2 x AMD EPYC 75F3 32-Core testing with a ASRockRack ROME2D16-2T (P3.30 BIOS) and ASPEED on Ubuntu 21.10 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 2204097-NE-EPYC75F3N46
epyc-75f3-new
2 x AMD EPYC 75F3 32-Core testing with a ASRockRack ROME2D16-2T (P3.30 BIOS) and ASPEED on Ubuntu 21.10 via the Phoronix Test Suite.
,,"A","AA","B","C"
Processor,,2 x AMD EPYC 75F3 32-Core @ 2.95GHz (64 Cores / 128 Threads),2 x AMD EPYC 75F3 32-Core @ 2.95GHz (64 Cores / 128 Threads),2 x AMD EPYC 75F3 32-Core @ 2.95GHz (64 Cores / 128 Threads),2 x AMD EPYC 75F3 32-Core @ 2.95GHz (64 Cores / 128 Threads)
Motherboard,,ASRockRack ROME2D16-2T (P3.30 BIOS),ASRockRack ROME2D16-2T (P3.30 BIOS),ASRockRack ROME2D16-2T (P3.30 BIOS),ASRockRack ROME2D16-2T (P3.30 BIOS)
Chipset,,AMD Starship/Matisse,AMD Starship/Matisse,AMD Starship/Matisse,AMD Starship/Matisse
Memory,,128GB,128GB,128GB,128GB
Disk,,1000GB Western Digital WD_BLACK SN850 1TB,1000GB Western Digital WD_BLACK SN850 1TB,1000GB Western Digital WD_BLACK SN850 1TB,1000GB Western Digital WD_BLACK SN850 1TB
Graphics,,ASPEED,ASPEED,ASPEED,ASPEED
Audio,,AMD Starship/Matisse,AMD Starship/Matisse,AMD Starship/Matisse,AMD Starship/Matisse
Network,,2 x Intel 10G X550T,2 x Intel 10G X550T,2 x Intel 10G X550T,2 x Intel 10G X550T
OS,,Ubuntu 21.10,Ubuntu 21.10,Ubuntu 21.10,Ubuntu 21.10
Kernel,,5.17.0-051700rc4daily20220219-generic (x86_64),5.17.0-051700rc4daily20220219-generic (x86_64),5.17.0-051700rc4daily20220219-generic (x86_64),5.17.0-051700rc4daily20220219-generic (x86_64)
Desktop,,GNOME Shell 40.5,GNOME Shell 40.5,GNOME Shell 40.5,GNOME Shell 40.5
Display Server,,X Server,X Server,X Server,X Server
Vulkan,,1.1.182,1.1.182,1.1.182,1.1.182
Compiler,,GCC 11.2.0,GCC 11.2.0,GCC 11.2.0,GCC 11.2.0
File-System,,ext4,ext4,ext4,ext4
Screen Resolution,,1024x768,1024x768,1024x768,1024x768
,,"A","AA","B","C"
"libavif avifenc - Encoder Speed: 0 (sec)",LIB,69.460,69.411,70.327,70.646
"libavif avifenc - Encoder Speed: 2 (sec)",LIB,38.784,38.728,37.566,39.573
"libavif avifenc - Encoder Speed: 6 (sec)",LIB,4.278,4.093,3.986,4.215
"libavif avifenc - Encoder Speed: 6, Lossless (sec)",LIB,7.215,7.389,7.514,7.185
"libavif avifenc - Encoder Speed: 10, Lossless (sec)",LIB,5.010,5.229,5.197,4.971
"oneDNN - Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU (ms)",LIB,2.94158,3.7792,3.18091,3.85444
"oneDNN - Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU (ms)",LIB,2.63912,2.54811,2.56643,2.54404
"oneDNN - Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU (ms)",LIB,4.05569,4.25865,4.77292,2.55861
"oneDNN - Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU (ms)",LIB,0.747084,0.815632,0.757826,0.74301
"oneDNN - Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU (ms)",LIB,,,,
"oneDNN - Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU (ms)",LIB,,,,
"oneDNN - Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU (ms)",LIB,0.705380,0.708812,0.684799,0.689583
"oneDNN - Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU (ms)",LIB,11.2361,11.1395,11.2174,11.1942
"oneDNN - Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU (ms)",LIB,2.12767,2.10407,1.94632,1.99639
"oneDNN - Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU (ms)",LIB,0.897288,1.24701,0.928893,0.78443
