| User | PB7591 |
| Upload Date | January 28 2025 08:26 PM |
| Views | 5 |
| System Information | |
|---|---|
| Operating System | Microsoft Windows 11 Pro (64-bit) |
| Model | Generic |
| Motherboard | ASRock TRX40 Creator |
| Power Plan | High performance |
| CPU Information | |
|---|---|
| Name | AMD Ryzen Threadripper 3970X |
| Topology | 1 Processor, 32 Cores, 64 Threads |
| Identifier | AuthenticAMD Family 23 Model 49 Stepping 0 |
| Base Frequency | 3.70 GHz |
| Cluster 1 | 32 Cores |
| L1 Instruction Cache | 32.0 KB x 32 |
| L1 Data Cache | 32.0 KB x 32 |
| L2 Cache | 512 KB x 32 |
| L3 Cache | 16.0 MB x 8 |
| Memory Information | |
|---|---|
| Size | 128.00 GB |
| Inference Information | |
|---|---|
| Framework | ONNX |
| Backend | CPU |
| Device | Default |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
979
183.3 IPS |
|
|
Image Classification (F16)
|
100% |
982
183.8 IPS |
|
|
Image Classification (I8)
|
97% |
1676
313.6 IPS |
|
|
Image Segmentation (F32)
|
100% |
1031
17.2 IPS |
|
|
Image Segmentation (F16)
|
100% |
1068
17.8 IPS |
|
|
Image Segmentation (I8)
|
97% |
1892
31.6 IPS |
|
|
Pose Estimation (F32)
|
100% |
13116
15.9 IPS |
|
|
Pose Estimation (F16)
|
100% |
17446
21.1 IPS |
|
|
Pose Estimation (I8)
|
100% |
15025
18.2 IPS |
|
|
Object Detection (F32)
|
100% |
788
58.9 IPS |
|
|
Object Detection (F16)
|
100% |
787
58.7 IPS |
|
|
Object Detection (I8)
|
60% |
695
51.9 IPS |
|
|
Face Detection (F32)
|
100% |
1996
23.7 IPS |
|
|
Face Detection (F16)
|
100% |
2030
24.1 IPS |
|
|
Face Detection (I8)
|
87% |
2732
32.5 IPS |
|
|
Depth Estimation (F32)
|
100% |
6275
48.7 IPS |
|
|
Depth Estimation (F16)
|
100% |
6234
48.3 IPS |
|
|
Depth Estimation (I8)
|
74% |
7774
60.3 IPS |
|
|
Style Transfer (F32)
|
100% |
18835
24.8 IPS |
|
|
Style Transfer (F16)
|
100% |
18659
24.5 IPS |
|
|
Style Transfer (I8)
|
85% |
17627
23.2 IPS |
|
|
Image Super-Resolution (F32)
|
100% |
2198
78.5 IPS |
|
|
Image Super-Resolution (F16)
|
100% |
2173
77.6 IPS |
|
|
Image Super-Resolution (I8)
|
97% |
2085
74.5 IPS |
|
|
Text Classification (F32)
|
100% |
720
1.04 KIPS |
|
|
Text Classification (F16)
|
100% |
697
1.00 KIPS |
|
|
Text Classification (I8)
|
94% |
267
383.7 IPS |
|
|
Machine Translation (F32)
|
100% |
934
17.2 IPS |
|
|
Machine Translation (F16)
|
100% |
968
17.8 IPS |
|
|
Machine Translation (I8)
|
67% |
1500
27.6 IPS |