opencl benchmark smoke test

ARMv8 Neoverse-V2 testing with a Quanta Cloud QuantaGrid S74G-2U 1S7GZ9Z0000 S7G MB (CG1) (3A06 BIOS) and NVIDIA GH200 480GB on Ubuntu 22.04 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2402266-NE-OPENCLBEN88&grs.

opencl benchmark smoke testProcessorMotherboardMemoryDiskGraphicsNetworkOSKernelDisplay DriverOpenCLVulkanCompilerFile-SystemScreen ResolutionabcdefARMv8 Neoverse-V2 @ 3.39GHz (72 Cores)Quanta Cloud QuantaGrid S74G-2U 1S7GZ9Z0000 S7G MB (CG1) (3A06 BIOS)1 x 480GB DRAM-6400MT/s960GB SAMSUNG MZ1L2960HCJR-00A07 + 1920GB SAMSUNG MZTL21T9NVIDIA GH200 480GB2 x Mellanox MT2910 + 2 x QLogic FastLinQ QL41000 10/25/40/50GbEUbuntu 22.046.5.0-1007-NVIDIA-64k (aarch64)NVIDIAOpenCL 3.0 CUDA 12.4.891.3.277GCC 11.4.0 + CUDA 11.5ext41920x1200OpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- --build=aarch64-linux-gnu --disable-libquadmath --disable-libquadmath-support --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-fix-cortex-a53-843419 --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-nls --enable-objc-gc=auto --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-linux-gnu --program-prefix=aarch64-linux-gnu- --target=aarch64-linux-gnu --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-target-system-zlib=auto -v Processor Details- Scaling Governor: cppc_cpufreq performance (Boost: Disabled)Graphics Details- BAR1 / Visible vRAM Size: N/A - vBIOS Version: 96.00.7e.00.02Security Details- gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Not affected + srbds: Not affected + tsx_async_abort: Not affected

opencl benchmark smoke testfinancebench: Monte-Carlo OpenCLopencl-benchmark: Memory Bandwidth Coalesced Writefinancebench: Black-Scholes OpenCLclpeak: Kernel Latencyarrayfire: Conjugate Gradient OpenCLcl-mem: Writeblender: BMW27 - CUDAopencl-benchmark: Memory Bandwidth Coalesced Readclpeak: Transfer Bandwidth enqueueWriteBufferclpeak: Transfer Bandwidth enqueueReadBuffercl-mem: Readopencl-benchmark: FP64 Computeopencl-benchmark: INT64 Computeclpeak: Integer Computeopencl-benchmark: FP32 Computecl-mem: Copyopencl-benchmark: INT16 Computeopencl-benchmark: INT8 Computeclpeak: Global Memory Bandwidthclpeak: Double-Precision Computeopencl-benchmark: INT32 Computeclpeak: Single-Precision Computeclpeak: Integer 24-bit Computeabcdef58.9746683688.044.3184.792.9982359.330.773614.32379.83295.591045.331.0203.24833143.1962.966308.430.94130.6233485.6832963.7632.99164543.4933101.4059.1860013733.624.3284.783.0022362.63616.79379.79295.58104631.0013.24833132.9562.961308.530.93430.6173486.1732959.8432.98764543.3333102.7759.5079993707.634.3174.773.0012358.13617.16379.65295.511045.930.9933.24833144.0562.975308.630.93330.6333484.4832960.8632.99164546.2733102.5159.0509993684.024.3054.792.9872361.93616.23379.55295.331046.3313.24533118.562.953308.530.93430.623486.1732960.3632.99664546.7633103.858.9500013690.924.334.82.992360.23615.04379.32295.221046.131.0013.24733116.4362.987308.530.9530.6273485.532948.132.98464538.9133101.2259.8883731.964.2934.782.9862361.630.823612.22379.43295.41046.231.0223.24733144.0562.946308.530.93430.6273486.0632958.3132.98764541.8633102OpenBenchmarking.org

FinanceBench

Benchmark: Monte-Carlo OpenCL

OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-07-25Benchmark: Monte-Carlo OpenCLabcdef1326395265SE +/- 0.06, N = 358.9759.1959.5159.0558.9559.891. (CXX) g++ options: -O3 -march=native -fopenmp

ProjectPhysX OpenCL-Benchmark

Operation: Memory Bandwidth Coalesced Write

OpenBenchmarking.orgGB/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.2Operation: Memory Bandwidth Coalesced Writeabcdef8001600240032004000SE +/- 12.89, N = 33688.043733.623707.633684.023690.923731.961. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

FinanceBench

Benchmark: Black-Scholes OpenCL

OpenBenchmarking.orgms, Fewer Is BetterFinanceBench 2016-07-25Benchmark: Black-Scholes OpenCLabcdef0.97431.94862.92293.89724.8715SE +/- 0.006, N = 34.3184.3284.3174.3054.3304.2931. (CXX) g++ options: -O3 -march=native -fopenmp

clpeak

OpenCL Test: Kernel Latency

OpenBenchmarking.orgus, Fewer Is Betterclpeak 1.1.2OpenCL Test: Kernel Latencyabcdef1.082.163.244.325.4SE +/- 0.01, N = 34.794.784.774.794.804.781. (CXX) g++ options: -O3

ArrayFire

Test: Conjugate Gradient OpenCL

OpenBenchmarking.orgms, Fewer Is BetterArrayFire 3.9Test: Conjugate Gradient OpenCLabcdef0.67551.3512.02652.7023.3775SE +/- 0.004, N = 32.9983.0023.0012.9872.9902.9861. (CXX) g++ options: -O3

cl-mem

Benchmark: Write

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: Writeabcdef5001000150020002500SE +/- 0.67, N = 32359.32362.62358.12361.92360.22361.61. (CC) gcc options: -O2 -flto -lOpenCL

