Intel Arc Graphics B580 GPU Compute Benchmarks

Intel Arc B580 Battlemage Graphics for OpenCL / GPU compute benchmarks for a future article.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2412128-PTS-GPUCOMPU05
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
Allow Limiting Results To Certain Suite(s)

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
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

Sensor Monitoring

Show Accumulated Sensor Monitoring Data For Displayed Results
Generate Power Efficiency / Performance Per Watt Results

Run Management

Highlight
Result
Toggle/Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
Arc A580
December 10
  52 Minutes
Arc A750
December 10
  48 Minutes
Arc A770
December 10
  55 Minutes
Arc B580
December 10
  1 Hour, 29 Minutes
RTX 4060
December 06
  1 Hour, 51 Minutes
RTX 4070
December 05
  1 Hour, 14 Minutes
RTX 4070 SUPER
December 05
  1 Hour, 8 Minutes
RTX 4070 Ti SUPER
December 06
  1 Hour
RX 7600
December 10
  1 Hour, 43 Minutes
RX 7600 XT
December 10
  1 Hour, 34 Minutes
RX 7700 XT
December 10
  1 Hour, 14 Minutes
RX 7800 XT
December 10
  1 Hour, 15 Minutes
RX 7900 GRE
December 11
  59 Minutes
RX 7900 XT
December 11
  1 Hour, 3 Minutes
RX 7900 XTX
December 11
  59 Minutes
XTX 2
December 11
  14 Minutes
XTX 3
December 11
  14 Minutes
Invert Behavior (Only Show Selected Data)
  1 Hour, 5 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):


Intel Arc Graphics B580 GPU Compute BenchmarksProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLOpenCLCompilerFile-SystemScreen ResolutionDisplay DriverArc A580Arc A750Arc A770Arc B580RTX 4060RTX 4070RTX 4070 SUPERRTX 4070 Ti SUPERRX 7600RX 7600 XTRX 7700 XTRX 7800 XTRX 7900 GRERX 7900 XTRX 7900 XTXXTX 2XTX 3Intel Core Ultra 9 285K @ 5.10GHz (24 Cores)ASUS ROG MAXIMUS Z890 HERO (1101 BIOS)Intel Device ae7f2 x 16GB DDR5-6400MT/s Micron CP16G64C38U5B.M8D14001GB Western Digital WD_BLACK SN850X 4000GB + 1000GB Western Digital WDS100T1X0E-00AFY0Intel Arc A580 DG2 8GBIntel Device 7f50ASUS VP28URealtek Device 8126 + Intel I226-V + Intel Wi-Fi 7Ubuntu 24.106.13.0-rc1-phx (x86_64)GNOME Shell 47.0X Server 1.21.1.134.6 Mesa 25.0~git2412080600.8dda40~oibaf~o (git-8dda40c 2024-12-08 oracular-oibaf-ppOpenCL 3.0GCC 14.2.0ext43840x2160Intel Arc A750 DG2 8GB1000GB Western Digital WDS100T1X0E-00AFY0 + 4001GB Western Digital WD_BLACK SN850X 4000GBIntel Arc A770 DG2 16GB4001GB Western Digital WD_BLACK SN850X 4000GB + 1000GB Western Digital WDS100T1X0E-00AFY0Intel BMG G21 12GB1000GB Western Digital WDS100T1X0E-00AFY0 + 4001GB Western Digital WD_BLACK SN850X 4000GBASUS NVIDIA GeForce RTX 4060 8GB6.11.0-9-generic (x86_64)NVIDIA 565.57.014.6.0OpenCL 3.0 CUDA 12.7.33ASUS NVIDIA GeForce RTX 4070 12GB4001GB Western Digital WD_BLACK SN850X 4000GB + 1000GB Western Digital WDS100T1X0E-00AFY0ASUS NVIDIA GeForce RTX 4070 SUPER 12GBASUS NVIDIA GeForce RTX 4070 Ti SUPER 16GBAMD Radeon RX 7600 8GB6.13.0-rc1-phx (x86_64)4.6 Mesa 24.3.0-devel (LLVM 19.1.2 DRM 3.59)OpenCL 2.1 AMD-APP (3635.0)XFX AMD Radeon RX 7600 XT 16GBXFX AMD Radeon RX 7700 XT 12GB1000GB Western Digital WDS100T1X0E-00AFY0 + 4001GB Western Digital WD_BLACK SN850X 4000GBAMD Radeon RX 7800 XT 16GB4001GB Western Digital WD_BLACK SN850X 4000GB + 1000GB Western Digital WDS100T1X0E-00AFY0AMD Radeon RX 7900 GRE 16GB1000GB Western Digital WDS100T1X0E-00AFY0 + 4001GB Western Digital WD_BLACK SN850X 4000GBAMD Radeon RX 7900 XT 20GBXFX AMD Radeon RX 7900 XTX 24GBOpenBenchmarking.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,rust --enable-libphobos-checking=release --enable-libstdcxx-backtrace --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-14-zdkDXv/gcc-14-14.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-14-zdkDXv/gcc-14-14.2.0/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 -vProcessor Details- Scaling Governor: intel_pstate performance (EPP: default) - CPU Microcode: 0x113 - Thermald 2.5.8Security 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; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affectedGraphics Details- RTX 4060: BAR1 / Visible vRAM Size: 8192 MiB - vBIOS Version: 95.07.31.00.e3- RTX 4070: BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 95.04.49.00.03- RTX 4070 SUPER: BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 95.04.69.00.01- RTX 4070 Ti SUPER: BAR1 / Visible vRAM Size: 16384 MiB - vBIOS Version: 95.03.45.00.9c- RX 7600: BAR1 / Visible vRAM Size: 8176 MB- RX 7600 XT: BAR1 / Visible vRAM Size: 16368 MB- RX 7700 XT: BAR1 / Visible vRAM Size: 12272 MB- RX 7800 XT: BAR1 / Visible vRAM Size: 16368 MB- RX 7900 GRE: BAR1 / Visible vRAM Size: 16368 MB- RX 7900 XT: BAR1 / Visible vRAM Size: 20464 MB- RX 7900 XTX: BAR1 / Visible vRAM Size: 24560 MB- XTX 2: BAR1 / Visible vRAM Size: 24560 MB- XTX 3: BAR1 / Visible vRAM Size: 24560 MBOpenCL Details- RTX 4060: GPU Compute Cores: 3072- RTX 4070: GPU Compute Cores: 5888- RTX 4070 SUPER: GPU Compute Cores: 7168- RTX 4070 Ti SUPER: GPU Compute Cores: 8448

Arc A580Arc A750Arc A770Arc B580RTX 4060RTX 4070RTX 4070 SUPERRTX 4070 Ti SUPERRX 7600RX 7600 XTRX 7700 XTRX 7800 XTRX 7900 GRERX 7900 XTRX 7900 XTXXTX 2XTX 3Result OverviewPhoronix Test Suite100%209%318%428%537%HashcatclpeakFluidX3DSHOC Scalable HeterOgeneous ComputingDarktable

