Intel Arc Graphics vs. NVIDIA Linux Compute - October 2023

Benchmarks by Michael Larabel for a future article.

HTML result view exported from: https://openbenchmarking.org/result/2310268-NE-COMPUTEAR41&grs&sor.

Intel Arc Graphics vs. NVIDIA Linux Compute - October 2023ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorOSKernelDesktopDisplay ServerOpenGLOpenCLCompilerFile-SystemScreen ResolutionDisplay DriverArc A380Arc A580Arc A750Arc A770RTX 3060RTX 3060 TiRTX 3070RTX 3070 TiRTX 3080RTX 4060Intel Core i9-13900K @ 5.50GHz (24 Cores / 32 Threads)ASUS PRIME Z790-P WIFI (0812 BIOS)Intel Device 7a2732GBWestern Digital WD_BLACK SN850X 4000GB + Western Digital WD_BLACK SN850X 1000GBIntel Arc A380 DG2 6GB (2450MHz)Realtek ALC897ASUS VP28UUbuntu 23.106.6.0-060600rc5-generic (x86_64)GNOME Shell 45.0X Server + Wayland4.6 Mesa 23.3~git2310140600.29e2e9~oibaf~m (git-29e2e92 2023-10-14 mantic-oibaf-ppa)OpenCL 3.0GCC 13.2.0ext41920x1080Intel Arc A580 DG2 8GB (2400MHz)Intel Arc A750 DG2 8GB (2400MHz)Intel Arc A770 DG2 16GB (2400MHz)eVGA NVIDIA GeForce RTX 3060 12GBX Server 1.21.1.7NVIDIA 545.23.064.6.0OpenCL 3.0 CUDA 12.3.68NVIDIA GeForce RTX 3060 Ti 8GBNVIDIA GeForce RTX 3070 8GBNVIDIA GeForce RTX 3070 Ti 8GBNVIDIA GeForce RTX 3080 10GBMSI NVIDIA GeForce RTX 4060 8GBOpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- --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,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-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/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-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Processor Details- Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x119 - Thermald 2.5.4Python Details- Python 3.11.6Security Details- gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: 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 RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected Graphics Details- RTX 3060: BAR1 / Visible vRAM Size: 256 MiB - vBIOS Version: 94.06.14.40.46- RTX 3060 Ti: BAR1 / Visible vRAM Size: 256 MiB - vBIOS Version: 94.04.25.00.2c- RTX 3070: BAR1 / Visible vRAM Size: 256 MiB - vBIOS Version: 94.04.25.00.2b- RTX 3070 Ti: BAR1 / Visible vRAM Size: 256 MiB - vBIOS Version: 94.04.5b.00.02- RTX 3080: BAR1 / Visible vRAM Size: 256 MiB - vBIOS Version: 94.02.20.00.07- RTX 4060: BAR1 / Visible vRAM Size: 256 MiB - vBIOS Version: 95.07.31.00.e3OpenCL Details- RTX 3060: GPU Compute Cores: 3584- RTX 3060 Ti: GPU Compute Cores: 4864- RTX 3070: GPU Compute Cores: 5888- RTX 3070 Ti: GPU Compute Cores: 6144- RTX 3080: GPU Compute Cores: 8704- RTX 4060: GPU Compute Cores: 3072

Intel Arc Graphics vs. NVIDIA Linux Compute - October 2023clpeak: Integer Computeclpeak: Integer 24-bit Computeclpeak: Single-Precision Computehashcat: SHA-512fluidx3d: FP32-FP16Sfluidx3d: FP32-FP16Cfluidx3d: FP32-FP32hashcat: TrueCrypt RIPEMD160 + XTShashcat: MD5shoc: OpenCL - MD5 Hashclpeak: Global Memory Bandwidthvkresample: 2x - Singleshoc: OpenCL - Texture Read Bandwidthshoc: OpenCL - FFT SPshoc: OpenCL - S3Dshoc: OpenCL - Bus Speed Readbackshoc: OpenCL - Triadshoc: OpenCL - Bus Speed DownloadArc A380Arc A580Arc A750Arc A770RTX 3060RTX 3060 TiRTX 3070RTX 3070 TiRTX 3080RTX 40601484.661484.043315.8228450000010971115622101025100888833336.4378120.4362.113454.745422.11278.370111.234210.472011.77174065.044068.459748.267978166673882348325322815832618693333318.5424387.8720.611731.2171170.37214.64722.424119.991023.45294833.884834.1911371.119003833334212395224703127673008683333322.3360396.8019.173766.3141192.04225.25422.392220.505023.24525530.715519.1113008.6810784000004422427126163837573515513333326.0882397.6217.318983.0931219.91226.19022.437420.021923.47006311.446336.8712309.219776166674143354321412906202479770000015.1053315.0526.3201270.57886.872172.71326.344723.115624.02677798.688000.2715298.7613553833335116466626164021383465095714321.1964379.9921.0912107.371123.75212.44226.337323.401823.998710067.0510095.6719674.2516476166675191502726284949634158970000025.3311390.4420.2292124.531135.73219.88026.343223.380724.000710643.4410700.7320722.7316592333336837592135154987884233287142926.2263529.7915.8122076.611509.24286.62726.342723.748924.016714227.5514210.9127261.6123009500008226775841826762885840290000036.5157638.2212.7612205.281919.33339.34726.341823.919624.02227559.917587.9314783.0912179333333085315816313657672997046666718.9249238.3932.5371790.40722.942156.10513.192812.343412.8371OpenBenchmarking.org

