OpenCL Intel Arc Graphics Comparison

Tests for a future article by Michale Larabel.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2303110-PTS-INTELOPE63
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results
Show Result Confidence Charts

Limit displaying results to tests within:

CPU Massive 3 Tests
Creator Workloads 2 Tests
HPC - High Performance Computing 2 Tests
Machine Learning 2 Tests
NVIDIA GPU Compute 5 Tests
OpenCL 4 Tests

Statistics

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

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Disable Color Branding
Prefer Vertical Bar Graphs
No Box Plots
On Line Graphs With Missing Data, Connect The Line Gaps

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs
Condense Test Profiles With Multiple Version Results Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
Intel Arc A380
March 07 2023
  42 Minutes
Intel Arc A750
March 06 2023
  1 Hour, 9 Minutes
Intel Arc A770
March 06 2023
  59 Minutes
GTX 1660 SUPER
March 11 2023
  1 Hour, 50 Minutes
RTX 2060
March 10 2023
  1 Hour, 18 Minutes
RTX 3060
March 10 2023
  1 Hour, 9 Minutes
RX 6500 XT
March 09 2023
  1 Hour, 10 Minutes
RX 6600
March 09 2023
  47 Minutes
RX 6700 XT
March 09 2023
  48 Minutes
Invert Hiding All Results Option
  1 Hour, 6 Minutes

Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):


OpenCL Intel Arc Graphics ComparisonProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLOpenCLCompilerFile-SystemScreen ResolutionDisplay DriverIntel Arc A770Intel Arc A750Intel Arc A380RX 6600RX 6700 XTRX 6500 XTRTX 3060RTX 2060GTX 1660 SUPERAMD Ryzen 9 7950X 16-Core @ 4.50GHz (16 Cores / 32 Threads)ASUS ROG CROSSHAIR X670E HERO (9922 BIOS)AMD Device 14d832GBWestern Digital WD_BLACK SN850X 1000GB + 2000GBIntel Arc A770 DG2 16GB (2400MHz)Intel DG2 AudioASUS MG28UIntel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411Ubuntu 23.046.2.2-060202-generic (x86_64)GNOME Shell 43.2X Server 1.21.1.6 + Wayland4.6 Mesa 23.1.0-devel (git-0d8a54f 2023-03-06 lunar-oibaf-ppa)OpenCL 3.0GCC 12.2.0ext43840x2160Intel Arc A750 DG2 8GB (2400MHz)Intel Arc A380 DG2 6GB (2450MHz)2 x 16 GB DDR5-6000MT/s F5-6000J3038F16GGigabyte AMD Radeon RX 6600 8GB (2750/875MHz)AMD Navi 21/23X Server 1.21.1.64.6 Mesa 23.1.0-devel (git-5f5e30b 2023-03-09 lunar-oibaf-ppa) (LLVM 15.0.7 DRM 3.49)OpenCL 2.1 AMD-APP (3513.0)AMD Radeon RX 6700 XT 12GB (2855/1000MHz)Sapphire AMD Radeon RX 6500 XT 4GB (2975/1124MHz)32GBeVGA NVIDIA GeForce RTX 3060 12GBNVIDIA GA106 HD AudioX Server 1.21.1.7NVIDIA 530.30.024.6.0OpenCL 2.1 AMD-APP (3513.0) + OpenCL 3.0 CUDA 12.1.68NVIDIA GeForce RTX 2060 6GBNVIDIA TU106 HD AudioeVGA NVIDIA GeForce GTX 1660 SUPER 6GBNVIDIA TU116 HD AudioOpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- Intel Arc A770: --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-PG9DkL/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-PG9DkL/gcc-12-12.2.0/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 - Intel Arc A750: --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-PG9DkL/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-PG9DkL/gcc-12-12.2.0/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 - Intel Arc A380: --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-PG9DkL/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-PG9DkL/gcc-12-12.2.0/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 - RX 6600: --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-EzbZRD/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-EzbZRD/gcc-12-12.2.0/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 - RX 6700 XT: --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-EzbZRD/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-EzbZRD/gcc-12-12.2.0/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 - RX 6500 XT: --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-EzbZRD/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-EzbZRD/gcc-12-12.2.0/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 - RTX 3060: --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-EzbZRD/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-EzbZRD/gcc-12-12.2.0/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 - RTX 2060: --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-EzbZRD/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-EzbZRD/gcc-12-12.2.0/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 - GTX 1660 SUPER: --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-EzbZRD/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-EzbZRD/gcc-12-12.2.0/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- Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa601203Security 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 affectedGraphics Details- RX 6600: BAR1 / Visible vRAM Size: 8176 MB - vBIOS Version: 113-D53201-R66E- RX 6700 XT: BAR1 / Visible vRAM Size: 12272 MB - vBIOS Version: 113-D5121100-101- RX 6500 XT: BAR1 / Visible vRAM Size: 4080 MB - vBIOS Version: 113-D6320100-S06- RTX 3060: BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 94.06.14.40.46- RTX 2060: BAR1 / Visible vRAM Size: 256 MiB - vBIOS Version: 90.06.2e.00.05- GTX 1660 SUPER: BAR1 / Visible vRAM Size: 256 MiB - vBIOS Version: 90.16.42.00.86OpenCL Details- RTX 3060: GPU Compute Cores: 3584- RTX 2060: GPU Compute Cores: 1920- GTX 1660 SUPER: GPU Compute Cores: 1408