Intel Arc Graphics B580 GPU Compute Benchmarksshoc: OpenCL - Reductionhashcat: SHA-512shoc: OpenCL - GEMM SGEMM_Ncl-mem: Readclpeak: Kernel Latencyclpeak: Integer 24-bit Computehashcat: 7-Zipshoc: OpenCL - S3Dclpeak: Single-Precision Computegpuowl: 77936867gpuowl: 57885161gpuowl: 332220523clpeak: Double-Precision Computefluidx3d: FP32-FP16Shashcat: TrueCrypt RIPEMD160 + XTSshoc: OpenCL - Texture Read Bandwidthshoc: OpenCL - FFT SPfluidx3d: FP32-FP16Ccl-mem: Writecl-mem: Copyhashcat: MD5shoc: OpenCL - MD5 Hashfluidx3d: FP32-FP32blender: Classroom - Radeon HIPblender: Barbershop - Radeon HIPblender: Pabellon Barcelona - Radeon HIPindigobench: OpenCL GPU - Bedroomblender: BMW27 - Radeon HIPclpeak: Global Memory Bandwidthblender: Fishy Cat - Radeon HIPindigobench: OpenCL GPU - Supercarblender: Junkshop - Radeon HIPdarktable: Boat - OpenCLblender: Pabellon Barcelona - NVIDIA CUDAblender: Fishy Cat - NVIDIA CUDAblender: Barbershop - NVIDIA CUDAblender: Classroom - NVIDIA CUDAblender: Fishy Cat - NVIDIA OptiXblender: BMW27 - NVIDIA CUDAblender: Barbershop - NVIDIA OptiXblender: Junkshop - NVIDIA CUDAblender: Classroom - NVIDIA OptiXblender: Pabellon Barcelona - NVIDIA OptiXblender: Junkshop - NVIDIA OptiXhashcat: SHA1clpeak: Integer Computeblender: BMW27 - NVIDIA OptiXdarktable: Server Rack - OpenCLblender: Barbershop - Intel oneAPIblender: Junkshop - Intel oneAPIdarktable: Server Room - OpenCLclpeak: Transfer Bandwidth enqueueReadBufferblender: Classroom - Intel oneAPIblender: Pabellon Barcelona - Intel oneAPIshoc: OpenCL - Bus Speed Readbackdarktable: Masskrug - OpenCLshoc: OpenCL - Triadclpeak: Transfer Bandwidth enqueueWriteBufferblender: Fishy Cat - Intel oneAPIblender: BMW27 - Intel oneAPIArc A580Arc A750Arc A770Arc B580RTX 4060RTX 4070RTX 4070 SUPERRTX 4070 Ti SUPERRX 7600RX 7600 XTRX 7700 XTRX 7800 XTRX 7900 GRERX 7900 XTRX 7900 XTXXTX 2XTX 369.71897878333331778.83143.735.164046.13248000215.0369755.803624271100724.3531191.773304294.4259.62624900000018.42342447387.922.67945741600004047.250.111199.8629.310.88444.0450.1611.91391.62911.009320.1515.7178.19599430500002202.80157.832.484844.46247175228.22211384.243814325500883.8381174.223759281.1270.13144170000022.79552416396.942.67454956800004841.890.111172.9825.820.87937.5443.2411.91521.62311.032917.3313.66134.260810645333332512.05242.934.505510.61245133228.44613005.744098368263991.2361226.813893428.2310.63549068333325.81602441396.502.69162090800005521.580.112167.3525.970.87436.0344.7811.91471.62811.020116.4513.2261.62083502400005395.39244.564540.68248833106.47114526.18536.29658.47109.96909.168801388986813.0761079.2619262430224000016.77081500417.073.92723988200004540.640.190284.8234.370.9509.9045.3152.7014.48561.73612.566711.8820.9124.42246.88112135500004525.11238.04.687530.06538750155.07414678.32277.29375.9958.57265.8929603570071761.66721.3643106225.1213.52978711666718.873616039.707236.1928.8942.25991.4139.56163.5238.8919.6119.25101.4832.1424.5126.5819.6995123500007511.149.300.1320.99912.8113.21681.66712.349912.26379.78123243500009693.12443.24.6214325.531028375287.50727884.65527.98711.91112.10510.8646316905882824.701333.875381391.1328.45694385000036.2607287818.032435.7748.0061.71751.9325.39103.6224.4412.7912.1869.0226.4416.9617.3217.541824473333314278.036.640.1230.90712.8213.21681.59412.598112.26379.623277858333311512.1442.84.6617376.901199963295.20334179.19634.38853.24134.75619.6451338123462870.011284.245595397.6328.76744733333343.8498278319.519432.5351.9461.64743.4219.5780.4319.5010.0910.1854.6317.3613.3614.8610.862192751666717337.735.780.1160.88312.8213.21681.56312.647612.26405.567323443333314009.7577.44.8721147.071418075383.15841278.38724.11975.61155.31712.3962939475502906.851803.907166519.2358.07855198333350.2923375723.596563.2559.0521.51838.2317.2971.6517.248.879.0347.9915.5111.9213.169.792540496666721079.085.180.1130.85312.8013.21461.54412.675612.26259.92810637833332254.40260.617.367422.3247790071.16278579.65383.83515.2977.83335.022166235893770.768780.7182285258.3237.52193926666715.0829118359.32244.46126.779.47432.06227.0154.2826.32845.442.46793125666671817.020.1370.95614.49411.63011.5775260.61511565000002247.59260.917.247378.9049298774.95888495.58424.99571.8686.01342.102175317914795.413778.5242341256.7236.52383821666715.0274116955.29231.01116.6430.18226.3250.4644.332.453102506000001801.610.1300.95214.49241.62411.5286350.02418912500004314.50390.718.7712911.62781988165.44915382.86669.64899.82137.04570.1425884013471023.8451169.062667386.5353.43974508333327.1628138836.27151.8679.4813.67021.14358.3735.2638.55329.931.942169360500003382.560.1210.86214.51031.54711.7522543.15819037500004704.98560.518.6313703.17840613213.10916593.53716.85960.92147.08627.8531264782001101.661751.853113536.1489.14013173333329.1842170931.91130.1274.0117.19818.52489.3531.7845.68126.111.774173279833333633.890.1160.82214.49781.53311.6699513.32623407166676549.26520.117.7918837.001064075242.92522414.04915.751223.99185.53822.9138476129001697.931594.043883516.9469.15011318333337.3692183627.15112.6459.9317.02615.13425.0225.6944.57223.761.758213450833334822.730.1200.82914.50221.54011.7228580.53127695000007128.58715.717.3220591.861186613255.27924891.561089.721450.68221.53962.2053367225751437.872234.035781700.3648.66039680000044.7445300622.4091.3147.9123.94112.55571.1922.0262.13419.511.570257994833335476.720.1100.80314.50181.49411.7201587.56632872000008011.70858.517.1523094.691413100301.42627894.511264.761688.26259.881165.7855859317251665.082697.816066824.1784.06862148333348.8077322618.7777.3541.0128.63910.67664.5318.9071.24217.131.501296961500006143.360.1070.78114.47841.48711.7540584.17332300000008211.75864.417.1424016.971422100296.4928215.111270.651709.40260.891176.4451909081001478.982701.095512834.8782.96903660000049.143315018.5179.241.0628.59710.81675.9919.1270.69916.891.495299711000006313.880.1160.7714.28091.53912.0946564.81832247000008158.19863.317.2323094.671420800294.1628413.961270.651709.40260.891173.8954229046001781.112692.825464836.8784.36905820000049.7741320318.679.0741.328.58410.71670.0319.0771.25816.841.55299758000006266.770.1140.80314.28031.48311.8647OpenBenchmarking.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.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: ReductionXTX 3XTX 2RX 7900 XTXRX 7900 XTRX 7900 GRERX 7800 XTRX 7700 XTRX 7600 XTRX 7600RTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 4060Arc B580Arc A770Arc A750Arc A580130260390520650SE +/- 4.17, N = 12SE +/- 2.74, N = 12SE +/- 1.14, N = 12SE +/- 2.78, N = 12SE +/- 0.53, N = 11SE +/- 0.08, N = 11SE +/- 0.15, N = 10SE +/- 0.70, N = 13SE +/- 0.08, N = 12SE +/- 0.88, N = 15SE +/- 0.02, N = 11SE +/- 0.74, N = 15SE +/- 6.54, N = 12SE +/- 0.13, N = 10SE +/- 0.18, N = 9564.82584.17587.57580.53513.33543.16350.02260.62259.93405.57379.62379.78246.8861.62134.2678.2069.721. (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-512XTX 3XTX 2RX 7900 XTXRX 7900 XTRX 7900 GRERX 7800 XTRX 7700 XTRX 7600 XTRX 7600RTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 4060Arc B580Arc A770Arc A750Arc A580700M1400M2100M2800M3500MSE +/- 1766918.22, N = 6SE +/- 1182652.39, N = 6SE +/- 1160866.53, N = 6SE +/- 9450282.18, N = 6SE +/- 549393.61, N = 6SE +/- 2013123.61, N = 6SE +/- 1186427.88, N = 6SE +/- 4046287.74, N = 6SE +/- 2352079.46, N = 6SE +/- 1068566.02, N = 6SE +/- 1194082.63, N = 6SE +/- 150332.96, N = 5SE +/- 624855.54, N = 6SE +/- 375721.53, N = 6SE +/- 202758.75, N = 632247000003230000000328720000027695000002340716667190375000018912500001156500000106378333332344333332778583333232435000012135500003502400001064533333943050000787833333

