Nom du GPU | GP107 | TU117 |
---|---|---|
GPU variant | GP107-400-A1 | — |
Architecture | Pascal | Turing |
Fonderie | Samsung | TSMC |
Taille du processus | 14 nm | 12 nm |
Transistors | 3,300 million | 4,700 million |
Taille des matrices | 132 mm² | 200 mm² |
Date de publication | Oct 25th, 2016 | May 6th, 2021 |
---|---|---|
Génération | GeForce 10 | Quadro |
Prédécesseur | GeForce 900 | — |
Successeur | GeForce 20 | — |
Production | End-of-life | Active |
Prix de lancement | 139 USD | — |
Bus interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
Critiques | 58 in our database | — |
Base clock | 1291 MHz | 1065 MHz |
---|---|---|
Boost clock | 1392 MHz | 1395 MHz |
Mémoire clock | 1752 MHz 7 Gbps effective | 1250 MHz 10 Gbps effective |
Taille de la mémoire | 4 GB | 4 GB |
---|---|---|
Type de mémoire | GDDR5 | GDDR6 |
Bus mémoire | 128 bit | 128 bit |
Bande passante | 112.1 GB/s | 160.0 GB/s |
Shading units | 768 | 896 |
---|---|---|
TMUs | 48 | 56 |
ROPs | 32 | 32 |
Comptage SM | 6 | 14 |
Cache L1 | 48 KB (per SM) | 64 KB (per SM) |
Cache L2 | 1024 KB | 1024 KB |
Taux de pixel | 44.54 GPixel/s | 44.64 GPixel/s |
---|---|---|
Taux de texture | 66.82 GTexel/s | 78.12 GTexel/s |
FP16 (half) performance | 33.41 GFLOPS (1:64) | 5.000 TFLOPS (2:1) |
FP32 (float) performance | 2.138 TFLOPS | 2.500 TFLOPS |
FP64 (double) performance | 66.82 GFLOPS (1:32) | 78.12 GFLOPS (1:32) |
Taille Slot | Dual-slot | Single-slot |
---|---|---|
Longueur | 145 mm 5.7 inches | — |
Taille | 111 mm 4.4 inches | — |
TDP | 75 W | 50 W |
Suggestions pour le PSU | 250 W | 250 W |
Sorties | 1x DVI1x HDMI1x DisplayPort | 4x mini-DisplayPort |
Connecteurs de puissance | None | None |
Board number | PG210 | — |
DirectX | 12 (12_1) | 12 (12_1) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 3.0 | 3.0 |
Vulkan | 1.2 | 1.2 |
CUDA | 6.1 | 7.5 |
Shader model | 6.4 | 6.6 |