Nom du GPU | GA102 | GF100 |
---|---|---|
GPU variant | GA102-300-A1 | GF100-850-A3 |
Architecture | Ampere | Fermi |
Fonderie | Samsung | TSMC |
Taille du processus | 8 nm | 40 nm |
Transistors | 28,300 million | 3,100 million |
Taille des matrices | 628 mm² | 529 mm² |
Date de publication | Sep 1st, 2020 | Feb 23rd, 2011 |
---|---|---|
Génération | GeForce 30 | Quadro |
Production | Active | End-of-life |
Prix de lancement | 1,499 USD | 2,499 USD |
Bus interface | PCIe 4.0 x16 | PCIe 2.0 x16 |
gpu.details.availability | Sep 24th, 2020 | — |
Prédécesseur | GeForce 20 | — |
Prix courant | Amazon / Newegg | — |
Critiques | 56 in our database | 26 in our database |
Base clock | 1395 MHz | — |
---|---|---|
Boost clock | 1695 MHz | — |
Mémoire clock | 1219 MHz 19.5 Gbps effective | 750 MHz 3 Gbps effective |
GPU clock | — | 513 MHz |
Shader clock | — | 1026 MHz |
Taille de la mémoire | 24 GB | 2.5 GB |
---|---|---|
Type de mémoire | GDDR6X | GDDR5 |
Bus mémoire | 384 bit | 320 bit |
Bande passante | 936.2 GB/s | 120.0 GB/s |
Shading units | 10496 | 352 |
---|---|---|
TMUs | 328 | 44 |
ROPs | 112 | 40 |
Comptage SM | 82 | 11 |
Tensor cores | 328 | — |
RT cores | 82 | — |
Cache L1 | 128 KB (per SM) | 64 KB (per SM) |
Cache L2 | 6 MB | 640 KB |
Taux de pixel | 189.8 GPixel/s | 11.29 GPixel/s |
---|---|---|
Taux de texture | 556.0 GTexel/s | 22.57 GTexel/s |
FP16 (half) performance | 35.58 TFLOPS (1:1) | — |
FP32 (float) performance | 35.58 TFLOPS | 722.3 GFLOPS |
FP64 (double) performance | 556.0 GFLOPS (1:64) | 361.2 GFLOPS (1:2) |
Taille Slot | Triple-slot | Dual-slot |
---|---|---|
Longueur | 336 mm 13.2 inches | 248 mm 9.8 inches |
Taille | 140 mm 5.5 inches | 111 mm 4.4 inches |
TDP | 350 W | 152 W |
Suggestions pour le PSU | 750 W | 450 W |
Sorties | 1x HDMI3x DisplayPort | 1x DVI2x DisplayPort |
Connecteurs de puissance | 1x 12-pin | 1x 6-pin |
Board number | PG132 SKU 10 | P2007 |
Taille | 61 mm 2.4 inches | — |
DirectX | 12 Ultimate (12_2) | 12 (11_0) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 3.0 | 1.1 |
Vulkan | 1.2 | — |
CUDA | 8.6 | 2.0 |
Shader model | 6.6 | 5.1 |