onnx gh200

ARMv8 Neoverse-V2 testing with a Quanta Cloud QuantaGrid S74G-2U 1S7GZ9Z0000 S7G MB (CG1) (3A06 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 2402042-NE-ONNXGH20009

Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result

Hide
Result

Result
Identifier

Performance Per
Dollar

Date
Run

Test
Duration

February 04

1 Hour, 46 Minutes

February 04

1 Hour, 58 Minutes

February 04

25 Minutes

February 04

25 Minutes

Invert Hiding All Results Option

1 Hour, 9 Minutes

Only show results where is faster than

Only show results matching title/arguments (delimit multiple options with a comma):

Do not show results matching title/arguments (delimit multiple options with a comma):

onnx gh200 ARMv8 Neoverse-V2 testing with a Quanta Cloud QuantaGrid S74G-2U 1S7GZ9Z0000 S7G MB (CG1) (3A06 BIOS) and ASPEED on Ubuntu 23.10 via the Phoronix Test Suite. ,,"a","b","c","d" Processor,,ARMv8 Neoverse-V2 @ 3.39GHz (72 Cores),ARMv8 Neoverse-V2 @ 3.39GHz (72 Cores),ARMv8 Neoverse-V2 @ 3.39GHz (72 Cores),ARMv8 Neoverse-V2 @ 3.39GHz (72 Cores) Motherboard,,Quanta Cloud QuantaGrid S74G-2U 1S7GZ9Z0000 S7G MB (CG1) (3A06 BIOS),Quanta Cloud QuantaGrid S74G-2U 1S7GZ9Z0000 S7G MB (CG1) (3A06 BIOS),Quanta Cloud QuantaGrid S74G-2U 1S7GZ9Z0000 S7G MB (CG1) (3A06 BIOS),Quanta Cloud QuantaGrid S74G-2U 1S7GZ9Z0000 S7G MB (CG1) (3A06 BIOS) Memory,,1 x 480GB DRAM-6400MT/s,1 x 480GB DRAM-6400MT/s,1 x 480GB DRAM-6400MT/s,1 x 480GB DRAM-6400MT/s Disk,,960GB SAMSUNG MZ1L2960HCJR-00A07 + 1920GB SAMSUNG MZTL21T9,960GB SAMSUNG MZ1L2960HCJR-00A07 + 1920GB SAMSUNG MZTL21T9,960GB SAMSUNG MZ1L2960HCJR-00A07 + 1920GB SAMSUNG MZTL21T9,960GB SAMSUNG MZ1L2960HCJR-00A07 + 1920GB SAMSUNG MZTL21T9 Graphics,,ASPEED,ASPEED,ASPEED,ASPEED Network,,2 x Mellanox MT2910 + 2 x QLogic FastLinQ QL41000 10/25/40/50GbE,2 x Mellanox MT2910 + 2 x QLogic FastLinQ QL41000 10/25/40/50GbE,2 x Mellanox MT2910 + 2 x QLogic FastLinQ QL41000 10/25/40/50GbE,2 x Mellanox MT2910 + 2 x QLogic FastLinQ QL41000 10/25/40/50GbE OS,,Ubuntu 23.10,Ubuntu 23.10,Ubuntu 23.10,Ubuntu 23.10 Kernel,,6.5.0-15-generic (aarch64),6.5.0-15-generic (aarch64),6.5.0-15-generic (aarch64),6.5.0-15-generic (aarch64) Compiler,,GCC 13.2.0,GCC 13.2.0,GCC 13.2.0,GCC 13.2.0 File-System,,ext4,ext4,ext4,ext4 Screen Resolution,,1920x1200,1920x1200,1920x1200,1920x1200 ,,"a","b","c","d" "ONNX Runtime - Model: GPT-2 - Device: CPU - Executor: Parallel (Inferences/sec)",HIB,,,, "ONNX Runtime - Model: GPT-2 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,,,, "ONNX Runtime - Model: yolov4 - Device: CPU - Executor: Parallel (Inferences/sec)",HIB,8.36597,8.30820,8.6564,8.34625 "ONNX Runtime - Model: yolov4 - Device: CPU - Executor: Parallel (Inference Time Cost (ms))",LIB,119.530,120.422,115.518,119.81 "ONNX Runtime - Model: yolov4 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,11.0687,11.1851,11.3685,11.4108 "ONNX Runtime - Model: yolov4 - Device: CPU - Executor: Standard (Inference Time Cost (ms))",LIB,90.3501,89.4041,87.9548,87.628 "ONNX Runtime - Model: T5 Encoder - Device: CPU - Executor: Parallel (Inferences/sec)",HIB,75.2417,74.1639,76.2605,78.5892 "ONNX Runtime - Model: T5 Encoder - Device: CPU - Executor: Parallel (Inference Time Cost (ms))",LIB,13.2889,13.4822,13.1099,12.7215 "ONNX Runtime - Model: T5 Encoder - Device: CPU - Executor: Standard (Inferences/sec)",HIB,367.963,374.207,374.202,344.562 "ONNX Runtime - Model: T5 Encoder - Device: CPU - Executor: Standard (Inference Time Cost (ms))",LIB,2.71650,2.67306,2.66641,2.89589 "ONNX Runtime - Model: bertsquad-12 - Device: CPU - Executor: Parallel (Inferences/sec)",HIB,,,, "ONNX Runtime - Model: bertsquad-12 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,,,, "ONNX Runtime - Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel (Inferences/sec)",HIB,548.965,532.261,539.31,536.915 "ONNX Runtime - Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel (Inference Time Cost (ms))",LIB,1.82009,1.87709,1.85241,1.86068 "ONNX Runtime - Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,1112.69,1125.55,1164.06,1154.69 "ONNX Runtime - Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard (Inference Time Cost (ms))",LIB,0.897753,0.887622,0.858087,0.865053 "ONNX Runtime - Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel (Inferences/sec)",HIB,1.47621,1.47745,1.52538,1.48956 "ONNX Runtime - Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel (Inference Time Cost (ms))",LIB,677.751,676.874,655.567,671.335 "ONNX Runtime - Model: fcn-resnet101-11 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,1.48485,1.49458,1.4664,1.48493 "ONNX Runtime - Model: fcn-resnet101-11 - Device: CPU - Executor: Standard (Inference Time Cost (ms))",LIB,673.470,669.125,681.935,673.423 "ONNX Runtime - Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel (Inferences/sec)",HIB,,,, "ONNX Runtime - Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,,,, "ONNX Runtime - Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel (Inferences/sec)",HIB,241.428,241.101,246.944,245.086 "ONNX Runtime - Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel (Inference Time Cost (ms))",LIB,4.14119,4.14668,4.04811,4.07887 "ONNX Runtime - Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,272.681,277.494,290.32,284.01 "ONNX Runtime - Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard (Inference Time Cost (ms))",LIB,3.66668,3.60302,3.44312,3.51969 "ONNX Runtime - Model: super-resolution-10 - Device: CPU - Executor: Parallel (Inferences/sec)",HIB,43.3703,42.7739,41.6917,42.8567 "ONNX Runtime - Model: super-resolution-10 - Device: CPU - Executor: Parallel (Inference Time Cost (ms))",LIB,23.0604,23.3815,23.9848,23.3328 "ONNX Runtime - Model: super-resolution-10 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,149.545,148.714,148.299,149.676 "ONNX Runtime - Model: super-resolution-10 - Device: CPU - Executor: Standard (Inference Time Cost (ms))",LIB,6.68539,6.72220,6.74173,6.67817 "ONNX Runtime - Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel (Inferences/sec)",HIB,,,, "ONNX Runtime - Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,,,,