B550M Pro4
Geekbench ML Score
8770
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2
Result Information
| Upload Date | August 28 2024 07:36 PM |
| Views | 2 |
System Information
| System Information | |
|---|---|
| Operating System | Microsoft Windows 11 Pro (64-bit) |
| Model | B550M Pro4 |
| Motherboard | ASRock B550M Pro4 |
| CPU Information | |
|---|---|
| Name | AMD Ryzen 7 5700X |
| Topology | 1 Processor, 8 Cores, 16 Threads |
| Identifier | AuthenticAMD Family 25 Model 33 Stepping 2 |
| Base Frequency | 3.40 GHz |
| Cluster 1 | 8 Cores |
| L1 Instruction Cache | 32.0 KB x 8 |
| L1 Data Cache | 32.0 KB x 8 |
| L2 Cache | 512 KB x 8 |
| L3 Cache | 32.0 MB x 1 |
| Memory Information | |
|---|---|
| Size | 32.00 GB |
| Inference Information | |
|---|---|
| Framework | ONNX |
| Backend | DirectML |
| Device | NVIDIA GeForce RTX 3080 |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
3553
664.9 IPS |
|
|
Image Classification (F16)
|
100% |
3615
676.5 IPS |
|
|
Image Classification (I8)
|
100% |
2866
536.3 IPS |
|
|
Image Segmentation (F32)
|
100% |
7752
129.5 IPS |
|
|
Image Segmentation (F16)
|
100% |
7690
128.4 IPS |
|
|
Image Segmentation (I8)
|
98% |
5589
93.3 IPS |
|
|
Pose Estimation (F32)
|
100% |
63450
76.8 IPS |
|
|
Pose Estimation (F16)
|
100% |
62585
75.8 IPS |
|
|
Pose Estimation (I8)
|
100% |
49955
60.5 IPS |
|
|
Object Detection (F32)
|
100% |
3709
276.9 IPS |
|
|
Object Detection (F16)
|
100% |
3660
273.2 IPS |
|
|
Object Detection (I8)
|
56% |
3285
245.2 IPS |
|
|
Face Detection (F32)
|
100% |
14101
167.7 IPS |
|
|
Face Detection (F16)
|
100% |
13507
160.6 IPS |
|
|
Face Detection (I8)
|
89% |
8974
106.7 IPS |
|
|
Depth Estimation (F32)
|
100% |
24622
190.9 IPS |
|
|
Depth Estimation (F16)
|
100% |
23732
184.0 IPS |
|
|
Depth Estimation (I8)
|
94% |
15802
122.5 IPS |
|
|
Style Transfer (F32)
|
100% |
138911
182.7 IPS |
|
|
Style Transfer (F16)
|
100% |
136938
180.1 IPS |
|
|
Style Transfer (I8)
|
98% |
91987
121.0 IPS |
|
|
Image Super-Resolution (F32)
|
100% |
16885
603.0 IPS |
|
|
Image Super-Resolution (F16)
|
100% |
16531
590.4 IPS |
|
|
Image Super-Resolution (I8)
|
99% |
9927
354.5 IPS |
|
|
Text Classification (F32)
|
100% |
1088
1.56 KIPS |
|
|
Text Classification (F16)
|
100% |
1094
1.57 KIPS |
|
|
Text Classification (I8)
|
98% |
499
717.8 IPS |
|
|
Machine Translation (F32)
|
100% |
2226
41.0 IPS |
|
|
Machine Translation (F16)
|
100% |
2203
40.5 IPS |
|
|
Machine Translation (I8)
|
70% |
809
14.9 IPS |
