OpenCL ROCm AMD

AMD Ryzen 9 7950X 16-Core testing with a ASUS ROG CROSSHAIR X670E HERO (9922 BIOS) and Sapphire AMD Radeon RX 6500 XT 4GB on Ubuntu 23.04 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2303112-NE-OPENCLROC53
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:

HPC - High Performance Computing 2 Tests
Machine Learning 2 Tests
NVIDIA GPU Compute 3 Tests
OpenCL 3 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
RX 6600
March 09 2023
  1 Hour, 9 Minutes
RX 6700 XT
March 09 2023
  58 Minutes
6700 XT
March 09 2023
  15 Minutes
AMD 6700XT
March 09 2023
  15 Minutes
RX 6500 XT
March 09 2023
  1 Hour, 25 Minutes
Invert Hiding All Results Option
  48 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 ROCm AMDOpenBenchmarking.orgPhoronix Test SuiteAMD Ryzen 9 7950X 16-Core @ 4.50GHz (16 Cores / 32 Threads)ASUS ROG CROSSHAIR X670E HERO (9922 BIOS)AMD Device 14d82 x 16 GB DDR5-6000MT/s F5-6000J3038F16GWestern Digital WD_BLACK SN850X 1000GB + 2000GBGigabyte AMD Radeon RX 6600 8GB (2750/875MHz)AMD Radeon RX 6700 XT 12GB (2855/1000MHz)Sapphire AMD Radeon RX 6500 XT 4GB (2975/1124MHz)AMD Navi 21/23ASUS MG28UIntel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411Ubuntu 23.046.2.2-060202-generic (x86_64)GNOME Shell 43.2X Server 1.21.1.64.6 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)GCC 12.2.0ext43840x2160ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerOpenGLOpenCLCompilerFile-SystemScreen ResolutionOpenCL ROCm AMD BenchmarksSystem Logs- Transparent Huge Pages: madvise- --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 - Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa601203- 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- 6700 XT: BAR1 / Visible vRAM Size: 12272 MB - vBIOS Version: 113-D5121100-101- AMD 6700XT: 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- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

RX 6600RX 6700 XT6700 XTAMD 6700XTRX 6500 XTResult OverviewPhoronix Test Suite100%158%216%275%333%SHOC Scalable HeterOgeneous ComputingFluidX3DLeelaChessZeroclpeak

OpenCL ROCm AMDshoc: OpenCL - Triadshoc: OpenCL - Reductionshoc: OpenCL - Bus Speed Downloadshoc: OpenCL - Bus Speed Readbackshoc: OpenCL - Texture Read Bandwidthclpeak: Global Memory Bandwidthclpeak: Transfer Bandwidth enqueueReadBufferclpeak: Transfer Bandwidth enqueueWriteBuffershoc: OpenCL - S3Dclpeak: Double-Precision Computeclpeak: Single-Precision Computeshoc: OpenCL - GEMM SGEMM_Nshoc: OpenCL - MD5 Hashclpeak: Integer 24-bit Computeclpeak: Integer Computefluidx3d: FP32-FP32fluidx3d: FP32-FP16Cfluidx3d: FP32-FP16Slczero: OpenCLclpeak: Kernel LatencyRX 6600RX 6700 XT6700 XTAMD 6700XTRX 6500 XT12.2654208.07614.336314.0904603.589191.264.9722.6479.7646569.748032.821778.0711.89717831.732164.23962183818161479111.8023.6167626.30828.856126.4047641.156311.694.9922.65110.295807.5311441.234337.6016.393710802.432991.011382279327861946013.3924.0596624.59728.854926.3997661.364310.65.0722.82111.154807.7811246.94608.7416.400510793.542986.91375278927851969913.1123.0553626.40828.856126.4033647.199310.615.0422.15108.208810.7611260.174550.6116.39710709.572994.051377282828051993013.216.3591139.2667.16367.0477535.113122.865.0123.5223.5439336.004790.971063.037.08204680.821270.5949510301011739011.45OpenBenchmarking.org

GPU Power Consumption Monitor

OpenBenchmarking.orgWattsGPU Power Consumption MonitorPhoronix Test Suite System MonitoringRX 6700 XTRX 6600AMD 6700XT6700 XT306090120150Min: 4 / Avg: 66.55 / Max: 188Min: 3 / Avg: 38.83 / Max: 100Min: 4 / Avg: 62.25 / Max: 187Min: 4 / Avg: 62.11 / Max: 188

SHOC Scalable HeterOgeneous Computing

OpenBenchmarking.orgGB/s Per Watt, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: TriadRX 6700 XTRX 6600AMD 6700XT6700 XT0.84421.68842.53263.37684.2213.4972.1253.3843.752