"oneDNN - Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU (ms)",LIB,1.68391,1.07515,1.853,1.23753
"oneDNN - Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU (ms)",LIB,0.878553,0.904662,0.803426,0.829217
"oneDNN - Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU (ms)",LIB,3874.18,4530.24,4336.25,4224.87
"oneDNN - Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU (ms)",LIB,1693.03,1803.51,1810.37,1713.39
"oneDNN - Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU (ms)",LIB,3819.45,4416.22,4623.03,4390.23
"oneDNN - Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU (ms)",LIB,,,,
"oneDNN - Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU (ms)",LIB,,,,
"oneDNN - Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU (ms)",LIB,,,,
"oneDNN - Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU (ms)",LIB,1624.246,2016.94,1801.29,1696.6
"oneDNN - Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU (ms)",LIB,11.51214,17.5534,12.4965,21.6718
"oneDNN - Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU (ms)",LIB,,4276.7,4464.12,3862.48
"oneDNN - Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU (ms)",LIB,,1711.61,1734.92,1721.12
"oneDNN - Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU (ms)",LIB,,22.9061,27.3436,29.1013
"oneDNN - Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU (ms)",LIB,,,,
"ONNX Runtime - Model: GPT-2 - Device: CPU - Executor: Parallel (Inferences/min)",HIB,,1308,1225,1242
"ONNX Runtime - Model: GPT-2 - Device: CPU - Executor: Standard (Inferences/min)",HIB,,13234,13106,9094
"ONNX Runtime - Model: yolov4 - Device: CPU - Executor: Parallel (Inferences/min)",HIB,,434,436,436
"ONNX Runtime - Model: yolov4 - Device: CPU - Executor: Standard (Inferences/min)",HIB,,355,291,316
"ONNX Runtime - Model: bertsquad-12 - Device: CPU - Executor: Parallel (Inferences/min)",HIB,,594,592,592
"ONNX Runtime - Model: bertsquad-12 - Device: CPU - Executor: Standard (Inferences/min)",HIB,,540,643,539
"ONNX Runtime - Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel (Inferences/min)",HIB,,123,123,124
"ONNX Runtime - Model: fcn-resnet101-11 - Device: CPU - Executor: Standard (Inferences/min)",HIB,,170,158,152
"ONNX Runtime - Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel (Inferences/min)",HIB,,1225,1235,1229
"ONNX Runtime - Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard (Inferences/min)",HIB,,1194,1244,1279
"ONNX Runtime - Model: super-resolution-10 - Device: CPU - Executor: Parallel (Inferences/min)",HIB,,4320,4242,4233
"ONNX Runtime - Model: super-resolution-10 - Device: CPU - Executor: Standard (Inferences/min)",HIB,,4626,7762,4488
"perf-bench - Benchmark: Epoll Wait (ops/sec)",HIB,2352,2299,2572,2062
"perf-bench - Benchmark: Futex Hash (ops/sec)",HIB,2976792,2976712,2979134,2945494
"perf-bench - Benchmark: Memcpy 1MB (GB/sec)",HIB,42.868389,42.829829,44.147916,42.926485
"perf-bench - Benchmark: Memset 1MB (GB/sec)",HIB,62.455072,63.415414,63.789341,63.185354
"perf-bench - Benchmark: Sched Pipe (ops/sec)",HIB,345990,351368,346133,339461
"perf-bench - Benchmark: Futex Lock-Pi (ops/sec)",HIB,77,77,80,77
"perf-bench - Benchmark: Syscall Basic (ops/sec)",HIB,17051621,17052202,16941879,16924594