clpeak

OpenCL Test: Integer Compute

OpenBenchmarking.orgGIOPS, More Is Betterclpeak 1.1.2OpenCL Test: Integer ComputeRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 4060RTX 3060Arc A770Arc A750Arc A580Arc A3803K6K9K12K15KSE +/- 73.29, N = 13SE +/- 47.35, N = 13SE +/- 5.08, N = 13SE +/- 13.43, N = 13SE +/- 13.40, N = 3SE +/- 3.38, N = 13SE +/- 7.88, N = 3SE +/- 3.74, N = 3SE +/- 3.59, N = 3SE +/- 0.22, N = 414227.5510643.4410067.057798.687559.916311.445530.714833.884065.041484.661. (CXX) g++ options: -O3

clpeak

OpenCL Test: Integer 24-bit Compute

OpenBenchmarking.orgGIOPS, More Is Betterclpeak 1.1.2OpenCL Test: Integer 24-bit ComputeRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 4060RTX 3060Arc A770Arc A750Arc A580Arc A3803K6K9K12K15KSE +/- 48.38, N = 13SE +/- 41.98, N = 13SE +/- 17.10, N = 13SE +/- 42.07, N = 13SE +/- 0.58, N = 3SE +/- 8.59, N = 13SE +/- 3.66, N = 3SE +/- 2.06, N = 3SE +/- 0.41, N = 3SE +/- 0.13, N = 414210.9110700.7310095.678000.277587.936336.875519.114834.194068.451484.041. (CXX) g++ options: -O3

clpeak

OpenCL Test: Single-Precision Compute

OpenBenchmarking.orgGFLOPS, More Is Betterclpeak 1.1.2OpenCL Test: Single-Precision ComputeRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 4060Arc A770RTX 3060Arc A750Arc A580Arc A3806K12K18K24K30KSE +/- 181.88, N = 13SE +/- 137.23, N = 13SE +/- 38.39, N = 13SE +/- 67.44, N = 13SE +/- 0.10, N = 3SE +/- 0.78, N = 3SE +/- 13.72, N = 13SE +/- 2.25, N = 3SE +/- 1.76, N = 3SE +/- 0.38, N = 327261.6120722.7319674.2515298.7614783.0913008.6812309.2111371.119748.263315.821. (CXX) g++ options: -O3

Hashcat

Benchmark: SHA-512

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.2.4Benchmark: SHA-512RTX 3080RTX 3070 TiRTX 3070RTX 3060 TiRTX 4060Arc A770RTX 3060Arc A750Arc A580Arc A380500M1000M1500M2000M2500MSE +/- 6840650.55, N = 6SE +/- 2377767.39, N = 6SE +/- 2876620.32, N = 6SE +/- 3243497.77, N = 6SE +/- 88191.71, N = 3SE +/- 594138.03, N = 5SE +/- 852610.37, N = 6SE +/- 6115031.57, N = 6SE +/- 871174.18, N = 6SE +/- 862167.81, N = 6230095000016592333331647616667135538333312179333331078400000977616667900383333797816667284500000

FluidX3D

Test: FP32-FP16S

OpenBenchmarking.orgMLUPs/s, More Is BetterFluidX3D 2.9Test: FP32-FP16SRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiArc A770Arc A750RTX 3060Arc A580RTX 4060Arc A3802K4K6K8K10KSE +/- 3.06, N = 3SE +/- 0.88, N = 3SE +/- 0.33, N = 3SE +/- 2.33, N = 3SE +/- 30.66, N = 3SE +/- 0.88, N = 3SE +/- 0.33, N = 3SE +/- 8.41, N = 3SE +/- 0.00, N = 3SE +/- 10.37, N = 38226683751915116442242124143388230851097

FluidX3D

Test: FP32-FP16C

OpenBenchmarking.orgMLUPs/s, More Is BetterFluidX3D 2.9Test: FP32-FP16CRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiArc A770Arc A750RTX 3060Arc A580RTX 4060Arc A38017003400510068008500SE +/- 7.80, N = 3SE +/- 3.53, N = 3SE +/- 1.00, N = 3SE +/- 7.51, N = 3SE +/- 45.67, N = 3SE +/- 14.29, N = 3SE +/- 2.73, N = 3SE +/- 20.04, N = 3SE +/- 0.67, N = 3SE +/- 0.33, N = 37758592150274666427139523543348331581115

