AMD Radeon RX 570 vs NVIDIA Tesla V100 PCIe 16 GB
Processeur graphique
| Nom du GPU | Polaris 20 | GV100 |
|---|---|---|
| GPU variant | Polaris 20 XL (215-0910052) | — |
| Architecture | GCN 4.0 | Volta |
| Fonderie | GlobalFoundries | TSMC |
| Taille du processus | 14 nm | 12 nm |
| Transistors | 5,700 million | 21,100 million |
| Taille des matrices | 232 mm² | 815 mm² |
Carte graphique
| Date de publication | Apr 18th, 2017 | Jun 21st, 2017 |
|---|---|---|
| Génération | Polaris | Tesla |
| Production | Active | End-of-life |
| Prix de lancement | 169 USD | — |
| Prix courant | Amazon / Newegg | — |
| Bus interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
| Critiques | 29 in our database | — |
| Prédécesseur | Arctic Islands | — |
| Successeur | Vega | — |
Vitesse clock
| Base clock | 1168 MHz | 1245 MHz |
|---|---|---|
| Boost clock | 1244 MHz | 1380 MHz |
| Mémoire clock | 1750 MHz 7 Gbps effective | 876 MHz 1752 Mbps effective |
Mémoire
| Taille de la mémoire | 4 GB | 16 GB |
|---|---|---|
| Type de mémoire | GDDR5 | HBM2 |
| Bus mémoire | 256 bit | 4096 bit |
| Bande passante | 224.0 GB/s | 897.0 GB/s |
Render Config
| Shading units | 2048 | 5120 |
|---|---|---|
| TMUs | 128 | 320 |
| ROPs | 32 | 128 |
| Compute units | 32 | — |
| Cache L1 | 16 KB (per CU) | 128 KB (per SM) |
| Cache L2 | 2 MB | 6 MB |
| Comptage SM | — | 80 |
| Tensor cores | — | 640 |
Performance théorique
| Taux de pixel | 39.81 GPixel/s | 176.6 GPixel/s |
|---|---|---|
| Taux de texture | 159.2 GTexel/s | 441.6 GTexel/s |
| FP16 (half) performance | 5.095 TFLOPS (1:1) | 28.26 TFLOPS (2:1) |
| FP32 (float) performance | 5.095 TFLOPS | 14.13 TFLOPS |
| FP64 (double) performance | 318.5 GFLOPS (1:16) | 7.066 TFLOPS (1:2) |
Board Design
| Taille Slot | Dual-slot | Dual-slot |
|---|---|---|
| Longueur | 241 mm 9.5 inches | — |
| TDP | 150 W | 300 W |
| Suggestions pour le PSU | 450 W | 700 W |
| Sorties | 1x DVI1x HDMI3x DisplayPort | No outputs |
| Connecteurs de puissance | 1x 6-pin | 2x 8-pin |
| Board number | C940, D000 | PG500 SKU 200 |
Caractéristiques graphiques
| DirectX | 12 (12_0) | 12 (12_1) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.1 | 3.0 |
| Vulkan | 1.2 | 1.2 |
| Shader model | 6.4 | 6.6 |
| CUDA | — | 7.0 |
