Nom du GPU | GK20A | GP104 |
---|---|---|
Architecture | Kepler 2.0 | Pascal |
Fonderie | TSMC | TSMC |
Taille du processus | 28 nm | 16 nm |
Transistors | unknown | 7,200 million |
Taille des matrices | unknown | 314 mm² |
GPU variant | — | GP104-100-A1 |
Date de publication | Oct 15th, 2014 | — |
---|---|---|
Génération | Tegra | — |
Production | End-of-life | — |
Bus interface | IGP | — |
Base clock | 756 MHz | 1607 MHz |
---|---|---|
Boost clock | 951 MHz | 1733 MHz |
Mémoire clock | System Shared | 1251 MHz 10 Gbps effective |
Taille de la mémoire | System Shared | 4 GB |
---|---|---|
Type de mémoire | System Shared | GDDR5X |
Bus mémoire | System Shared | 256 bit |
Bande passante | System Dependent | 320.3 GB/s |
Shading units | 192 | 1920 |
---|---|---|
TMUs | 8 | 120 |
ROPs | 4 | 64 |
Comptage SMX | 1 | — |
Cache L1 | 16 KB (per SMX) | 48 KB (per SM) |
Cache L2 | 128 KB | 2 MB |
Comptage SM | — | 15 |
Taux de pixel | 3.804 GPixel/s | 110.9 GPixel/s |
---|---|---|
Taux de texture | 7.608 GTexel/s | 208.0 GTexel/s |
FP32 (float) performance | 365.2 GFLOPS | 6.655 TFLOPS |
FP64 (double) performance | 11.41 GFLOPS (1:32) | 208.0 GFLOPS (1:32) |
FP16 (half) performance | — | 104.0 GFLOPS (1:64) |
Taille Slot | IGP | Dual-slot |
---|---|---|
TDP | 8 W | unknown |
Sorties | No outputs | No outputs |
Longueur | — | 267 mm 10.5 inches |
Suggestions pour le PSU | — | 200 W |
Connecteurs de puissance | — | 1x 8-pin |
Board number | — | PG413 SKU 100 |
DirectX | 12 (11_0) | 12 (12_1) |
---|---|---|
OpenGL | ES 3.1 | 4.6 |
OpenCL | — | 3.0 |
Vulkan | 1.1 | 1.2 |
CUDA | 3.2 | 6.1 |
Shader model | 5.1 | 6.4 |
Date de publication | — | Dec 12th, 2017 |
---|---|---|
Génération | — | Mining GPUs |
Production | — | End-of-life |
Bus interface | — | PCIe 3.0 x16 |