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_NXTX 3XTX 2RX 7900 XTXRX 7900 XTRX 7900 GRERX 7800 XTRX 7700 XTRX 7600 XTRX 7600RTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 4060Arc B580Arc A770Arc A750Arc A5803K6K9K12K15KSE +/- 45.98, N = 11SE +/- 17.93, N = 11SE +/- 6.16, N = 10SE +/- 5.84, N = 10SE +/- 5.03, N = 10SE +/- 3.33, N = 9SE +/- 2.60, N = 9SE +/- 11.54, N = 11SE +/- 19.61, N = 11SE +/- 6.25, N = 10SE +/- 24.39, N = 9SE +/- 141.18, N = 15SE +/- 31.44, N = 15SE +/- 5.35, N = 11SE +/- 11.95, N = 108158.198211.758011.707128.586549.264704.984314.502247.592254.4014009.7011512.109693.124525.115395.392512.052202.801778.831. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

cl-mem

A basic OpenCL memory benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: ReadXTX 3XTX 2RX 7900 XTXRX 7900 XTRX 7900 GRERX 7800 XTRX 7700 XTRX 7600 XTRX 7600RTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 4060Arc A770Arc A750Arc A5802004006008001000SE +/- 1.74, N = 11SE +/- 1.34, N = 10SE +/- 1.28, N = 9SE +/- 0.54, N = 9SE +/- 0.17, N = 8SE +/- 0.15, N = 6SE +/- 0.24, N = 6SE +/- 1.35, N = 9SE +/- 1.17, N = 8SE +/- 0.80, N = 8SE +/- 0.45, N = 6SE +/- 0.09, N = 7SE +/- 0.04, N = 6SE +/- 0.00, N = 6863.3864.4858.5715.7520.1560.5390.7260.9260.6577.4442.8443.2238.0242.9157.8143.71. (CC) gcc options: -O2 -flto -lOpenCL

Benchmark: Read

Arc B580: The test quit with a non-zero exit status.

clpeak

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

OpenBenchmarking.orgus, Fewer Is Betterclpeak 1.1.2OpenCL Test: Kernel LatencyXTX 3XTX 2RX 7900 XTXRX 7900 XTRX 7900 GRERX 7800 XTRX 7700 XTRX 7600 XTRX 7600RTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 4060Arc B580Arc A770Arc A750Arc A58050100150200250SE +/- 0.03, N = 12SE +/- 0.05, N = 12SE +/- 0.05, N = 12SE +/- 0.03, N = 12SE +/- 0.05, N = 12SE +/- 0.18, N = 15SE +/- 0.07, N = 12SE +/- 0.01, N = 15SE +/- 0.04, N = 15SE +/- 0.04, N = 15SE +/- 0.05, N = 15SE +/- 1.67, N = 7SE +/- 0.10, N = 12SE +/- 0.08, N = 12SE +/- 0.02, N = 1217.2317.1417.1517.3217.7918.6318.7717.2417.364.874.664.624.68244.5634.5032.4835.161. (CXX) g++ options: -O3

OpenBenchmarking.orgGIOPS, More Is Betterclpeak 1.1.2OpenCL Test: Integer 24-bit ComputeXTX 3XTX 2RX 7900 XTXRX 7900 XTRX 7900 GRERX 7800 XTRX 7700 XTRX 7600 XTRX 7600RTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 4060Arc B580Arc A770Arc A750Arc A5805K10K15K20K25KSE +/- 106.68, N = 13SE +/- 78.91, N = 13SE +/- 64.76, N = 13SE +/- 66.84, N = 13SE +/- 46.29, N = 13SE +/- 30.00, N = 15SE +/- 22.87, N = 13SE +/- 46.15, N = 15SE +/- 93.44, N = 13SE +/- 70.70, N = 14SE +/- 33.56, N = 13SE +/- 0.62, N = 7SE +/- 5.95, N = 4SE +/- 1.88, N = 4SE +/- 0.30, N = 423094.6724016.9723094.6920591.8618837.0013703.1712911.627378.907422.3221147.0717376.9014325.537530.064540.685510.614844.464046.131. (CXX) g++ options: -O3

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-ZipXTX 3XTX 2RX 7900 XTXRX 7900 XTRX 7900 GRERX 7800 XTRX 7700 XTRX 7600 XTRX 7600RTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 4060Arc B580Arc A770Arc A750Arc A580300K600K900K1200K1500KSE +/- 885.60, N = 8SE +/- 1483.53, N = 8SE +/- 1182.42, N = 8SE +/- 1329.67, N = 8SE +/- 1268.64, N = 8SE +/- 3699.93, N = 15SE +/- 2910.85, N = 9SE +/- 2047.01, N = 8SE +/- 2113.56, N = 8SE +/- 5954.67, N = 8SE +/- 985.43, N = 8SE +/- 579.46, N = 6SE +/- 66.67, N = 3SE +/- 125.00, N = 4SE +/- 122.47, N = 414208001422100141310011866131064075840613781988492987477900141807511999631028375538750248833245133247175248000

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: S3DXTX 3XTX 2RX 7900 XTXRX 7900 XTRX 7900 GRERX 7800 XTRX 7700 XTRX 7600 XTRX 7600RTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 4060Arc B580Arc A770Arc A750Arc A58080160240320400SE +/- 2.36, N = 3SE +/- 1.02, N = 3SE +/- 2.63, N = 3SE +/- 1.91, N = 15SE +/- 1.18, N = 3SE +/- 0.62, N = 9SE +/- 0.29, N = 3SE +/- 0.25, N = 13SE +/- 0.08, N = 12SE +/- 0.18, N = 13SE +/- 0.15, N = 15SE +/- 0.03, N = 12SE +/- 0.22, N = 15SE +/- 0.31, N = 15SE +/- 0.23, N = 15294.16296.49301.43255.28242.93213.11165.4574.9671.16383.16295.20287.51155.07106.47228.45228.22215.041. (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.orgGFLOPS, More Is Betterclpeak 1.1.2OpenCL Test: Single-Precision ComputeXTX 3XTX 2RX 7900 XTXRX 7900 XTRX 7900 GRERX 7800 XTRX 7700 XTRX 7600 XTRX 7600RTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 4060Arc B580Arc A770Arc A750Arc A5809K18K27K36K45KSE +/- 69.59, N = 12SE +/- 53.66, N = 12SE +/- 25.56, N = 12SE +/- 31.09, N = 12SE +/- 23.93, N = 12SE +/- 12.54, N = 12SE +/- 6.51, N = 12SE +/- 69.55, N = 15SE +/- 17.53, N = 13SE +/- 141.03, N = 13SE +/- 70.91, N = 13SE +/- 1.87, N = 8SE +/- 1.39, N = 4SE +/- 0.54, N = 4SE +/- 0.86, N = 428413.9628215.1127894.5124891.5622414.0416593.5315382.868495.588579.6541278.3834179.1927884.6514678.3214526.1813005.7411384.249755.801. (CXX) g++ options: -O3