OpenBenchmarking.orgGB/s Per Watt, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: ReductionRX 6700 XTRX 6600AMD 6700XT6700 XT163248648070.8220.3473.4467.07

OpenBenchmarking.orgGB/s Per Watt, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Bus Speed DownloadRX 6700 XTRX 6600AMD 6700XT6700 XT1.24022.48043.72064.96086.2014.4612.7894.1575.512

OpenBenchmarking.orgGB/s Per Watt, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Bus Speed ReadbackRX 6700 XTRX 6600AMD 6700XT6700 XT0.97991.95982.93973.91964.89954.3552.6623.7724.234

OpenBenchmarking.orgGB/s Per Watt, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Texture Read BandwidthRX 6700 XTRX 6600AMD 6700XT6700 XT91827364533.8338.2236.0736.74

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: TriadRX 6700 XTRX 6600RX 6500 XTAMD 6700XT6700 XT612182430SE +/- 0.1999, N = 4SE +/- 0.0985, N = 15SE +/- 0.0647, N = 323.616712.26546.359123.055324.05961. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: ReductionRX 6700 XTRX 6600RX 6500 XTAMD 6700XT6700 XT140280420560700SE +/- 1.07, N = 4SE +/- 0.14, N = 4SE +/- 0.02, N = 3626.31208.08139.27626.41624.601. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Bus Speed DownloadRX 6700 XTRX 6600RX 6500 XTAMD 6700XT6700 XT714212835SE +/- 0.0008, N = 4SE +/- 0.0012, N = 4SE +/- 0.0003, N = 328.856114.33637.163628.856128.85491. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Bus Speed ReadbackRX 6700 XTRX 6600RX 6500 XTAMD 6700XT6700 XT612182430SE +/- 0.0007, N = 4SE +/- 0.0085, N = 4SE +/- 0.0002, N = 326.404714.09047.047726.403326.39971. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

OpenBenchmarking.orgGB/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: Texture Read BandwidthRX 6700 XTRX 6600RX 6500 XTAMD 6700XT6700 XT140280420560700SE +/- 1.16, N = 4SE +/- 3.98, N = 15SE +/- 2.35, N = 3641.16603.59535.11647.20661.361. (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: Global Memory BandwidthRX 6700 XTRX 6600RX 6500 XTAMD 6700XT6700 XT70140210280350SE +/- 0.82, N = 5SE +/- 0.57, N = 5SE +/- 0.31, N = 3311.69191.26122.86310.61310.601. (CXX) g++ options: -O3

OpenBenchmarking.orgGBPS Per Watt, More Is Betterclpeak 1.1.2OpenCL Test: Transfer Bandwidth enqueueReadBufferRX 6700 XTRX 6600AMD 6700XT6700 XT0.3510.7021.0531.4041.7551.2291.5601.2351.225

OpenBenchmarking.orgGBPS, More Is Betterclpeak 1.1.2OpenCL Test: Transfer Bandwidth enqueueReadBufferRX 6700 XTRX 6600RX 6500 XTAMD 6700XT6700 XT1.14082.28163.42244.56325.704SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 34.994.975.015.045.071. (CXX) g++ options: -O3

OpenBenchmarking.orgGBPS, More Is Betterclpeak 1.1.2OpenCL Test: Transfer Bandwidth enqueueWriteBufferRX 6700 XTRX 6600RX 6500 XTAMD 6700XT6700 XT612182430SE +/- 0.01, N = 3SE +/- 0.18, N = 15SE +/- 0.20, N = 1522.6522.6423.5222.1522.821. (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: S3DRX 6700 XTRX 6600RX 6500 XTAMD 6700XT6700 XT20406080100SE +/- 0.83, N = 11SE +/- 0.18, N = 3SE +/- 0.95, N = 15110.3079.7623.54108.21111.151. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

clpeak

OpenBenchmarking.orgGFLOPS Per Watt, More Is Betterclpeak 1.1.2OpenCL Test: Single-Precision ComputeRX 6700 XTRX 6600AMD 6700XT6700 XT400800120016002000916.94839.62647.141984.75

OpenBenchmarking.orgGFLOPS, More Is Betterclpeak 1.1.2OpenCL Test: Double-Precision ComputeRX 6700 XTRX 6600RX 6500 XTAMD 6700XT6700 XT2004006008001000SE +/- 0.76, N = 6SE +/- 1.11, N = 6SE +/- 0.44, N = 3807.53569.74336.00810.76807.781. (CXX) g++ options: -O3

OpenBenchmarking.orgGFLOPS, More Is Betterclpeak 1.1.2OpenCL Test: Single-Precision ComputeRX 6700 XTRX 6600RX 6500 XTAMD 6700XT6700 XT2K4K6K8K10KSE +/- 41.68, N = 7SE +/- 27.15, N = 7SE +/- 48.42, N = 311441.238032.824790.9711260.1711246.901. (CXX) g++ options: -O3