Intel Arc A770Intel Arc A750Intel Arc A380RX 6600RX 6700 XTRX 6500 XTRTX 3060RTX 2060GTX 1660 SUPERResult OverviewPhoronix Test Suite100%212%323%435%546%LeelaChessZeroFluidX3DFluidX3DFluidX3DOpenCLFP32-FP32FP32-FP16SFP32-FP16C

OpenCL Intel Arc Graphics Comparisonshoc: OpenCL - S3Dclpeak: Integer 24-bit Computeshoc: OpenCL - GEMM SGEMM_Nblender: Pabellon Barcelona - NVIDIA OptiXlczero: OpenCLfluidx3d: FP32-FP32fluidx3d: FP32-FP16Sfluidx3d: FP32-FP16Cclpeak: Single-Precision Computeshoc: OpenCL - MD5 Hashhashcat: SHA-512hashcat: SHA1blender: Pabellon Barcelona - Intel oneAPIhashcat: TrueCrypt RIPEMD160 + XTSclpeak: Integer Computeblender: BMW27 - Intel oneAPIblender: Classroom - Intel oneAPIhashcat: MD5blender: Fishy Cat - Intel oneAPIdarktable: Server Room - OpenCLclpeak: Global Memory Bandwidthblender: Barbershop - Intel oneAPIblender: Fishy Cat - NVIDIA OptiXblender: BMW27 - NVIDIA OptiXblender: Barbershop - NVIDIA OptiXblender: Classroom - NVIDIA OptiXdarktable: Boat - OpenCLshoc: OpenCL - Texture Read Bandwidthdarktable: Server Rack - OpenCLhashcat: 7-Zipdarktable: Masskrug - OpenCLblender: Pabellon Barcelona - NVIDIA CUDAblender: Barbershop - NVIDIA CUDAblender: Classroom - NVIDIA CUDAblender: Fishy Cat - NVIDIA CUDAblender: BMW27 - NVIDIA CUDAshoc: OpenCL - Max SP FlopsIntel Arc A770Intel Arc A750Intel Arc A380RX 6600RX 6700 XTRX 6500 XTRTX 3060RTX 2060GTX 1660 SUPER225.9114435.602459.871322026234348421413007.2224.17849736166671517861666782.773571004442.4020.7856.13345098333329.540.779397.26191.341.858980.5790.1012479251.4483574907209.9383911.912100.101010125123963396611381.5721.16278634500001338011666785.183136883914.6221.0658.602952321666731.350.874396.57198.812.166882.9780.2072469002.07675876578.7541454.55608.4053909739120311203320.416.1732683000004066600000296.761018001453.2272.02191.86998810000098.112.268120.71611.994.082451.8050.2172.476154678079.76467831.731778.0714791962181618388032.8211.89712164.23191.26603.589110.29510802.434337.601946013822786279311441.2316.39372991.01311.69641.15623.54394680.821063.037390495101110304790.977.08201270.59122.86535.11336.26213592131421335249808833337732200000293825248757166670.80925.7912.35120.4533.671.6880.1284241221.538143.42226.2954.4357.3725.7049.981358518193707371110416333338243285714305188262866142860.68430.8614.81162.2841.221.6530.1114420701.531177.49273.7864.3364.0028.79199.3394281604294429997791000006125428571230463186538000000.92181.0937.94336.6084.652.1880.1153349601.740235.32347.7583.2086.4537.12OpenBenchmarking.org

