Nom du GPU | TU117 | GF100 |
---|---|---|
GPU variant | N18S-G5 | GF100-825-A3 |
Architecture | Turing | Fermi |
Fonderie | TSMC | TSMC |
Taille du processus | 12 nm | 40 nm |
Transistors | 4,700 million | 3,100 million |
Taille des matrices | 200 mm² | 529 mm² |
Date de publication | Aug 25th, 2020 | — |
---|---|---|
Génération | GeForce MX (4xx) | — |
Production | Active | — |
Bus interface | PCIe 4.0 x4 | — |
Base clock | 1395 MHz | — |
---|---|---|
Boost clock | 1575 MHz | — |
Mémoire clock | 1250 MHz 10 Gbps effective | 702 MHz 2.8 Gbps effective |
GPU clock | — | 475 MHz |
Shader clock | — | 950 MHz |
Taille de la mémoire | 2 GB | 2 GB |
---|---|---|
Type de mémoire | GDDR6 | GDDR5 |
Bus mémoire | 64 bit | 256 bit |
Bande passante | 80.00 GB/s | 89.86 GB/s |
Shading units | 896 | 256 |
---|---|---|
TMUs | 56 | 32 |
ROPs | 32 | 32 |
Comptage SM | 14 | 8 |
Cache L1 | 64 KB (per SM) | 64 KB (per SM) |
Cache L2 | 512 KB | 512 KB |
Taux de pixel | 50.40 GPixel/s | 7.600 GPixel/s |
---|---|---|
Taux de texture | 88.20 GTexel/s | 15.20 GTexel/s |
FP16 (half) performance | 5.645 TFLOPS (2:1) | — |
FP32 (float) performance | 2.822 TFLOPS | 486.4 GFLOPS |
FP64 (double) performance | 88.20 GFLOPS (1:32) | 243.2 GFLOPS (1:2) |
TDP | 31 W | 142 W |
---|---|---|
Sorties | No outputs | 1x DVI2x DisplayPort |
Connecteurs de puissance | None | 1x 6-pin |
Taille Slot | — | Single-slot |
Longueur | — | 241 mm 9.5 inches |
Taille | — | 111 mm 4.4 inches |
Suggestions pour le PSU | — | 300 W |
Board number | — | P1031 |
DirectX | 12 (12_1) | 12 (11_0) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 3.0 | 1.1 |
Vulkan | 1.2 | — |
CUDA | 7.5 | 2.0 |
Shader model | 6.6 | 5.1 |
Date de publication | — | Nov 2nd, 2010 |
---|---|---|
Génération | — | Quadro |
Production | — | End-of-life |
Prix de lancement | — | 1,199 USD |
Bus interface | — | PCIe 2.0 x16 |
Critiques | — | 26 in our database |