Upload Date | April 22 2024 08:04 PM |
Views | 5 |
System Information | |
---|---|
Operating System | Microsoft Windows 11 Pro for Workstations (64-bit) |
Model | Gigabyte Technology Co., Ltd. TRX50 AERO D |
Motherboard | Gigabyte Technology Co., Ltd. TRX50 AERO D |
Power Plan | Ultimate Performance |
CPU Information | |
---|---|
Name | AMD Ryzen Threadripper 7960X 24-Cores |
Topology | 1 Processor, 24 Cores, 48 Threads |
Identifier | AuthenticAMD Family 25 Model 24 Stepping 1 |
Base Frequency | 4.20 GHz |
Cluster 1 | 24 Cores |
L1 Instruction Cache | 32.0 KB x 24 |
L1 Data Cache | 32.0 KB x 24 |
L2 Cache | 1.00 MB x 24 |
L3 Cache | 32.0 MB x 4 |
Memory Information | |
---|---|
Size | 64.00 GB |
Inference Information | |
---|---|
Framework | ONNX |
Backend | DirectML |
Device | NVIDIA GeForce RTX 4080 |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
11419
2.14 KIPS |
|
Image Classification (F16)
|
100% |
12595
2.36 KIPS |
|
Image Classification (I8)
|
100% |
10660
1.99 KIPS |
|
Image Segmentation (F32)
|
100% |
20613
344.3 IPS |
|
Image Segmentation (F16)
|
100% |
20197
337.3 IPS |
|
Image Segmentation (I8)
|
98% |
19199
320.7 IPS |
|
Pose Estimation (F32)
|
100% |
237181
287.2 IPS |
|
Pose Estimation (F16)
|
100% |
237583
287.7 IPS |
|
Pose Estimation (I8)
|
100% |
207956
251.8 IPS |
|
Object Detection (F32)
|
100% |
7863
587.1 IPS |
|
Object Detection (F16)
|
100% |
7818
583.7 IPS |
|
Object Detection (I8)
|
56% |
4323
322.7 IPS |
|
Face Detection (F32)
|
100% |
41864
497.8 IPS |
|
Face Detection (F16)
|
100% |
41636
495.1 IPS |
|
Face Detection (I8)
|
89% |
37092
441.0 IPS |
|
Depth Estimation (F32)
|
100% |
75292
583.9 IPS |
|
Depth Estimation (F16)
|
100% |
68056
527.8 IPS |
|
Depth Estimation (I8)
|
95% |
55478
430.2 IPS |
|
Style Transfer (F32)
|
100% |
345161
454.0 IPS |
|
Style Transfer (F16)
|
100% |
338783
445.6 IPS |
|
Style Transfer (I8)
|
98% |
308630
406.0 IPS |
|
Image Super-Resolution (F32)
|
100% |
50852
1.82 KIPS |
|
Image Super-Resolution (F16)
|
100% |
50246
1.79 KIPS |
|
Image Super-Resolution (I8)
|
99% |
39372
1.41 KIPS |
|
Text Classification (F32)
|
100% |
3279
4.71 KIPS |
|
Text Classification (F16)
|
100% |
3300
4.74 KIPS |
|
Text Classification (I8)
|
98% |
1929
2.77 KIPS |
|
Machine Translation (F32)
|
100% |
5598
103.0 IPS |
|
Machine Translation (F16)
|
100% |
5609
103.2 IPS |
|
Machine Translation (I8)
|
70% |
3082
56.7 IPS |