AMD Radeon Pro VII vs NVIDIA Tesla T10 Processor
Processeur graphique
| Nom du GPU | Vega 20 | GT200B |
|---|---|---|
| GPU variant | Vega 20 GL XT | — |
| Architecture | GCN 5.1 | Tesla 2.0 |
| Fonderie | TSMC | TSMC |
| Taille du processus | 7 nm | 55 nm |
| Transistors | 13,230 million | 1,400 million |
| Taille des matrices | 331 mm² | 470 mm² |
Carte graphique
| Date de publication | May 13th, 2020 | Apr 9th, 2009 |
|---|---|---|
| Génération | Radeon Pro | Tesla |
| Production | Active | End-of-life |
| Prix de lancement | 1,899 USD | — |
| Bus interface | PCIe 4.0 x16 | PCIe 2.0 x16 |
Vitesse clock
| Base clock | 1400 MHz | — |
|---|---|---|
| Boost clock | 1700 MHz | — |
| Mémoire clock | 1000 MHz 2 Gbps effective | 800 MHz 1600 Mbps effective |
| GPU clock | — | 610 MHz |
| Shader clock | — | 1296 MHz |
Mémoire
| Taille de la mémoire | 16 GB | 4 GB |
|---|---|---|
| Type de mémoire | HBM2 | GDDR3 |
| Bus mémoire | 4096 bit | 512 bit |
| Bande passante | 1,024 GB/s | 102.4 GB/s |
Render Config
| Shading units | 3840 | 240 |
|---|---|---|
| TMUs | 240 | 80 |
| ROPs | 64 | 32 |
| Compute units | 60 | — |
| Cache L1 | 16 KB (per CU) | — |
| Cache L2 | 4 MB | 256 KB |
| Comptage SM | — | 30 |
Performance théorique
| Taux de pixel | 108.8 GPixel/s | 19.52 GPixel/s |
|---|---|---|
| Taux de texture | 408.0 GTexel/s | 48.80 GTexel/s |
| FP16 (half) performance | 26.11 TFLOPS (2:1) | — |
| FP32 (float) performance | 13.06 TFLOPS | 622.1 GFLOPS |
| FP64 (double) performance | 6.528 TFLOPS (1:2) | 77.76 GFLOPS (1:8) |
Board Design
| Taille Slot | Dual-slot | Dual-slot |
|---|---|---|
| Longueur | 305 mm 12 inches | 267 mm 10.5 inches |
| Taille | 111 mm 4.4 inches | — |
| TDP | 250 W | 188 W |
| Suggestions pour le PSU | 600 W | 450 W |
| Sorties | 6x mini-DisplayPort | No outputs |
| Connecteurs de puissance | 1x 6-pin + 1x 8-pin | — |
| Board number | D360-37 | — |
Caractéristiques graphiques
| DirectX | 12 (12_1) | 11.1 (10_0) |
|---|---|---|
| OpenGL | 4.6 | 3.3 |
| OpenCL | 2.1 | 1.1 |
| Vulkan | 1.2 | — |
| Shader model | 6.4 | 4.0 |
| CUDA | — | 1.3 |