FluidX3D

Test: FP32-FP32

OpenBenchmarking.orgMLUPs/s, More Is BetterFluidX3D 2.9Test: FP32-FP32RTX 3080RTX 3070 TiRTX 3070RTX 3060 TiArc A770Arc A580Arc A750RTX 3060RTX 4060Arc A3809001800270036004500SE +/- 2.52, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 1.45, N = 3SE +/- 5.57, N = 3SE +/- 2.73, N = 3SE +/- 8.02, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3418235152628261626162532247021411631622

Hashcat

Benchmark: TrueCrypt RIPEMD160 + XTS

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.2.4Benchmark: TrueCrypt RIPEMD160 + XTSRTX 3080RTX 3070 TiRTX 3070RTX 3060 TiArc A770RTX 4060Arc A750RTX 3060Arc A580Arc A380140K280K420K560K700KSE +/- 2376.78, N = 8SE +/- 1315.08, N = 8SE +/- 403.09, N = 8SE +/- 2383.72, N = 8SE +/- 178.43, N = 7SE +/- 2383.51, N = 3SE +/- 1857.90, N = 6SE +/- 2070.36, N = 15SE +/- 319.81, N = 6SE +/- 149.30, N = 4676288498788494963402138383757365767312767290620281583101025

Hashcat

Benchmark: MD5

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.2.4Benchmark: MD5RTX 3080RTX 3070 TiRTX 3070Arc A770RTX 3060 TiArc A750RTX 4060Arc A580RTX 3060Arc A38013000M26000M39000M52000M65000MSE +/- 62354336.92, N = 6SE +/- 42136771.15, N = 7SE +/- 25896432.92, N = 7SE +/- 14282919.09, N = 6SE +/- 39649619.33, N = 7SE +/- 32959759.98, N = 6SE +/- 48062540.28, N = 3SE +/- 52502537.50, N = 6SE +/- 40085550.18, N = 6SE +/- 10038904.88, N = 658402900000423328714294158970000035155133333346509571433008683333329970466667261869333332479770000010088883333

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: MD5 Hash

OpenBenchmarking.orgGHash/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: MD5 HashRTX 3080RTX 3070 TiArc A770RTX 3070Arc A750RTX 3060 TiRTX 4060Arc A580RTX 3060Arc A380816243240SE +/- 0.1231, N = 14SE +/- 0.0040, N = 13SE +/- 0.0148, N = 15SE +/- 0.0181, N = 13SE +/- 0.0328, N = 13SE +/- 0.0208, N = 13SE +/- 0.0125, N = 3SE +/- 0.0057, N = 13SE +/- 0.0089, N = 12SE +/- 0.0096, N = 1036.515726.226326.088225.331122.336021.196418.924918.542415.10536.43781. (CXX) g++ options: -O2 -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt

clpeak

OpenCL Test: Global Memory Bandwidth

OpenBenchmarking.orgGBPS, More Is Betterclpeak 1.1.2OpenCL Test: Global Memory BandwidthRTX 3080RTX 3070 TiArc A770Arc A750RTX 3070Arc A580RTX 3060 TiRTX 3060RTX 4060Arc A380140280420560700SE +/- 0.92, N = 11SE +/- 0.68, N = 15SE +/- 0.13, N = 8SE +/- 0.15, N = 8SE +/- 0.02, N = 11SE +/- 0.07, N = 8SE +/- 0.53, N = 11SE +/- 0.84, N = 9SE +/- 0.06, N = 3SE +/- 0.08, N = 5638.22529.79397.62396.80390.44387.87379.99315.05238.39120.431. (CXX) g++ options: -O3

VkResample

Upscale: 2x - Precision: Single

OpenBenchmarking.orgms, Fewer Is BetterVkResample 1.0Upscale: 2x - Precision: SingleRTX 3080RTX 3070 TiArc A770Arc A750RTX 3070Arc A580RTX 3060 TiRTX 3060RTX 4060Arc A3801428425670SE +/- 0.02, N = 5SE +/- 0.00, N = 5SE +/- 0.00, N = 6SE +/- 0.01, N = 6SE +/- 0.00, N = 5SE +/- 0.00, N = 6SE +/- 0.01, N = 5SE +/- 0.00, N = 5SE +/- 0.00, N = 3SE +/- 0.04, N = 312.7615.8117.3219.1720.2320.6121.0926.3232.5462.111. (CXX) g++ options: -O3

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: Texture Read Bandwidth

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Texture Read BandwidthRTX 3080RTX 3070RTX 3060 TiRTX 3070 TiRTX 4060RTX 3060Arc A770Arc A750Arc A580Arc A3805001000150020002500SE +/- 4.76, N = 3SE +/- 4.90, N = 4SE +/- 3.45, N = 4SE +/- 5.97, N = 4SE +/- 2.12, N = 3SE +/- 2.22, N = 4SE +/- 1.66, N = 3SE +/- 21.20, N = 15SE +/- 0.06, N = 3SE +/- 2.94, N = 32205.282124.532107.372076.611790.401270.57983.09766.31731.22454.751. (CXX) g++ options: -O2 -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: FFT SP

