AMD Radeon R9 370 vs NVIDIA Tesla P100 SXM2
Processeur graphique
| Nom du GPU | Trinidad | GP100 |
|---|---|---|
| GPU variant | Trinidad PRO (215-0870020) | GP100-890-A1 |
| Architecture | GCN 1.0 | Pascal |
| Fonderie | TSMC | TSMC |
| Taille du processus | 28 nm | 16 nm |
| Transistors | 2,800 million | 15,300 million |
| Taille des matrices | 212 mm² | 610 mm² |
Carte graphique
| Date de publication | May 5th, 2015 | Apr 5th, 2016 |
|---|---|---|
| Génération | Pirate Islands | Tesla |
| Production | End-of-life | End-of-life |
| Bus interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
| Prédécesseur | Volcanic Islands | — |
| Successeur | Arctic Islands | — |
Vitesse clock
| Base clock | 925 MHz | 1328 MHz |
|---|---|---|
| Boost clock | 975 MHz | 1480 MHz |
| Mémoire clock | 1400 MHz 5.6 Gbps effective | 715 MHz 1430 Mbps effective |
Mémoire
| Taille de la mémoire | 2 GB | 16 GB |
|---|---|---|
| Type de mémoire | GDDR5 | HBM2 |
| Bus mémoire | 256 bit | 4096 bit |
| Bande passante | 179.2 GB/s | 732.2 GB/s |
Render Config
| Shading units | 1280 | 3584 |
|---|---|---|
| TMUs | 80 | 224 |
| ROPs | 32 | 96 |
| Compute units | 24 | — |
| Cache L1 | 16 KB (per CU) | 24 KB (per SM) |
| Cache L2 | 512 KB | 4 MB |
| Comptage SM | — | 56 |
Performance théorique
| Taux de pixel | 31.20 GPixel/s | 142.1 GPixel/s |
|---|---|---|
| Taux de texture | 78.00 GTexel/s | 331.5 GTexel/s |
| FP32 (float) performance | 2.496 TFLOPS | 10.61 TFLOPS |
| FP64 (double) performance | 156.0 GFLOPS (1:16) | 5.304 TFLOPS (1:2) |
| FP16 (half) performance | — | 21.22 TFLOPS (2:1) |
Board Design
| Taille Slot | Dual-slot | — |
|---|---|---|
| Longueur | 221 mm 8.7 inches | — |
| Taille | 111 mm 4.4 inches | — |
| TDP | 110 W | 300 W |
| Suggestions pour le PSU | 300 W | 700 W |
| Sorties | 2x DVI1x HDMI1x DisplayPort | No outputs |
| Connecteurs de puissance | 1x 6-pin | None |
Caractéristiques graphiques
| DirectX | 12 (11_1) | 12 (12_1) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 1.2 | 3.0 |
| Vulkan | 1.2 | 1.2 |
| Shader model | 5.1 | 6.4 |
| CUDA | — | 6.0 |
