extra compute smoke

Benchmarks for a future article.

HTML result view exported from: https://openbenchmarking.org/result/2411268-PTS-EXTRACOM10&sro&grw.

extra compute smokeProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLOpenCLCompilerFile-SystemScreen ResolutionDisplay DriverA770 aA770 bA580 aA580 bA750 aA750 b7800XT a7800XT b7700XT a7700XT b79800GRE a79800GRE b7900XT7900 XT x7900 XT b7900XTX7900XTX b7600XT a7600XT b76007600 b4060 a4060 b4070 a4070 b70 Ti SUPER a70 Ti SUPER b4070 super a4070 super bRTX 40804080 b4080 super abbc4090 a4090 b4090 cAMD Ryzen 7 9800X3D 8-Core @ 5.27GHz (8 Cores / 16 Threads)ASRock X870E Taichi (3.12.AS02 BIOS)AMD Device 14d82 x 16GB DDR5-6000MT/s F5-6000J2836G16GWestern Digital WD_BLACK SN850X 2000GBIntel Arc A770 DG2 16GBIntel DG2 AudioDELL U2723QERealtek Device 8126 + MEDIATEK Device 0717Ubuntu 24.046.12.0-rc6-phx-drm-next (x86_64)GNOME Shell 46.0X Server + Wayland4.6 Mesa 25.0~git2411220600.25b8f4~oibaf~n (git-25b8f4f 2024-11-22 noble-oibaf-ppa)OpenCL 3.0GCC 13.2.0ext43840x2160Intel Arc A580 DG2 8GBIntel Arc A750 DG2 8GBAMD Ryzen 7 9800X3D 8-Core @ 6.22GHz (8 Cores / 16 Threads)AMD Radeon RX 7800 XT 16GBAMD Navi 31 HDMI/DP6.8.0-49-generic (x86_64)4.6 Mesa 25.0~git2411230600.3aa749~oibaf~n (git-3aa7497 2024-11-23 noble-oibaf-ppa) (LLVM 18.1.8 DRM 3.58)OpenCL 2.1 AMD-APP (3625.0)XFX AMD Radeon RX 7700 XT 12GBAMD Radeon RX 7900 GRE 16GBAMD Radeon RX 7900 XT 20GBXFX AMD Radeon RX 7900 XTX 24GBXFX AMD Radeon RX 7600 XT 16GBAMD Radeon RX 7600 8GBMSI NVIDIA GeForce RTX 4060 8GBNVIDIA AD107 HD AudioX Server 1.21.1.11NVIDIA 565.57.014.6.0OpenCL 3.0 CUDA 12.7.33NVIDIA GeForce RTX 4070 12GBNVIDIA AD104 HD AudioASUS NVIDIA GeForce RTX 4070 Ti SUPER 16GBNVIDIA Device 22bbNVIDIA GeForce RTX 4070 SUPER 12GBNVIDIA AD104 HD AudioNVIDIA GeForce RTX 4080 16GBNVIDIA Device 22bbNVIDIA GeForce RTX 4080 SUPER 16GBNVIDIA GeForce RTX 4090 24GBNVIDIA AD102 HD AudioOpenBenchmarking.orgKernel Details- A770 a: Transparent Huge Pages: madvise- A770 b: Transparent Huge Pages: madvise- A580 a: Transparent Huge Pages: madvise- A580 b: Transparent Huge Pages: madvise- A750 a: Transparent Huge Pages: madvise- A750 b: Transparent Huge Pages: madvise- 7800XT a: Transparent Huge Pages: madvise- 7800XT b: Transparent Huge Pages: madvise- 7700XT a: Transparent Huge Pages: madvise- 7700XT b: Transparent Huge Pages: madvise- 79800GRE a: Transparent Huge Pages: madvise- 79800GRE b: Transparent Huge Pages: madvise- 7900XT: Transparent Huge Pages: madvise- 7900 XT x: Transparent Huge Pages: madvise- 7900 XT b: Transparent Huge Pages: madvise- 7900XTX: Transparent Huge Pages: madvise- 7900XTX b: Transparent Huge Pages: madvise- 7600XT a: Transparent Huge Pages: madvise- 7600XT b: Transparent Huge Pages: madvise- 7600: Transparent Huge Pages: madvise- 7600 b: Transparent Huge Pages: madvise- 4060 a: nouveau.modeset=0 - Transparent Huge Pages: madvise- 4060 b: nouveau.modeset=0 - Transparent Huge Pages: madvise- 4070 a: nouveau.modeset=0 - Transparent Huge Pages: madvise- 4070 b: nouveau.modeset=0 - Transparent Huge Pages: madvise- 70 Ti SUPER a: nouveau.modeset=0 - Transparent Huge Pages: madvise- 70 Ti SUPER b: nouveau.modeset=0 - Transparent Huge Pages: madvise- 4070 super a: nouveau.modeset=0 - Transparent Huge Pages: madvise- 4070 super b: nouveau.modeset=0 - Transparent Huge Pages: madvise- RTX 4080: nouveau.modeset=0 - Transparent Huge Pages: madvise- 4080 b: nouveau.modeset=0 - Transparent Huge Pages: madvise- 4080 super a: nouveau.modeset=0 - Transparent Huge Pages: madvise- bb: nouveau.modeset=0 - Transparent Huge Pages: madvise- c: nouveau.modeset=0 - Transparent Huge Pages: madvise- 4090 a: nouveau.modeset=0 - Transparent Huge Pages: madvise- 4090 b: nouveau.modeset=0 - Transparent Huge Pages: madvise- 4090 c: nouveau.modeset=0 - Transparent Huge Pages: madviseCompiler 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-backtrace --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-13-uJ7kn6/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-uJ7kn6/gcc-13-13.2.0/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-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- A770 a: Scaling Governor: amd-pstate-epp performance (Boost: Enabled EPP: performance) - CPU Microcode: 0xb404023- A770 b: Scaling Governor: amd-pstate-epp performance (Boost: Enabled EPP: performance) - CPU Microcode: 0xb404023- A580 a: Scaling Governor: amd-pstate-epp performance (Boost: Enabled EPP: performance) - CPU Microcode: 0xb404023- A580 b: Scaling Governor: amd-pstate-epp performance (Boost: Enabled EPP: performance) - CPU Microcode: 0xb404023- A750 a: Scaling Governor: amd-pstate-epp performance (Boost: Enabled EPP: performance) - CPU Microcode: 0xb404023- A750 b: Scaling Governor: amd-pstate-epp performance (Boost: Enabled EPP: performance) - CPU Microcode: 0xb404023- 7800XT a: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xb404023- 7800XT