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: FFT SPRTX 3080RTX 3070 TiArc A770Arc A750Arc A580RTX 3070RTX 3060 TiRTX 3060RTX 4060Arc A380400800120016002000SE +/- 0.31, N = 12SE +/- 0.06, N = 12SE +/- 9.02, N = 15SE +/- 7.59, N = 13SE +/- 9.38, N = 15SE +/- 0.28, N = 12SE +/- 0.05, N = 12SE +/- 0.26, N = 12SE +/- 0.20, N = 3SE +/- 0.22, N = 121919.331509.241219.911192.041170.371135.731123.75886.87722.94422.111. (CXX) g++ options: -O2 -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: S3D

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: S3DRTX 3080RTX 3070 TiArc A770Arc A750RTX 3070Arc A580RTX 3060 TiRTX 3060RTX 4060Arc A38070140210280350SE +/- 0.05, N = 13SE +/- 0.07, N = 13SE +/- 0.84, N = 3SE +/- 1.04, N = 3SE +/- 0.05, N = 13SE +/- 0.72, N = 3SE +/- 0.03, N = 13SE +/- 0.01, N = 13SE +/- 0.02, N = 3SE +/- 0.55, N = 3339.35286.63226.19225.25219.88214.65212.44172.71156.1178.371. (CXX) g++ options: -O2 -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: Bus Speed Readback

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Bus Speed ReadbackRTX 3060RTX 3070RTX 3070 TiRTX 3080RTX 3060 TiArc A770Arc A580Arc A750RTX 4060Arc A380612182430SE +/- 0.00, N = 13SE +/- 0.00, N = 13SE +/- 0.00, N = 13SE +/- 0.00, N = 13SE +/- 0.00, N = 13SE +/- 0.00, N = 13SE +/- 0.00, N = 13SE +/- 0.01, N = 13SE +/- 0.00, N = 3SE +/- 0.00, N = 1226.3426.3426.3426.3426.3422.4422.4222.3913.1911.231. (CXX) g++ options: -O2 -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: Triad

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: TriadRTX 3080RTX 3070 TiRTX 3060 TiRTX 3070RTX 3060Arc A750Arc A770Arc A580RTX 4060Arc A380612182430SE +/- 0.01, N = 13SE +/- 0.00, N = 13SE +/- 0.00, N = 13SE +/- 0.00, N = 13SE +/- 0.01, N = 13SE +/- 0.07, N = 12SE +/- 0.06, N = 15SE +/- 0.07, N = 12SE +/- 0.01, N = 3SE +/- 0.01, N = 1223.9223.7523.4023.3823.1220.5120.0219.9912.3410.471. (CXX) g++ options: -O2 -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: Bus Speed Download

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Bus Speed DownloadRTX 3060RTX 3080RTX 3070 TiRTX 3070RTX 3060 TiArc A770Arc A580Arc A750RTX 4060Arc A380612182430SE +/- 0.00, N = 13SE +/- 0.00, N = 13SE +/- 0.00, N = 13SE +/- 0.00, N = 13SE +/- 0.00, N = 13SE +/- 0.00, N = 14SE +/- 0.00, N = 14SE +/- 0.02, N = 14SE +/- 0.00, N = 3SE +/- 0.00, N = 1224.0324.0224.0224.0024.0023.4723.4523.2512.8411.771. (CXX) g++ options: -O2 -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt

clpeak

GPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is Betterclpeak 1.1.2GPU Power Consumption MonitorArc A380RTX 3060RTX 3060 TiRTX 3070RTX 3070 TiRTX 3080Arc A580Arc A750Arc A7704080120160200Min: 20.6 / Avg: 35.02 / Max: 40.3Min: 16.74 / Avg: 40.47 / Max: 87.04Min: 19.79 / Avg: 50.54 / Max: 109.99Min: 15.88 / Avg: 50.63 / Max: 125.42Min: 23.18 / Avg: 75.65 / Max: 163.22Min: 25.48 / Avg: 89.78 / Max: 191.24Min: 40.1 / Avg: 96.76 / Max: 118.1Min: 37.6 / Avg: 114.09 / Max: 140Min: 34.8 / Avg: 116.1 / Max: 144.4

clpeak

OpenCL Test: Single-Precision Compute

OpenBenchmarking.orgGFLOPS Per Watt, More Is Betterclpeak 1.1.2OpenCL Test: Single-Precision ComputeRTX 3070RTX 3060RTX 3080RTX 3060 TiRTX 3070 TiArc A770Arc A580Arc A750Arc A38080160240320400388.59304.16303.64302.68273.92112.05100.7499.6794.69

