Upload Date | August 19 2024 12:05 PM |
Views | 1 |
System Information | |
---|---|
Operating System | Microsoft Windows 11 Pro (64-bit) |
Model | Generic |
Motherboard | ASRock TRX40 Taichi |
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 | 256.00 GB |
Inference Information | |
---|---|
Framework | ONNX |
Backend | DirectML |
Device | NVIDIA GeForce RTX 2080 SUPER |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
5832
1.09 KIPS |
|
Image Classification (F16)
|
100% |
5798
1.09 KIPS |
|
Image Classification (I8)
|
100% |
4287
802.2 IPS |
|
Image Segmentation (F32)
|
100% |
8285
138.4 IPS |
|
Image Segmentation (F16)
|
100% |
8619
143.9 IPS |
|
Image Segmentation (I8)
|
98% |
6943
116.0 IPS |
|
Pose Estimation (F32)
|
100% |
72359
87.6 IPS |
|
Pose Estimation (F16)
|
100% |
72701
88.0 IPS |
|
Pose Estimation (I8)
|
100% |
59448
72.0 IPS |
|
Object Detection (F32)
|
100% |
3580
267.3 IPS |
|
Object Detection (F16)
|
100% |
3510
262.0 IPS |
|
Object Detection (I8)
|
61% |
3080
230.0 IPS |
|
Face Detection (F32)
|
100% |
15790
187.7 IPS |
|
Face Detection (F16)
|
100% |
16124
191.7 IPS |
|
Face Detection (I8)
|
89% |
12406
147.5 IPS |
|
Depth Estimation (F32)
|
100% |
33248
257.8 IPS |
|
Depth Estimation (F16)
|
100% |
36486
282.9 IPS |
|
Depth Estimation (I8)
|
95% |
26178
203.0 IPS |
|
Style Transfer (F32)
|
100% |
118818
156.3 IPS |
|
Style Transfer (F16)
|
100% |
119601
157.3 IPS |
|
Style Transfer (I8)
|
98% |
99213
130.5 IPS |
|
Image Super-Resolution (F32)
|
100% |
21236
758.4 IPS |
|
Image Super-Resolution (F16)
|
100% |
20412
729.0 IPS |
|
Image Super-Resolution (I8)
|
99% |
13162
470.0 IPS |
|
Text Classification (F32)
|
100% |
1488
2.14 KIPS |
|
Text Classification (F16)
|
100% |
1492
2.14 KIPS |
|
Text Classification (I8)
|
98% |
1000
1.44 KIPS |
|
Machine Translation (F32)
|
100% |
2821
51.9 IPS |
|
Machine Translation (F16)
|
100% |
2788
51.3 IPS |
|
Machine Translation (I8)
|
70% |
1364
25.1 IPS |