b: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xb404023- 7700XT a: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xb404023- 7700XT b: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xb404023- 79800GRE a: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xb404023- 79800GRE b: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xb404023- 7900XT: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xb404023- 7900 XT x: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xb404023- 7900 XT b: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xb404023- 7900XTX: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xb404023- 7900XTX b: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xb404023- 7600XT a: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xb404023- 7600XT b: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xb404023- 7600: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xb404023- 7600 b: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xb404023- 4060 a: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xb404023- 4060 b: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xb404023- 4070 a: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xb404023- 4070 b: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xb404023- 70 Ti SUPER a: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xb404023- 70 Ti SUPER b: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xb404023- 4070 super a: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xb404023- 4070 super b: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xb404023- RTX 4080: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xb404023- 4080 b: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xb404023- 4080 super a: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xb404023- bb: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xb404023- c: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xb404023- 4090 a: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xb404023- 4090 b: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xb404023- 4090 c: Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xb404023Security Details- gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: 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 Enhanced / Automatic IBRS; IBPB: conditional; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affectedGraphics Details- 7800XT a: BAR1 / Visible vRAM Size: 16368 MB- 7800XT b: BAR1 / Visible vRAM Size: 16368 MB- 7700XT a: BAR1 / Visible vRAM Size: 12272 MB- 7700XT b: BAR1 / Visible vRAM Size: 12272 MB- 79800GRE a: BAR1 / Visible vRAM Size: 16368 MB- 79800GRE b: BAR1 / Visible vRAM Size: 16368 MB- 7900XT: BAR1 / Visible vRAM Size: 20464 MB- 7900 XT x: BAR1 / Visible vRAM Size: 20464 MB- 7900 XT b: BAR1 / Visible vRAM Size: 20464 MB- 7900XTX: BAR1 / Visible vRAM Size: 24560 MB- 7900XTX b: BAR1 / Visible vRAM Size: 24560 MB- 7600XT a: BAR1 / Visible vRAM Size: 16368 MB- 7600XT b: BAR1 / Visible vRAM Size: 16368 MB- 7600: BAR1 / Visible vRAM Size: 8176 MB- 7600 b: BAR1 / Visible vRAM Size: 8176 MB- 4060 a: BAR1 / Visible vRAM Size: 8192 MiB - vBIOS Version: 95.07.31.00.e3- 4060 b: BAR1 / Visible vRAM Size: 8192 MiB - vBIOS Version: 95.07.31.00.e3- 4070 a: BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 95.04.49.00.03- 4070 b: BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 95.04.49.00.03- 70 Ti SUPER a: BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 95.03.45.00.9c- 70 Ti SUPER b: BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 95.03.45.00.9c- 4070 super a: BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 95.04.69.00.01- 4070 super b: BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 95.04.69.00.01- RTX 4080: BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 95.03.0e.00.04- 4080 b: BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 95.03.0e.00.04- 4080 super a: BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 95.03.44.00.01- bb: BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 95.03.44.00.01- c: BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 95.03.44.00.01- 4090 a: BAR1 / Visible vRAM Size: 32768 MiB - vBIOS Version: 95.02.20.00.01- 4090 b: BAR1 / Visible vRAM Size: 32768 MiB - vBIOS Version: 95.02.20.00.01- 4090 c: BAR1 / Visible vRAM Size: 32768 MiB - vBIOS Version: 95.02.20.00.01OpenCL Details- 4060 a: GPU Compute Cores: 3072- 4060 b: GPU Compute Cores: 3072- 4070 a: GPU Compute Cores: 5888- 4070 b: GPU Compute Cores: 5888- 70 Ti SUPER a: GPU Compute Cores: 8448- 70 Ti SUPER b: GPU Compute Cores: 8448- 4070 super a: GPU Compute Cores: 7168- 4070 super b: GPU Compute Cores: 7168- RTX 4080: GPU Compute Cores: 9728- 4080 b: GPU Compute Cores: 9728- 4080 super a: GPU Compute Cores: 10240- bb: GPU Compute Cores: 10240- c: GPU Compute Cores: 10240- 4090 a: GPU Compute Cores: 16384- 4090 b: GPU Compute Cores: 16384- 4090 c: GPU Compute Cores: 16384

