Nom du GPU | GF100 | TU117 |
---|---|---|
GPU variant | GF100-825-A3 | — |
Architecture | Fermi | Turing |
Fonderie | TSMC | TSMC |
Taille du processus | 40 nm | 12 nm |
Transistors | 3,100 million | 4,700 million |
Taille des matrices | 529 mm² | 200 mm² |
Date de publication | Nov 2nd, 2010 | May 6th, 2021 |
---|---|---|
Génération | Quadro | Quadro |
Production | End-of-life | Active |
Prix de lancement | 1,199 USD | — |
Bus interface | PCIe 2.0 x16 | PCIe 3.0 x16 |
Critiques | 26 in our database | — |
GPU clock | 475 MHz | — |
---|---|---|
Shader clock | 950 MHz | — |
Mémoire clock | 702 MHz 2.8 Gbps effective | 1250 MHz 10 Gbps effective |
Base clock | — | 1065 MHz |
Boost clock | — | 1395 MHz |
Taille de la mémoire | 2 GB | 8 GB |
---|---|---|
Type de mémoire | GDDR5 | GDDR6 |
Bus mémoire | 256 bit | 128 bit |
Bande passante | 89.86 GB/s | 160.0 GB/s |
Shading units | 256 | 896 |
---|---|---|
TMUs | 32 | 56 |
ROPs | 32 | 32 |
Comptage SM | 8 | 14 |
Cache L1 | 64 KB (per SM) | 64 KB (per SM) |
Cache L2 | 512 KB | 1024 KB |
Taux de pixel | 7.600 GPixel/s | 44.64 GPixel/s |
---|---|---|
Taux de texture | 15.20 GTexel/s | 78.12 GTexel/s |
FP32 (float) performance | 486.4 GFLOPS | 2.500 TFLOPS |
FP64 (double) performance | 243.2 GFLOPS (1:2) | 78.12 GFLOPS (1:32) |
FP16 (half) performance | — | 5.000 TFLOPS (2:1) |
Taille Slot | Single-slot | Single-slot |
---|---|---|
Longueur | 241 mm 9.5 inches | — |
Taille | 111 mm 4.4 inches | — |
TDP | 142 W | 50 W |
Suggestions pour le PSU | 300 W | 250 W |
Sorties | 1x DVI2x DisplayPort | 4x mini-DisplayPort |
Connecteurs de puissance | 1x 6-pin | None |
Board number | P1031 | — |
DirectX | 12 (11_0) | 12 (12_1) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 1.1 | 3.0 |
Vulkan | — | 1.2 |
CUDA | 2.0 | 7.5 |
Shader model | 5.1 | 6.6 |