SHOC Scalable HeterOgeneous Computing

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

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: S3DIntel Arc A770Intel Arc A750Intel Arc A380RX 6600RX 6700 XTRX 6500 XT50100150200250SE +/- 0.40, N = 3SE +/- 0.42, N = 3SE +/- 0.18, N = 3SE +/- 0.83, N = 11SE +/- 0.95, N = 15225.91209.9478.7579.76110.3023.541. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

clpeak

Clpeak is designed to test the peak capabilities of OpenCL devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGIOPS, More Is Betterclpeak 1.1.2OpenCL Test: Integer 24-bit ComputeIntel Arc A770Intel Arc A750Intel Arc A380RX 6600RX 6700 XTRX 6500 XT2K4K6K8K10KSE +/- 3.59, N = 3SE +/- 1.12, N = 3SE +/- 14.90, N = 7SE +/- 16.15, N = 7SE +/- 11.19, N = 34435.603911.911454.557831.7310802.434680.821. (CXX) g++ options: -O3

SHOC Scalable HeterOgeneous Computing

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

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: GEMM SGEMM_NIntel Arc A770Intel Arc A750Intel Arc A380RX 6600RX 6700 XTRX 6500 XT9001800270036004500SE +/- 16.77, N = 15SE +/- 14.19, N = 9SE +/- 3.55, N = 4SE +/- 57.13, N = 15SE +/- 1.40, N = 32459.872100.10608.411778.074337.601063.031. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.4Blend File: Pabellon Barcelona - Compute: NVIDIA OptiXRTX 3060RTX 2060GTX 1660 SUPER4080120160200SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.10, N = 336.2649.98199.33

LeelaChessZero

LeelaChessZero (lc0 / lczero) is a chess engine automated vian neural networks. This test profile can be used for OpenCL, CUDA + cuDNN, and BLAS (CPU-based) benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.28Backend: OpenCLIntel Arc A770Intel Arc A750Intel Arc A380RX 6600RX 6700 XTRX 6500 XTRTX 3060RTX 2060GTX 1660 SUPER5K10K15K20K25KSE +/- 95.50, N = 3SE +/- 118.76, N = 4SE +/- 29.31, N = 3SE +/- 146.89, N = 3SE +/- 6.69, N = 3SE +/- 48.14, N = 3SE +/- 58.34, N = 3SE +/- 27.44, N = 31322010101390914791194607390213591358594281. (CXX) g++ options: -flto -pthread

FluidX3D

FluidX3D is a speedy and memory efficient Boltzmann CFD (Computational Fluid Dynamics) software package implemented using OpenCL and intended for GPU acceleration. FluidX3D is developed by Moritz Lehmann and written free for non-commercial use. This is a test profile measuring the system OpenCL performance using the FluidX3D benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMLUPs/s, More Is BetterFluidX3D 2.3Test: FP32-FP32Intel Arc A770Intel Arc A750Intel Arc A380RX 6600RX 6700 XTRX 6500 XTRTX 3060RTX 2060GTX 1660 SUPER6001200180024003000SE +/- 2.52, N = 3SE +/- 2.03, N = 3SE +/- 0.33, N = 3SE +/- 4.84, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 1.20, N = 3SE +/- 0.00, N = 3262325127399621382495213118191604

OpenBenchmarking.orgMLUPs/s, More Is BetterFluidX3D 2.3Test: FP32-FP16SIntel Arc A770Intel Arc A750Intel Arc A380RX 6600RX 6700 XTRX 6500 XTRTX 3060RTX 2060GTX 1660 SUPER9001800270036004500SE +/- 2.96, N = 3SE +/- 9.94, N = 3SE +/- 0.88, N = 3SE +/- 6.36, N = 3SE +/- 0.58, N = 3SE +/- 0.88, N = 3SE +/- 0.67, N = 3SE +/- 0.58, N = 3434839631203181627861011421337072944