SHOC Scalable HeterOgeneous Computing

OpenBenchmarking.orgGFLOPS Per Watt, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: GEMM SGEMM_NRX 6700 XTRX 6600AMD 6700XT6700 XT60120180240300228.49102.61275.30227.59

OpenBenchmarking.orgGFLOPS, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: GEMM SGEMM_NRX 6700 XTRX 6600RX 6500 XTAMD 6700XT6700 XT10002000300040005000SE +/- 57.13, N = 15SE +/- 3.55, N = 4SE +/- 1.40, N = 34337.601778.071063.034550.614608.741. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -lmpi_cxx -lmpi

OpenBenchmarking.orgGHash/s, More Is BetterSHOC Scalable HeterOgeneous Computing 2020-04-17Target: OpenCL - Benchmark: MD5 HashRX 6700 XTRX 6600RX 6500 XTAMD 6700XT6700 XT48121620SE +/- 0.0023, N = 4SE +/- 0.0013, N = 4SE +/- 0.0003, N = 316.393711.89717.082016.397016.40051. (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 ComputeRX 6700 XTRX 6600RX 6500 XTAMD 6700XT6700 XT2K4K6K8K10KSE +/- 16.15, N = 7SE +/- 14.90, N = 7SE +/- 11.19, N = 310802.437831.734680.8210709.5710793.541. (CXX) g++ options: -O3

OpenBenchmarking.orgGIOPS Per Watt, More Is Betterclpeak 1.1.2OpenCL Test: Integer ComputeRX 6700 XTRX 6600AMD 6700XT6700 XT4080120160200139.75142.02147.69160.59

OpenBenchmarking.orgGIOPS, More Is Betterclpeak 1.1.2OpenCL Test: Integer ComputeRX 6700 XTRX 6600RX 6500 XTAMD 6700XT6700 XT6001200180024003000SE +/- 3.08, N = 7SE +/- 6.13, N = 7SE +/- 3.85, N = 32991.012164.231270.592994.052986.901. (CXX) g++ options: -O3

FluidX3D

OpenBenchmarking.orgMLUPs/s Per Watt, More Is BetterFluidX3D 2.3Test: FP32-FP16CRX 6700 XTRX 6600AMD 6700XT6700 XT51015202520.8622.5221.1721.12

OpenBenchmarking.orgMLUPs/s, More Is BetterFluidX3D 2.3Test: FP32-FP32RX 6700 XTRX 6600RX 6500 XTAMD 6700XT6700 XT30060090012001500SE +/- 4.84, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3138296249513771375

OpenBenchmarking.orgMLUPs/s Per Watt, More Is BetterFluidX3D 2.3Test: FP32-FP16SRX 6700 XTRX 6600AMD 6700XT6700 XT71421283526.0328.0926.4526.31

OpenBenchmarking.orgMLUPs/s, More Is BetterFluidX3D 2.3Test: FP32-FP16CRX 6700 XTRX 6600RX 6500 XTAMD 6700XT6700 XT6001200180024003000SE +/- 2.03, N = 3SE +/- 2.19, N = 3SE +/- 0.88, N = 327931838103028282789

OpenBenchmarking.orgMLUPs/s, More Is BetterFluidX3D 2.3Test: FP32-FP16SRX 6700 XTRX 6600RX 6500 XTAMD 6700XT6700 XT6001200180024003000SE +/- 6.36, N = 3SE +/- 0.88, N = 3SE +/- 0.58, N = 327861816101128052785

LeelaChessZero

OpenBenchmarking.orgNodes Per Second Per Watt, More Is BetterLeelaChessZero 0.28Backend: OpenCLRX 6700 XTRX 6600AMD 6700XT6700 XT306090120150115.31152.26114.22112.72

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.28Backend: OpenCLRX 6700 XTRX 6600RX 6500 XTAMD 6700XT6700 XT4K8K12K16K20KSE +/- 146.89, N = 3SE +/- 29.31, N = 3SE +/- 6.69, N = 31946014791739019930196991. (CXX) g++ options: -flto -pthread

Meta Performance Per Watts

OpenBenchmarking.orgPerformance Per Watts, More Is BetterMeta Performance Per WattsPerformance Per WattsRX 6700 XTRX 6600AMD 6700XT6700 XT90180270360450433.14284.22433.56435.92

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 LatencyRX 6700 XTRX 6600RX 6500 XTAMD 6700XT6700 XT3691215SE +/- 0.10, N = 15SE +/- 0.10, N = 15SE +/- 0.09, N = 313.3911.8011.4513.2113.111. (CXX) g++ options: -O3