GpuOwl

GpuOwl is a Mersenne primality tester leveraging OpenCL for cross-vendor GPU acceleration. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations / Second, More Is BetterGpuOwl 7.5Exponent: 77936867XTX 3XTX 2RX 7900 XTXRX 7900 XTRX 7900 GRERX 7800 XTRX 7700 XTRX 7600 XTRX 7600RTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 4060Arc B58030060090012001500SE +/- 0.53, N = 3SE +/- 0.40, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.40, N = 3SE +/- 0.00, N = 3SE +/- 0.05, N = 3SE +/- 0.30, N = 3SE +/- 0.13, N = 3SE +/- 0.16, N = 3SE +/- 0.37, N = 3SE +/- 0.58, N = 31270.651270.651264.761089.72915.75716.85669.64424.99383.83724.11634.38527.98277.29536.291. (CXX) g++ options: -O3 -lgmp -lOpenCL

Exponent: 77936867

Arc A580: The test run did not produce a result. E: ./open 20241210 04:36:17 Exception gpu_error: BUILD_PROGRAM_FAILURE clBuildProgram at gpuowl-7.5/src/clwrap.cpp:245 build

Arc A750: The test run did not produce a result. E: ./open 20241210 05:52:16 Exception gpu_error: BUILD_PROGRAM_FAILURE clBuildProgram at gpuowl-7.5/src/clwrap.cpp:245 build

Arc A770: The test run did not produce a result. E: ./open 20241210 08:20:11 Exception gpu_error: BUILD_PROGRAM_FAILURE clBuildProgram at gpuowl-7.5/src/clwrap.cpp:245 build

OpenBenchmarking.orgIterations / Second, More Is BetterGpuOwl 7.5Exponent: 57885161XTX 3XTX 2RX 7900 XTXRX 7900 XTRX 7900 GRERX 7800 XTRX 7700 XTRX 7600 XTRX 7600RTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 4060Arc B580400800120016002000SE +/- 3.79, N = 3SE +/- 1.40, N = 3SE +/- 0.86, N = 3SE +/- 0.81, N = 3SE +/- 0.27, N = 3SE +/- 0.11, N = 3SE +/- 0.09, N = 3SE +/- 0.00, N = 3SE +/- 0.42, N = 3SE +/- 0.17, N = 3SE +/- 0.54, N = 3SE +/- 0.58, N = 31709.401709.401688.261450.681223.99960.92899.82571.86515.29975.61853.24711.91375.99658.471. (CXX) g++ options: -O3 -lgmp -lOpenCL

Exponent: 57885161

Arc A580: The test run did not produce a result. E: ./open 20241210 04:35:52 Exception gpu_error: BUILD_PROGRAM_FAILURE clBuildProgram at gpuowl-7.5/src/clwrap.cpp:245 build

Arc A750: The test run did not produce a result. E: ./open 20241210 05:51:51 Exception gpu_error: BUILD_PROGRAM_FAILURE clBuildProgram at gpuowl-7.5/src/clwrap.cpp:245 build

Arc A770: The test run did not produce a result. E: ./open 20241210 08:19:46 Exception gpu_error: BUILD_PROGRAM_FAILURE clBuildProgram at gpuowl-7.5/src/clwrap.cpp:245 build

OpenBenchmarking.orgIterations / Second, More Is BetterGpuOwl 7.5Exponent: 332220523XTX 3XTX 2RX 7900 XTXRX 7900 XTRX 7900 GRERX 7800 XTRX 7700 XTRX 7600 XTRX 7600RTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 4060Arc B58060120180240300SE +/- 0.10, N = 3SE +/- 0.07, N = 3SE +/- 0.09, N = 3SE +/- 0.19, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.09, N = 3SE +/- 0.04, N = 3260.89260.89259.88221.53185.53147.08137.0486.0177.83155.31134.75112.1058.57109.961. (CXX) g++ options: -O3 -lgmp -lOpenCL

Exponent: 332220523

Arc A580: The test run did not produce a result. E: ./open 20241210 04:36:41 Exception gpu_error: BUILD_PROGRAM_FAILURE clBuildProgram at gpuowl-7.5/src/clwrap.cpp:245 build

Arc A750: The test run did not produce a result. E: ./open 20241210 05:52:40 Exception gpu_error: BUILD_PROGRAM_FAILURE clBuildProgram at gpuowl-7.5/src/clwrap.cpp:245 build

Arc A770: The test run did not produce a result. E: ./open 20241210 08:20:35 Exception gpu_error: BUILD_PROGRAM_FAILURE clBuildProgram at gpuowl-7.5/src/clwrap.cpp:245 build

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: Double-Precision ComputeXTX 3XTX 2RX 7900 XTXRX 7900 XTRX 7900 GRERX 7800 XTRX 7700 XTRX 7600 XTRX 7600RTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 4060Arc B58030060090012001500SE +/- 1.25, N = 8SE +/- 0.59, N = 8SE +/- 4.24, N = 7SE +/- 2.78, N = 7SE +/- 3.09, N = 7SE +/- 0.32, N = 7SE +/- 0.67, N = 7SE +/- 1.86, N = 6SE +/- 2.39, N = 6SE +/- 2.22, N = 6SE +/- 0.70, N = 6SE +/- 0.01, N = 31173.891176.441165.78962.20822.91627.85570.14342.10335.02712.39619.64510.86265.89909.161. (CXX) g++ options: -O3

OpenCL Test: Double-Precision Compute

Arc A580: The test run did not produce a result.

Arc A750: The test run did not produce a result.

Arc A770: The test run did not produce a result.

FluidX3D

OpenBenchmarking.orgMLUPs/s, More Is BetterFluidX3D 3.0Test: FP32-FP16SXTX 3XTX 2RX 7900 XTXRX 7900 XTRX 7900 GRERX 7800 XTRX 7700 XTRX 7600 XTRX 7600RTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 4060Arc B580Arc A770Arc A750Arc A5802K4K6K8K10KSE +/- 55.50, N = 15SE +/- 64.52, N = 15SE +/- 35.62, N = 3SE +/- 12.70, N = 3SE +/- 3.18, N = 3SE +/- 4.63, N = 3SE +/- 12.33, N = 3SE +/- 0.67, N = 3SE +/- 0.67, N = 3SE +/- 0.88, N = 3SE +/- 0.58, N = 3SE +/- 7.57, N = 3SE +/- 27.93, N = 15SE +/- 6.74, N = 3SE +/- 13.01, N = 354225190558553363847312625882175216662935133463129608801409838143624

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 + XTSXTX 3XTX 2RX 7900 XTXRX 7900 XTRX 7900 GRERX 7800 XTRX 7700 XTRX 7600 XTRX 7600RTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 4060Arc B580Arc A770Arc A750Arc A580200K400K600K800K1000KSE +/- 1493.05, N = 8SE +/- 1160.47, N = 8SE +/- 723.83, N = 8SE +/- 446.01, N = 8SE +/- 47254.23, N = 15SE +/- 147.08, N = 7SE +/- 20554.84, N = 15SE +/- 5845.11, N = 8SE +/- 5423.39, N = 13SE +/- 2512.78, N = 8SE +/- 2610.06, N = 15SE +/- 63.35, N = 7SE +/- 212.08, N = 8SE +/- 190.86, N = 8SE +/- 198.81, N = 7904600908100931725722575612900478200401347317914235893947550812346690588357007388986368263325500271100