extra compute smokeblender: BMW27 - Intel oneAPIopencl-benchmark: INT8 Computeblender: Junkshop - Intel oneAPIblender: Classroom - Intel oneAPIblender: Pabellon Barcelona - Intel oneAPIblender: BMW27 - Radeon HIPblender: Junkshop - Radeon HIPopencl-benchmark: Memory Bandwidth Coalesced Readopencl-benchmark: Memory Bandwidth Coalesced Writeopencl-benchmark: INT16 Computeblender: Fishy Cat - Intel oneAPIblender: Barbershop - Intel oneAPIopencl-benchmark: INT32 Computeopencl-benchmark: INT64 Computeopencl-benchmark: FP16 Computeopencl-benchmark: FP32 Computeblender: Classroom - Radeon HIPblender: Fishy Cat - Radeon HIPblender: Barbershop - Radeon HIPblender: Pabellon Barcelona - Radeon HIPopencl-benchmark: FP64 Computeblender: BMW27 - NVIDIA CUDAblender: BMW27 - NVIDIA OptiXblender: Classroom - NVIDIA CUDAblender: Classroom - NVIDIA OptiXblender: Fishy Cat - NVIDIA CUDAblender: Fishy Cat - NVIDIA OptiXblender: Pabellon Barcelona - NVIDIA CUDAblender: Pabellon Barcelona - NVIDIA OptiXblender: Barbershop - NVIDIA CUDAblender: Barbershop - NVIDIA OptiXblender: Junkshop - NVIDIA CUDAblender: Junkshop - NVIDIA OptiXvkpeak: fp32-scalarvkpeak: fp32-vec4vkpeak: fp16-scalarvkpeak: fp16-vec4vkpeak: fp64-scalarvkpeak: fp64-vec4vkpeak: int32-scalarvkpeak: int32-vec4vkpeak: int16-scalarvkpeak: int16-vec4fluidx3d: FP32-FP32fluidx3d: FP32-FP16Cfluidx3d: FP32-FP16SA770 aA770 bA580 aA580 bA750 aA750 b7800XT a7800XT b7700XT a7700XT b79800GRE a79800GRE b7900XT7900 XT x7900 XT b7900XTX7900XTX b7600XT a7600XT b76007600 b4060 a4060 b4070 a4070 b70 Ti SUPER a70 Ti SUPER b4070 super a4070 super bRTX 40804080 b4080 super abbc4090 a4090 b4090 c12.7511.20225.8635.8244.26225.94435.5430.05915.78164.225.441.28818.26812.10719001.4715880.5224448.4526098.6725594163436312.7711.20125.8435.8344.25225.97437.8930.09415.78164.315.3731.27718.50312.04818841.2115880.5524453.1426098.6125924165436215.448.51429.4244.1449.91191.32411.8424.10919.55198.373.9211.01513.9429.14613840.9211911.4318205.7519564.3124803397369715.358.42129.4644.0549.9190.87412.524.14919.55198.583.9180.99713.8329.14313850.5511911.8418322.1619566.3724573352368813.1310.13525.6837.2842.75210.34415.9927.40516.64171.324.7961.16916.04810.75316875.7613896.5621374.5122837.5324553858410913.1410.13625.7937.2942.75210.71415.0327.42116.65171.214.7671.16416.23110.7816915.6813899.621381.8222841.672466386240747.30418.5925.58467.6353.7812.0843.7963.0632.98217.65631.3631.68130.550.62316493.3214397.2416486.930880.52649.85649.114082.544070.0815969.6732488.031704313231387.2718.5625.44465.84355.3912.3013.8373.05337.35919.24331.3531.57130.5872.020.62516548.3614513.5216540.6231072.02650.53649.354093.224084.1816012.2732569.81701314831306.79921.6129.57350.69259.311.3783.5452.87130.94515.71235.9435.76152.8779.730.56415061.5413337.0715029.1929829.5591.3590.523755.023749.8515024.1331554.811399267325297.40421.6529.5357.85265.3313.6153.6452.85930.35615.7135.9235.78152.8279.680.56815056.1213332.9715022.229833.29591.68590.893755.873761.1315025.4731539.8213942685252010.39415.2423.29449.73343.2819.1274.913.58945.38125.05626.4325.76113.1659.740.81521585.818485.0721446.8539765.47846.71846.855203.485176.3320062.7838271.251824389738439.00515.2123.27439.9340.2819.0184.8613.62945.03424.09626.4325.85113.4259.80.81421371.6817934.9220946.0238931.57845.97845.355160.675123.4319847.0337897.5718503942387410.74912.4218.94569.37428.5721.9755.8064.37354.95128.26421.7622.2391.747.090.9424908.3221555.6724906.146829.04978.19976.736155.826144.2423802.9148144.7429755971561512.43612.4318.93636.48470.1722.3685.7584.37056.45429.07821.7822.1691.6747.140.93724830.2921450.7124888.5046762.48977.42976.656150.986124.3323699.6847917.6630176223569512.30212.4518.98632.57429.9221.9495.754.30355.96228.79121.8722.2991.8147.130.9224817.2621460.924875.8146787.11977.57976.816149.356126.0823711.9247960.1129965999562914.7112.2116.65743.12568.0324.8296.8374.8166.18734.39618.7819.3480.2340.61.1330298.3425211.2929352.8954161.351183.741178.827169.017160.5927722.554973.4732846522575714.80310.8116.65645.37564.6725.3526.794.91266.72734.11118.7819.3180.1340.741.12130043.7924912.0929113.5853785.741178.1211747156.047124.9427659.0454918.643363637957874.37830.6844.17230.98201.867.5482.2541.90219.7449.8954.4750.64233.5116.060.3579336.778278.989336.1318194.7368.26368.682338.732340.79321.0819025.411166231221374.3730.6644.22231.75201.337.5342.2531.91519.8599.96754.4450.64233.84116.050.3579333.188277.499369.1418248.62367.82368.712341.582340.859327.9719137.961166231821264.08932.0245.45233.31206.246.9652.051.6417.9019.28857.9953.99244.42124.210.3618486.357530.418506.1216306.93365.43363.282112.652117.818265.2916851.931199234621954.05132.0445.45232.9205.516.9222.051.65717.9059.27858.1153.95244.21124.130.368446.47498.098504.0916306.51365.37363.082112.232116.948264.6916845.51199234022086.214252.92258.257.388.4912.09616.97616.4180.26419.39.0638.724.2839.8919.3291.3926.31164.13101.1332.6219.728482.410955.328234.069500.41266.98267.058521.18523.25580.026097.151620312629576.214252.93258.287.3718.4912.08916.97716.4180.26419.349.0638.6724.239.819.3391.3826.31163.97101.4233.2419.718394.9610880.368200.019463.01267.06267.048521.218522.865583.966087.5716203126295812.091465.02456.1914.13116.2223.42832.46931.5080.50911.836.2622.9915.4423.2411.551.4716.8794.8262.4320.3712.6116376.4621695.116316.9818791.54514.24514.1316385.4816334.6810775.4912103.3928895407464012.157464.95456.6814.12116.2693.43232.56531.5170.50911.846.323.0115.4423.2711.551.4816.9194.9262.2720.3412.6116417.721695.2116315.5618786.6514.15514.1416389.9616334.6910779.6712102.2428885408464016.945619.42604.3820.08423.1424.28146.32944.8230.7269.085.0716.9411.6617.378.7137.5212.8870.9347.7615.689.7923384.130937.8423349.2226704.03732.04735.3923328.6923272.4715083.4316861.3838817248631216.949619.37603.6520.09123.1414.27846.32944.8230.7269.065.0816.9311.7417.428.6937.4912.8870.8747.1915.79.823385.930939.223350.0526703.81732.08735.4523330.0623272.2115101.516897.838807248631014.308464.98453.3716.7819.6724.14539.32338.10.61510.265.6419.313.1619.889.8943.214.6381.2954.5817.5310.9219899.3526289.3919731.1222737.78620.54620.3619764.6119758.412756.7114241.2327585576520714.29465.06453.7416.78119.6584.12339.24438.1010.61510.245.6319.3113.119.99.8743.1714.681.6654.3717.5510.8619896.8426290.3119766.6222738.54620.55620.3519724.9919720.8112749.414229.9127585575521020.04652.53601.4123.11226.5154.51153.19851.4320.8357.94.414.449.9215.367.6732.2211.0862.2841.8613.98.5926925.993558326852.1330821.39842.88842.752681626814.5617709.2320146.5538407751724720.038652.6600.3523.04426.5734.51853.19951.5860.8357.934.3914.439.9215.377.6332.2511.0862.2641.5913.948.5726867.9435493.7726775.1130750.68842.77842.626823.7626733.6517706.7520136.0538407755725120.87680.58616.0424.00127.594.24855.34153.5140.8657.824.4314.349.9915.137.4731.5310.9861.4741.4413.878.5627995.0937041.2927880.0732019.86877.58877.3927917.7727848.9518444.7420951.4339958064744420.863680.52616.524.00327.5884.24555.21153.5170.8657.844.4314.3310.0115.147.4531.4910.9461.0541.4913.928.5327959.5236957.627880.8132011.31876.25876.1127923.9527850.8518447.1520900.7740618062744420.863680.45617.1824.00327.5914.24655.20453.5280.8657.84.4414.329.9815.187.4631.5110.9561.3441.4713.868.5627964.4536957.2127880.3132018.94876.29875.8327916.0427849.1718446.8520907.4140538062744632.897927.8901.6138.2944.2474.33888.58185.6861.3925.853.5810.387.8510.885.4221.188.8245.8732.1911.127.1445178.9259624.7244970.3551625.871409.441409.1844900.2244804.5929562.5333053.42574311205945333.079927.85900.8838.30644.2554.34888.685.6431.3925.863.5910.377.810.915.4121.28.8445.8832.1511.117.1845079.359582.0144972.9851616.181409.461411.7844809.8444728.5829560.9933056.71574211206944932.896927.78901.1838.28344.2464.34888.59585.651.3925.813.5910.387.8310.875.4221.168.8445.8132.1711.157.1845082.1959442.544857.9951505.181409.441409.1244890.8244805.929563.2433060.165742112029448OpenBenchmarking.org

