Upload Date | May 08 2024 10:55 PM |
Views | 2 |
System Information | |
---|---|
Operating System | Microsoft Windows 11 Pro (64-bit) |
Model | ASRock X670E Taichi |
Motherboard | ASRock X670E Taichi |
Power Plan | High performance |
CPU Information | |
---|---|
Name | AMD Ryzen 9 7900 |
Topology | 1 Processor, 12 Cores, 24 Threads |
Identifier | AuthenticAMD Family 25 Model 97 Stepping 2 |
Base Frequency | 3.70 GHz |
Cluster 1 | 12 Cores |
L1 Instruction Cache | 32.0 KB x 12 |
L1 Data Cache | 32.0 KB x 12 |
L2 Cache | 1.00 MB x 12 |
L3 Cache | 32.0 MB x 2 |
Memory Information | |
---|---|
Size | 64.00 GB |
Inference Information | |
---|---|
Framework | ONNX |
Backend | DirectML |
Device | NVIDIA GeForce RTX 4090 |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
12312
2.30 KIPS |
|
Image Classification (F16)
|
100% |
12382
2.32 KIPS |
|
Image Classification (I8)
|
100% |
10742
2.01 KIPS |
|
Image Segmentation (F32)
|
100% |
22025
367.8 IPS |
|
Image Segmentation (F16)
|
100% |
20958
350.0 IPS |
|
Image Segmentation (I8)
|
98% |
20140
336.4 IPS |
|
Pose Estimation (F32)
|
100% |
286058
346.4 IPS |
|
Pose Estimation (F16)
|
100% |
286296
346.7 IPS |
|
Pose Estimation (I8)
|
100% |
248658
301.1 IPS |
|
Object Detection (F32)
|
100% |
8602
642.2 IPS |
|
Object Detection (F16)
|
100% |
8683
648.2 IPS |
|
Object Detection (I8)
|
54% |
8031
599.5 IPS |
|
Face Detection (F32)
|
100% |
48244
573.6 IPS |
|
Face Detection (F16)
|
100% |
49098
583.8 IPS |
|
Face Detection (I8)
|
88% |
40019
475.8 IPS |
|
Depth Estimation (F32)
|
100% |
81199
629.7 IPS |
|
Depth Estimation (F16)
|
100% |
81427
631.5 IPS |
|
Depth Estimation (I8)
|
95% |
63606
493.3 IPS |
|
Style Transfer (F32)
|
100% |
500384
658.2 IPS |
|
Style Transfer (F16)
|
100% |
512322
673.9 IPS |
|
Style Transfer (I8)
|
98% |
430758
566.6 IPS |
|
Image Super-Resolution (F32)
|
100% |
55785
1.99 KIPS |
|
Image Super-Resolution (F16)
|
100% |
55772
1.99 KIPS |
|
Image Super-Resolution (I8)
|
99% |
40775
1.46 KIPS |
|
Text Classification (F32)
|
100% |
2991
4.30 KIPS |
|
Text Classification (F16)
|
100% |
2960
4.25 KIPS |
|
Text Classification (I8)
|
98% |
1835
2.64 KIPS |
|
Machine Translation (F32)
|
100% |
4798
88.3 IPS |
|
Machine Translation (F16)
|
100% |
4979
91.6 IPS |
|
Machine Translation (I8)
|
70% |
2750
50.6 IPS |