Nom du GPU | Polaris 21 | GK110B |
---|---|---|
GPU variant | Polaris 21 PRO | — |
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 |
Date de publication | Jun 5th, 2017 | — |
---|---|---|
Génération | Radeon Pro Mac (500 Series) | — |
Production | Active | — |
Bus interface | PCIe 3.0 x8 | — |
GPU clock | 850 MHz | — |
---|---|---|
Mémoire clock | 1275 MHz 5.1 Gbps effective | 1502 MHz 6 Gbps effective |
Base clock | — | 745 MHz |
Boost clock | — | 876 MHz |
Taille de la mémoire | 2 GB | 12 GB |
---|---|---|
Type de mémoire | GDDR5 | GDDR5 |
Bus mémoire | 128 bit | 384 bit |
Bande passante | 81.60 GB/s | 288.4 GB/s |
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 | 1024 KB | 1536 KB |
Comptage SMX | — | 15 |
Taux de pixel | 13.60 GPixel/s | 52.56 GPixel/s |
---|---|---|
Taux de texture | 40.80 GTexel/s | 210.2 GTexel/s |
FP16 (half) performance | 1,306 GFLOPS (1:1) | — |
FP32 (float) performance | 1,306 GFLOPS | 5.046 TFLOPS |
FP64 (double) performance | 81.60 GFLOPS (1:16) | 1.682 TFLOPS (1:3) |
Taille Slot | IGP | Dual-slot |
---|---|---|
TDP | 75 W | 245 W |
Sorties | No outputs | No outputs |
Connecteurs de puissance | None | — |
Longueur | — | 267 mm 10.5 inches |
Suggestions pour le PSU | — | 550 W |
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 |
Date de publication | — | Nov 22nd, 2013 |
---|---|---|
Génération | — | Tesla |
Production | — | End-of-life |
Prix de lancement | — | 7,699 USD |
Bus interface | — | PCIe 3.0 x16 |