Blender

Blend File: BMW27 - Compute: CUDA

OpenBenchmarking.orgSeconds, Fewer Is BetterBlenderBlend File: BMW27 - Compute: CUDAaf714212835SE +/- 0.16, N = 330.7730.82

ProjectPhysX OpenCL-Benchmark

Operation: Memory Bandwidth Coalesced Read

OpenBenchmarking.orgGB/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.2Operation: Memory Bandwidth Coalesced Readabcdef8001600240032004000SE +/- 0.88, N = 33614.323616.793617.163616.233615.043612.221. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

clpeak

OpenCL Test: Transfer Bandwidth enqueueWriteBuffer

OpenBenchmarking.orgGBPS, More Is Betterclpeak 1.1.2OpenCL Test: Transfer Bandwidth enqueueWriteBufferabcdef80160240320400SE +/- 0.04, N = 3379.83379.79379.65379.55379.32379.431. (CXX) g++ options: -O3

clpeak

OpenCL Test: Transfer Bandwidth enqueueReadBuffer

OpenBenchmarking.orgGBPS, More Is Betterclpeak 1.1.2OpenCL Test: Transfer Bandwidth enqueueReadBufferabcdef60120180240300SE +/- 0.04, N = 3295.59295.58295.51295.33295.22295.401. (CXX) g++ options: -O3

cl-mem

Benchmark: Read

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: Readabcdef2004006008001000SE +/- 0.06, N = 31045.31046.01045.91046.31046.11046.21. (CC) gcc options: -O2 -flto -lOpenCL

ProjectPhysX OpenCL-Benchmark

Operation: FP64 Compute

OpenBenchmarking.orgTFLOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.2Operation: FP64 Computeabcdef714212835SE +/- 0.00, N = 331.0231.0030.9931.0031.0031.021. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

ProjectPhysX OpenCL-Benchmark

Operation: INT64 Compute

OpenBenchmarking.orgTIOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.2Operation: INT64 Computeabcdef0.73081.46162.19242.92323.654SE +/- 0.002, N = 33.2483.2483.2483.2453.2473.2471. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

clpeak

OpenCL Test: Integer Compute

OpenBenchmarking.orgGIOPS, More Is Betterclpeak 1.1.2OpenCL Test: Integer Computeabcdef7K14K21K28K35KSE +/- 0.38, N = 333143.1933132.9533144.0533118.5033116.4333144.051. (CXX) g++ options: -O3

ProjectPhysX OpenCL-Benchmark

Operation: FP32 Compute

OpenBenchmarking.orgTFLOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.2Operation: FP32 Computeabcdef1428425670SE +/- 0.01, N = 362.9762.9662.9862.9562.9962.951. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

cl-mem

Benchmark: Copy

OpenBenchmarking.orgGB/s, More Is Bettercl-mem 2017-01-13Benchmark: Copyabcdef70140210280350SE +/- 0.07, N = 3308.4308.5308.6308.5308.5308.51. (CC) gcc options: -O2 -flto -lOpenCL

ProjectPhysX OpenCL-Benchmark

Operation: INT16 Compute

OpenBenchmarking.orgTIOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.2Operation: INT16 Computeabcdef714212835SE +/- 0.01, N = 330.9430.9330.9330.9330.9530.931. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

ProjectPhysX OpenCL-Benchmark

Operation: INT8 Compute

OpenBenchmarking.orgTIOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.2Operation: INT8 Computeabcdef714212835SE +/- 0.00, N = 330.6230.6230.6330.6230.6330.631. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

clpeak

OpenCL Test: Global Memory Bandwidth

OpenBenchmarking.orgGBPS, More Is Betterclpeak 1.1.2OpenCL Test: Global Memory Bandwidthabcdef7001400210028003500SE +/- 0.36, N = 33485.683486.173484.483486.173485.503486.061. (CXX) g++ options: -O3

clpeak

OpenCL Test: Double-Precision Compute

OpenBenchmarking.orgGFLOPS, More Is Betterclpeak 1.1.2OpenCL Test: Double-Precision Computeabcdef7K14K21K28K35KSE +/- 1.90, N = 332963.7632959.8432960.8632960.3632948.1032958.311. (CXX) g++ options: -O3

ProjectPhysX OpenCL-Benchmark

Operation: INT32 Compute

OpenBenchmarking.orgTIOPs/s, More Is BetterProjectPhysX OpenCL-Benchmark 1.2Operation: INT32 Computeabcdef816243240SE +/- 0.00, N = 332.9932.9932.9933.0032.9832.991. (CXX) g++ options: -std=c++17 -pthread -lOpenCL

clpeak

OpenCL Test: Single-Precision Compute

OpenBenchmarking.orgGFLOPS, More Is Betterclpeak 1.1.2OpenCL Test: Single-Precision Computeabcdef14K28K42K56K70KSE +/- 1.66, N = 364543.4964543.3364546.2764546.7664538.9164541.861. (CXX) g++ options: -O3

clpeak

OpenCL Test: Integer 24-bit Compute

OpenBenchmarking.orgGIOPS, More Is Betterclpeak 1.1.2OpenCL Test: Integer 24-bit Computeabcdef7K14K21K28K35KSE +/- 1.71, N = 333101.4033102.7733102.5133103.8033101.2233102.001. (CXX) g++ options: -O3


Phoronix Test Suite v10.8.5