clpeak

GPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is Betterclpeak 1.1.2GPU Power Consumption MonitorArc A380RTX 3070RTX 3060RTX 3060 TiArc A580Arc A750Arc A770RTX 3070 TiRTX 30804080120160200Min: 20.8 / Avg: 28.44 / Max: 36.1Min: 15.74 / Avg: 59.37 / Max: 138.32Min: 17.29 / Avg: 59.47 / Max: 109.76Min: 19.91 / Avg: 61.92 / Max: 131.92Min: 40 / Avg: 67.15 / Max: 126.8Min: 37.1 / Avg: 70.74 / Max: 143.7Min: 34.4 / Avg: 71.79 / Max: 147.5Min: 23.38 / Avg: 88.4 / Max: 189.38Min: 25.61 / Avg: 106.55 / Max: 241.78

clpeak

OpenCL Test: Global Memory Bandwidth

OpenBenchmarking.orgGBPS Per Watt, More Is Betterclpeak 1.1.2OpenCL Test: Global Memory BandwidthRTX 3070RTX 3060 TiRTX 3070 TiRTX 3080Arc A580Arc A750Arc A770RTX 3060Arc A3802468106.5776.1375.9935.9905.7765.6095.5395.2984.234

clpeak

GPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is Betterclpeak 1.1.2GPU Power Consumption MonitorRTX 3060Arc A380RTX 3060 TiRTX 3070RTX 3070 TiRTX 3080Arc A580Arc A770Arc A7504080120160200Min: 17.06 / Avg: 44.08 / Max: 96.89Min: 20.9 / Avg: 48.31 / Max: 60Min: 20.44 / Avg: 54.88 / Max: 125.27Min: 15.47 / Avg: 56.54 / Max: 136.46Min: 23.88 / Avg: 79.31 / Max: 183.17Min: 26.87 / Avg: 99.89 / Max: 225.98Min: 40.1 / Avg: 123.61 / Max: 150.1Min: 34.9 / Avg: 150.35 / Max: 191.4Min: 37.4 / Avg: 152.16 / Max: 190.1

clpeak

OpenCL Test: Integer 24-bit Compute

OpenBenchmarking.orgGIOPS Per Watt, More Is Betterclpeak 1.1.2OpenCL Test: Integer 24-bit ComputeRTX 3070RTX 3060 TiRTX 3060RTX 3080RTX 3070 TiArc A770Arc A580Arc A750Arc A3804080120160200178.56145.78143.77142.27134.9236.7132.9131.8130.72

clpeak

GPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is Betterclpeak 1.1.2GPU Power Consumption MonitorRTX 3060Arc A380RTX 3070RTX 3060 TiRTX 3070 TiRTX 3080Arc A580Arc A770Arc A7504080120160200Min: 16.55 / Avg: 44.67 / Max: 96.93Min: 20.9 / Avg: 49.9 / Max: 60Min: 15.75 / Avg: 55.49 / Max: 137.51Min: 21.46 / Avg: 55.6 / Max: 126.47Min: 25.11 / Avg: 83.11 / Max: 187.87Min: 29.83 / Avg: 102.14 / Max: 239Min: 40.1 / Avg: 122.81 / Max: 150.1Min: 34.6 / Avg: 151.28 / Max: 190.1Min: 37.5 / Avg: 151.94 / Max: 190.4

clpeak

OpenCL Test: Integer Compute

OpenBenchmarking.orgGIOPS Per Watt, More Is Betterclpeak 1.1.2OpenCL Test: Integer ComputeRTX 3070RTX 3060RTX 3060 TiRTX 3080RTX 3070 TiArc A770Arc A580Arc A750Arc A3804080120160200181.41141.30140.26139.30128.0736.5633.1031.8129.75

FluidX3D

GPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterFluidX3D 2.9GPU Power Consumption MonitorArc A380RTX 3060Arc A580RTX 3060 TiRTX 3070Arc A750Arc A770RTX 3070 TiRTX 308060120180240300Min: 21 / Avg: 43 / Max: 43.8Min: 17.01 / Avg: 117.04 / Max: 128.59Min: 40.3 / Avg: 138.24 / Max: 150.1Min: 21.64 / Avg: 148.87 / Max: 166.76Min: 15.95 / Avg: 153.79 / Max: 175.14Min: 37.4 / Avg: 160.01 / Max: 180Min: 35.1 / Avg: 170.51 / Max: 190.4Min: 25.29 / Avg: 218.05 / Max: 254.31Min: 29.52 / Avg: 267.73 / Max: 319.28

FluidX3D

Test: FP32-FP16S

OpenBenchmarking.orgMLUPs/s Per Watt, More Is BetterFluidX3D 2.9Test: FP32-FP16SRTX 3060RTX 3060 TiRTX 3070RTX 3070 TiRTX 3080Arc A580Arc A750Arc A770Arc A38081624324035.4034.3733.7531.3630.7328.0826.3225.9425.52