Blender

Blend File: BMW27 - Compute: Intel oneAPI

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: BMW27 - Compute: Intel oneAPIA580 aA580 bA750 aA750 bA770 aA770 b4812162015.4415.3513.1313.1412.7512.77

ProjectPhysX OpenCL-Benchmark

Operation: INT8 Compute

OpenBenchmarking.orgTIOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.6Operation: INT8 Compute4060 a4060 b4070 a4070 b4070 super a4070 super b4080 b4080 super a4090 a4090 b4090 c70 Ti SUPER a70 Ti SUPER b76007600 b7600XT a7600XT b7700XT a7700XT b7800XT a7800XT b7900 XT b7900 XT x7900XT7900XTX7900XTX b79800GRE a79800GRE bA580 aA580 bA750 aA750 bA770 aA770 bRTX 4080bbc816243240SE +/- 0.038, N = 36.2146.21412.09112.15714.30814.29020.03820.87032.89733.07932.89616.94516.9494.0894.0514.3784.3706.7997.4047.3047.27012.30212.43610.74914.71014.80310.3949.0058.5148.42110.13510.13611.20211.20120.04020.86320.8631. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

Blender

Blend File: Junkshop - Compute: Intel oneAPI

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Junkshop - Compute: Intel oneAPIA580 aA580 bA750 aA750 bA770 aA770 b71421283529.4229.4625.6825.7925.8625.84

Blender

Blend File: Classroom - Compute: Intel oneAPI

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Classroom - Compute: Intel oneAPIA580 aA580 bA750 aA750 bA770 aA770 b102030405044.1444.0537.2837.2935.8235.83

Blender

Blend File: Pabellon Barcelona - Compute: Intel oneAPI

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Pabellon Barcelona - Compute: Intel oneAPIA580 aA580 bA750 aA750 bA770 aA770 b112233445549.9149.9042.7542.7544.2644.25

Blender

Blend File: BMW27 - Compute: Radeon HIP

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: BMW27 - Compute: Radeon HIP76007600 b7600XT a7600XT b7700XT a7700XT b7800XT a7800XT b7900 XT b7900 XT x7900XT7900XTX7900XTX b79800GRE a79800GRE b714212835SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 332.0232.0430.6830.6621.6121.6518.5918.5612.4512.4312.4212.2110.8115.2415.21

Blender

Blend File: Junkshop - Compute: Radeon HIP

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Junkshop - Compute: Radeon HIP76007600 b7600XT a7600XT b7700XT a7700XT b7800XT a7800XT b7900 XT b7900 XT x7900XT7900XTX7900XTX b79800GRE a79800GRE b1020304050SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 345.4545.4544.1744.2229.5729.5025.5825.4418.9818.9318.9416.6516.6523.2923.27

ProjectPhysX OpenCL-Benchmark

Operation: Memory Bandwidth Coalesced Read

OpenBenchmarking.orgGB/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.6Operation: Memory Bandwidth Coalesced Read4060 a4060 b4070 a4070 b4070 super a4070 super b4080 b4080 super a4090 a4090 b4090 c70 Ti SUPER a70 Ti SUPER b76007600 b7600XT a7600XT b7700XT a7700XT b7800XT a7800XT b7900 XT b7900 XT x7900XT7900XTX7900XTX b79800GRE a79800GRE bA580 aA580 bA750 aA750 bA770 aA770 bRTX 4080bbc2004006008001000SE +/- 1.95, N = 3252.92252.93465.02464.95464.98465.06652.60680.58927.80927.85927.78619.42619.37233.31232.90230.98231.75350.69357.85467.60465.84632.57636.48569.37743.12645.37449.73439.90191.32190.87210.34210.71225.94225.97652.53680.52680.451. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

