Gigabyte Technology Co., Ltd. TRX50 AERO D
Geekbench ML Score
26142
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2
Result Information
| Upload Date | October 16 2024 03:44 PM |
| Views | 2 |
System Information
| System Information | |
|---|---|
| Operating System | Microsoft Windows Server 2025 Datacenter (64-bit) |
| Model | Gigabyte Technology Co., Ltd. TRX50 AERO D |
| Motherboard | Gigabyte Technology Co., Ltd. TRX50 AERO D |
| Power Plan | High 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% |
11523
2.16 KIPS |
|
|
Image Classification (F16)
|
100% |
12612
2.36 KIPS |
|
|
Image Classification (I8)
|
100% |
9849
1.84 KIPS |
|
|
Image Segmentation (F32)
|
100% |
20795
347.3 IPS |
|
|
Image Segmentation (F16)
|
100% |
19757
330.0 IPS |
|
|
Image Segmentation (I8)
|
98% |
18598
310.6 IPS |
|
|
Pose Estimation (F32)
|
100% |
235698
285.4 IPS |
|
|
Pose Estimation (F16)
|
100% |
234680
284.2 IPS |
|
|
Pose Estimation (I8)
|
100% |
207314
251.0 IPS |
|
|
Object Detection (F32)
|
100% |
7866
587.2 IPS |
|
|
Object Detection (F16)
|
100% |
7942
592.9 IPS |
|
|
Object Detection (I8)
|
56% |
7349
548.7 IPS |
|
|
Face Detection (F32)
|
100% |
40899
486.3 IPS |
|
|
Face Detection (F16)
|
100% |
43794
520.7 IPS |
|
|
Face Detection (I8)
|
89% |
37237
442.8 IPS |
|
|
Depth Estimation (F32)
|
100% |
75330
584.2 IPS |
|
|
Depth Estimation (F16)
|
100% |
68609
532.1 IPS |
|
|
Depth Estimation (I8)
|
94% |
55847
433.1 IPS |
|
|
Style Transfer (F32)
|
100% |
329655
433.6 IPS |
|
|
Style Transfer (F16)
|
100% |
329013
432.8 IPS |
|
|
Style Transfer (I8)
|
98% |
284115
373.7 IPS |
|
|
Image Super-Resolution (F32)
|
100% |
43081
1.54 KIPS |
|
|
Image Super-Resolution (F16)
|
100% |
46033
1.64 KIPS |
|
|
Image Super-Resolution (I8)
|
99% |
34042
1.22 KIPS |
|
|
Text Classification (F32)
|
100% |
2911
4.18 KIPS |
|
|
Text Classification (F16)
|
100% |
2911
4.18 KIPS |
|
|
Text Classification (I8)
|
98% |
1862
2.68 KIPS |
|
|
Machine Translation (F32)
|
100% |
5491
101.1 IPS |
|
|
Machine Translation (F16)
|
100% |
5489
101.0 IPS |
|
|
Machine Translation (I8)
|
70% |
3023
55.6 IPS |