FluidX3D

GPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterFluidX3D 2.9GPU Power Consumption MonitorArc A380Arc A580RTX 3060Arc A770Arc A750RTX 3060 TiRTX 3070RTX 3070 TiRTX 308060120180240300Min: 21.7 / Avg: 51.3 / Max: 52.6Min: 40.2 / Avg: 139.66 / Max: 150.1Min: 16.51 / Avg: 142.03 / Max: 155Min: 35.2 / Avg: 170.51 / Max: 190.3Min: 37.5 / Avg: 172.23 / Max: 190.2Min: 21.39 / Avg: 178.87 / Max: 199.46Min: 16.07 / Avg: 194.69 / Max: 219.74Min: 25.26 / Avg: 254.21 / Max: 289.93Min: 28.31 / Avg: 271.77 / Max: 319.53

FluidX3D

Test: FP32-FP16C

OpenBenchmarking.orgMLUPs/s Per Watt, More Is BetterFluidX3D 2.9Test: FP32-FP16CRTX 3080RTX 3060 TiRTX 3070Arc A770RTX 3060Arc A580RTX 3070 TiArc A750Arc A38071421283528.5526.0925.8225.0524.9524.9423.2922.9521.73

FluidX3D

GPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterFluidX3D 2.9GPU Power Consumption MonitorArc A380RTX 3060RTX 3060 TiArc A580RTX 3070Arc A750Arc A770RTX 3070 TiRTX 308050100150200250Min: 21.8 / Avg: 37.08 / Max: 37.5Min: 16.08 / Avg: 102.23 / Max: 108.29Min: 20.07 / Avg: 129.56 / Max: 139.85Min: 40.1 / Avg: 130.97 / Max: 139.2Min: 15.81 / Avg: 133.5 / Max: 143.42Min: 49.1 / Avg: 148.38 / Max: 155.1Min: 34.8 / Avg: 152.03 / Max: 164Min: 23.26 / Avg: 197.93 / Max: 215.93Min: 25.75 / Avg: 246.69 / Max: 275.19

FluidX3D

Test: FP32-FP32

OpenBenchmarking.orgMLUPs/s Per Watt, More Is BetterFluidX3D 2.9Test: FP32-FP32RTX 3060RTX 3060 TiRTX 3070Arc A580RTX 3070 TiArc A770RTX 3080Arc A380Arc A75051015202520.9420.1919.6919.3317.7617.2116.9516.7816.65

VkResample

GPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterVkResample 1.0GPU Power Consumption MonitorArc A380RTX 3060Arc A580RTX 3060 TiRTX 3070Arc A770Arc A750RTX 3070 TiRTX 308060120180240300Min: 21.6 / Avg: 38.27 / Max: 50.2Min: 16.13 / Avg: 72.49 / Max: 162.82Min: 40 / Avg: 77.15 / Max: 150.1Min: 19.87 / Avg: 79.1 / Max: 197.47Min: 15.91 / Avg: 81.48 / Max: 217.9Min: 34.6 / Avg: 82.84 / Max: 190.1Min: 49.1 / Avg: 98.58 / Max: 190Min: 23.39 / Avg: 103.86 / Max: 289.3Min: 25.78 / Avg: 106.73 / Max: 319.86

SHOC Scalable HeterOgeneous Computing

GPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17GPU Power Consumption MonitorArc A380RTX 3060RTX 3060 TiRTX 3070Arc A580RTX 3070 TiArc A750Arc A770RTX 308050100150200250Min: 21.8 / Avg: 37.58 / Max: 52.1Min: 17.23 / Avg: 81.57 / Max: 110.53Min: 19.11 / Avg: 102.77 / Max: 141.54Min: 15.67 / Avg: 112.11 / Max: 160.82Min: 40.1 / Avg: 125.64 / Max: 147Min: 22.2 / Avg: 143.77 / Max: 191.19Min: 48.7 / Avg: 144.36 / Max: 175.3Min: 34.6 / Avg: 150.57 / Max: 191Min: 24.08 / Avg: 185.32 / Max: 248.69

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: Texture Read Bandwidth

OpenBenchmarking.orgGB/s Per Watt, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Texture Read BandwidthRTX 3060 TiRTX 3070RTX 3060RTX 3070 TiArc A380RTX 3080Arc A770Arc A580Arc A75051015202520.50518.95115.57614.44412.10211.9006.5295.8205.308

SHOC Scalable HeterOgeneous Computing

GPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17GPU Power Consumption MonitorArc A380RTX 3060RTX 3070Arc A770RTX 3060 TiArc A580RTX 3070 TiArc A750RTX 308020406080100Min: 21.8 / Avg: 23.47 / Max: 29.4Min: 17.09 / Avg: 32.76 / Max: 48.03Min: 15.42 / Avg: 34.78 / Max: 54.42Min: 34.1 / Avg: 38.26 / Max: 55.1Min: 19.21 / Avg: 38.37 / Max: 59.47Min: 40.2 / Avg: 42.78 / Max: 54.1Min: 22.48 / Avg: 55.69 / Max: 86.98Min: 51.2 / Avg: 59.99 / Max: 82.3Min: 23.94 / Avg: 64.4 / Max: 106.5

