Upload Date | May 08 2024 06:26 AM |
Views | 4 |
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 | Balanced |
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 | 4.35 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% |
12005
2.25 KIPS |
|
Image Classification (F16)
|
100% |
13057
2.44 KIPS |
|
Image Classification (I8)
|
100% |
10135
1.90 KIPS |
|
Image Segmentation (F32)
|
100% |
21437
358.0 IPS |
|
Image Segmentation (F16)
|
100% |
20194
337.3 IPS |
|
Image Segmentation (I8)
|
98% |
19266
321.8 IPS |
|
Pose Estimation (F32)
|
100% |
238049
288.3 IPS |
|
Pose Estimation (F16)
|
100% |
237481
287.6 IPS |
|
Pose Estimation (I8)
|
100% |
209003
253.1 IPS |
|
Object Detection (F32)
|
100% |
8061
601.8 IPS |
|
Object Detection (F16)
|
100% |
8204
612.5 IPS |
|
Object Detection (I8)
|
56% |
7408
553.0 IPS |
|
Face Detection (F32)
|
100% |
40575
482.4 IPS |
|
Face Detection (F16)
|
100% |
41027
487.8 IPS |
|
Face Detection (I8)
|
89% |
36805
437.6 IPS |
|
Depth Estimation (F32)
|
100% |
74070
574.4 IPS |
|
Depth Estimation (F16)
|
100% |
67424
522.9 IPS |
|
Depth Estimation (I8)
|
95% |
54380
421.7 IPS |
|
Style Transfer (F32)
|
100% |
343756
452.2 IPS |
|
Style Transfer (F16)
|
100% |
346214
455.4 IPS |
|
Style Transfer (I8)
|
98% |
302405
397.8 IPS |
|
Image Super-Resolution (F32)
|
100% |
49932
1.78 KIPS |
|
Image Super-Resolution (F16)
|
100% |
50991
1.82 KIPS |
|
Image Super-Resolution (I8)
|
99% |
37918
1.35 KIPS |
|
Text Classification (F32)
|
100% |
3336
4.79 KIPS |
|
Text Classification (F16)
|
100% |
3384
4.86 KIPS |
|
Text Classification (I8)
|
98% |
2028
2.91 KIPS |
|
Machine Translation (F32)
|
100% |
5740
105.6 IPS |
|
Machine Translation (F16)
|
100% |
5666
104.3 IPS |
|
Machine Translation (I8)
|
70% |
2996
55.1 IPS |