ProjectPhysX OpenCL-Benchmark

Operation: Memory Bandwidth Coalesced Write

OpenBenchmarking.orgGB/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.6Operation: Memory Bandwidth Coalesced Write4060 a4060 b4070 a4070 b4070 super a4070 super b4080 b4080 super a4090 a4090 b4090 c70 Ti SUPER a70 Ti SUPER b76007600 b7600XT a7600XT b7700XT a7700XT b7800XT a7800XT b7900 XT b7900 XT x7900XT7900XTX7900XTX b79800GRE a79800GRE bA580 aA580 bA750 aA750 bA770 aA770 bRTX 4080bbc2004006008001000SE +/- 2.90, N = 3258.25258.28456.19456.68453.37453.74600.35616.04901.61900.88901.18604.38603.65206.24205.51201.86201.33259.30265.33353.78355.39429.92470.17428.57568.03564.67343.28340.28411.84412.50415.99415.03435.54437.89601.41616.50617.181. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

ProjectPhysX OpenCL-Benchmark

Operation: INT16 Compute

OpenBenchmarking.orgTIOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.6Operation: INT16 Compute4060 a4060 b4070 a4070 b4070 super a4070 super b4080 b4080 super a4090 a4090 b4090 c70 Ti SUPER a70 Ti SUPER b76007600 b7600XT a7600XT b7700XT a7700XT b7800XT a7800XT b7900 XT b7900 XT x7900XT7900XTX7900XTX b79800GRE a79800GRE bA580 aA580 bA750 aA750 bA770 aA770 bRTX 4080bbc918273645SE +/- 0.086, N = 37.3807.37114.13114.12116.78016.78123.04424.00138.29038.30638.28320.08420.0916.9656.9227.5487.53411.37813.61512.08412.30121.94922.36821.97524.82925.35219.12719.01824.10924.14927.40527.42130.05930.09423.11224.00324.0031. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

Blender

Blend File: Fishy Cat - Compute: Intel oneAPI

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Fishy Cat - Compute: Intel oneAPIA580 aA580 bA750 aA750 bA770 aA770 b51015202519.5519.5516.6416.6515.7815.78

Blender

Blend File: Barbershop - Compute: Intel oneAPI

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Barbershop - Compute: Intel oneAPIA580 aA580 bA750 aA750 bA770 aA770 b4080120160200198.37198.58171.32171.21164.22164.31

ProjectPhysX OpenCL-Benchmark

Operation: INT32 Compute

OpenBenchmarking.orgTIOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.6Operation: INT32 Compute4060 a4060 b4070 a4070 b4070 super a4070 super b4080 b4080 super a4090 a4090 b4090 c70 Ti SUPER a70 Ti SUPER b76007600 b7600XT a7600XT b7700XT a7700XT b7800XT a7800XT b7900 XT b7900 XT x7900XT7900XTX7900XTX b79800GRE a79800GRE bA580 aA580 bA750 aA750 bA770 aA770 bRTX 4080bbc1020304050SE +/- 0.032, N = 38.4918.49116.22216.26919.67219.65826.57327.59044.24744.25544.24623.14223.1412.0502.0502.2542.2533.5453.6453.7963.8375.7505.7585.8066.8376.7904.9104.8613.9213.9184.7964.7675.4405.37326.51527.58827.5911. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

ProjectPhysX OpenCL-Benchmark

Operation: INT64 Compute

OpenBenchmarking.orgTIOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.6Operation: INT64 Compute4060 a4060 b4070 a4070 b4070 super a4070 super b4080 b4080 super a4090 a4090 b4090 c70 Ti SUPER a70 Ti SUPER b76007600 b7600XT a7600XT b7700XT a7700XT b7800XT a7800XT b7900 XT b7900 XT x7900XT7900XTX7900XTX b79800GRE a79800GRE bA580 aA580 bA750 aA750 bA770 aA770 bRTX 4080bbc1.10522.21043.31564.42085.526SE +/- 0.011, N = 32.0962.0893.4283.4324.1454.1234.5184.2484.3384.3484.3484.2814.2781.6401.6571.9021.9152.8712.8593.0603.0534.3034.3704.3734.8104.9123.5893.6291.0150.9971.1691.1641.2881.2774.5114.2454.2461. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

ProjectPhysX OpenCL-Benchmark

Operation: FP16 Compute

OpenBenchmarking.orgTFLOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.6Operation: FP16 Compute4060 a4060 b4070 a4070 b4070 super a4070 super b4080 b4080 super a4090 a4090 b4090 c70 Ti SUPER a70 Ti SUPER b76007600 b7600XT a7600XT b7700XT a7700XT b7800XT a7800XT b7900 XT b7900 XT x7900XT7900XTX7900XTX b79800GRE a79800GRE bA580 aA580 bA750 aA750 bA770 aA770 bRTX 4080bbc20406080100SE +/- 0.29, N = 316.9816.9832.4732.5739.3239.2453.2055.3488.5888.6088.6046.3346.3317.9017.9119.7419.8630.9530.3632.9837.3655.9656.4554.9566.1966.7345.3845.0313.9413.8316.0516.2318.2718.5053.2055.2155.201. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

ProjectPhysX OpenCL-Benchmark

Operation: FP32 Compute

OpenBenchmarking.orgTFLOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.6Operation: FP32 Compute4060 a4060 b4070 a4070 b4070 super a4070 super b4080 b4080 super a4090 a4090 b4090 c70 Ti SUPER a70 Ti SUPER b76007600 b7600XT a7600XT b7700XT a7700XT b7800XT a7800XT b7900 XT b7900 XT x7900XT7900XTX7900XTX b79800GRE a79800GRE bA580 aA580 bA750 aA750 bA770 aA770 bRTX 4080bbc20406080100SE +/- 0.040, N = 316.41816.41831.50831.51738.10038.10151.58653.51485.68685.64385.65044.82344.8239.2889.2789.8909.96715.71215.71017.65619.24328.79129.07828.26434.39634.11125.05624.0969.1469.14310.75310.78012.10712.04851.43253.51753.5281. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

