ROMED8-2T vs ROMED8-2T
| ROMED8-2T | ROMED8-2T | Difference | |
|---|---|---|---|
| Single Precision | 2640 | 2640 | 100.0% |
| ROMED8-2T | |||
| ROMED8-2T | |||
| Half Precision | 946 | 946 | 100.0% |
| ROMED8-2T | |||
| ROMED8-2T | |||
| Quantized | 2625 | 2625 | 100.0% |
| ROMED8-2T | |||
| ROMED8-2T | |||
| Geekbench AI 1.2.0 | Geekbench AI 1.2.0 | ||
System Information
| ROMED8-2T | ROMED8-2T | |
|---|---|---|
| AI Framework | ONNX | ONNX |
| AI Backend | CPU | CPU |
| AI Device | AMD EPYC 7F52 | AMD EPYC 7F52 |
| Operating System | Microsoft Windows 10 Pro (64-bit) | Microsoft Windows 10 Pro (64-bit) |
| Model | ROMED8-2T | ROMED8-2T |
| Processor |
AMD EPYC 7F52 @ 3.50 GHz
1 Processor, 16 Cores, 32 Threads |
AMD EPYC 7F52 @ 3.50 GHz
1 Processor, 16 Cores, 32 Threads |
| Processor ID | AuthenticAMD Family 23 Model 49 Stepping 0 | AuthenticAMD Family 23 Model 49 Stepping 0 |
| Processor Codename | ||
| Processor Package | ||
| Motherboard | ASRockRack ROMED8-2T | ASRockRack ROMED8-2T |
| Northbridge | ||
| Southbridge | ||
| BIOS | American Megatrends Inc. P3.80 | American Megatrends Inc. P3.80 |
| Memory | 256.00 GB | 256.00 GB |
AI Performance
| ROMED8-2T | ROMED8-2T | Difference | |
|---|---|---|---|
| Image Classification (SP) | 1942 | 1942 | 100.0% |
| ROMED8-2T | |||
| ROMED8-2T | |||
| Image Classification (HP) | 309 | 309 | 100.0% |
| ROMED8-2T | |||
| ROMED8-2T | |||
| Image Classification (Q) | 2621 | 2621 | 100.0% |
| ROMED8-2T | |||
| ROMED8-2T | |||
| Image Segmentation (SP) | 755 | 755 | 100.0% |
| ROMED8-2T | |||
| ROMED8-2T | |||
| Image Segmentation (HP) | 383 | 383 | 100.0% |
| ROMED8-2T | |||
| ROMED8-2T | |||
| Image Segmentation (Q) | 1394 | 1394 | 100.0% |
| ROMED8-2T | |||
| ROMED8-2T | |||
| Pose Estimation (SP) | 11000 | 11000 | 100.0% |
| ROMED8-2T | |||
| ROMED8-2T | |||
| Pose Estimation (HP) | 6760 | 6760 | 100.0% |
| ROMED8-2T | |||
| ROMED8-2T | |||
| Pose Estimation (Q) | 9449 | 9449 | 100.0% |
| ROMED8-2T | |||
| ROMED8-2T | |||
| Object Detection (SP) | 2186 | 2186 | 100.0% |
| ROMED8-2T | |||
| ROMED8-2T | |||
| Object Detection (HP) | 389 | 389 | 100.0% |
| ROMED8-2T | |||
| ROMED8-2T | |||
| Object Detection (Q) | 1923 | 1923 | 100.0% |
| ROMED8-2T | |||
| ROMED8-2T | |||
| Face Detection (SP) | 4988 | 4988 | 100.0% |
| ROMED8-2T | |||
| ROMED8-2T | |||
| Face Detection (HP) | 899 | 899 | 100.0% |
| ROMED8-2T | |||
| ROMED8-2T | |||
| Face Detection (Q) | 5193 | 5193 | 100.0% |
| ROMED8-2T | |||
| ROMED8-2T | |||
| Depth Estimation (SP) | 8266 | 8266 | 100.0% |
| ROMED8-2T | |||
| ROMED8-2T | |||
| Depth Estimation (HP) | 1611 | 1611 | 100.0% |
| ROMED8-2T | |||
| ROMED8-2T | |||
| Depth Estimation (Q) | 6737 | 6737 | 100.0% |
| ROMED8-2T | |||
| ROMED8-2T | |||
| Style Transfer (SP) | 16203 | 16203 | 100.0% |
| ROMED8-2T | |||
| ROMED8-2T | |||
| Style Transfer (HP) | 13951 | 13951 | 100.0% |
| ROMED8-2T | |||
| ROMED8-2T | |||
| Style Transfer (Q) | 15064 | 15064 | 100.0% |
| ROMED8-2T | |||
| ROMED8-2T | |||
| Image Super-Resolution (SP) | 1325 | 1325 | 100.0% |
| ROMED8-2T | |||
| ROMED8-2T | |||
| Image Super-Resolution (HP) | 1033 | 1033 | 100.0% |
| ROMED8-2T | |||
| ROMED8-2T | |||
| Image Super-Resolution (Q) | 1201 | 1201 | 100.0% |
| ROMED8-2T | |||
| ROMED8-2T | |||
| Text Classification (SP) | 565 | 565 | 100.0% |
| ROMED8-2T | |||
| ROMED8-2T | |||
| Text Classification (HP) | 275 | 275 | 100.0% |
| ROMED8-2T | |||
| ROMED8-2T | |||
| Text Classification (Q) | 269 | 269 | 100.0% |
| ROMED8-2T | |||
| ROMED8-2T | |||
| Machine Translation (SP) | 933 | 933 | 100.0% |
| ROMED8-2T | |||
| ROMED8-2T | |||
| Machine Translation (HP) | 324 | 324 | 100.0% |
| ROMED8-2T | |||
| ROMED8-2T | |||
| Machine Translation (Q) | 1378 | 1378 | 100.0% |
| ROMED8-2T | |||
| ROMED8-2T | |||
