Nom du GPU | GA102 | GV100 |
---|---|---|
Architecture | Ampere | Volta |
Fonderie | Samsung | TSMC |
Taille du processus | 8 nm | 12 nm |
Transistors | 28,300 million | 21,100 million |
Taille des matrices | 628 mm² | 815 mm² |
Date de publication | Apr 12th, 2021 | Mar 27th, 2018 |
---|---|---|
Génération | Quadro | Tesla |
Production | Active | End-of-life |
Bus interface | PCIe 4.0 x16 | PCIe 3.0 x16 |
Base clock | 1170 MHz | 1230 MHz |
---|---|---|
Boost clock | 1695 MHz | 1380 MHz |
Mémoire clock | 2000 MHz 16 Gbps effective | 876 MHz 1752 Mbps effective |
Taille de la mémoire | 24 GB | 32 GB |
---|---|---|
Type de mémoire | GDDR6 | HBM2 |
Bus mémoire | 384 bit | 4096 bit |
Bande passante | 768.0 GB/s | 897.0 GB/s |
Shading units | 8192 | 5120 |
---|---|---|
TMUs | 256 | 320 |
ROPs | 96 | 128 |
Comptage SM | 64 | 80 |
Tensor cores | 256 | 640 |
RT cores | 64 | — |
Cache L1 | 128 KB (per SM) | 128 KB (per SM) |
Cache L2 | 6 MB | 6 MB |
Taux de pixel | 162.7 GPixel/s | 176.6 GPixel/s |
---|---|---|
Taux de texture | 433.9 GTexel/s | 441.6 GTexel/s |
FP16 (half) performance | 27.77 TFLOPS (1:1) | 28.26 TFLOPS (2:1) |
FP32 (float) performance | 27.77 TFLOPS | 14.13 TFLOPS |
FP64 (double) performance | 867.8 GFLOPS (1:32) | 7.066 TFLOPS (1:2) |
Taille Slot | Dual-slot | Dual-slot |
---|---|---|
Longueur | 267 mm 10.5 inches | — |
Taille | 112 mm 4.4 inches | — |
TDP | 230 W | 250 W |
Suggestions pour le PSU | 550 W | 600 W |
Sorties | 4x DisplayPort | No outputs |
Connecteurs de puissance | 1x 8-pin | 2x 8-pin |
Board number | — | PG500 SKU 200 |
DirectX | 12 Ultimate (12_2) | 12 (12_1) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 3.0 | 3.0 |
Vulkan | 1.2 | 1.2 |
CUDA | 8.6 | 7.0 |
Shader model | 6.6 | 6.6 |