Nom du GPU | Navi 12 | TU104 |
---|---|---|
GPU variant | Navi 12 | TU104-895-A1 |
Architecture | RDNA 1.0 | Turing |
Fonderie | TSMC | TSMC |
Taille du processus | 7 nm | 12 nm |
Transistors | unknown | 13,600 million |
Taille des matrices | unknown | 545 mm² |
Date de publication | Dec 1st, 2020 | Sep 13th, 2018 |
---|---|---|
Génération | Radeon Pro | Tesla |
Production | Active | Active |
Bus interface | PCIe 4.0 x16 | PCIe 3.0 x16 |
Base clock | 1000 MHz | 585 MHz |
---|---|---|
Boost clock | 1600 MHz | 1590 MHz |
Mémoire clock | 1000 MHz 2 Gbps effective | 1250 MHz 10 Gbps effective |
Taille de la mémoire | 8 GB | 16 GB |
---|---|---|
Type de mémoire | HBM2 | GDDR6 |
Bus mémoire | 2048 bit | 256 bit |
Bande passante | 512.0 GB/s | 320.0 GB/s |
Shading units | 2304 | 2560 |
---|---|---|
TMUs | 144 | 160 |
ROPs | 64 | 64 |
Compute units | 36 | — |
Cache L2 | 4 MB | 4 MB |
Comptage SM | — | 40 |
Tensor cores | — | 320 |
RT cores | — | 40 |
Cache L1 | — | 64 KB (per SM) |
Taux de pixel | 102.4 GPixel/s | 101.8 GPixel/s |
---|---|---|
Taux de texture | 230.4 GTexel/s | 254.4 GTexel/s |
FP16 (half) performance | 14.75 TFLOPS (2:1) | 65.13 TFLOPS (8:1) |
FP32 (float) performance | 7.373 TFLOPS | 8.141 TFLOPS |
FP64 (double) performance | 460.8 GFLOPS (1:16) | 254.4 GFLOPS (1:32) |
Taille Slot | Dual-slot | Single-slot |
---|---|---|
Longueur | 267 mm 10.5 inches | 168 mm 6.6 inches |
Taille | 111 mm 4.4 inches | — |
TDP | 225 W | 70 W |
Suggestions pour le PSU | 550 W | 250 W |
Sorties | No outputs | No outputs |
Connecteurs de puissance | 1x 8-pin | None |
Board number | — | PG183 SKU 200 |
DirectX | 12 (12_1) | 12 Ultimate (12_2) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 2.2 | 3.0 |
Vulkan | 1.2 | 1.2 |
Shader model | 6.5 | 6.6 |
CUDA | — | 7.5 |