Nom du GPU | GA106 | TU117 |
---|---|---|
Architecture | Ampere | Turing |
Fonderie | Samsung | TSMC |
Taille du processus | 8 nm | 12 nm |
Transistors | 13,250 million | 4,700 million |
Taille des matrices | 276 mm² | 200 mm² |
Date de publication | Unknown | — |
---|---|---|
gpu.details.availability | 2021 | — |
Génération | Quadro Mobile (Ax000) | — |
Production | Active | — |
Bus interface | PCIe 4.0 x16 | — |
Base clock | 562 MHz | 1065 MHz |
---|---|---|
Boost clock | 1200 MHz | 1395 MHz |
Mémoire clock | 1500 MHz 12 Gbps effective | 1250 MHz 10 Gbps effective |
Taille de la mémoire | 6 GB | 4 GB |
---|---|---|
Type de mémoire | GDDR6 | GDDR6 |
Bus mémoire | 192 bit | 128 bit |
Bande passante | 288.0 GB/s | 160.0 GB/s |
Shading units | 3328 | 896 |
---|---|---|
TMUs | 104 | 56 |
ROPs | 48 | 32 |
Comptage SM | 26 | 14 |
Tensor cores | 104 | — |
RT cores | 26 | — |
Cache L1 | 128 KB (per SM) | 64 KB (per SM) |
Cache L2 | 3 MB | 1024 KB |
Taux de pixel | 57.60 GPixel/s | 44.64 GPixel/s |
---|---|---|
Taux de texture | 124.8 GTexel/s | 78.12 GTexel/s |
FP16 (half) performance | 7.987 TFLOPS (1:1) | 5.000 TFLOPS (2:1) |
FP32 (float) performance | 7.987 TFLOPS | 2.500 TFLOPS |
FP64 (double) performance | 124.8 GFLOPS (1:64) | 78.12 GFLOPS (1:32) |
Taille Slot | Dual-slot | Single-slot |
---|---|---|
TDP | 70 W | 50 W |
Sorties | 4x mini-DisplayPort | 4x mini-DisplayPort |
Connecteurs de puissance | None | None |
Longueur | 167 mm 6.6 inches | — |
Taille | 69 mm 2.7 inches | — |
Suggestions pour le PSU | 250 W | 250 W |
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 | 7.5 |
Shader model | 6.6 | 6.6 |
Date de publication | Aug 10th, 2021 | May 6th, 2021 |
---|---|---|
gpu.details.availability | Oct, 2021 | — |
Génération | Quadro | Quadro |
Production | Active | Active |
Prix de lancement | 449 USD | — |
Bus interface | PCIe 4.0 x16 | PCIe 3.0 x16 |