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 BandwidthXTX 3XTX 2RX 7900 XTXRX 7900 XTRX 7900 GRERX 7800 XTRX 7700 XTRX 7600 XTRX 7600RTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 4060Arc B580Arc A770Arc A750Arc A5806001200180024003000SE +/- 35.31, N = 15SE +/- 34.97, N = 15SE +/- 10.01, N = 8SE +/- 3.86, N = 8SE +/- 6.85, N = 8SE +/- 1.56, N = 8SE +/- 38.05, N = 15SE +/- 1.89, N = 6SE +/- 1.71, N = 6SE +/- 1.12, N = 6SE +/- 1.58, N = 6SE +/- 0.23, N = 3SE +/- 3.42, N = 3SE +/- 0.13, N = 3SE +/- 1.95, N = 31781.111478.981665.081437.871697.931101.661023.85795.41770.772906.852870.012824.701761.66813.08991.24883.84724.351. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: FFT SPXTX 3XTX 2RX 7900 XTXRX 7900 XTRX 7900 GRERX 7800 XTRX 7700 XTRX 7600 XTRX 7600RTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 4060Arc B580Arc A770Arc A750Arc A5806001200180024003000SE +/- 1.95, N = 12SE +/- 1.46, N = 12SE +/- 0.65, N = 12SE +/- 2.09, N = 12SE +/- 1.68, N = 12SE +/- 0.32, N = 11SE +/- 0.26, N = 11SE +/- 1.40, N = 12SE +/- 0.73, N = 11SE +/- 0.39, N = 11SE +/- 0.97, N = 11SE +/- 1.23, N = 12SE +/- 6.21, N = 14SE +/- 6.19, N = 14SE +/- 4.67, N = 142692.822701.092697.812234.031594.041751.851169.06778.52780.721803.901284.241333.87721.361079.261226.811174.221191.771. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

FluidX3D

OpenBenchmarking.orgMLUPs/s, More Is BetterFluidX3D 3.0Test: FP32-FP16CXTX 3XTX 2RX 7900 XTXRX 7900 XTRX 7900 GRERX 7800 XTRX 7700 XTRX 7600 XTRX 7600RTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 4060Arc B580Arc A770Arc A750Arc A58015003000450060007500SE +/- 146.37, N = 15SE +/- 79.60, N = 15SE +/- 25.72, N = 3SE +/- 12.98, N = 3SE +/- 12.25, N = 3SE +/- 4.26, N = 3SE +/- 12.17, N = 3SE +/- 2.52, N = 3SE +/- 3.51, N = 3SE +/- 0.67, N = 3SE +/- 0.00, N = 3SE +/- 1.86, N = 3SE +/- 53.38, N = 3SE +/- 6.03, N = 3SE +/- 11.85, N = 354645512606657813883311326672341228571665595538131061926389337593304

cl-mem

A basic OpenCL memory benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: WriteXTX 3XTX 2RX 7900 XTXRX 7900 XTRX 7900 GRERX 7800 XTRX 7700 XTRX 7600 XTRX 7600RTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 4060Arc A770Arc A750Arc A5802004006008001000SE +/- 6.29, N = 15SE +/- 0.26, N = 10SE +/- 0.13, N = 9SE +/- 1.15, N = 9SE +/- 0.18, N = 8SE +/- 0.10, N = 6SE +/- 0.03, N = 6SE +/- 0.16, N = 9SE +/- 0.80, N = 8SE +/- 0.43, N = 8SE +/- 0.39, N = 6SE +/- 0.13, N = 7SE +/- 0.02, N = 6SE +/- 0.03, N = 6836.8834.8824.1700.3516.9536.1386.5256.7258.3519.2397.6391.1225.1428.2281.1294.41. (CC) gcc options: -O2 -flto -lOpenCL

Benchmark: Write

Arc B580: The test quit with a non-zero exit status.

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: CopyXTX 3XTX 2RX 7900 XTXRX 7900 XTRX 7900 GRERX 7800 XTRX 7700 XTRX 7600 XTRX 7600RTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 4060Arc A770Arc A750Arc A5802004006008001000SE +/- 0.34, N = 11SE +/- 0.07, N = 10SE +/- 0.04, N = 9SE +/- 1.30, N = 9SE +/- 0.13, N = 8SE +/- 0.04, N = 6SE +/- 0.07, N = 6SE +/- 0.52, N = 9SE +/- 0.51, N = 8SE +/- 0.39, N = 8SE +/- 0.37, N = 6SE +/- 0.03, N = 7SE +/- 0.13, N = 6SE +/- 0.02, N = 6784.3782.9784.0648.6469.1489.1353.4236.5237.5358.0328.7328.4213.5310.6270.1259.61. (CC) gcc options: -O2 -flto -lOpenCL

Benchmark: Copy

Arc B580: The test quit with a non-zero exit status.

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: MD5XTX 3XTX 2RX 7900 XTXRX 7900 XTRX 7900 GRERX 7800 XTRX 7700 XTRX 7600 XTRX 7600RTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 4060Arc B580Arc A770Arc A750Arc A58020000M40000M60000M80000M100000MSE +/- 61322309.24, N = 6SE +/- 32898500.47, N = 6SE +/- 59177554.40, N = 6SE +/- 51306033.87, N = 6SE +/- 39002994.90, N = 6SE +/- 68956476.21, N = 6SE +/- 32738088.59, N = 6SE +/- 119926498.09, N = 6SE +/- 49647307.19, N = 6SE +/- 35399027.76, N = 6SE +/- 24181996.29, N = 6SE +/- 7420485.16, N = 5SE +/- 20961320.20, N = 6SE +/- 8077829.74, N = 6SE +/- 8638479.80, N = 66905820000069036600000686214833336039680000050113183333401317333333974508333323838216667219392666677855198333367447333333569438500002978711666724302240000354906833333144170000026249000000

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 HashXTX 3XTX 2RX 7900 XTXRX 7900 XTRX 7900 GRERX 7800 XTRX 7700 XTRX 7600 XTRX 7600RTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 4060Arc B580Arc A770Arc A750Arc A5801122334455SE +/- 0.04, N = 14SE +/- 0.06, N = 14SE +/- 0.03, N = 13SE +/- 0.05, N = 13SE +/- 0.00, N = 13SE +/- 0.03, N = 12SE +/- 0.01, N = 12SE +/- 0.11, N = 14SE +/- 0.03, N = 13SE +/- 0.02, N = 13SE +/- 0.01, N = 12SE +/- 0.00, N = 13SE +/- 0.03, N = 15SE +/- 0.01, N = 13SE +/- 0.01, N = 1349.7749.1448.8144.7437.3729.1827.1615.0315.0850.2943.8536.2618.8716.7725.8222.8018.421. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

FluidX3D

OpenBenchmarking.orgMLUPs/s, More Is BetterFluidX3D 3.0Test: FP32-FP32XTX 3XTX 2RX 7900 XTXRX 7900 XTRX 7900 GRERX 7800 XTRX 7700 XTRX 7600 XTRX 7600RTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 4060Arc B580Arc A770Arc A750Arc A5808001600240032004000SE +/- 38.87, N = 3SE +/- 18.15, N = 3SE +/- 4.04, N = 3SE +/- 8.84, N = 3SE +/- 3.18, N = 3SE +/- 4.58, N = 3SE +/- 6.39, N = 3SE +/- 0.00, N = 3SE +/- 0.88, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 1.67, N = 3SE +/- 7.26, N = 3SE +/- 10.07, N = 3SE +/- 17.46, N = 332033150322630061836170913881169118337572783287816031500244124162447

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Classroom - Compute: Radeon HIPXTX 3XTX 2RX 7900 XTXRX 7900 XTRX 7900 GRERX 7800 XTRX 7700 XTRX 7600 XTRX 76001326395265SE +/- 0.07, N = 3SE +/- 0.03, N = 3SE +/- 0.23, N = 3SE +/- 0.12, N = 3SE +/- 0.43, N = 4SE +/- 0.04, N = 3SE +/- 0.04, N = 318.6018.5118.7722.4027.1531.9136.2755.2959.32

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Barbershop - Compute: Radeon HIPXTX 3XTX 2RX 7900 XTXRX 7900 XTRX 7900 GRERX 7800 XTRX 7700 XTRX 7600 XTRX 760050100150200250SE +/- 0.69, N = 3SE +/- 0.09, N = 3SE +/- 0.43, N = 3SE +/- 0.50, N = 3SE +/- 0.09, N = 3SE +/- 0.19, N = 3SE +/- 0.43, N = 379.0779.2077.3591.31112.64130.12151.86231.01244.46

