AMD Radeon RX 560X vs NVIDIA Tesla K40m
Processeur graphique
| Nom du GPU | Polaris 21 | GK110B |
|---|---|---|
| GPU variant | Polaris 21 XT (215-0908004) | — |
| Architecture | GCN 4.0 | Kepler |
| Fonderie | GlobalFoundries | TSMC |
| Taille du processus | 14 nm | 28 nm |
| Transistors | 3,000 million | 7,080 million |
| Taille des matrices | 123 mm² | 561 mm² |
Carte graphique
| Date de publication | Apr 11th, 2018 | Nov 22nd, 2013 |
|---|---|---|
| Génération | Polaris | Tesla |
| Production | Active | End-of-life |
| Bus interface | PCIe 3.0 x8 | PCIe 3.0 x16 |
| Prédécesseur | Polaris | — |
| Successeur | Vega | — |
| Prix de lancement | — | 7,699 USD |
Vitesse clock
| Base clock | 1175 MHz | 745 MHz |
|---|---|---|
| Boost clock | 1275 MHz | 876 MHz |
| Mémoire clock | 1750 MHz 7 Gbps effective | 1502 MHz 6 Gbps effective |
Mémoire
| Taille de la mémoire | 4 GB | 12 GB |
|---|---|---|
| Type de mémoire | GDDR5 | GDDR5 |
| Bus mémoire | 128 bit | 384 bit |
| Bande passante | 112.0 GB/s | 288.4 GB/s |
Render Config
| Shading units | 1024 | 2880 |
|---|---|---|
| TMUs | 64 | 240 |
| ROPs | 16 | 48 |
| Compute units | 16 | — |
| Cache L1 | 16 KB (per CU) | 16 KB (per SMX) |
| Cache L2 | 1024 KB | 1536 KB |
| Comptage SMX | — | 15 |
Performance théorique
| Taux de pixel | 20.40 GPixel/s | 52.56 GPixel/s |
|---|---|---|
| Taux de texture | 81.60 GTexel/s | 210.2 GTexel/s |
| FP16 (half) performance | 2.611 TFLOPS (1:1) | — |
| FP32 (float) performance | 2.611 TFLOPS | 5.046 TFLOPS |
| FP64 (double) performance | 163.2 GFLOPS (1:16) | 1.682 TFLOPS (1:3) |
Board Design
| Taille Slot | Dual-slot | Dual-slot |
|---|---|---|
| Longueur | 170 mm 6.7 inches | 267 mm 10.5 inches |
| TDP | 75 W | 245 W |
| Suggestions pour le PSU | 250 W | 550 W |
| Sorties | 1x DVI1x HDMI1x DisplayPort | No outputs |
| Connecteurs de puissance | None | — |
| Board number | C994 | — |
Caractéristiques graphiques
| DirectX | 12 (12_0) | 12 (11_1) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.1 | 3.0 |
| Vulkan | 1.2 | 1.1 |
| Shader model | 6.4 | 5.1 |
| CUDA | — | 3.5 |
