vkpeak-2 Intel Core i9-10980XE testing with a ASUS PRIME X299-A (3301 BIOS) and AMD Radeon Pro VII/Radeon Inst t MI50 32GB 16GB on openSUSE 20240423 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2404277-NE-VKPEAK29587&grw .
vkpeak-2 Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server OpenGL OpenCL Compiler File-System Screen Resolution AMD Radeon Pro VII Intel Core i9-10980XE @ 4.80GHz (18 Cores / 36 Threads) ASUS PRIME X299-A (3301 BIOS) Intel Sky Lake-E DMI3 Registers 128GB 4001GB Corsair Force MP510 + 8002GB Samsung SSD 870 + 2 x 6001GB Seagate ST6000VX001-2BD1 + 2 x 2000GB Western Digital WD20EFRX-68A + 6001GB Western Digital WD60EFAX-68J + 250GB Samsung SSD 840 + 500GB Samsung SSD 850 + 2000GB Seagate BarraCud + 0GB USB3.0 CRW-0 + 0GB USB3.0 CRW-1 + 0GB USB3.0 CRW-2 + 0GB USB3.0 CRW-3 AMD Radeon Pro VII/Radeon Inst t MI50 32GB 16GB Realtek ALC1220 HP Z27n G2 Intel I219-V openSUSE 20240423 6.8.7-1-default (x86_64) KDE Plasma 6.0.4 X Server 1.21.1.12 + Wayland 4.6 Mesa 24.0.3 (LLVM 18.1.3 DRM 3.57) OpenCL 3.0 GCC 13.2.1 20240206 [revision 67ac78caf31f7cb3202177e6428a46d829b70f23] + Clang 18.1.4 + LLVM 18.1.4 tmpfs 2560x1440 OpenBenchmarking.org - nvme_core.default_ps_max_latency_us=0 - Transparent Huge Pages: always - Scaling Governor: intel_pstate powersave (EPP: balance_performance) - CPU Microcode: 0x5003605 - GLAMOR - BAR1 / Visible vRAM Size: 256 MB - gather_data_sampling: Mitigation of Microcode + itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + reg_file_data_sampling: Not affected + retbleed: Vulnerable + 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: Vulnerable; IBPB: disabled; STIBP: disabled; PBRSB-eIBRS: Vulnerable; BHI: Vulnerable + srbds: Not affected + tsx_async_abort: Mitigation of TSX disabled
vkpeak-2 vkpeak: fp32-scalar vkpeak: fp32-vec4 vkpeak: fp16-scalar vkpeak: fp16-vec4 vkpeak: fp64-scalar vkpeak: fp64-vec4 vkpeak: int32-scalar vkpeak: int32-vec4 vkpeak: int16-scalar vkpeak: int16-vec4 AMD Radeon Pro VII 13016.49 12272.66 6512.59 22156.99 6183.13 6093.80 4331.78 4332.73 6509.41 21768.77 OpenBenchmarking.org
vkpeak fp32-scalar OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20230730 fp32-scalar AMD Radeon Pro VII 3K 6K 9K 12K 15K SE +/- 0.33, N = 3 13016.49
vkpeak fp32-vec4 OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20230730 fp32-vec4 AMD Radeon Pro VII 3K 6K 9K 12K 15K SE +/- 24.58, N = 3 12272.66
vkpeak fp16-scalar OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20230730 fp16-scalar AMD Radeon Pro VII 1400 2800 4200 5600 7000 SE +/- 0.02, N = 3 6512.59
vkpeak fp16-vec4 OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20230730 fp16-vec4 AMD Radeon Pro VII 5K 10K 15K 20K 25K SE +/- 35.43, N = 3 22156.99
vkpeak fp64-scalar OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20230730 fp64-scalar AMD Radeon Pro VII 1300 2600 3900 5200 6500 SE +/- 14.53, N = 3 6183.13
vkpeak fp64-vec4 OpenBenchmarking.org GFLOPS, More Is Better vkpeak 20230730 fp64-vec4 AMD Radeon Pro VII 1300 2600 3900 5200 6500 SE +/- 155.40, N = 3 6093.80
vkpeak int32-scalar OpenBenchmarking.org GIOPS, More Is Better vkpeak 20230730 int32-scalar AMD Radeon Pro VII 900 1800 2700 3600 4500 SE +/- 0.14, N = 3 4331.78
vkpeak int32-vec4 OpenBenchmarking.org GIOPS, More Is Better vkpeak 20230730 int32-vec4 AMD Radeon Pro VII 900 1800 2700 3600 4500 SE +/- 0.03, N = 3 4332.73
vkpeak int16-scalar OpenBenchmarking.org GIOPS, More Is Better vkpeak 20230730 int16-scalar AMD Radeon Pro VII 1400 2800 4200 5600 7000 SE +/- 3.10, N = 3 6509.41
vkpeak int16-vec4 OpenBenchmarking.org GIOPS, More Is Better vkpeak 20230730 int16-vec4 AMD Radeon Pro VII 5K 10K 15K 20K 25K SE +/- 65.72, N = 3 21768.77
Phoronix Test Suite v10.8.4