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Pabellon Barcelona - Compute: Radeon HIPXTX 3XTX 2RX 7900 XTXRX 7900 XTRX 7900 GRERX 7800 XTRX 7700 XTRX 7600 XTRX 7600306090120150SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.20, N = 3SE +/- 0.06, N = 3SE +/- 0.33, N = 3SE +/- 0.50, N = 3SE +/- 0.10, N = 341.3041.0641.0147.9159.9374.0179.48116.64126.77

IndigoBench

This is a test of Indigo Renderer's IndigoBench benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: OpenCL GPU - Scene: BedroomXTX 3XTX 2RX 7900 XTXRX 7900 XTRX 7900 GRERX 7800 XTRX 7700 XTRX 7600RTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 4060714212835SE +/- 0.050, N = 3SE +/- 0.034, N = 3SE +/- 0.015, N = 3SE +/- 0.011, N = 3SE +/- 0.018, N = 3SE +/- 0.003, N = 3SE +/- 0.003, N = 3SE +/- 0.006, N = 3SE +/- 0.005, N = 3SE +/- 0.002, N = 328.58428.59728.63923.94117.02617.19813.6709.47423.59619.51918.0329.707

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: BMW27 - Compute: Radeon HIPXTX 3XTX 2RX 7900 XTXRX 7900 XTRX 7900 GRERX 7800 XTRX 7700 XTRX 7600 XTRX 7600714212835SE +/- 0.11, N = 5SE +/- 0.03, N = 4SE +/- 0.08, N = 4SE +/- 0.04, N = 3SE +/- 0.23, N = 3SE +/- 0.15, N = 3SE +/- 0.04, N = 310.7110.8110.6712.5515.1318.5221.1430.1832.06

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 BandwidthXTX 3XTX 2RX 7900 XTXRX 7900 XTRX 7900 GRERX 7800 XTRX 7700 XTRX 7600 XTRX 7600RTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 4060Arc B580Arc A770Arc A750Arc A580150300450600750SE +/- 1.55, N = 9SE +/- 1.77, N = 9SE +/- 0.83, N = 8SE +/- 2.08, N = 8SE +/- 0.64, N = 8SE +/- 0.32, N = 6SE +/- 0.27, N = 6SE +/- 0.67, N = 10SE +/- 1.92, N = 10SE +/- 0.06, N = 10SE +/- 0.66, N = 10SE +/- 0.13, N = 9SE +/- 0.19, N = 8SE +/- 0.11, N = 9SE +/- 0.18, N = 9670.03675.99664.53571.19425.02489.35358.37226.32227.01563.25432.53435.77236.19417.07396.50396.94387.921. (CXX) g++ options: -O3

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Fishy Cat - Compute: Radeon HIPXTX 3XTX 2RX 7900 XTXRX 7900 XTRX 7900 GRERX 7800 XTRX 7700 XTRX 7600 XTRX 76001224364860SE +/- 0.07, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.19, N = 3SE +/- 0.17, N = 3SE +/- 0.01, N = 3SE +/- 0.09, N = 319.0719.1218.9022.0225.6931.7835.2650.4654.28

IndigoBench

This is a test of Indigo Renderer's IndigoBench benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.4Acceleration: OpenCL GPU - Scene: SupercarXTX 3XTX 2RX 7900 XTXRX 7900 XTRX 7900 GRERX 7800 XTRX 7700 XTRX 7600RTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 40601632486480SE +/- 0.28, N = 3SE +/- 0.18, N = 3SE +/- 0.11, N = 3SE +/- 0.09, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.08, N = 3SE +/- 0.15, N = 3SE +/- 0.17, N = 3SE +/- 0.05, N = 371.2670.7071.2462.1344.5745.6838.5526.3359.0551.9548.0128.89

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Junkshop - Compute: Radeon HIPXTX 3XTX 2RX 7900 XTXRX 7900 XTRX 7900 GRERX 7800 XTRX 7700 XTRX 7600 XTRX 76001020304050SE +/- 0.07, N = 3SE +/- 0.03, N = 3SE +/- 0.08, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.12, N = 3SE +/- 0.50, N = 316.8416.8917.1319.5123.7626.1129.9344.3345.44

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 4.8.1Test: Boat - Acceleration: OpenCLXTX 3XTX 2RX 7900 XTXRX 7900 XTRX 7900 GRERX 7800 XTRX 7700 XTRX 7600 XTRX 7600RTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 4060Arc B580Arc A770Arc A750Arc A5800.88361.76722.65083.53444.418SE +/- 0.004, N = 10SE +/- 0.004, N = 10SE +/- 0.005, N = 9SE +/- 0.002, N = 10SE +/- 0.002, N = 9SE +/- 0.005, N = 8SE +/- 0.002, N = 9SE +/- 0.004, N = 10SE +/- 0.004, N = 9SE +/- 0.003, N = 10SE +/- 0.004, N = 9SE +/- 0.004, N = 7SE +/- 0.004, N = 8SE +/- 0.005, N = 8SE +/- 0.005, N = 81.5501.4951.5011.5701.7581.7741.9422.4532.4671.5181.6471.7172.2593.9272.6912.6742.679

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Pabellon Barcelona - Compute: NVIDIA CUDARTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 406020406080100SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 338.2343.4251.9391.41

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Fishy Cat - Compute: NVIDIA CUDARTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 4060918273645SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.07, N = 3SE +/- 0.02, N = 317.2919.5725.3939.56

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Barbershop - Compute: NVIDIA CUDARTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 40604080120160200SE +/- 0.62, N = 3SE +/- 0.03, N = 3SE +/- 0.36, N = 3SE +/- 0.37, N = 371.6580.43103.62163.52

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Classroom - Compute: NVIDIA CUDARTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 4060918273645SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 317.2419.5024.4438.89

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Fishy Cat - Compute: NVIDIA OptiXRTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 4060510152025SE +/- 0.01, N = 5SE +/- 0.10, N = 5SE +/- 0.07, N = 4SE +/- 0.15, N = 38.8710.0912.7919.61

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: BMW27 - Compute: NVIDIA CUDARTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 4060510152025SE +/- 0.03, N = 5SE +/- 0.03, N = 5SE +/- 0.05, N = 4SE +/- 0.02, N = 39.0310.1812.1819.25

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Barbershop - Compute: NVIDIA OptiXRTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 406020406080100SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.23, N = 3SE +/- 0.04, N = 347.9954.6369.02101.48

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Junkshop - Compute: NVIDIA CUDARTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 4060714212835SE +/- 0.01, N = 4SE +/- 0.07, N = 3SE +/- 0.11, N = 3SE +/- 0.01, N = 315.5117.3626.4432.14

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Classroom - Compute: NVIDIA OptiXRTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 4060612182430SE +/- 0.01, N = 4SE +/- 0.00, N = 4SE +/- 0.06, N = 3SE +/- 0.03, N = 311.9213.3616.9624.51

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Pabellon Barcelona - Compute: NVIDIA OptiXRTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 4060612182430SE +/- 0.01, N = 4SE +/- 0.02, N = 4SE +/- 0.03, N = 3SE +/- 0.02, N = 313.1614.8617.3226.58

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Junkshop - Compute: NVIDIA OptiXRTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 4060510152025SE +/- 0.01, N = 5SE +/- 0.01, N = 5SE +/- 0.25, N = 3SE +/- 0.01, N = 39.7910.8617.5419.69

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: SHA1XTX 3XTX 2RX 7900 XTXRX 7900 XTRX 7900 GRERX 7800 XTRX 7700 XTRX 7600 XTRX 7600RTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 4060Arc B580Arc A770Arc A750Arc A5806000M12000M18000M24000M30000MSE +/- 24909352.33, N = 6SE +/- 8141679.46, N = 6SE +/- 46728830.62, N = 6SE +/- 22128976.73, N = 6SE +/- 2610204.33, N = 6SE +/- 20629558.08, N = 6SE +/- 9988348.77, N = 6SE +/- 23827752.26, N = 6SE +/- 22178749.84, N = 6SE +/- 13909341.39, N = 6SE +/- 9883142.21, N = 6SE +/- 1814221.60, N = 5SE +/- 2281315.41, N = 5SE +/- 1758806.41, N = 5SE +/- 2199454.48, N = 52997580000029971100000296961500002579948333321345083333173279833331693605000010250600000931256666725404966667219275166671824473333395123500002398820000620908000054956800004574160000