OpenBenchmarking.orgMLUPs/s, More Is BetterFluidX3D 2.3Test: FP32-FP16CIntel Arc A770Intel Arc A750Intel Arc A380RX 6600RX 6700 XTRX 6500 XTRTX 3060RTX 2060GTX 1660 SUPER9001800270036004500SE +/- 0.88, N = 3SE +/- 2.03, N = 3SE +/- 2.19, N = 3SE +/- 2.03, N = 3SE +/- 0.88, N = 3SE +/- 3.33, N = 3SE +/- 0.67, N = 3SE +/- 15.01, N = 3421439661120183827931030352437112999

clpeak

Clpeak is designed to test the peak capabilities of OpenCL devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS, More Is Betterclpeak 1.1.2OpenCL Test: Single-Precision ComputeIntel Arc A770Intel Arc A750Intel Arc A380RX 6600RX 6700 XTRX 6500 XT3K6K9K12K15KSE +/- 2.82, N = 3SE +/- 4.43, N = 3SE +/- 27.15, N = 7SE +/- 41.68, N = 7SE +/- 48.42, N = 313007.2211381.573320.418032.8211441.234790.971. (CXX) g++ options: -O3

SHOC Scalable HeterOgeneous Computing

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

OpenBenchmarking.orgGHash/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: MD5 HashIntel Arc A770Intel Arc A750Intel Arc A380RX 6600RX 6700 XTRX 6500 XT612182430SE +/- 0.0113, N = 15SE +/- 0.0060, N = 15SE +/- 0.0013, N = 4SE +/- 0.0023, N = 4SE +/- 0.0003, N = 324.178421.16276.173011.897116.39377.08201. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

Hashcat

Hashcat is an open-source, advanced password recovery tool supporting GPU acceleration with OpenCL, NVIDIA CUDA, and Radeon ROCm. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.2.4Benchmark: SHA-512Intel Arc A770Intel Arc A750Intel Arc A380RTX 3060RTX 2060GTX 1660 SUPER200M400M600M800M1000MSE +/- 611782.46, N = 6SE +/- 930859.82, N = 6SE +/- 521163.23, N = 6SE +/- 1639037.66, N = 6SE +/- 587164.29, N = 79736166678634500002683000009808833331041633333779100000

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.2.4Benchmark: SHA1Intel Arc A770Intel Arc A750Intel Arc A380RTX 3060RTX 2060GTX 1660 SUPER3000M6000M9000M12000M15000MSE +/- 10398667.12, N = 6SE +/- 1699297.24, N = 6SE +/- 5138612.00, N = 6SE +/- 16544937.78, N = 7SE +/- 5874347.55, N = 715178616667133801166674066600000773220000082432857146125428571

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.4Blend File: Pabellon Barcelona - Compute: Intel oneAPIIntel Arc A770Intel Arc A750Intel Arc A38060120180240300SE +/- 0.07, N = 3SE +/- 0.02, N = 382.7785.18296.76

Hashcat

Hashcat is an open-source, advanced password recovery tool supporting GPU acceleration with OpenCL, NVIDIA CUDA, and Radeon ROCm. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.2.4Benchmark: TrueCrypt RIPEMD160 + XTSIntel Arc A770Intel Arc A750Intel Arc A380RTX 3060RTX 2060GTX 1660 SUPER80K160K240K320K400KSE +/- 819.84, N = 8SE +/- 722.21, N = 8SE +/- 786.89, N = 8SE +/- 413.36, N = 8SE +/- 706.33, N = 8357100313688101800293825305188230463

clpeak

Clpeak is designed to test the peak capabilities of OpenCL devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGIOPS, More Is Betterclpeak 1.1.2OpenCL Test: Integer ComputeIntel Arc A770Intel Arc A750Intel Arc A380RX 6600RX 6700 XTRX 6500 XT10002000300040005000SE +/- 7.85, N = 3SE +/- 1.75, N = 3SE +/- 6.13, N = 7SE +/- 3.08, N = 7SE +/- 3.85, N = 34442.403914.621453.222164.232991.011270.591. (CXX) g++ options: -O3

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.4Blend File: BMW27 - Compute: Intel oneAPIIntel Arc A770Intel Arc A750Intel Arc A3801632486480SE +/- 0.04, N = 3SE +/- 0.02, N = 320.7821.0672.02

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.4Blend File: Classroom - Compute: Intel oneAPIIntel Arc A770Intel Arc A750Intel Arc A3804080120160200SE +/- 0.03, N = 3SE +/- 0.01, N = 356.1058.60191.86

