vkpeak-1

AMD EPYC 7F52 16-Core testing with a ASRockRack ROMED8-2T v1.03 (P3.80 BIOS) and llvmpipe on Debian 12 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2501212-NE-VKPEAK10593&grr.

vkpeak-1ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLCompilerFile-SystemScreen Resolutiongpu-1AMD EPYC 7F52 16-Core @ 3.50GHz (16 Cores / 32 Threads)ASRockRack ROMED8-2T v1.03 (P3.80 BIOS)AMD Starship/Matisse8 x 32GB DDR4-3200MT/s Samsung M393A4K40EB3-CWE1000GB Samsung SSD 980 PRO 1TBllvmpipe (210/405MHz)NVIDIA GA102 HD AudioSDM-X932 x Intel X550Debian 126.1.0-30-amd64 (x86_64)Cinnamon 5.6.8X Server 1.21.1.7NVIDIA 565.57.014.5 Mesa 22.3.6 (LLVM 15.0.6 256 bits)OpenCL 3.0 CUDA 12.7.33GCC 12.2.0 + CUDA 12.6ext41280x1024OpenBenchmarking.org- Transparent Huge Pages: always- Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x830107c - BAR1 / Visible vRAM Size: 32768 MiB - vBIOS Version: 94.02.59.00.05- 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: Mitigation of untrained return thunk; SMT enabled with STIBP protection + spec_rstack_overflow: Mitigation of safe RET + 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; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected

vkpeak-1vkpeak: int16-vec4vkpeak: int16-scalarvkpeak: int32-vec4vkpeak: int32-scalarvkpeak: fp64-vec4vkpeak: fp64-scalarvkpeak: fp16-vec4vkpeak: fp16-scalarvkpeak: fp32-vec4vkpeak: fp32-scalargpu-113933.2612718.3319534.2819632.74635.20633.6722093.2720237.9126986.2420365.14OpenBenchmarking.org

vkpeak

int16-vec4

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20240505int16-vec4gpu-13K6K9K12K15KSE +/- 36.86, N = 313933.26

vkpeak

int16-scalar

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20240505int16-scalargpu-13K6K9K12K15KSE +/- 0.34, N = 312718.33

vkpeak

int32-vec4

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20240505int32-vec4gpu-14K8K12K16K20KSE +/- 1.27, N = 319534.28

vkpeak

int32-scalar

OpenBenchmarking.orgGIOPS, More Is Bettervkpeak 20240505int32-scalargpu-14K8K12K16K20KSE +/- 45.29, N = 319632.74

vkpeak

fp64-vec4

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20240505fp64-vec4gpu-1140280420560700SE +/- 1.63, N = 3635.20

vkpeak

fp64-scalar

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20240505fp64-scalargpu-1140280420560700SE +/- 0.01, N = 3633.67

vkpeak

fp16-vec4

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20240505fp16-vec4gpu-15K10K15K20K25KSE +/- 115.85, N = 322093.27

vkpeak

fp16-scalar

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20240505fp16-scalargpu-14K8K12K16K20KSE +/- 129.60, N = 320237.91

vkpeak

fp32-vec4

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20240505fp32-vec4gpu-16K12K18K24K30KSE +/- 124.91, N = 326986.24

vkpeak

fp32-scalar

OpenBenchmarking.orgGFLOPS, More Is Bettervkpeak 20240505fp32-scalargpu-14K8K12K16K20KSE +/- 105.28, N = 320365.14

Phoronix Test Suite v10.8.5