Gigabyte Technology Co., Ltd. TRX50 AERO D
Geekbench ML Score
26319
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2
Result Information
| Upload Date | October 05 2024 12:15 PM |
| Views | 2 |
System Information
| System Information | |
|---|---|
| Operating System | Microsoft Windows Server 2025 Datacenter Evaluation (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% |
11650
2.18 KIPS |
|
|
Image Classification (F16)
|
100% |
12773
2.39 KIPS |
|
|
Image Classification (I8)
|
100% |
9976
1.87 KIPS |
|
|
Image Segmentation (F32)
|
100% |
20731
346.2 IPS |
|
|
Image Segmentation (F16)
|
100% |
19953
333.2 IPS |
|
|
Image Segmentation (I8)
|
98% |
18937
316.3 IPS |
|
|
Pose Estimation (F32)
|
100% |
235900
285.7 IPS |
|
|
Pose Estimation (F16)
|
100% |
235195
284.8 IPS |
|
|
Pose Estimation (I8)
|
100% |
206991
250.7 IPS |
|
|
Object Detection (F32)
|
100% |
8154
608.8 IPS |
|
|
Object Detection (F16)
|
100% |
8185
611.1 IPS |
|
|
Object Detection (I8)
|
56% |
7554
564.0 IPS |
|
|
Face Detection (F32)
|
100% |
40339
479.6 IPS |
|
|
Face Detection (F16)
|
100% |
41845
497.5 IPS |
|
|
Face Detection (I8)
|
89% |
36461
433.5 IPS |
|
|
Depth Estimation (F32)
|
100% |
74663
579.0 IPS |
|
|
Depth Estimation (F16)
|
100% |
68200
528.9 IPS |
|
|
Depth Estimation (I8)
|
95% |
55074
427.1 IPS |
|
|
Style Transfer (F32)
|
100% |
329379
433.3 IPS |
|
|
Style Transfer (F16)
|
100% |
321390
422.8 IPS |
|
|
Style Transfer (I8)
|
98% |
293188
385.7 IPS |
|
|
Image Super-Resolution (F32)
|
100% |
43013
1.54 KIPS |
|
|
Image Super-Resolution (F16)
|
100% |
43455
1.55 KIPS |
|
|
Image Super-Resolution (I8)
|
99% |
34372
1.23 KIPS |
|
|
Text Classification (F32)
|
100% |
3254
4.68 KIPS |
|
|
Text Classification (F16)
|
100% |
3191
4.59 KIPS |
|
|
Text Classification (I8)
|
98% |
1959
2.81 KIPS |
|
|
Machine Translation (F32)
|
100% |
5356
98.6 IPS |
|
|
Machine Translation (F16)
|
100% |
5398
99.3 IPS |
|
|
Machine Translation (I8)
|
70% |
2979
54.8 IPS |