Hashcat

Hashcat is an open-source, advanced password recovery tool supporting GPU acceleration with OpenCL, NVIDIA CUDA, and Radeon ROCm. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.2.4Benchmark: MD5Intel Arc A770Intel Arc A750Intel Arc A380RTX 3060RTX 2060GTX 1660 SUPER7000M14000M21000M28000M35000MSE +/- 13663123.52, N = 6SE +/- 6369794.17, N = 6SE +/- 20678175.56, N = 6SE +/- 41546522.57, N = 7SE +/- 25475412.98, N = 733450983333295232166679988100000248757166672628661428618653800000

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.4Blend File: Fishy Cat - Compute: Intel oneAPIIntel Arc A770Intel Arc A750Intel Arc A38020406080100SE +/- 0.03, N = 3SE +/- 0.03, N = 329.5431.3598.11

Darktable

Darktable is an open-source photography / workflow application this will use any system-installed Darktable program or on Windows will automatically download the pre-built binary from the project. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 4.2.1Test: Server Room - Acceleration: OpenCLIntel Arc A770Intel Arc A750Intel Arc A380RTX 3060RTX 2060GTX 1660 SUPER0.51031.02061.53092.04122.5515SE +/- 0.001, N = 12SE +/- 0.001, N = 11SE +/- 0.001, N = 11SE +/- 0.001, N = 12SE +/- 0.003, N = 110.7790.8742.2680.8090.6840.921

clpeak

Clpeak is designed to test the peak capabilities of OpenCL devices. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGBPS, More Is Betterclpeak 1.1.2OpenCL Test: Global Memory BandwidthIntel Arc A770Intel Arc A750Intel Arc A380RX 6600RX 6700 XTRX 6500 XT90180270360450SE +/- 0.09, N = 8SE +/- 0.20, N = 8SE +/- 0.57, N = 5SE +/- 0.82, N = 5SE +/- 0.31, N = 3397.26396.57120.71191.26311.69122.861. (CXX) g++ options: -O3

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.4Blend File: Barbershop - Compute: Intel oneAPIIntel Arc A770Intel Arc A750Intel Arc A380130260390520650SE +/- 0.06, N = 3SE +/- 0.37, N = 3191.34198.81611.99

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.4Blend File: Fishy Cat - Compute: NVIDIA OptiXRTX 3060RTX 2060GTX 1660 SUPER20406080100SE +/- 0.25, N = 3SE +/- 0.23, N = 3SE +/- 0.24, N = 325.7930.8681.09

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.4Blend File: BMW27 - Compute: NVIDIA OptiXRTX 3060RTX 2060GTX 1660 SUPER918273645SE +/- 0.12, N = 6SE +/- 0.17, N = 4SE +/- 0.18, N = 312.3514.8137.94

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.4Blend File: Barbershop - Compute: NVIDIA OptiXRTX 3060RTX 2060GTX 1660 SUPER70140210280350SE +/- 0.04, N = 3SE +/- 0.09, N = 3SE +/- 0.16, N = 3120.45162.28336.60

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.4Blend File: Classroom - Compute: NVIDIA OptiXRTX 3060RTX 2060GTX 1660 SUPER20406080100SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 333.6741.2284.65

Darktable

Darktable is an open-source photography / workflow application this will use any system-installed Darktable program or on Windows will automatically download the pre-built binary from the project. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 4.2.1Test: Boat - Acceleration: OpenCLIntel Arc A770Intel Arc A750Intel Arc A380RTX 3060RTX 2060GTX 1660 SUPER0.91851.8372.75553.6744.5925SE +/- 0.003, N = 9SE +/- 0.003, N = 9SE +/- 0.002, N = 10SE +/- 0.002, N = 10SE +/- 0.001, N = 101.8582.1664.0821.6881.6532.188

SHOC Scalable HeterOgeneous Computing

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

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Texture Read BandwidthIntel Arc A770Intel Arc A750Intel Arc A380RX 6600RX 6700 XTRX 6500 XT2004006008001000SE +/- 1.38, N = 3SE +/- 0.24, N = 3SE +/- 3.98, N = 15SE +/- 1.16, N = 4SE +/- 2.35, N = 3980.58882.98451.81603.59641.16535.111. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

