Nom du GPU | Vega 10 | GM107 |
---|---|---|
GPU variant | Vega 10 XL GL (215-0894304) | N16P-Q1-A2 |
Architecture | GCN 5.0 | Maxwell |
Fonderie | GlobalFoundries | TSMC |
Taille du processus | 14 nm | 28 nm |
Transistors | 12,500 million | 1,870 million |
Taille des matrices | 495 mm² | 148 mm² |
Date de publication | Aug 26th, 2018 | — |
---|---|---|
Génération | Radeon Pro | — |
Production | Active | — |
Bus interface | PCIe 3.0 x16 | — |
Base clock | 852 MHz | — |
---|---|---|
Boost clock | 1500 MHz | — |
Mémoire clock | 945 MHz 1890 Mbps effective | 1253 MHz 5 Gbps effective |
GPU clock | — | 993 MHz |
Taille de la mémoire | 16 GB | 2 GB |
---|---|---|
Type de mémoire | HBM2 | GDDR5 |
Bus mémoire | 2048 bit | 128 bit |
Bande passante | 483.8 GB/s | 80.19 GB/s |
Shading units | 3584 | 512 |
---|---|---|
TMUs | 224 | 32 |
ROPs | 64 | 16 |
Compute units | 56 | — |
Cache L1 | 16 KB (per CU) | 64 KB (per SMM) |
Cache L2 | 4 MB | 2 MB |
Comptage SMM | — | 4 |
Taux de pixel | 96.00 GPixel/s | 15.89 GPixel/s |
---|---|---|
Taux de texture | 336.0 GTexel/s | 31.78 GTexel/s |
FP16 (half) performance | 21.50 TFLOPS (2:1) | — |
FP32 (float) performance | 10.75 TFLOPS | 1,017 GFLOPS |
FP64 (double) performance | 672.0 GFLOPS (1:16) | 31.78 GFLOPS (1:32) |
Taille Slot | Dual-slot | MXM Module |
---|---|---|
Longueur | 267 mm 10.5 inches | — |
Taille | 111 mm 4.4 inches | — |
TDP | 230 W | 40 W |
Suggestions pour le PSU | 550 W | — |
Sorties | 1x mini-DisplayPort | No outputs |
Connecteurs de puissance | 2x 8-pin | None |
DirectX | 12 (12_1) | 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 | — | 5.0 |
Date de publication | — | Aug 18th, 2015 |
---|---|---|
Génération | — | Quadro Mobile (Mx000M) |
Production | — | End-of-life |
Bus interface | — | MXM-A (3.0) |
Critiques | — | 26 in our database |