ARMv8 Neoverse-N1 testing with a GIGABYTE G242-P36-00 MP32-AR2-00 v01000100 (F31k SCP: 2.10.20220531 BIOS) and ASPEED on Ubuntu 23.10 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 2402068-NE-NEWAMP18865
new amp
ARMv8 Neoverse-N1 testing with a GIGABYTE G242-P36-00 MP32-AR2-00 v01000100 (F31k SCP: 2.10.20220531 BIOS) and ASPEED on Ubuntu 23.10 via the Phoronix Test Suite.
,,"a","b","c"
Processor,,ARMv8 Neoverse-N1 @ 3.00GHz (128 Cores),ARMv8 Neoverse-N1 @ 3.00GHz (128 Cores),ARMv8 Neoverse-N1 @ 3.00GHz (128 Cores)
Motherboard,,GIGABYTE G242-P36-00 MP32-AR2-00 v01000100 (F31k SCP: 2.10.20220531 BIOS),GIGABYTE G242-P36-00 MP32-AR2-00 v01000100 (F31k SCP: 2.10.20220531 BIOS),GIGABYTE G242-P36-00 MP32-AR2-00 v01000100 (F31k SCP: 2.10.20220531 BIOS)
Chipset,,Ampere Computing LLC Altra PCI Root Complex A,Ampere Computing LLC Altra PCI Root Complex A,Ampere Computing LLC Altra PCI Root Complex A
Memory,,16 x 32GB DDR4-3200MT/s Samsung M393A4K40DB3-CWE,16 x 32GB DDR4-3200MT/s Samsung M393A4K40DB3-CWE,16 x 32GB DDR4-3200MT/s Samsung M393A4K40DB3-CWE
Disk,,800GB Micron_7450_MTFDKBA800TFS,800GB Micron_7450_MTFDKBA800TFS,800GB Micron_7450_MTFDKBA800TFS
Graphics,,ASPEED,ASPEED,ASPEED
Monitor,,VGA HDMI,VGA HDMI,VGA HDMI
Network,,2 x Intel I350,2 x Intel I350,2 x Intel I350
OS,,Ubuntu 23.10,Ubuntu 23.10,Ubuntu 23.10
Kernel,,6.5.0-13-generic (aarch64),6.5.0-13-generic (aarch64),6.5.0-13-generic (aarch64)
Compiler,,GCC 13.2.0,GCC 13.2.0,GCC 13.2.0
File-System,,ext4,ext4,ext4
Screen Resolution,,1920x1080,1920x1080,1920x1080
,,"a","b","c"
"ONNX Runtime - Model: GPT-2 - Device: CPU - Executor: Parallel (Inferences/sec)",HIB,154.293,154.899,154.703
"ONNX Runtime - Model: GPT-2 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,178.736,176.523,177.439
"ONNX Runtime - Model: yolov4 - Device: CPU - Executor: Parallel (Inferences/sec)",HIB,6.09066,6.16283,6.20055
"ONNX Runtime - Model: yolov4 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,7.13777,7.11377,7.12556
"ONNX Runtime - Model: T5 Encoder - Device: CPU - Executor: Parallel (Inferences/sec)",HIB,250.556,251.252,251.457
"ONNX Runtime - Model: T5 Encoder - Device: CPU - Executor: Standard (Inferences/sec)",HIB,258.637,258.855,253.597
"ONNX Runtime - Model: bertsquad-12 - Device: CPU - Executor: Parallel (Inferences/sec)",HIB,10.9277,11.7545,11.1091
"ONNX Runtime - Model: bertsquad-12 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,22.1724,22.0769,21.9998
"ONNX Runtime - Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel (Inferences/sec)",HIB,576.593,566.725,576.227
"ONNX Runtime - Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,701.371,698.343,700.482
"ONNX Runtime - Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel (Inferences/sec)",HIB,1.12538,1.14758,1.13122
"ONNX Runtime - Model: fcn-resnet101-11 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,1.20414,1.24444,1.25872
"ONNX Runtime - Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel (Inferences/sec)",HIB,9.81261,9.82943,9.80991
"ONNX Runtime - Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,11.0025,10.7484,10.9854
"ONNX Runtime - Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel (Inferences/sec)",HIB,131.488,132,130.705
"ONNX Runtime - Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,170.121,167.736,170.632
"ONNX Runtime - Model: super-resolution-10 - Device: CPU - Executor: Parallel (Inferences/sec)",HIB,75.7142,75.6672,75.6401
"ONNX Runtime - Model: super-resolution-10 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,79.4944,79.5166,79.4851