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: Bus Speed Readback

OpenBenchmarking.orgGB/s Per Watt, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Bus Speed ReadbackRTX 3060RTX 3070RTX 3060 TiArc A770Arc A580Arc A380RTX 3070 TiRTX 3080Arc A7500.18090.36180.54270.72360.90450.8040.7570.6860.5860.5240.4790.4730.4090.373

SHOC Scalable HeterOgeneous Computing

GPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17GPU Power Consumption MonitorArc A380RTX 3060RTX 3070RTX 3060 TiArc A770Arc A580RTX 3070 TiArc A750RTX 308020406080100Min: 21.7 / Avg: 23.31 / Max: 28.6Min: 16.99 / Avg: 32.61 / Max: 47.53Min: 15.76 / Avg: 34.72 / Max: 53.78Min: 19.58 / Avg: 37.66 / Max: 58.43Min: 34 / Avg: 38.42 / Max: 52.7Min: 40 / Avg: 42.83 / Max: 52.2Min: 22.64 / Avg: 54.3 / Max: 86.56Min: 49.6 / Avg: 59.11 / Max: 72.7Min: 24.66 / Avg: 64.69 / Max: 107.33

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: Bus Speed Download

OpenBenchmarking.orgGB/s Per Watt, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Bus Speed DownloadRTX 3060RTX 3070RTX 3060 TiArc A770Arc A580Arc A380RTX 3070 TiArc A750RTX 30800.16580.33160.49740.66320.8290.7370.6910.6370.6110.5480.5050.4420.3930.371

SHOC Scalable HeterOgeneous Computing

GPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17GPU Power Consumption MonitorArc A380RTX 3060RTX 3070Arc A770RTX 3060 TiArc A580Arc A750RTX 3070 TiRTX 3080306090120150Min: 21.9 / Avg: 36.53 / Max: 60Min: 16.99 / Avg: 50.33 / Max: 129.6Min: 15.56 / Avg: 53.11 / Max: 132.9Min: 34.1 / Avg: 54.94 / Max: 142.5Min: 19.24 / Avg: 56.78 / Max: 138.69Min: 40 / Avg: 59.88 / Max: 137Min: 49 / Avg: 75.62 / Max: 133.4Min: 22.5 / Avg: 76.61 / Max: 176.47Min: 24.87 / Avg: 84.21 / Max: 182.95

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: MD5 Hash

OpenBenchmarking.orgGHash/s Per Watt, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: MD5 HashRTX 3070Arc A770RTX 3080RTX 3060 TiRTX 3070 TiArc A580RTX 3060Arc A750Arc A3800.10730.21460.32190.42920.53650.4770.4750.4340.3730.3420.3100.3000.2950.176

SHOC Scalable HeterOgeneous Computing

GPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17GPU Power Consumption MonitorArc A380RTX 3060Arc A770RTX 3070RTX 3060 TiArc A580Arc A750RTX 3070 TiRTX 308020406080100Min: 21.8 / Avg: 22.62 / Max: 25.7Min: 16.82 / Avg: 36.11 / Max: 56.08Min: 34 / Avg: 36.22 / Max: 44.6Min: 15.71 / Avg: 37.83 / Max: 64.45Min: 19.43 / Avg: 40.83 / Max: 66.45Min: 40.1 / Avg: 41.89 / Max: 47.9Min: 48.9 / Avg: 57.32 / Max: 68.1Min: 22.99 / Avg: 62.48 / Max: 96.6Min: 25.03 / Avg: 73.33 / Max: 115.21

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: FFT SP

OpenBenchmarking.orgGFLOPS Per Watt, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: FFT SPArc A770RTX 3070Arc A580RTX 3060 TiRTX 3080RTX 3060RTX 3070 TiArc A750Arc A38081624324033.6830.0227.9427.5226.1824.5624.1620.8018.67

SHOC Scalable HeterOgeneous Computing

GPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17GPU Power Consumption MonitorArc A380RTX 3060RTX 3070RTX 3060 TiArc A770Arc A580RTX 3070 TiRTX 3080Arc A7501632486480Min: 17.1 / Avg: 21.09 / Max: 24.9Min: 16.9 / Avg: 29.19 / Max: 41.21Min: 15.56 / Avg: 29.48 / Max: 42.63Min: 19.77 / Avg: 31.57 / Max: 43.95Min: 34.1 / Avg: 40.63 / Max: 61.4Min: 40 / Avg: 44.94 / Max: 60.9Min: 23.35 / Avg: 47.28 / Max: 76.72Min: 25.43 / Avg: 55.03 / Max: 86.68Min: 41.2 / Avg: 56.37 / Max: 76

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: Triad

OpenBenchmarking.orgGB/s Per Watt, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: TriadRTX 3070RTX 3060RTX 3060 TiRTX 3070 TiArc A380Arc A770Arc A580RTX 3080Arc A7500.17840.35680.53520.71360.8920.7930.7920.7410.5020.4970.4930.4450.4350.364

