B450 Steel Legend
Geekbench ML Score
14175
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2
Result Information
| User | artyomtw |
| Upload Date | August 16 2024 09:20 PM |
| Views | 3 |
System Information
| System Information | |
|---|---|
| Operating System | Windows 11 Pro (64-bit) |
| Model | B450 Steel Legend |
| Motherboard | ASRock B450 Steel Legend |
| CPU Information | |
|---|---|
| Name | AMD Ryzen 5 3600 |
| Topology | 1 Processor, 6 Cores, 12 Threads |
| Identifier | AuthenticAMD Family 23 Model 113 Stepping 0 |
| Base Frequency | 3.80 GHz |
| Cluster 1 | 6 Cores |
| L1 Instruction Cache | 32.0 KB x 6 |
| L1 Data Cache | 32.0 KB x 6 |
| L2 Cache | 512 KB x 6 |
| L3 Cache | 16.0 MB x 2 |
| Memory Information | |
|---|---|
| Size | 32.00 GB |
| Inference Information | |
|---|---|
| Framework | ONNX |
| Backend | DirectML |
| Device | NVIDIA GeForce RTX 4060 Ti |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
6988
1.31 KIPS |
|
|
Image Classification (F16)
|
100% |
7382
1.38 KIPS |
|
|
Image Classification (I8)
|
100% |
6709
1.26 KIPS |
|
|
Image Segmentation (F32)
|
100% |
9334
155.9 IPS |
|
|
Image Segmentation (F16)
|
100% |
9350
156.2 IPS |
|
|
Image Segmentation (I8)
|
98% |
8754
146.2 IPS |
|
|
Pose Estimation (F32)
|
100% |
101186
122.5 IPS |
|
|
Pose Estimation (F16)
|
100% |
101332
122.7 IPS |
|
|
Pose Estimation (I8)
|
100% |
88984
107.8 IPS |
|
|
Object Detection (F32)
|
100% |
3816
284.9 IPS |
|
|
Object Detection (F16)
|
100% |
3778
282.1 IPS |
|
|
Object Detection (I8)
|
63% |
3590
268.0 IPS |
|
|
Face Detection (F32)
|
100% |
18340
218.1 IPS |
|
|
Face Detection (F16)
|
100% |
17890
212.7 IPS |
|
|
Face Detection (I8)
|
89% |
15543
184.8 IPS |
|
|
Depth Estimation (F32)
|
100% |
39342
305.1 IPS |
|
|
Depth Estimation (F16)
|
100% |
40369
313.1 IPS |
|
|
Depth Estimation (I8)
|
94% |
34515
267.7 IPS |
|
|
Style Transfer (F32)
|
100% |
169772
223.3 IPS |
|
|
Style Transfer (F16)
|
100% |
168553
221.7 IPS |
|
|
Style Transfer (I8)
|
98% |
152894
201.1 IPS |
|
|
Image Super-Resolution (F32)
|
100% |
27972
999.0 IPS |
|
|
Image Super-Resolution (F16)
|
100% |
27694
989.0 IPS |
|
|
Image Super-Resolution (I8)
|
99% |
21528
768.8 IPS |
|
|
Text Classification (F32)
|
100% |
2477
3.56 KIPS |
|
|
Text Classification (F16)
|
100% |
2500
3.59 KIPS |
|
|
Text Classification (I8)
|
98% |
1624
2.33 KIPS |
|
|
Machine Translation (F32)
|
100% |
2785
51.3 IPS |
|
|
Machine Translation (F16)
|
100% |
2806
51.6 IPS |
|
|
Machine Translation (I8)
|
70% |
1758
32.3 IPS |
