AMD Radeon R7 360 vs NVIDIA Tesla K40m
Processeur graphique
| Nom du GPU | Tobago | GK110B |
|---|---|---|
| GPU variant | Tobago PRO (215-0875010) | — |
| Architecture | GCN 2.0 | Kepler |
| Fonderie | TSMC | TSMC |
| Taille du processus | 28 nm | 28 nm |
| Transistors | 2,080 million | 7,080 million |
| Taille des matrices | 160 mm² | 561 mm² |
Carte graphique
| Date de publication | Jun 18th, 2015 | Nov 22nd, 2013 |
|---|---|---|
| Génération | Pirate Islands | Tesla |
| Production | End-of-life | End-of-life |
| Prix de lancement | 109 USD | 7,699 USD |
| Bus interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
| Prédécesseur | Volcanic Islands | — |
| Successeur | Arctic Islands | — |
Vitesse clock
| Base clock | 1000 MHz | 745 MHz |
|---|---|---|
| Boost clock | 1050 MHz | 876 MHz |
| Mémoire clock | 1500 MHz 6 Gbps effective | 1502 MHz 6 Gbps effective |
Mémoire
| Taille de la mémoire | 2 GB | 12 GB |
|---|---|---|
| Type de mémoire | GDDR5 | GDDR5 |
| Bus mémoire | 128 bit | 384 bit |
| Bande passante | 96.00 GB/s | 288.4 GB/s |
Render Config
| Shading units | 768 | 2880 |
|---|---|---|
| TMUs | 48 | 240 |
| ROPs | 16 | 48 |
| Compute units | 12 | — |
| Cache L1 | 16 KB (per CU) | 16 KB (per SMX) |
| Cache L2 | 256 KB | 1536 KB |
| Comptage SMX | — | 15 |
Performance théorique
| Taux de pixel | 16.80 GPixel/s | 52.56 GPixel/s |
|---|---|---|
| Taux de texture | 50.40 GTexel/s | 210.2 GTexel/s |
| FP32 (float) performance | 1.613 TFLOPS | 5.046 TFLOPS |
| FP64 (double) performance | 100.8 GFLOPS (1:16) | 1.682 TFLOPS (1:3) |
Board Design
| Taille Slot | Single-slot | Dual-slot |
|---|---|---|
| Longueur | 165 mm 6.5 inches | 267 mm 10.5 inches |
| TDP | 100 W | 245 W |
| Suggestions pour le PSU | 300 W | 550 W |
| Sorties | 1x DVI1x HDMI1x DisplayPort | No outputs |
| Connecteurs de puissance | 1x 6-pin | — |
| Board number | C582, C936 | — |
Caractéristiques graphiques
| DirectX | 12 (12_0) | 12 (11_1) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.0 | 3.0 |
| Vulkan | 1.2 | 1.1 |
| Shader model | 6.3 | 5.1 |
| CUDA | — | 3.5 |