SHOC Scalable HeterOgeneous Computing

GPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17GPU Power Consumption MonitorArc A380RTX 3060RTX 3070Arc A770RTX 3060 TiArc A580Arc A750RTX 3070 TiRTX 308020406080100Min: 17.1 / Avg: 17.22 / Max: 18.1Min: 16.35 / Avg: 32.16 / Max: 46.07Min: 16 / Avg: 33.18 / Max: 47.37Min: 34 / Avg: 34.32 / Max: 34.9Min: 20.41 / Avg: 34.96 / Max: 48.91Min: 39.9 / Avg: 40.14 / Max: 40.4Min: 41.3 / Avg: 43.1 / Max: 47.4Min: 24.03 / Avg: 57.67 / Max: 84.1Min: 26.68 / Avg: 62.93 / Max: 90.64

SHOC Scalable HeterOgeneous Computing

Target: OpenCL - Benchmark: S3D

OpenBenchmarking.orgGFLOPS Per Watt, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: S3DRTX 3070Arc A770RTX 3060 TiRTX 3080RTX 3060Arc A580Arc A750RTX 3070 TiArc A3802468106.6276.5916.0775.3935.3705.3485.2274.9704.550

Hashcat

GPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterHashcat 6.2.4GPU Power Consumption MonitorArc A380RTX 3060RTX 3060 TiArc A770Arc A580RTX 3070Arc A750RTX 3070 TiRTX 308060120180240300Min: 17.1 / Avg: 37.39 / Max: 60.1Min: 16.2 / Avg: 69.82 / Max: 144.39Min: 20.72 / Avg: 78.91 / Max: 195.71Min: 34.4 / Avg: 79.78 / Max: 191.2Min: 40 / Avg: 82 / Max: 150Min: 16.15 / Avg: 86.98 / Max: 219.28Min: 41.7 / Avg: 97.59 / Max: 190.8Min: 24.04 / Avg: 117.16 / Max: 268.81Min: 26.71 / Avg: 134.38 / Max: 319.29

Hashcat

Benchmark: TrueCrypt RIPEMD160 + XTS

OpenBenchmarking.orgH/s Per Watt, More Is BetterHashcat 6.2.4Benchmark: TrueCrypt RIPEMD160 + XTSRTX 3070RTX 3060 TiRTX 3080Arc A770RTX 3070 TiRTX 3060Arc A580Arc A750Arc A380120024003600480060005690.385096.145032.594810.054257.194162.603434.073204.992701.62

Hashcat

GPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterHashcat 6.2.4GPU Power Consumption MonitorArc A380RTX 3060Arc A580Arc A770RTX 3060 TiArc A750RTX 3070RTX 3070 TiRTX 308060120180240300Min: 17.1 / Avg: 37.41 / Max: 60Min: 16.13 / Avg: 81.72 / Max: 137.52Min: 40 / Avg: 95.33 / Max: 150Min: 34.7 / Avg: 107.22 / Max: 190.4Min: 20.52 / Avg: 111.24 / Max: 189.66Min: 41.3 / Avg: 116.8 / Max: 190.4Min: 16.16 / Avg: 123.79 / Max: 219.85Min: 24.03 / Avg: 156.24 / Max: 263.71Min: 27.14 / Avg: 191.17 / Max: 319.61

Hashcat

Benchmark: SHA-512

OpenBenchmarking.orgH/s Per Watt, More Is BetterHashcat 6.2.4Benchmark: SHA-512RTX 3070RTX 3060 TiRTX 3080RTX 3060RTX 3070 TiArc A770Arc A580Arc A750Arc A3803M6M9M12M15M13309738.3312183846.7912036097.4111963431.6810619913.2610057649.158368950.157708944.757604204.29

Hashcat

GPU Power Consumption Monitor

OpenBenchmarking.orgWatts, Fewer Is BetterHashcat 6.2.4GPU Power Consumption MonitorArc A380RTX 3060Arc A580RTX 3060 TiArc A770RTX 3070Arc A750RTX 3070 TiRTX 308060120180240300Min: 17 / Avg: 38.17 / Max: 60.1Min: 16.58 / Avg: 84.93 / Max: 145.89Min: 40 / Avg: 94.06 / Max: 150.1Min: 19.97 / Avg: 108.66 / Max: 199.01Min: 34.5 / Avg: 108.86 / Max: 190Min: 15.64 / Avg: 115.67 / Max: 219.86Min: 41.5 / Avg: 117.24 / Max: 190.6Min: 23.41 / Avg: 154.85 / Max: 277.85Min: 25.73 / Avg: 180.94 / Max: 320.09

Hashcat

Benchmark: MD5

OpenBenchmarking.orgH/s Per Watt, More Is BetterHashcat 6.2.4Benchmark: MD5RTX 3070Arc A770RTX 3080RTX 3060 TiRTX 3060Arc A580RTX 3070 TiArc A380Arc A75080M160M240M320M400M359546330.84322935646.85322772613.53318901788.06291983308.60278406690.76273378599.67264299083.09256619755.49

Phoronix Test Suite v10.8.4