Blender

Blend File: Classroom - Compute: Radeon HIP

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Classroom - Compute: Radeon HIP76007600 b7600XT a7600XT b7700XT a7700XT b7800XT a7800XT b7900 XT b7900 XT x7900XT7900XTX7900XTX b79800GRE a79800GRE b1326395265SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 357.9958.1154.4754.4435.9435.9231.3631.3521.8721.7821.7618.7818.7826.4326.43

Blender

Blend File: Fishy Cat - Compute: Radeon HIP

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Fishy Cat - Compute: Radeon HIP76007600 b7600XT a7600XT b7700XT a7700XT b7800XT a7800XT b7900 XT b7900 XT x7900XT7900XTX7900XTX b79800GRE a79800GRE b1224364860SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 353.9953.9550.6450.6435.7635.7831.6831.5722.2922.1622.2319.3419.3125.7625.85

Blender

Blend File: Barbershop - Compute: Radeon HIP

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Barbershop - Compute: Radeon HIP76007600 b7600XT a7600XT b7700XT a7700XT b7800XT a7800XT b7900 XT b7900 XT x7900XT7900XTX7900XTX b79800GRE a79800GRE b50100150200250SE +/- 0.07, N = 3SE +/- 0.04, N = 3SE +/- 0.07, N = 3244.42244.21233.50233.84152.87152.82130.55130.5891.8191.6791.7080.2380.13113.16113.42

Blender

Blend File: Pabellon Barcelona - Compute: Radeon HIP

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Pabellon Barcelona - Compute: Radeon HIP76007600 b7600XT a7600XT b7700XT a7700XT b7800XT b7900 XT b7900 XT x7900XT7900XTX7900XTX b79800GRE a79800GRE b306090120150SE +/- 0.03, N = 3SE +/- 0.02, N = 3124.21124.13116.06116.0579.7379.6872.0247.1347.1447.0940.6040.7459.7459.80

ProjectPhysX OpenCL-Benchmark

Operation: FP64 Compute

OpenBenchmarking.orgTFLOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.6Operation: FP64 Compute4060 a4060 b4070 a4070 b4070 super a4070 super b4080 b4080 super a4090 a4090 b4090 c70 Ti SUPER a70 Ti SUPER b76007600 b7600XT a7600XT b7700XT a7700XT b7800XT a7800XT b7900 XT b7900 XT x7900XT7900XTX7900XTX b79800GRE a79800GRE bRTX 4080bbc0.31320.62640.93961.25281.566SE +/- 0.007, N = 30.2640.2640.5090.5090.6150.6150.8350.8651.3921.3921.3920.7260.7260.3610.3600.3570.3570.5640.5680.6230.6250.9200.9370.9401.1301.1210.8150.8140.8350.8650.8651. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

Blender

Blend File: BMW27 - Compute: NVIDIA CUDA

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: BMW27 - Compute: NVIDIA CUDA4060 a4060 b4070 a4070 b4070 super a4070 super b4080 b4080 super a4090 a4090 b4090 c70 Ti SUPER a70 Ti SUPER bRTX 4080bbc51015202519.3019.3411.8311.8410.2610.247.937.825.855.865.819.089.067.907.847.80

Blender

Blend File: BMW27 - Compute: NVIDIA OptiX

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: BMW27 - Compute: NVIDIA OptiX4060 a4060 b4070 a4070 b4070 super a4070 super b4080 b4080 super a4090 a4090 b4090 c70 Ti SUPER a70 Ti SUPER bRTX 4080bbc36912159.069.066.266.305.645.634.394.433.583.593.595.075.084.404.434.44

Blender

Blend File: Classroom - Compute: NVIDIA CUDA

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Classroom - Compute: NVIDIA CUDA4060 a4060 b4070 a4070 b4070 super a4070 super b4080 b4080 super a4090 a4090 b4090 c70 Ti SUPER a70 Ti SUPER bRTX 4080bbc91827364538.7038.6722.9923.0119.3019.3114.4314.3410.3810.3710.3816.9416.9314.4414.3314.32

Blender

Blend File: Classroom - Compute: NVIDIA OptiX

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Classroom - Compute: NVIDIA OptiX4060 a4060 b4070 a4070 b4070 super a4070 super b4080 b4080 super a4090 a4090 b4090 c70 Ti SUPER a70 Ti SUPER bRTX 4080bbc61218243024.2824.2015.4415.4413.1613.109.929.997.857.807.8311.6611.749.9210.019.98

Blender

Blend File: Fishy Cat - Compute: NVIDIA CUDA

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Fishy Cat - Compute: NVIDIA CUDA4060 a4060 b4070 a4070 b4070 super a4070 super b4080 b4080 super a4090 a4090 b4090 c70 Ti SUPER a70 Ti SUPER bRTX 4080bbc91827364539.8939.8023.2423.2719.8819.9015.3715.1310.8810.9110.8717.3717.4215.3615.1415.18

Blender

Blend File: Fishy Cat - Compute: NVIDIA OptiX

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Fishy Cat - Compute: NVIDIA OptiX4060 a4060 b4070 a4070 b4070 super a4070 super b4080 b4080 super a4090 a4090 b4090 c70 Ti SUPER a70 Ti SUPER bRTX 4080bbc51015202519.3219.3311.5011.509.899.877.637.475.425.415.428.718.697.677.457.46

Blender

Blend File: Pabellon Barcelona - Compute: NVIDIA CUDA

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Pabellon Barcelona - Compute: NVIDIA CUDA4060 a4060 b4070 a4070 b4070 super a4070 super b4080 b4080 super a4090 a4090 b4090 c70 Ti SUPER a70 Ti SUPER bRTX 4080bbc2040608010091.3991.3851.4751.4843.2043.1732.2531.5321.1821.2021.1637.5237.4932.2231.4931.51

Blender

Blend File: Pabellon Barcelona - Compute: NVIDIA OptiX

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Pabellon Barcelona - Compute: NVIDIA OptiX4060 a4060 b4070 a4070 b4070 super a4070 super b4080 b4080 super a4090 a4090 b4090 c70 Ti SUPER a70 Ti SUPER bRTX 4080bbc61218243026.3126.3116.8716.9114.6314.6011.0810.988.828.848.8412.8812.8811.0810.9410.95

