Gigabyte Technology Co., Ltd. TRX40 DESIGNARE
Geekbench ML Score
1448
ONNX CPU Inference Score
Geekbench ML 0.6.0 for Windows AVX2
Result Information
| Upload Date | August 16 2024 03:04 PM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Microsoft Windows 11 Pro (64-bit) |
| Model | Gigabyte Technology Co., Ltd. TRX40 DESIGNARE |
| Motherboard | Gigabyte Technology Co., Ltd. TRX40 DESIGNARE |
| Power Plan | Power saver |
| CPU Information | |
|---|---|
| Name | AMD Ryzen Threadripper 3960X |
| Topology | 1 Processor, 24 Cores, 48 Threads |
| Identifier | AuthenticAMD Family 23 Model 49 Stepping 0 |
| Base Frequency | 3.79 GHz |
| Cluster 1 | 24 Cores |
| L1 Instruction Cache | 32.0 KB x 24 |
| L1 Data Cache | 32.0 KB x 24 |
| L2 Cache | 512 KB x 24 |
| L3 Cache | 16.0 MB x 8 |
| Memory Information | |
|---|---|
| Size | 224.00 GB |
| Inference Information | |
|---|---|
| Framework | ONNX |
| Backend | CPU |
| Device | Default |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
592
110.8 IPS |
|
|
Image Classification (F16)
|
100% |
590
110.4 IPS |
|
|
Image Classification (I8)
|
97% |
1061
198.5 IPS |
|
|
Image Segmentation (F32)
|
100% |
579
9.67 IPS |
|
|
Image Segmentation (F16)
|
100% |
557
9.30 IPS |
|
|
Image Segmentation (I8)
|
97% |
1024
17.1 IPS |
|
|
Pose Estimation (F32)
|
100% |
5412
6.55 IPS |
|
|
Pose Estimation (F16)
|
100% |
5413
6.55 IPS |
|
|
Pose Estimation (I8)
|
100% |
6819
8.26 IPS |
|
|
Object Detection (F32)
|
100% |
661
49.3 IPS |
|
|
Object Detection (F16)
|
100% |
664
49.6 IPS |
|
|
Object Detection (I8)
|
60% |
483
36.0 IPS |
|
|
Face Detection (F32)
|
100% |
1595
19.0 IPS |
|
|
Face Detection (F16)
|
100% |
1586
18.9 IPS |
|
|
Face Detection (I8)
|
87% |
1852
22.0 IPS |
|
|
Depth Estimation (F32)
|
100% |
3967
30.8 IPS |
|
|
Depth Estimation (F16)
|
100% |
3997
31.0 IPS |
|
|
Depth Estimation (I8)
|
74% |
5301
41.1 IPS |
|
|
Style Transfer (F32)
|
100% |
10266
13.5 IPS |
|
|
Style Transfer (F16)
|
100% |
10180
13.4 IPS |
|
|
Style Transfer (I8)
|
85% |
11511
15.1 IPS |
|
|
Image Super-Resolution (F32)
|
100% |
1236
44.1 IPS |
|
|
Image Super-Resolution (F16)
|
100% |
1239
44.3 IPS |
|
|
Image Super-Resolution (I8)
|
97% |
1163
41.5 IPS |
|
|
Text Classification (F32)
|
100% |
465
668.7 IPS |
|
|
Text Classification (F16)
|
100% |
480
689.7 IPS |
|
|
Text Classification (I8)
|
94% |
167
239.5 IPS |
|
|
Machine Translation (F32)
|
100% |
669
12.3 IPS |
|
|
Machine Translation (F16)
|
100% |
660
12.2 IPS |
|
|
Machine Translation (I8)
|
67% |
933
17.2 IPS |
