Nom du GPU | Venus | GP108 |
---|---|---|
GPU variant | Venus XT | — |
Architecture | GCN 1.0 | Pascal |
Fonderie | TSMC | Samsung |
Taille du processus | 28 nm | 14 nm |
Transistors | 1,500 million | 1,800 million |
Taille des matrices | 123 mm² | 74 mm² |
Date de publication | Apr 1st, 2013 | Jan 5th, 2018 |
---|---|---|
Génération | Solar System (HD 8800M) | Quadro Mobile (Px000) |
Production | End-of-life | End-of-life |
Bus interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
Prédécesseur | London | — |
Successeur | Crystal System | — |
Base clock | 725 MHz | 1455 MHz |
---|---|---|
Boost clock | 775 MHz | 1518 MHz |
Mémoire clock | 1125 MHz 4.5 Gbps effective | 1253 MHz 5 Gbps effective |
Taille de la mémoire | 2 GB | 2 GB |
---|---|---|
Type de mémoire | GDDR5 | GDDR5 |
Bus mémoire | 128 bit | 64 bit |
Bande passante | 72.00 GB/s | 40.10 GB/s |
Shading units | 640 | 256 |
---|---|---|
TMUs | 40 | 16 |
ROPs | 16 | 16 |
Compute units | 10 | — |
Cache L1 | 16 KB (per CU) | 48 KB (per SM) |
Cache L2 | 256 KB | 512 KB |
Comptage SM | — | 2 |
Taux de pixel | 12.40 GPixel/s | 24.29 GPixel/s |
---|---|---|
Taux de texture | 31.00 GTexel/s | 24.29 GTexel/s |
FP32 (float) performance | 992.0 GFLOPS | 777.2 GFLOPS |
FP64 (double) performance | 62.00 GFLOPS (1:16) | 24.29 GFLOPS (1:32) |
FP16 (half) performance | — | 12.14 GFLOPS (1:64) |
TDP | unknown | 18 W |
---|---|---|
Sorties | No outputs | No outputs |
Connecteurs de puissance | — | None |
DirectX | 12 (11_1) | 12 (12_1) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 1.2 | 3.0 |
Vulkan | 1.2 | 1.2 |
Shader model | 5.1 | 6.4 |
CUDA | — | 6.1 |