Blender

Blend File: Barbershop - Compute: NVIDIA CUDA

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Barbershop - Compute: NVIDIA CUDA4060 a4060 b4070 a4070 b4070 super a4070 super b4080 b4080 super a4090 a4090 b4090 c70 Ti SUPER a70 Ti SUPER bRTX 4080bbc4080120160200164.13163.9794.8294.9281.2981.6662.2661.4745.8745.8845.8170.9370.8762.2861.0561.34

Blender

Blend File: Barbershop - Compute: NVIDIA OptiX

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Barbershop - Compute: NVIDIA OptiX4060 a4060 b4070 a4070 b4070 super a4070 super b4080 b4080 super a4090 a4090 b4090 c70 Ti SUPER a70 Ti SUPER bRTX 4080bbc20406080100101.13101.4262.4362.2754.5854.3741.5941.4432.1932.1532.1747.7647.1941.8641.4941.47

Blender

Blend File: Junkshop - Compute: NVIDIA CUDA

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Junkshop - Compute: NVIDIA CUDA4060 a4060 b4070 a4070 b4070 super a4070 super b4080 b4080 super a4090 a4090 b4090 c70 Ti SUPER a70 Ti SUPER bRTX 4080bbc81624324032.6233.2420.3720.3417.5317.5513.9413.8711.1211.1111.1515.6815.7013.9013.9213.86

Blender

Blend File: Junkshop - Compute: NVIDIA OptiX

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Junkshop - Compute: NVIDIA OptiX4060 a4060 b4070 a4070 b4070 super a4070 super b4080 b4080 super a4090 a4090 b4090 c70 Ti SUPER a70 Ti SUPER bRTX 4080bbc51015202519.7219.7112.6112.6110.9210.868.578.567.147.187.189.799.808.598.538.56

vkpeak

fp32-scalar

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20240505fp32-scalar4060 a4060 b4070 a4070 b4070 super a4070 super b4080 b4080 super a4090 a4090 b4090 c70 Ti SUPER a70 Ti SUPER b76007600 b7600XT a7600XT b7700XT a7700XT b7800XT a7800XT b7900 XT b7900 XT x7900XT7900XTX7900XTX b79800GRE a79800GRE bA580 aA580 bA750 aA750 bA770 aA770 bRTX 4080bbc10K20K30K40K50KSE +/- 32.16, N = 38482.408394.9616376.4616417.7019899.3519896.8426867.9427995.0945178.9245079.3045082.1923384.1023385.908486.358446.409336.779333.1815061.5415056.1216493.3216548.3624817.2624830.2924908.3230298.3430043.7921585.8021371.6813840.9213850.5516875.7616915.6819001.4718841.2126925.9927959.5227964.45

vkpeak

fp32-vec4

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20240505fp32-vec44060 a4060 b4070 a4070 b4070 super a4070 super b4080 b4080 super a4090 a4090 b4090 c70 Ti SUPER a70 Ti SUPER b76007600 b7600XT a7600XT b7700XT a7700XT b7800XT a7800XT b7900 XT b7900 XT x7900XT7900XTX7900XTX b79800GRE a79800GRE bA580 aA580 bA750 aA750 bA770 aA770 bRTX 4080bbc13K26K39K52K65KSE +/- 24.70, N = 310955.3210880.3621695.1021695.2126289.3926290.3135493.7737041.2959624.7259582.0159442.5030937.8430939.207530.417498.098278.988277.4913337.0713332.9714397.2414513.5221460.9021450.7121555.6725211.2924912.0918485.0717934.9211911.4311911.8413896.5613899.6015880.5215880.5535583.0036957.6036957.21

vkpeak

fp16-scalar

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20240505fp16-scalar4060 a4060 b4070 a4070 b4070 super a4070 super b4080 b4080 super a4090 a4090 b4090 c70 Ti SUPER a70 Ti SUPER b76007600 b7600XT a7600XT b7700XT a7700XT b7800XT a7800XT b7900 XT b7900 XT x7900XT7900XTX7900XTX b79800GRE a79800GRE bA580 aA580 bA750 aA750 bA770 aA770 bRTX 4080bbc10K20K30K40K50KSE +/- 13.41, N = 38234.068200.0116316.9816315.5619731.1219766.6226775.1127880.0744970.3544972.9844857.9923349.2223350.058506.128504.099336.139369.1415029.1915022.2016486.9016540.6224875.8124888.5024906.1029352.8929113.5821446.8520946.0218205.7518322.1621374.5121381.8224448.4524453.1426852.1327880.8127880.31

vkpeak

fp16-vec4

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20240505fp16-vec44060 a4060 b4070 a4070 b4070 super a4070 super b4080 b4080 super a4090 a4090 b4090 c70 Ti SUPER a70 Ti SUPER b76007600 b7600XT a7600XT b7700XT a7700XT b7800XT a7800XT b7900 XT b7900 XT x7900XT7900XTX7900XTX b79800GRE a79800GRE bA580 aA580 bA750 aA750 bA770 aA770 bRTX 4080bbc12K24K36K48K60KSE +/- 49.56, N = 39500.419463.0118791.5418786.6022737.7822738.5430750.6832019.8651625.8751616.1851505.1826704.0326703.8116306.9316306.5118194.7018248.6229829.5029833.2930880.5231072.0246787.1146762.4846829.0454161.3553785.7439765.4738931.5719564.3119566.3722837.5322841.6726098.6726098.6130821.3932011.3132018.94

vkpeak

fp64-scalar

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20240505fp64-scalar4060 a4060 b4070 a4070 b4070 super a4070 super b4080 b4080 super a4090 a4090 b4090 c70 Ti SUPER a70 Ti SUPER b76007600 b7600XT a7600XT b7700XT a7700XT b7800XT a7800XT b7900 XT b7900 XT x7900XT7900XTX7900XTX b79800GRE a79800GRE bRTX 4080bbc30060090012001500SE +/- 0.21, N = 3266.98267.06514.24514.15620.54620.55842.77877.581409.441409.461409.44732.04732.08365.43365.37368.26367.82591.30591.68649.85650.53977.57977.42978.191183.741178.12846.71845.97842.88876.25876.29

