Nom du GPU | GP102 | GA102 |
---|---|---|
Architecture | Pascal | Ampere |
Fonderie | TSMC | Samsung |
Taille du processus | 16 nm | 8 nm |
Transistors | 11,800 million | 28,300 million |
Taille des matrices | 471 mm² | 628 mm² |
GPU variant | — | GA102-350-A1 |
Date de publication | Never Released | Unknown |
---|---|---|
Génération | GeForce 10 | GeForce 30 |
Prédécesseur | GeForce 900 | GeForce 20 |
Successeur | GeForce 20 | — |
Production | End-of-life | Unreleased |
Bus interface | PCIe 3.0 x16 | PCIe 4.0 x16 |
Critiques | 149 in our database | 55 in our database |
gpu.details.availability | — | 2022 |
Prix de lancement | — | 1,699 USD |
Base clock | 1557 MHz | 1560 MHz |
---|---|---|
Boost clock | 1670 MHz | 1860 MHz |
Mémoire clock | 1376 MHz 11 Gbps effective | 1325 MHz 21.2 Gbps effective |
Taille de la mémoire | 10 GB | 24 GB |
---|---|---|
Type de mémoire | GDDR5X | GDDR6X |
Bus mémoire | 320 bit | 384 bit |
Bande passante | 440.3 GB/s | 1,018 GB/s |
Shading units | 3200 | 10752 |
---|---|---|
TMUs | 200 | 336 |
ROPs | 80 | 112 |
Comptage SM | 25 | 84 |
Cache L1 | 48 KB (per SM) | 128 KB (per SM) |
Cache L2 | 2.5 MB | 6 MB |
Tensor cores | — | 336 |
RT cores | — | 84 |
Taux de pixel | 133.6 GPixel/s | 208.3 GPixel/s |
---|---|---|
Taux de texture | 334.0 GTexel/s | 625.0 GTexel/s |
FP16 (half) performance | 167.0 GFLOPS (1:64) | 40.00 TFLOPS (1:1) |
FP32 (float) performance | 10.69 TFLOPS | 40.00 TFLOPS |
FP64 (double) performance | 334.0 GFLOPS (1:32) | 625.0 GFLOPS (1:64) |
Taille Slot | Dual-slot | Triple-slot |
---|---|---|
Longueur | 267 mm 10.5 inches | 336 mm 13.2 inches |
Taille | 112 mm 4.4 inches | 140 mm 5.5 inches |
Taille | 40 mm 1.6 inches | 61 mm 2.4 inches |
TDP | 250 W | 450 W |
Suggestions pour le PSU | 600 W | 850 W |
Sorties | 1x HDMI3x DisplayPort | 1x HDMI3x DisplayPort |
Connecteurs de puissance | 1x 6-pin + 1x 8-pin | 1x 12-pin |
Board number | PG611 SKU 10 | PG132 SKU |
DirectX | 12 (12_1) | 12 Ultimate (12_2) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 3.0 | 3.0 |
Vulkan | 1.2 | 1.2 |
CUDA | 6.1 | 8.6 |
Shader model | 6.4 | 6.6 |