Nom du GPU | GA100 | TU104 |
---|---|---|
Architecture | Ampere | Turing |
Fonderie | TSMC | TSMC |
Taille du processus | 7 nm | 12 nm |
Transistors | 54,200 million | 13,600 million |
Taille des matrices | 826 mm² | 545 mm² |
GPU variant | — | TU104-895-A1 |
Date de publication | Apr 12th, 2021 | Sep 13th, 2018 |
---|---|---|
gpu.details.availability | 2021 | — |
Génération | Tesla | Tesla |
Production | Active | Active |
Bus interface | PCIe 4.0 x16 | PCIe 3.0 x16 |
Base clock | 930 MHz | 585 MHz |
---|---|---|
Boost clock | 1440 MHz | 1590 MHz |
Mémoire clock | 1215 MHz 2.4 Gbps effective | 1250 MHz 10 Gbps effective |
Taille de la mémoire | 24 GB | 16 GB |
---|---|---|
Type de mémoire | HBM2 | GDDR6 |
Bus mémoire | 3072 bit | 256 bit |
Bande passante | 933.1 GB/s | 320.0 GB/s |
Shading units | 3584 | 2560 |
---|---|---|
TMUs | 224 | 160 |
ROPs | 96 | 64 |
Comptage SM | 56 | 40 |
Tensor cores | 224 | 320 |
Cache L1 | 192 KB (per SM) | 64 KB (per SM) |
Cache L2 | 24 MB | 4 MB |
RT cores | — | 40 |
Taux de pixel | 138.2 GPixel/s | 101.8 GPixel/s |
---|---|---|
Taux de texture | 322.6 GTexel/s | 254.4 GTexel/s |
FP16 (half) performance | 10.32 TFLOPS (1:1) | 65.13 TFLOPS (8:1) |
FP32 (float) performance | 10.32 TFLOPS | 8.141 TFLOPS |
FP64 (double) performance | 5.161 TFLOPS (1:2) | 254.4 GFLOPS (1:32) |
Taille Slot | Dual-slot | Single-slot |
---|---|---|
Longueur | 267 mm 10.5 inches | 168 mm 6.6 inches |
Taille | 112 mm 4.4 inches | — |
TDP | 165 W | 70 W |
Suggestions pour le PSU | 450 W | 250 W |
Sorties | No outputs | No outputs |
Connecteurs de puissance | 8-pin EPS | None |
Board number | P1001 SKU 205 | PG183 SKU 200 |
DirectX | — | 12 Ultimate (12_2) |
---|---|---|
OpenGL | — | 4.6 |
OpenCL | 3.0 | 3.0 |
Vulkan | — | 1.2 |
CUDA | 8.0 | 7.5 |
Shader model | — | 6.6 |