System manufacturer System Product Name
Geekbench ML Score
25590
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2
Result Information
| Upload Date | August 17 2024 01:48 PM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Microsoft Windows 11 Pro (64-bit) |
| Model | System manufacturer System Product Name |
| Motherboard | ASUSTeK COMPUTER INC. ROG STRIX X570-I GAMING |
| Power Plan | High performance |
| CPU Information | |
|---|---|
| Name | AMD Ryzen 9 5900X |
| Topology | 1 Processor, 12 Cores, 24 Threads |
| Identifier | AuthenticAMD Family 25 Model 33 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 | 512 KB 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 |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
11169
2.09 KIPS |
|
|
Image Classification (F16)
|
100% |
11727
2.19 KIPS |
|
|
Image Classification (I8)
|
100% |
10065
1.88 KIPS |
|
|
Image Segmentation (F32)
|
100% |
15015
250.8 IPS |
|
|
Image Segmentation (F16)
|
100% |
15376
256.8 IPS |
|
|
Image Segmentation (I8)
|
98% |
14341
239.5 IPS |
|
|
Pose Estimation (F32)
|
100% |
272009
329.4 IPS |
|
|
Pose Estimation (F16)
|
100% |
271911
329.3 IPS |
|
|
Pose Estimation (I8)
|
100% |
238544
288.9 IPS |
|
|
Object Detection (F32)
|
100% |
6781
506.3 IPS |
|
|
Object Detection (F16)
|
100% |
6709
500.9 IPS |
|
|
Object Detection (I8)
|
54% |
6253
466.8 IPS |
|
|
Face Detection (F32)
|
100% |
37153
441.8 IPS |
|
|
Face Detection (F16)
|
100% |
38007
451.9 IPS |
|
|
Face Detection (I8)
|
88% |
32364
384.8 IPS |
|
|
Depth Estimation (F32)
|
100% |
85698
664.6 IPS |
|
|
Depth Estimation (F16)
|
100% |
80745
626.2 IPS |
|
|
Depth Estimation (I8)
|
94% |
61341
475.7 IPS |
|
|
Style Transfer (F32)
|
100% |
468248
615.9 IPS |
|
|
Style Transfer (F16)
|
100% |
467270
614.7 IPS |
|
|
Style Transfer (I8)
|
98% |
400965
527.4 IPS |
|
|
Image Super-Resolution (F32)
|
100% |
51265
1.83 KIPS |
|
|
Image Super-Resolution (F16)
|
100% |
48163
1.72 KIPS |
|
|
Image Super-Resolution (I8)
|
99% |
38262
1.37 KIPS |
|
|
Text Classification (F32)
|
100% |
2793
4.01 KIPS |
|
|
Text Classification (F16)
|
100% |
2767
3.98 KIPS |
|
|
Text Classification (I8)
|
98% |
1714
2.46 KIPS |
|
|
Machine Translation (F32)
|
100% |
3988
73.4 IPS |
|
|
Machine Translation (F16)
|
100% |
3969
73.0 IPS |
|
|
Machine Translation (I8)
|
70% |
2366
43.5 IPS |