"ONNX Runtime - Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel (Inferences/sec)",HIB,24.8599,24.8398,24.8612
"ONNX Runtime - Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,25.3641,25.0685,25.4554
"LZ4 Compression - Compression Level: 1 - Compression Speed (MB/s)",HIB,519.83,520.41,521.15
"LZ4 Compression - Compression Level: 1 - Decompression Speed (MB/s)",HIB,2815.2,2827.7,2841.8
"LZ4 Compression - Compression Level: 3 - Compression Speed (MB/s)",HIB,80.97,80.95,80.99
"LZ4 Compression - Compression Level: 3 - Decompression Speed (MB/s)",HIB,2492.2,2493.1,2491.6
"LZ4 Compression - Compression Level: 9 - Compression Speed (MB/s)",HIB,27.59,27.68,27.64
"LZ4 Compression - Compression Level: 9 - Decompression Speed (MB/s)",HIB,2511.8,2511,2512
"Llamafile - Test: llava-v1.5-7b-q4 - Acceleration: CPU (Tokens/sec)",HIB,3.31,3.02,3.31
"Llamafile - Test: mistral-7b-instruct-v0.2.Q8_0 - Acceleration: CPU (Tokens/sec)",HIB,3.15,2.89,2.83
"Llamafile - Test: wizardcoder-python-34b-v1.0.Q6_K - Acceleration: CPU (Tokens/sec)",HIB,1.78,1.74,1.77
"ONNX Runtime - Model: GPT-2 - Device: CPU - Executor: Parallel (Inference Time Cost (ms))",LIB,6.47235,6.44697,6.45507
"ONNX Runtime - Model: GPT-2 - Device: CPU - Executor: Standard (Inference Time Cost (ms))",LIB,5.58525,5.65511,5.62585
"ONNX Runtime - Model: yolov4 - Device: CPU - Executor: Parallel (Inference Time Cost (ms))",LIB,164.181,162.26,161.272
"ONNX Runtime - Model: yolov4 - Device: CPU - Executor: Standard (Inference Time Cost (ms))",LIB,140.095,140.568,140.335
"ONNX Runtime - Model: T5 Encoder - Device: CPU - Executor: Parallel (Inference Time Cost (ms))",LIB,3.98962,3.97869,3.9752
"ONNX Runtime - Model: T5 Encoder - Device: CPU - Executor: Standard (Inference Time Cost (ms))",LIB,3.86227,3.8592,3.93918
"ONNX Runtime - Model: bertsquad-12 - Device: CPU - Executor: Parallel (Inference Time Cost (ms))",LIB,91.5067,85.0699,90.0129
"ONNX Runtime - Model: bertsquad-12 - Device: CPU - Executor: Standard (Inference Time Cost (ms))",LIB,45.0965,45.2911,45.4499
"ONNX Runtime - Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel (Inference Time Cost (ms))",LIB,1.73248,1.76282,1.73356
"ONNX Runtime - Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard (Inference Time Cost (ms))",LIB,1.42343,1.42955,1.42532
"ONNX Runtime - Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel (Inference Time Cost (ms))",LIB,888.584,871.395,884
"ONNX Runtime - Model: fcn-resnet101-11 - Device: CPU - Executor: Standard (Inference Time Cost (ms))",LIB,830.466,803.571,794.456
"ONNX Runtime - Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel (Inference Time Cost (ms))",LIB,101.907,101.733,101.936
"ONNX Runtime - Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard (Inference Time Cost (ms))",LIB,90.885,93.0332,91.0258
"ONNX Runtime - Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel (Inference Time Cost (ms))",LIB,7.60357,7.57392,7.64929
"ONNX Runtime - Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard (Inference Time Cost (ms))",LIB,5.87533,5.95823,5.85706
"ONNX Runtime - Model: super-resolution-10 - Device: CPU - Executor: Parallel (Inference Time Cost (ms))",LIB,13.2062,13.2144,13.2191
"ONNX Runtime - Model: super-resolution-10 - Device: CPU - Executor: Standard (Inference Time Cost (ms))",LIB,12.576,12.5723,12.5774
"ONNX Runtime - Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel (Inference Time Cost (ms))",LIB,40.2226,40.2552,40.2202
"ONNX Runtime - Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard (Inference Time Cost (ms))",LIB,39.4206,39.8855,39.2789