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 ComputeXTX 3XTX 2RX 7900 XTXRX 7900 XTRX 7900 GRERX 7800 XTRX 7700 XTRX 7600 XTRX 7600RTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 4060Arc B580Arc A770Arc A750Arc A5805K10K15K20K25KSE +/- 4.08, N = 11SE +/- 6.63, N = 11SE +/- 3.10, N = 11SE +/- 6.45, N = 11SE +/- 2.50, N = 11SE +/- 2.25, N = 11SE +/- 0.98, N = 11SE +/- 59.99, N = 14SE +/- 102.12, N = 13SE +/- 75.61, N = 13SE +/- 36.28, N = 13SE +/- 0.43, N = 7SE +/- 4.18, N = 4SE +/- 3.31, N = 4SE +/- 0.96, N = 46266.776313.886143.365476.724822.733633.893382.561801.611817.0221079.0817337.7314278.037511.144540.645521.584841.894047.251. (CXX) g++ options: -O3

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: BMW27 - Compute: NVIDIA OptiXRTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 40603691215SE +/- 0.01, N = 7SE +/- 0.03, N = 15SE +/- 0.03, N = 6SE +/- 0.09, N = 55.185.786.649.30

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 4.8.1Test: Server Rack - Acceleration: OpenCLXTX 3XTX 2RX 7900 XTXRX 7900 XTRX 7900 GRERX 7800 XTRX 7700 XTRX 7600 XTRX 7600RTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 4060Arc B580Arc A770Arc A750Arc A5800.04280.08560.12840.17120.214SE +/- 0.001, N = 13SE +/- 0.001, N = 15SE +/- 0.001, N = 13SE +/- 0.001, N = 15SE +/- 0.001, N = 13SE +/- 0.001, N = 15SE +/- 0.001, N = 15SE +/- 0.000, N = 13SE +/- 0.000, N = 13SE +/- 0.000, N = 13SE +/- 0.000, N = 13SE +/- 0.005, N = 15SE +/- 0.001, N = 14SE +/- 0.001, N = 14SE +/- 0.001, N = 140.1140.1160.1070.1100.1200.1160.1210.1300.1370.1130.1160.1230.1320.1900.1120.1110.111

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Barbershop - Compute: Intel oneAPIArc B580Arc A770Arc A750Arc A58060120180240300SE +/- 0.12, N = 3SE +/- 0.30, N = 3SE +/- 0.32, N = 3SE +/- 0.39, N = 3284.82167.35172.98199.86

Blend File: Barbershop - Compute: Intel oneAPI

RX 7600: The test quit with a non-zero exit status. E: Error: Not freed memory blocks: 2, total unfreed memory 0.000107 MB

RX 7600 XT: The test quit with a non-zero exit status. E: Error: Not freed memory blocks: 2, total unfreed memory 0.000107 MB

RX 7700 XT: The test quit with a non-zero exit status. E: Error: Not freed memory blocks: 2, total unfreed memory 0.000107 MB

RX 7800 XT: The test quit with a non-zero exit status. E: Error: Not freed memory blocks: 2, total unfreed memory 0.000107 MB

RX 7900 GRE: The test quit with a non-zero exit status. E: Error: Not freed memory blocks: 2, total unfreed memory 0.000107 MB

RX 7900 XT: The test quit with a non-zero exit status. E: Error: Not freed memory blocks: 2, total unfreed memory 0.000107 MB

RX 7900 XTX: The test quit with a non-zero exit status. E: Error: Not freed memory blocks: 2, total unfreed memory 0.000107 MB

XTX 2: The test quit with a non-zero exit status. E: Error: Not freed memory blocks: 2, total unfreed memory 0.000107 MB

XTX 3: The test quit with a non-zero exit status. E: Error: Not freed memory blocks: 2, total unfreed memory 0.000107 MB

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Junkshop - Compute: Intel oneAPIArc B580Arc A770Arc A750Arc A580816243240SE +/- 0.15, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.10, N = 334.3725.9725.8229.31

Blend File: Junkshop - Compute: Intel oneAPI

RX 7600: The test quit with a non-zero exit status. E: Error: Found no Cycles device of the specified type

RX 7600 XT: The test quit with a non-zero exit status. E: Error: Found no Cycles device of the specified type

RX 7700 XT: The test quit with a non-zero exit status. E: Error: Found no Cycles device of the specified type

RX 7800 XT: The test quit with a non-zero exit status. E: Error: Found no Cycles device of the specified type

RX 7900 GRE: The test quit with a non-zero exit status. E: Error: Found no Cycles device of the specified type

RX 7900 XT: The test quit with a non-zero exit status. E: Error: Found no Cycles device of the specified type

RX 7900 XTX: The test quit with a non-zero exit status. E: Error: Found no Cycles device of the specified type

XTX 2: The test quit with a non-zero exit status. E: Error: Found no Cycles device of the specified type

XTX 3: The test quit with a non-zero exit status. E: Error: Found no Cycles device of the specified type

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 4.8.1Test: Server Room - Acceleration: OpenCLXTX 3XTX 2RX 7900 XTXRX 7900 XTRX 7900 GRERX 7800 XTRX 7700 XTRX 7600 XTRX 7600RTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 4060Arc B580Arc A770Arc A750Arc A5800.22480.44960.67440.89921.124SE +/- 0.005, N = 15SE +/- 0.005, N = 11SE +/- 0.008, N = 15SE +/- 0.006, N = 11SE +/- 0.005, N = 11SE +/- 0.006, N = 11SE +/- 0.006, N = 11SE +/- 0.002, N = 11SE +/- 0.002, N = 11SE +/- 0.002, N = 11SE +/- 0.001, N = 11SE +/- 0.005, N = 11SE +/- 0.001, N = 11SE +/- 0.001, N = 11SE +/- 0.002, N = 110.8030.7700.7810.8030.8290.8220.8620.9520.9560.8530.8830.9070.9990.9500.8740.8790.884

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: Transfer Bandwidth enqueueReadBufferRTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 4060Arc B5803691215SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 312.8012.8212.8212.819.901. (CXX) g++ options: -O3

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Classroom - Compute: Intel oneAPIArc B580Arc A770Arc A750Arc A5801020304050SE +/- 0.15, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 345.3136.0337.5444.04

Blend File: Classroom - Compute: Intel oneAPI

RX 7600: The test quit with a non-zero exit status. E: Error: Found no Cycles device of the specified type

RX 7600 XT: The test quit with a non-zero exit status. E: Error: Found no Cycles device of the specified type

RX 7700 XT: The test quit with a non-zero exit status. E: Error: Found no Cycles device of the specified type

RX 7800 XT: The test quit with a non-zero exit status. E: Error: Found no Cycles device of the specified type

RX 7900 GRE: The test quit with a non-zero exit status. E: Error: Found no Cycles device of the specified type

RX 7900 XT: The test quit with a non-zero exit status. E: Error: Found no Cycles device of the specified type

RX 7900 XTX: The test quit with a non-zero exit status. E: Error: Found no Cycles device of the specified type

XTX 2: The test quit with a non-zero exit status. E: Error: Found no Cycles device of the specified type

XTX 3: The test quit with a non-zero exit status. E: Error: Found no Cycles device of the specified type

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Pabellon Barcelona - Compute: Intel oneAPIArc B580Arc A770Arc A750Arc A5801224364860SE +/- 0.23, N = 3SE +/- 0.28, N = 3SE +/- 0.29, N = 3SE +/- 0.28, N = 352.7044.7843.2450.16

Blend File: Pabellon Barcelona - Compute: Intel oneAPI

RX 7600: The test quit with a non-zero exit status. E: Error: Found no Cycles device of the specified type

RX 7600 XT: The test quit with a non-zero exit status. E: Error: Found no Cycles device of the specified type

