Gigabyte Technology Co., Ltd. TRX50 AERO D
Geekbench ML Score
26384
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2
Result Information
| Upload Date | August 17 2024 02:49 PM |
| Views | 2 |
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% |
11282
2.11 KIPS |
|
|
Image Classification (F16)
|
100% |
12346
2.31 KIPS |
|
|
Image Classification (I8)
|
100% |
9696
1.81 KIPS |
|
|
Image Segmentation (F32)
|
100% |
20111
335.9 IPS |
|
|
Image Segmentation (F16)
|
100% |
20015
334.3 IPS |
|
|
Image Segmentation (I8)
|
98% |
18718
312.6 IPS |
|
|
Pose Estimation (F32)
|
100% |
235423
285.1 IPS |
|
|
Pose Estimation (F16)
|
100% |
236434
286.3 IPS |
|
|
Pose Estimation (I8)
|
100% |
207314
251.0 IPS |
|
|
Object Detection (F32)
|
100% |
7653
571.4 IPS |
|
|
Object Detection (F16)
|
100% |
7719
576.3 IPS |
|
|
Object Detection (I8)
|
56% |
7190
536.8 IPS |
|
|
Face Detection (F32)
|
100% |
40894
486.2 IPS |
|
|
Face Detection (F16)
|
100% |
43229
514.0 IPS |
|
|
Face Detection (I8)
|
89% |
36299
431.6 IPS |
|
|
Depth Estimation (F32)
|
100% |
74013
574.0 IPS |
|
|
Depth Estimation (F16)
|
100% |
65154
505.3 IPS |
|
|
Depth Estimation (I8)
|
95% |
53778
417.0 IPS |
|
|
Style Transfer (F32)
|
100% |
341389
449.1 IPS |
|
|
Style Transfer (F16)
|
100% |
336946
443.2 IPS |
|
|
Style Transfer (I8)
|
98% |
298608
392.8 IPS |
|
|
Image Super-Resolution (F32)
|
100% |
48818
1.74 KIPS |
|
|
Image Super-Resolution (F16)
|
100% |
48545
1.73 KIPS |
|
|
Image Super-Resolution (I8)
|
99% |
38630
1.38 KIPS |
|
|
Text Classification (F32)
|
100% |
3114
4.48 KIPS |
|
|
Text Classification (F16)
|
100% |
3108
4.47 KIPS |
|
|
Text Classification (I8)
|
98% |
1874
2.69 KIPS |
|
|
Machine Translation (F32)
|
100% |
5581
102.7 IPS |
|
|
Machine Translation (F16)
|
100% |
5628
103.6 IPS |
|
|
Machine Translation (I8)
|
70% |
2939
54.1 IPS |
