AMD Radeon Pro 5700 vs NVIDIA Tesla V100S PCIe 32 GB
Processeur graphique
| Nom du GPU | Navi 10 | GV100 |
|---|---|---|
| Architecture | RDNA 1.0 | Volta |
| Fonderie | TSMC | TSMC |
| Taille du processus | 7 nm | 12 nm |
| Transistors | 10,300 million | 21,100 million |
| Taille des matrices | 251 mm² | 815 mm² |
| GPU variant | Navi 10 XLA | — |
Carte graphique
| Date de publication | Aug 4th, 2020 | Nov 26th, 2019 |
|---|---|---|
| Génération | Radeon Pro Mac | Tesla |
| Production | Active | End-of-life |
| Bus interface | PCIe 4.0 x16 | PCIe 3.0 x16 |
Vitesse clock
| Base clock | 1243 MHz | 1245 MHz |
|---|---|---|
| Boost clock | 1350 MHz | 1597 MHz |
| Mémoire clock | 1500 MHz 12 Gbps effective | 1106 MHz 2.2 Gbps effective |
Mémoire
| Taille de la mémoire | 8 GB | 32 GB |
|---|---|---|
| Type de mémoire | GDDR6 | HBM2 |
| Bus mémoire | 256 bit | 4096 bit |
| Bande passante | 384.0 GB/s | 1,133 GB/s |
Render Config
| Shading units | 2304 | 5120 |
|---|---|---|
| TMUs | 144 | 320 |
| ROPs | 64 | 128 |
| Compute units | 36 | — |
| Cache L2 | 4 MB | 6 MB |
| Comptage SM | — | 80 |
| Tensor cores | — | 640 |
| Cache L1 | — | 128 KB (per SM) |
Performance théorique
| Taux de pixel | 86.40 GPixel/s | 204.4 GPixel/s |
|---|---|---|
| Taux de texture | 194.4 GTexel/s | 511.0 GTexel/s |
| FP16 (half) performance | 12.44 TFLOPS (2:1) | 32.71 TFLOPS (2:1) |
| FP32 (float) performance | 6.221 TFLOPS | 16.35 TFLOPS |
| FP64 (double) performance | 388.8 GFLOPS (1:16) | 8.177 TFLOPS (1:2) |
Board Design
| Taille Slot | IGP | Dual-slot |
|---|---|---|
| TDP | 130 W | 250 W |
| Suggestions pour le PSU | 300 W | 600 W |
| Sorties | No outputs | No outputs |
| Connecteurs de puissance | None | 2x 8-pin |
| Board number | — | PG500 |
Caractéristiques graphiques
| DirectX | 12 (12_1) | 12 (12_1) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.1 | 3.0 |
| Vulkan | 1.2 | 1.2 |
| Shader model | 6.5 | 6.6 |
| CUDA | — | 7.0 |