vkpeak

fp64-vec4

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20240505fp64-vec44060 a4060 b4070 a4070 b4070 super a4070 super b4080 b4080 super a4090 a4090 b4090 c70 Ti SUPER a70 Ti SUPER b76007600 b7600XT a7600XT b7700XT a7700XT b7800XT a7800XT b7900 XT b7900 XT x7900XT7900XTX7900XTX b79800GRE a79800GRE bRTX 4080bbc30060090012001500SE +/- 0.28, N = 3267.05267.04514.13514.14620.36620.35842.60877.391409.181411.781409.12735.39735.45363.28363.08368.68368.71590.52590.89649.11649.35976.81976.65976.731178.821174.00846.85845.35842.75876.11875.83

vkpeak

int32-scalar

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20240505int32-scalar4060 a4060 b4070 a4070 b4070 super a4070 super b4080 b4080 super a4090 a4090 b4090 c70 Ti SUPER a70 Ti SUPER b76007600 b7600XT a7600XT b7700XT a7700XT b7800XT a7800XT b7900 XT b7900 XT x7900XT7900XTX7900XTX b79800GRE a79800GRE bRTX 4080bbc10K20K30K40K50KSE +/- 1.85, N = 38521.108521.2116385.4816389.9619764.6119724.9926823.7627917.7744900.2244809.8444890.8223328.6923330.062112.652112.232338.732341.583755.023755.874082.544093.226149.356150.986155.827169.017156.045203.485160.6726816.0027923.9527916.04

vkpeak

int32-vec4

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20240505int32-vec44060 a4060 b4070 a4070 b4070 super a4070 super b4080 b4080 super a4090 a4090 b4090 c70 Ti SUPER a70 Ti SUPER b76007600 b7600XT a7600XT b7700XT a7700XT b7800XT a7800XT b7900 XT b7900 XT x7900XT7900XTX7900XTX b79800GRE a79800GRE bRTX 4080bbc10K20K30K40K50KSE +/- 5.87, N = 38523.208522.8616334.6816334.6919758.4019720.8126733.6527848.9544804.5944728.5844805.9023272.4723272.212117.812116.942340.702340.853749.853761.134070.084084.186126.086124.336144.247160.597124.945176.335123.4326814.5627850.8527849.17

vkpeak

int16-scalar

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20240505int16-scalar4060 a4060 b4070 a4070 b4070 super a4070 super b4080 b4080 super a4090 a4090 b4090 c70 Ti SUPER a70 Ti SUPER b76007600 b7600XT a7600XT b7700XT a7700XT b7800XT a7800XT b7900 XT b7900 XT x7900XT7900XTX7900XTX b79800GRE a79800GRE bRTX 4080bbc6K12K18K24K30KSE +/- 44.47, N = 35580.025583.9610775.4910779.6712756.7112749.4017706.7518444.7429562.5329560.9929563.2415083.4315101.508265.298264.699321.089327.9715024.1315025.4715969.6716012.2723711.9223699.6823802.9127722.5027659.0420062.7819847.0317709.2318447.1518446.85

vkpeak

int16-vec4

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20240505int16-vec44060 a4060 b4070 a4070 b4070 super a4070 super b4080 b4080 super a4090 a4090 b4090 c70 Ti SUPER a70 Ti SUPER b76007600 b7600XT a7600XT b7700XT a7700XT b7800XT a7800XT b7900 XT b7900 XT x7900XT7900XTX7900XTX b79800GRE a79800GRE bRTX 4080bbc12K24K36K48K60KSE +/- 112.01, N = 36097.156087.5712103.3912102.2414241.2314229.9120136.0520951.4333053.4233056.7133060.1616861.3816897.8016851.9316845.5019025.4119137.9631554.8131539.8232488.0332569.8047960.1147917.6648144.7454973.4754918.6438271.2537897.5720146.5520900.7720907.41

FluidX3D

Test: FP32-FP32

OpenBenchmarking.orgMLUPs/s, More Is BetterFluidX3D 3.0Test: FP32-FP324060 a4060 b4070 a4070 b4070 super a4070 super b4080 b4080 super a4090 a4090 b4090 c70 Ti SUPER a70 Ti SUPER b76007600 b7600XT a7600XT b7700XT a7700XT b7800XT a7800XT b7900 XT b7900 XT x7900XT7900XTX7900XTX b79800GRE a79800GRE bA580 aA580 bA750 aA750 bA770 aA770 bRTX 4080bbc12002400360048006000SE +/- 2.33, N = 31620162028892888275827583840399557435742574238813880119911991166116613991394170417012996301729753284336318241850248024572455246625592592384040614053

FluidX3D

Test: FP32-FP16C

OpenBenchmarking.orgMLUPs/s, More Is BetterFluidX3D 3.0Test: FP32-FP16C4060 a4060 b4070 a4070 b4070 super a4070 super b4080 b4080 super a4090 a4090 b4090 c70 Ti SUPER a70 Ti SUPER b76007600 b7600XT a7600XT b7700XT a7700XT b7800XT a7800XT b7900 XT b7900 XT x7900XT7900XTX7900XTX b79800GRE a79800GRE bA580 aA580 bA750 aA750 bA770 aA770 bRTX 4080bbc2K4K6K8K10KSE +/- 80.92, N = 33126312654075408557655757755806411205112061120272487248234623402312231826732685313231485999622359716522637938973942339733523858386241634165775180628062

FluidX3D

Test: FP32-FP16S

OpenBenchmarking.orgMLUPs/s, More Is BetterFluidX3D 3.0Test: FP32-FP16S4060 a4060 b4070 a4070 b4070 super a4070 super b4080 b4080 super a4090 a4090 b4090 c70 Ti SUPER a70 Ti SUPER b76007600 b7600XT a7600XT b7700XT a7700XT b7800XT a7800XT b7900 XT b7900 XT x7900XT7900XTX7900XTX b79800GRE a79800GRE bA580 aA580 bA750 aA750 bA770 aA770 bRTX 4080bbc2K4K6K8K10KSE +/- 58.21, N = 32957295846404640520752107251744494539449944863126310219522082137212625292520313831305629569556155757578738433874369736884109407443634362724774447446

Phoronix Test Suite v10.8.5