Nom du GPU | GV100 | GA107 |
---|---|---|
GPU variant | GV100-875-A1 | — |
Architecture | Volta | Ampere |
Fonderie | TSMC | Samsung |
Taille du processus | 12 nm | 8 nm |
Transistors | 21,100 million | unknown |
Taille des matrices | 815 mm² | unknown |
Date de publication | Mar 27th, 2018 | — |
---|---|---|
Génération | Quadro | — |
Production | End-of-life | — |
Prix de lancement | 8,999 USD | — |
Bus interface | PCIe 3.0 x16 | — |
Base clock | 1132 MHz | 1237 MHz |
---|---|---|
Boost clock | 1627 MHz | 1500 MHz |
Mémoire clock | 848 MHz 1696 Mbps effective | 1750 MHz 14 Gbps effective |
Taille de la mémoire | 32 GB | 4 GB |
---|---|---|
Type de mémoire | HBM2 | GDDR6 |
Bus mémoire | 4096 bit | 128 bit |
Bande passante | 868.4 GB/s | 224.0 GB/s |
Shading units | 5120 | 2048 |
---|---|---|
TMUs | 320 | 64 |
ROPs | 128 | 40 |
Comptage SM | 80 | 16 |
Tensor cores | 640 | 64 |
Cache L1 | 128 KB (per SM) | 128 KB (per SM) |
Cache L2 | 6 MB | 2 MB |
RT cores | — | 16 |
Taux de pixel | 208.3 GPixel/s | 60.00 GPixel/s |
---|---|---|
Taux de texture | 520.6 GTexel/s | 96.00 GTexel/s |
FP16 (half) performance | 33.32 TFLOPS (2:1) | 6.144 TFLOPS (1:1) |
FP32 (float) performance | 16.66 TFLOPS | 6.144 TFLOPS |
FP64 (double) performance | 8.330 TFLOPS (1:2) | 96.00 GFLOPS (1:64) |
Taille Slot | Dual-slot | IGP |
---|---|---|
Longueur | 267 mm 10.5 inches | — |
Taille | 111 mm 4.4 inches | — |
TDP | 250 W | unknown |
Suggestions pour le PSU | 600 W | — |
Sorties | 4x DisplayPort | No outputs |
Connecteurs de puissance | 8-pin EPS | None |
Board number | PG500 SKU 500 | — |
DirectX | 12 (12_1) | 12 Ultimate (12_2) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 3.0 | 3.0 |
Vulkan | 1.2 | 1.2 |
CUDA | 7.0 | 8.6 |
Shader model | 6.6 | 6.6 |
Date de publication | — | 2021 |
---|---|---|
gpu.details.availability | — | 2021 |
Génération | — | Quadro Mobile (Ax000) |
Production | — | Active |
Bus interface | — | PCIe 4.0 x16 |