Generic
Geekbench ML Score
13765
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2
Result Information
| User | PB7591 |
| Upload Date | January 28 2025 08:33 PM |
| Views | 3 |
System Information
| System Information | |
|---|---|
| Operating System | Microsoft Windows 11 Pro (64-bit) |
| Model | Generic |
| Motherboard | ASRock TRX40 Creator |
| Power Plan | High performance |
| CPU Information | |
|---|---|
| Name | AMD Ryzen Threadripper 3970X |
| Topology | 1 Processor, 32 Cores, 64 Threads |
| Identifier | AuthenticAMD Family 23 Model 49 Stepping 0 |
| Base Frequency | 3.70 GHz |
| Cluster 1 | 32 Cores |
| L1 Instruction Cache | 32.0 KB x 32 |
| L1 Data Cache | 32.0 KB x 32 |
| L2 Cache | 512 KB x 32 |
| L3 Cache | 16.0 MB x 8 |
| Memory Information | |
|---|---|
| Size | 128.00 GB |
| Inference Information | |
|---|---|
| Framework | ONNX |
| Backend | DirectML |
| Device | NVIDIA GeForce RTX 3090 |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
7330
1.37 KIPS |
|
|
Image Classification (F16)
|
100% |
7585
1.42 KIPS |
|
|
Image Classification (I8)
|
100% |
5153
964.3 IPS |
|
|
Image Segmentation (F32)
|
100% |
11063
184.8 IPS |
|
|
Image Segmentation (F16)
|
100% |
10432
174.2 IPS |
|
|
Image Segmentation (I8)
|
98% |
7846
131.0 IPS |
|
|
Pose Estimation (F32)
|
100% |
157579
190.8 IPS |
|
|
Pose Estimation (F16)
|
100% |
158623
192.1 IPS |
|
|
Pose Estimation (I8)
|
100% |
116260
140.8 IPS |
|
|
Object Detection (F32)
|
100% |
1707
127.5 IPS |
|
|
Object Detection (F16)
|
100% |
1687
126.0 IPS |
|
|
Object Detection (I8)
|
56% |
1585
118.4 IPS |
|
|
Face Detection (F32)
|
100% |
25034
297.7 IPS |
|
|
Face Detection (F16)
|
100% |
25190
299.5 IPS |
|
|
Face Detection (I8)
|
89% |
17144
203.8 IPS |
|
|
Depth Estimation (F32)
|
100% |
53072
411.6 IPS |
|
|
Depth Estimation (F16)
|
100% |
48983
379.9 IPS |
|
|
Depth Estimation (I8)
|
94% |
30534
236.8 IPS |
|
|
Style Transfer (F32)
|
100% |
227628
299.4 IPS |
|
|
Style Transfer (F16)
|
100% |
228777
300.9 IPS |
|
|
Style Transfer (I8)
|
98% |
161364
212.3 IPS |
|
|
Image Super-Resolution (F32)
|
100% |
28979
1.03 KIPS |
|
|
Image Super-Resolution (F16)
|
100% |
29548
1.06 KIPS |
|
|
Image Super-Resolution (I8)
|
99% |
17670
631.0 IPS |
|
|
Text Classification (F32)
|
100% |
1878
2.70 KIPS |
|
|
Text Classification (F16)
|
100% |
1871
2.69 KIPS |
|
|
Text Classification (I8)
|
98% |
1039
1.49 KIPS |
|
|
Machine Translation (F32)
|
100% |
2781
51.2 IPS |
|
|
Machine Translation (F16)
|
100% |
2763
50.8 IPS |
|
|
Machine Translation (I8)
|
70% |
1385
25.5 IPS |
