Upload Date | August 16 2024 02:58 PM |
Views | 4 |
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 Ti |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
6787
1.27 KIPS |
|
Image Classification (F16)
|
100% |
6620
1.24 KIPS |
|
Image Classification (I8)
|
100% |
4782
894.9 IPS |
|
Image Segmentation (F32)
|
100% |
6609
110.4 IPS |
|
Image Segmentation (F16)
|
100% |
11303
188.8 IPS |
|
Image Segmentation (I8)
|
98% |
7726
129.0 IPS |
|
Pose Estimation (F32)
|
100% |
169595
205.4 IPS |
|
Pose Estimation (F16)
|
100% |
167718
203.1 IPS |
|
Pose Estimation (I8)
|
100% |
125697
152.2 IPS |
|
Object Detection (F32)
|
100% |
2498
186.5 IPS |
|
Object Detection (F16)
|
100% |
2609
194.8 IPS |
|
Object Detection (I8)
|
56% |
2344
175.0 IPS |
|
Face Detection (F32)
|
100% |
22604
268.8 IPS |
|
Face Detection (F16)
|
100% |
23063
274.2 IPS |
|
Face Detection (I8)
|
89% |
15927
189.4 IPS |
|
Depth Estimation (F32)
|
100% |
51616
400.3 IPS |
|
Depth Estimation (F16)
|
100% |
50935
395.0 IPS |
|
Depth Estimation (I8)
|
94% |
31700
245.8 IPS |
|
Style Transfer (F32)
|
100% |
235111
309.3 IPS |
|
Style Transfer (F16)
|
100% |
239150
314.6 IPS |
|
Style Transfer (I8)
|
98% |
173439
228.1 IPS |
|
Image Super-Resolution (F32)
|
100% |
29409
1.05 KIPS |
|
Image Super-Resolution (F16)
|
100% |
28508
1.02 KIPS |
|
Image Super-Resolution (I8)
|
99% |
18570
663.2 IPS |
|
Text Classification (F32)
|
100% |
1576
2.26 KIPS |
|
Text Classification (F16)
|
100% |
1708
2.45 KIPS |
|
Text Classification (I8)
|
98% |
1030
1.48 KIPS |
|
Machine Translation (F32)
|
100% |
3117
57.4 IPS |
|
Machine Translation (F16)
|
100% |
3103
57.1 IPS |
|
Machine Translation (I8)
|
70% |
1430
26.3 IPS |