Upload Date | August 16 2024 03:01 PM |
Views | 2 |
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 | DirectML |
Device | NVIDIA GeForce RTX 3090 |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
6185
1.16 KIPS |
|
Image Classification (F16)
|
100% |
5899
1.10 KIPS |
|
Image Classification (I8)
|
100% |
4606
861.9 IPS |
|
Image Segmentation (F32)
|
100% |
10608
177.2 IPS |
|
Image Segmentation (F16)
|
100% |
10913
182.3 IPS |
|
Image Segmentation (I8)
|
98% |
7593
126.8 IPS |
|
Pose Estimation (F32)
|
100% |
148765
180.1 IPS |
|
Pose Estimation (F16)
|
100% |
156887
190.0 IPS |
|
Pose Estimation (I8)
|
100% |
119403
144.6 IPS |
|
Object Detection (F32)
|
100% |
2475
184.8 IPS |
|
Object Detection (F16)
|
100% |
2313
172.7 IPS |
|
Object Detection (I8)
|
56% |
2174
162.3 IPS |
|
Face Detection (F32)
|
100% |
21267
252.9 IPS |
|
Face Detection (F16)
|
100% |
20074
238.7 IPS |
|
Face Detection (I8)
|
89% |
14892
177.1 IPS |
|
Depth Estimation (F32)
|
100% |
47211
366.1 IPS |
|
Depth Estimation (F16)
|
100% |
44305
343.6 IPS |
|
Depth Estimation (I8)
|
94% |
29131
225.9 IPS |
|
Style Transfer (F32)
|
100% |
232655
306.0 IPS |
|
Style Transfer (F16)
|
100% |
232817
306.3 IPS |
|
Style Transfer (I8)
|
98% |
163167
214.6 IPS |
|
Image Super-Resolution (F32)
|
100% |
29371
1.05 KIPS |
|
Image Super-Resolution (F16)
|
100% |
28876
1.03 KIPS |
|
Image Super-Resolution (I8)
|
99% |
17935
640.5 IPS |
|
Text Classification (F32)
|
100% |
1639
2.36 KIPS |
|
Text Classification (F16)
|
100% |
1414
2.03 KIPS |
|
Text Classification (I8)
|
98% |
855
1.23 KIPS |
|
Machine Translation (F32)
|
100% |
2836
52.2 IPS |
|
Machine Translation (F16)
|
100% |
2969
54.6 IPS |
|
Machine Translation (I8)
|
70% |
1373
25.3 IPS |