Nom du GPU | GA104 | TU102 |
---|---|---|
GPU variant | GA104-200-A1 | TU102-875-A1 |
Architecture | Ampere | Turing |
Fonderie | Samsung | TSMC |
Taille du processus | 8 nm | 12 nm |
Transistors | 17,400 million | 18,600 million |
Taille des matrices | 392 mm² | 754 mm² |
Date de publication | Dec 1st, 2020 | Aug 13th, 2018 |
---|---|---|
gpu.details.availability | Dec 2nd, 2020 | — |
Génération | GeForce 30 | Quadro |
Prédécesseur | GeForce 20 | — |
Production | Active | Active |
Prix de lancement | 399 USD | 9,999 USD |
Bus interface | PCIe 4.0 x16 | PCIe 3.0 x16 |
Critiques | 64 in our database | — |
Base clock | 1410 MHz | 1230 MHz |
---|---|---|
Boost clock | 1665 MHz | 1620 MHz |
Mémoire clock | 1750 MHz 14 Gbps effective | 1750 MHz 14 Gbps effective |
Taille de la mémoire | 8 GB | 48 GB |
---|---|---|
Type de mémoire | GDDR6 | GDDR6 |
Bus mémoire | 256 bit | 384 bit |
Bande passante | 448.0 GB/s | 672.0 GB/s |
Shading units | 4864 | 4608 |
---|---|---|
TMUs | 152 | 288 |
ROPs | 80 | 96 |
Comptage SM | 38 | 72 |
Tensor cores | 152 | 576 |
RT cores | 38 | 72 |
Cache L1 | 128 KB (per SM) | 64 KB (per SM) |
Cache L2 | 4 MB | 6 MB |
Taux de pixel | 133.2 GPixel/s | 155.5 GPixel/s |
---|---|---|
Taux de texture | 253.1 GTexel/s | 466.6 GTexel/s |
FP16 (half) performance | 16.20 TFLOPS (1:1) | 29.86 TFLOPS (2:1) |
FP32 (float) performance | 16.20 TFLOPS | 14.93 TFLOPS |
FP64 (double) performance | 253.1 GFLOPS (1:64) | 466.6 GFLOPS (1:32) |
Taille Slot | Dual-slot | Dual-slot |
---|---|---|
Longueur | 242 mm 9.5 inches | 267 mm 10.5 inches |
Taille | 112 mm 4.4 inches | 111 mm 4.4 inches |
TDP | 200 W | 260 W |
Suggestions pour le PSU | 550 W | 600 W |
Sorties | 1x HDMI3x DisplayPort | No outputs |
Connecteurs de puissance | 1x 12-pin | 1x 6-pin + 1x 8-pin |
Board number | PG142 SKU 20 | — |
DirectX | 12 Ultimate (12_2) | 12 Ultimate (12_2) |
---|---|---|
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 |