RX 7700 XT: The test quit with a non-zero exit status. E: Error: Found no Cycles device of the specified type

RX 7800 XT: The test quit with a non-zero exit status. E: Error: Found no Cycles device of the specified type

RX 7900 GRE: The test quit with a non-zero exit status. E: Error: Found no Cycles device of the specified type

RX 7900 XT: The test quit with a non-zero exit status. E: Error: Found no Cycles device of the specified type

RX 7900 XTX: The test quit with a non-zero exit status. E: Error: Found no Cycles device of the specified type

XTX 2: The test quit with a non-zero exit status. E: Error: Found no Cycles device of the specified type

XTX 3: The test quit with a non-zero exit status. E: Error: Found no Cycles device of the specified type

SHOC Scalable HeterOgeneous Computing

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

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Bus Speed ReadbackXTX 3XTX 2RX 7900 XTXRX 7900 XTRX 7900 GRERX 7800 XTRX 7700 XTRX 7600 XTRX 7600RTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 4060Arc B580Arc A770Arc A750Arc A58048121620SE +/- 0.00, N = 12SE +/- 0.00, N = 15SE +/- 0.00, N = 12SE +/- 0.01, N = 12SE +/- 0.01, N = 12SE +/- 0.00, N = 12SE +/- 0.00, N = 12SE +/- 0.00, N = 12SE +/- 0.00, N = 11SE +/- 0.00, N = 11SE +/- 0.00, N = 11SE +/- 0.00, N = 12SE +/- 0.00, N = 12SE +/- 0.00, N = 12SE +/- 0.00, N = 1214.2814.2814.4814.5014.5014.5014.5114.4914.4913.2113.2213.2213.2214.4911.9111.9211.911. (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 4.8.1Test: Masskrug - Acceleration: OpenCLXTX 3XTX 2RX 7900 XTXRX 7900 XTRX 7900 GRERX 7800 XTRX 7700 XTRX 7600 XTRX 7600RTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 4060Arc B580Arc A770Arc A750Arc A5800.39060.78121.17181.56241.953SE +/- 0.009, N = 10SE +/- 0.006, N = 10SE +/- 0.009, N = 10SE +/- 0.007, N = 10SE +/- 0.006, N = 10SE +/- 0.007, N = 10SE +/- 0.007, N = 10SE +/- 0.004, N = 10SE +/- 0.004, N = 10SE +/- 0.005, N = 10SE +/- 0.003, N = 10SE +/- 0.012, N = 10SE +/- 0.005, N = 10SE +/- 0.007, N = 10SE +/- 0.006, N = 101.4831.5391.4871.4941.5401.5331.5471.6241.6301.5441.5631.5941.6671.7361.6281.6231.629

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: TriadXTX 3XTX 2RX 7900 XTXRX 7900 XTRX 7900 GRERX 7800 XTRX 7700 XTRX 7600 XTRX 7600RTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 4060Arc B580Arc A770Arc A750Arc A5803691215SE +/- 0.03, N = 11SE +/- 0.05, N = 11SE +/- 0.03, N = 11SE +/- 0.05, N = 11SE +/- 0.02, N = 11SE +/- 0.02, N = 11SE +/- 0.05, N = 11SE +/- 0.00, N = 12SE +/- 0.00, N = 12SE +/- 0.00, N = 12SE +/- 0.00, N = 12SE +/- 0.04, N = 12SE +/- 0.00, N = 12SE +/- 0.00, N = 12SE +/- 0.00, N = 1211.8612.0911.7511.7211.7211.6711.7511.5311.5812.6812.6512.6012.3512.5711.0211.0311.011. (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.orgGBPS, More Is Betterclpeak 1.1.2OpenCL Test: Transfer Bandwidth enqueueWriteBufferRTX 4070 Ti SUPERRTX 4070 SUPERRTX 4070RTX 4060Arc B5803691215SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 312.2612.2612.2612.2611.881. (CXX) g++ options: -O3

Blender

OpenBenchmarking.orgCelsius, Fewer Is BetterBlender 4.3GPU Temperature MonitorArc A770Arc A750Arc A5801326395265Min: 58 / Avg: 65.76 / Max: 69Min: 58 / Avg: 64.71 / Max: 69Min: 52 / Avg: 61.66 / Max: 66

OpenBenchmarking.orgCelsius, Fewer Is BetterBlender 4.3GPU Temperature MonitorArc A770Arc A750Arc A5801326395265Min: 49 / Avg: 63.37 / Max: 68Min: 57 / Avg: 63.76 / Max: 67Min: 54 / Avg: 61.31 / Max: 65

OpenBenchmarking.orgWatts, Fewer Is BetterBlender 4.3GPU Power Consumption MonitorArc B580Arc A770Arc A750Arc A5804080120160200Min: 36.7 / Avg: 103.85 / Max: 144.7Min: 34.5 / Avg: 140.85 / Max: 191.5Min: 36.6 / Avg: 142.95 / Max: 190.8Min: 41 / Avg: 118.74 / Max: 149.5

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: Fishy Cat - Compute: Intel oneAPIArc B580Arc A770Arc A750Arc A580510152025SE +/- 0.50, N = 15SE +/- 0.58, N = 15SE +/- 0.58, N = 15SE +/- 0.58, N = 1520.9116.4517.3320.15

Blend File: Fishy Cat - Compute: Intel oneAPI

RX 7600: The test quit with a non-zero exit status. E: Error: Found no Cycles device of the specified type

RX 7600 XT: The test quit with a non-zero exit status. E: Error: Found no Cycles device of the specified type

RX 7700 XT: The test quit with a non-zero exit status. E: Error: Found no Cycles device of the specified type

RX 7800 XT: The test quit with a non-zero exit status. E: Error: Found no Cycles device of the specified type

RX 7900 GRE: The test quit with a non-zero exit status. E: Error: Found no Cycles device of the specified type

RX 7900 XT: The test quit with a non-zero exit status. E: Error: Found no Cycles device of the specified type

RX 7900 XTX: The test quit with a non-zero exit status. E: Error: Found no Cycles device of the specified type

XTX 2: The test quit with a non-zero exit status. E: Error: Found no Cycles device of the specified type

XTX 3: The test quit with a non-zero exit status. E: Error: Found no Cycles device of the specified type

OpenBenchmarking.orgWatts, Fewer Is BetterBlender 4.3GPU Power Consumption MonitorArc B580Arc A770Arc A750Arc A5804080120160200Min: 36.2 / Avg: 80.66 / Max: 123.1Min: 34 / Avg: 145.05 / Max: 192.8Min: 36.5 / Avg: 140.33 / Max: 184.6Min: 40.9 / Avg: 119.07 / Max: 146.2

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.3Blend File: BMW27 - Compute: Intel oneAPIArc B580Arc A770Arc A750Arc A580612182430SE +/- 7.39, N = 15SE +/- 0.36, N = 15SE +/- 0.36, N = 15SE +/- 0.36, N = 1524.4213.2213.6615.71

Blend File: BMW27 - Compute: Intel oneAPI

RX 7600: The test quit with a non-zero exit status. E: Error: Found no Cycles device of the specified type

RX 7600 XT: The test quit with a non-zero exit status. E: Error: Found no Cycles device of the specified type

RX 7700 XT: The test quit with a non-zero exit status. E: Error: Found no Cycles device of the specified type

RX 7800 XT: The test quit with a non-zero exit status. E: Error: Found no Cycles device of the specified type

RX 7900 GRE: The test quit with a non-zero exit status. E: Error: Found no Cycles device of the specified type

RX 7900 XT: The test quit with a non-zero exit status. E: Error: Found no Cycles device of the specified type

RX 7900 XTX: The test quit with a non-zero exit status. E: Error: Found no Cycles device of the specified type

XTX 2: The test quit with a non-zero exit status. E: Error: Found no Cycles device of the specified type

XTX 3: The test quit with a non-zero exit status. E: Error: Found no Cycles device of the specified type