Gigabyte Technology Co., Ltd. TRX50 AERO D
Geekbench ML Score
26196
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2
Result Information
| Upload Date | August 15 2024 02:47 PM |
| Views | 3 |
System Information
| System Information | |
|---|---|
| Operating System | Microsoft Windows 11 Pro for Workstations (64-bit) |
| Model | Gigabyte Technology Co., Ltd. TRX50 AERO D |
| Motherboard | Gigabyte Technology Co., Ltd. TRX50 AERO D |
| Power Plan | Ultimate Performance |
| CPU Information | |
|---|---|
| Name | AMD Ryzen Threadripper 7960X 24-Cores |
| Topology | 1 Processor, 24 Cores, 48 Threads |
| Identifier | AuthenticAMD Family 25 Model 24 Stepping 1 |
| Base Frequency | 4.20 GHz |
| Cluster 1 | 24 Cores |
| L1 Instruction Cache | 32.0 KB x 24 |
| L1 Data Cache | 32.0 KB x 24 |
| L2 Cache | 1.00 MB x 24 |
| L3 Cache | 32.0 MB x 4 |
| Memory Information | |
|---|---|
| Size | 64.00 GB |
| Inference Information | |
|---|---|
| Framework | ONNX |
| Backend | DirectML |
| Device | NVIDIA GeForce RTX 4080 |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
11312
2.12 KIPS |
|
|
Image Classification (F16)
|
100% |
12279
2.30 KIPS |
|
|
Image Classification (I8)
|
100% |
10513
1.97 KIPS |
|
|
Image Segmentation (F32)
|
100% |
19815
330.9 IPS |
|
|
Image Segmentation (F16)
|
100% |
19654
328.2 IPS |
|
|
Image Segmentation (I8)
|
98% |
17687
295.4 IPS |
|
|
Pose Estimation (F32)
|
100% |
232173
281.2 IPS |
|
|
Pose Estimation (F16)
|
100% |
230449
279.1 IPS |
|
|
Pose Estimation (I8)
|
100% |
207049
250.7 IPS |
|
|
Object Detection (F32)
|
100% |
7697
574.6 IPS |
|
|
Object Detection (F16)
|
100% |
7701
574.9 IPS |
|
|
Object Detection (I8)
|
56% |
7262
542.1 IPS |
|
|
Face Detection (F32)
|
100% |
40818
485.3 IPS |
|
|
Face Detection (F16)
|
100% |
43328
515.2 IPS |
|
|
Face Detection (I8)
|
89% |
34355
408.5 IPS |
|
|
Depth Estimation (F32)
|
100% |
67462
523.2 IPS |
|
|
Depth Estimation (F16)
|
100% |
67169
520.9 IPS |
|
|
Depth Estimation (I8)
|
95% |
53289
413.3 IPS |
|
|
Style Transfer (F32)
|
100% |
340157
447.4 IPS |
|
|
Style Transfer (F16)
|
100% |
335607
441.5 IPS |
|
|
Style Transfer (I8)
|
98% |
297688
391.6 IPS |
|
|
Image Super-Resolution (F32)
|
100% |
47470
1.70 KIPS |
|
|
Image Super-Resolution (F16)
|
100% |
50258
1.79 KIPS |
|
|
Image Super-Resolution (I8)
|
99% |
38497
1.37 KIPS |
|
|
Text Classification (F32)
|
100% |
3142
4.52 KIPS |
|
|
Text Classification (F16)
|
100% |
3057
4.39 KIPS |
|
|
Text Classification (I8)
|
98% |
1902
2.73 KIPS |
|
|
Machine Translation (F32)
|
100% |
5500
101.2 IPS |
|
|
Machine Translation (F16)
|
100% |
5550
102.1 IPS |
|
|
Machine Translation (I8)
|
70% |
2878
53.0 IPS |
