Upload Date | August 18 2024 03:11 PM |
Views | 2 |
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% |
11032
2.06 KIPS |
|
Image Classification (F16)
|
100% |
11891
2.23 KIPS |
|
Image Classification (I8)
|
100% |
10252
1.92 KIPS |
|
Image Segmentation (F32)
|
100% |
20746
346.5 IPS |
|
Image Segmentation (F16)
|
100% |
20346
339.8 IPS |
|
Image Segmentation (I8)
|
98% |
18776
313.6 IPS |
|
Pose Estimation (F32)
|
100% |
233730
283.0 IPS |
|
Pose Estimation (F16)
|
100% |
232147
281.1 IPS |
|
Pose Estimation (I8)
|
100% |
209104
253.2 IPS |
|
Object Detection (F32)
|
100% |
7646
570.8 IPS |
|
Object Detection (F16)
|
100% |
7423
554.2 IPS |
|
Object Detection (I8)
|
56% |
7223
539.2 IPS |
|
Face Detection (F32)
|
100% |
41158
489.4 IPS |
|
Face Detection (F16)
|
100% |
42628
506.9 IPS |
|
Face Detection (I8)
|
89% |
36483
433.8 IPS |
|
Depth Estimation (F32)
|
100% |
67455
523.1 IPS |
|
Depth Estimation (F16)
|
100% |
65572
508.5 IPS |
|
Depth Estimation (I8)
|
95% |
54158
420.0 IPS |
|
Style Transfer (F32)
|
100% |
337429
443.9 IPS |
|
Style Transfer (F16)
|
100% |
335829
441.8 IPS |
|
Style Transfer (I8)
|
98% |
302313
397.7 IPS |
|
Image Super-Resolution (F32)
|
100% |
51130
1.83 KIPS |
|
Image Super-Resolution (F16)
|
100% |
48679
1.74 KIPS |
|
Image Super-Resolution (I8)
|
99% |
38690
1.38 KIPS |
|
Text Classification (F32)
|
100% |
2899
4.17 KIPS |
|
Text Classification (F16)
|
100% |
2899
4.17 KIPS |
|
Text Classification (I8)
|
98% |
1842
2.65 KIPS |
|
Machine Translation (F32)
|
100% |
5533
101.8 IPS |
|
Machine Translation (F16)
|
100% |
5546
102.1 IPS |
|
Machine Translation (I8)
|
70% |
2985
54.9 IPS |