Nom du GPU | Polaris 22 | GK107 |
---|---|---|
GPU variant | VegaM XL (D715A714) | — |
Architecture | GCN 4.0 | Kepler |
Fonderie | GlobalFoundries | TSMC |
Taille du processus | 14 nm | 28 nm |
Transistors | 5,000 million | 1,270 million |
Taille des matrices | 208 mm² | 118 mm² |
Date de publication | Feb 1st, 2018 | — |
---|---|---|
Génération | Vega (Vega M) | — |
Production | Active | — |
Bus interface | IGP | — |
Base clock | 931 MHz | — |
---|---|---|
Boost clock | 1011 MHz | — |
Mémoire clock | 700 MHz 1400 Mbps effective | 1250 MHz 5 Gbps effective |
GPU clock | — | 954 MHz |
Taille de la mémoire | 4 GB | 1024 MB |
---|---|---|
Type de mémoire | HBM2 | GDDR5 |
Bus mémoire | 1024 bit | 128 bit |
Bande passante | 179.2 GB/s | 80.00 GB/s |
Shading units | 1280 | 384 |
---|---|---|
TMUs | 80 | 32 |
ROPs | 32 | 16 |
Compute units | 20 | — |
Cache L1 | 16 KB (per CU) | 16 KB (per SMX) |
Cache L2 | 1024 KB | 128 KB |
Comptage SMX | — | 2 |
Taux de pixel | 32.35 GPixel/s | 7.632 GPixel/s |
---|---|---|
Taux de texture | 80.88 GTexel/s | 30.53 GTexel/s |
FP16 (half) performance | 2.588 TFLOPS (1:1) | — |
FP32 (float) performance | 2.588 TFLOPS | 732.7 GFLOPS |
FP64 (double) performance | 161.8 GFLOPS (1:16) | 30.53 GFLOPS (1:24) |
Taille Slot | IGP | Dual-slot |
---|---|---|
TDP | 65 W | 225 W |
Sorties | No outputs | No outputs |
Board number | D136 | — |
Longueur | — | 267 mm 10.5 inches |
Suggestions pour le PSU | — | 550 W |
Connecteurs de puissance | — | 1x 8-pin |
DirectX | 12 (12_0) | 12 (11_0) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 2.1 | 3.0 |
Vulkan | 1.2 | 1.1 |
Shader model | 6.4 | 5.1 |
CUDA | — | 3.0 |
Date de publication | — | Jul 23rd, 2013 |
---|---|---|
Génération | — | GRID |
Production | — | End-of-life |
Prix de lancement | — | 3,299 USD |
Bus interface | — | PCIe 3.0 x16 |