Upload Date | March 28 2025 12:38 AM |
Views | 1 |
System Information | |
---|---|
Operating System | Microsoft Windows 10 Pro (64-bit) |
Model | Gigabyte Technology Co., Ltd. X399 AORUS Gaming 7 |
Motherboard | Gigabyte Technology Co., Ltd. X399 AORUS Gaming 7 |
Power Plan | High performance |
CPU Information | |
---|---|
Name | AMD Ryzen Threadripper 1950X |
Topology | 1 Processor, 16 Cores, 32 Threads |
Identifier | AuthenticAMD Family 23 Model 1 Stepping 1 |
Base Frequency | 3.40 GHz |
Cluster 1 | 16 Cores |
L1 Instruction Cache | 64.0 KB x 16 |
L1 Data Cache | 32.0 KB x 16 |
L2 Cache | 512 KB x 16 |
L3 Cache | 8.00 MB x 4 |
Memory Information | |
---|---|
Size | 32.00 GB |
Inference Information | |
---|---|
Framework | ONNX |
Backend | DirectML |
Device | NVIDIA GeForce RTX 5070 Ti |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (F32)
|
100% |
8247
1.54 KIPS |
|
Image Classification (F16)
|
100% |
8283
1.55 KIPS |
|
Image Classification (I8)
|
100% |
7497
1.40 KIPS |
|
Image Segmentation (F32)
|
100% |
9672
161.5 IPS |
|
Image Segmentation (F16)
|
100% |
9855
164.6 IPS |
|
Image Segmentation (I8)
|
98% |
9489
158.5 IPS |
|
Pose Estimation (F32)
|
100% |
146708
177.7 IPS |
|
Pose Estimation (F16)
|
100% |
147195
178.2 IPS |
|
Pose Estimation (I8)
|
100% |
135048
163.5 IPS |
|
Object Detection (F32)
|
100% |
3432
256.2 IPS |
|
Object Detection (F16)
|
100% |
3527
263.3 IPS |
|
Object Detection (I8)
|
50% |
3419
255.3 IPS |
|
Face Detection (F32)
|
100% |
22599
268.7 IPS |
|
Face Detection (F16)
|
100% |
22808
271.2 IPS |
|
Face Detection (I8)
|
89% |
20082
238.8 IPS |
|
Depth Estimation (F32)
|
100% |
68097
528.1 IPS |
|
Depth Estimation (F16)
|
100% |
68149
528.5 IPS |
|
Depth Estimation (I8)
|
94% |
55436
429.9 IPS |
|
Style Transfer (F32)
|
100% |
261258
343.7 IPS |
|
Style Transfer (F16)
|
100% |
249489
328.2 IPS |
|
Style Transfer (I8)
|
98% |
222770
293.0 IPS |
|
Image Super-Resolution (F32)
|
100% |
32776
1.17 KIPS |
|
Image Super-Resolution (F16)
|
100% |
33030
1.18 KIPS |
|
Image Super-Resolution (I8)
|
99% |
26688
953.1 IPS |
|
Text Classification (F32)
|
100% |
2215
3.18 KIPS |
|
Text Classification (F16)
|
100% |
2215
3.18 KIPS |
|
Text Classification (I8)
|
98% |
1568
2.25 KIPS |
|
Machine Translation (F32)
|
100% |
2642
48.6 IPS |
|
Machine Translation (F16)
|
100% |
2663
49.0 IPS |
|
Machine Translation (I8)
|
70% |
1890
34.8 IPS |