NVIDIA Tesla P100 PCIe 16 GB vs NVIDIA Tesla V100 PCIe 32 GB
Processeur graphique
| Nom du GPU | GP100 | GV100 |
|---|---|---|
| GPU variant | GP100-893-A1 | — |
| Architecture | Pascal | Volta |
| Fonderie | TSMC | TSMC |
| Taille du processus | 16 nm | 12 nm |
| Transistors | 15,300 million | 21,100 million |
| Taille des matrices | 610 mm² | 815 mm² |
Carte graphique
| Date de publication | Jun 20th, 2016 | Mar 27th, 2018 |
|---|---|---|
| Génération | Tesla | Tesla |
| Production | End-of-life | End-of-life |
| Prix de lancement | 5,699 USD | — |
| Bus interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
Vitesse clock
| Base clock | 1190 MHz | 1230 MHz |
|---|---|---|
| Boost clock | 1329 MHz | 1380 MHz |
| Mémoire clock | 715 MHz 1430 Mbps effective | 876 MHz 1752 Mbps effective |
Mémoire
| Taille de la mémoire | 16 GB | 32 GB |
|---|---|---|
| Type de mémoire | HBM2 | HBM2 |
| Bus mémoire | 4096 bit | 4096 bit |
| Bande passante | 732.2 GB/s | 897.0 GB/s |
Render Config
| Shading units | 3584 | 5120 |
|---|---|---|
| TMUs | 224 | 320 |
| ROPs | 96 | 128 |
| Comptage SM | 56 | 80 |
| Cache L1 | 24 KB (per SM) | 128 KB (per SM) |
| Cache L2 | 4 MB | 6 MB |
| Tensor cores | — | 640 |
Performance théorique
| Taux de pixel | 127.6 GPixel/s | 176.6 GPixel/s |
|---|---|---|
| Taux de texture | 297.7 GTexel/s | 441.6 GTexel/s |
| FP16 (half) performance | 19.05 TFLOPS (2:1) | 28.26 TFLOPS (2:1) |
| FP32 (float) performance | 9.526 TFLOPS | 14.13 TFLOPS |
| FP64 (double) performance | 4.763 TFLOPS (1:2) | 7.066 TFLOPS (1:2) |
Board Design
| Taille Slot | Dual-slot | Dual-slot |
|---|---|---|
| Longueur | 267 mm 10.5 inches | — |
| TDP | 250 W | 250 W |
| Suggestions pour le PSU | 600 W | 600 W |
| Sorties | No outputs | No outputs |
| Connecteurs de puissance | 1x 8-pin | 2x 8-pin |
| Board number | — | PG500 SKU 200 |
Caractéristiques graphiques
| DirectX | 12 (12_1) | 12 (12_1) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.2 | 1.2 |
| CUDA | 6.0 | 7.0 |
| Shader model | 6.4 | 6.6 |
