 320 480 640 800 SE +/- 1.41, N = 3 SE +/- 0.61, N = 3 SE +/- 0.97, N = 3 718.82 453.18 709.17 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
yquake2 Renderer: OpenGL 3.x - AF: On - MSAA: On - Resolution: 1920 x 1080 OpenBenchmarking.org Frames Per Second, More Is Better yquake2 8.10 Renderer: OpenGL 3.x - AF: On - MSAA: On - Resolution: 1920 x 1080 GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 400 800 1200 1600 2000 SE +/- 11.50, N = 3 SE +/- 10.33, N = 3 SE +/- 8.29, N = 3 1744.4 1469.9 1605.5 1. (CC) gcc options: -shared -lm -ldl -rdynamic -lSDL2 -O2 -pipe -fomit-frame-pointer -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC
yquake2 Renderer: Vulkan - AF: On - MSAA: On - Resolution: 1920 x 1080 OpenBenchmarking.org Frames Per Second, More Is Better yquake2 8.10 Renderer: Vulkan - AF: On - MSAA: On - Resolution: 1920 x 1080 GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 400 800 1200 1600 2000 SE +/- 5.63, N = 3 SE +/- 5.05, N = 3 SE +/- 1.40, N = 3 1755.6 1627.5 1630.3 1. (CC) gcc options: -shared -lm -ldl -rdynamic -lSDL2 -O2 -pipe -fomit-frame-pointer -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC
MBW Test: Memory Copy - Array Size: 128 MiB OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy - Array Size: 128 MiB GSKILL EXPO I GSKILL DDR5-6000 Other GSKILL Repeat 4K 8K 12K 16K 20K SE +/- 46.27, N = 3 SE +/- 227.17, N = 3 SE +/- 281.01, N = 3 19400.26 18913.27 19642.94 1. (CC) gcc options: -O3 -march=native
Phoronix Test Suite v10.8.5