Darktable

Darktable is an open-source photography / workflow application this will use any system-installed Darktable program or on Windows will automatically download the pre-built binary from the project. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 4.2.1Test: Server Rack - Acceleration: OpenCLIntel Arc A770Intel Arc A750Intel Arc A380RTX 3060RTX 2060GTX 1660 SUPER0.04880.09760.14640.19520.244SE +/- 0.000, N = 14SE +/- 0.000, N = 14SE +/- 0.000, N = 14SE +/- 0.000, N = 14SE +/- 0.000, N = 140.1010.2070.2170.1280.1110.115

Hashcat

Hashcat is an open-source, advanced password recovery tool supporting GPU acceleration with OpenCL, NVIDIA CUDA, and Radeon ROCm. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgH/s, More Is BetterHashcat 6.2.4Benchmark: 7-ZipIntel Arc A770Intel Arc A750RTX 3060RTX 2060GTX 1660 SUPER90K180K270K360K450KSE +/- 311.92, N = 4SE +/- 302.77, N = 4SE +/- 340.66, N = 9SE +/- 232.40, N = 10SE +/- 191.02, N = 10247925246900424122442070334960

Benchmark: 7-Zip

Intel Arc A380: The test run did not produce a result.

Darktable

Darktable is an open-source photography / workflow application this will use any system-installed Darktable program or on Windows will automatically download the pre-built binary from the project. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 4.2.1Test: Masskrug - Acceleration: OpenCLIntel Arc A770Intel Arc A750Intel Arc A380RTX 3060RTX 2060GTX 1660 SUPER0.55711.11421.67132.22842.7855SE +/- 0.005, N = 11SE +/- 0.003, N = 10SE +/- 0.004, N = 10SE +/- 0.005, N = 10SE +/- 0.004, N = 101.4482.0762.4761.5381.5311.740

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.4Blend File: Pabellon Barcelona - Compute: NVIDIA CUDARTX 3060RTX 2060GTX 1660 SUPER50100150200250SE +/- 0.00, N = 3SE +/- 0.07, N = 3SE +/- 0.03, N = 3143.42177.49235.32

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.4Blend File: Barbershop - Compute: NVIDIA CUDARTX 3060RTX 2060GTX 1660 SUPER80160240320400SE +/- 0.09, N = 3SE +/- 0.29, N = 3SE +/- 0.01, N = 3226.29273.78347.75

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.4Blend File: Classroom - Compute: NVIDIA CUDARTX 3060RTX 2060GTX 1660 SUPER20406080100SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.07, N = 354.4364.3383.20

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.4Blend File: Fishy Cat - Compute: NVIDIA CUDARTX 3060RTX 2060GTX 1660 SUPER20406080100SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 357.3764.0086.45

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.4Blend File: BMW27 - Compute: NVIDIA CUDARTX 3060RTX 2060GTX 1660 SUPER918273645SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 325.7028.7937.12

GPU Power Consumption Monitor

OpenBenchmarking.orgWattsGPU Power Consumption MonitorPhoronix Test Suite System MonitoringIntel Arc A770Intel Arc A750Intel Arc A380RX 6600RX 6700 XTRTX 3060RTX 2060GTX 1660 SUPER4080120160200Min: 33.9 / Avg: 117.73 / Max: 193Min: 34.8 / Avg: 108.15 / Max: 192.8Min: 16.5 / Avg: 39.59 / Max: 60.1Min: 3 / Avg: 38.83 / Max: 100Min: 4 / Avg: 66.55 / Max: 188Min: 17.27 / Avg: 101.02 / Max: 174.59Min: 9.5 / Avg: 106.46 / Max: 165.25Min: 11.89 / Avg: 95.81 / Max: 128.25

SHOC Scalable HeterOgeneous Computing

OpenBenchmarking.orgWatts, Fewer Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17GPU Power Consumption MonitorIntel Arc A770Intel Arc A750Intel Arc A380306090120150Min: 34.3 / Avg: 80.98 / Max: 147.3Min: 35.9 / Avg: 68.46 / Max: 120Min: 16.7 / Avg: 32.7 / Max: 52.8

OpenBenchmarking.orgGFLOPS Per Watt, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Max SP FlopsIntel Arc A770Intel Arc A750Intel Arc A38010K20K30K40K50K44147.4811084.1047302.14

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Max SP FlopsIntel Arc A770Intel Arc A750Intel Arc A380800K1600K2400K3200K4000KSE +/- 29520.59, N = 6SE +/- 87205.31, N = 15357490775876515467801. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi