Nom du GPU | Navi 10 | TU104 |
---|---|---|
Architecture | RDNA 1.0 | Turing |
Fonderie | TSMC | TSMC |
Taille du processus | 7 nm | 12 nm |
Transistors | 10,300 million | 13,600 million |
Taille des matrices | 251 mm² | 545 mm² |
GPU variant | Navi 10 XTA | N19E-Q5-A1 |
Date de publication | Aug 4th, 2020 | — |
---|---|---|
Génération | Radeon Pro Mac | — |
Production | Active | — |
Bus interface | PCIe 4.0 x16 | — |
Base clock | 1243 MHz | 1365 MHz |
---|---|---|
Boost clock | 1499 MHz | 1770 MHz |
Mémoire clock | 1500 MHz 12 Gbps effective | 1750 MHz 14 Gbps effective |
Taille de la mémoire | 16 GB | 16 GB |
---|---|---|
Type de mémoire | GDDR6 | GDDR6 |
Bus mémoire | 256 bit | 256 bit |
Bande passante | 384.0 GB/s | 448.0 GB/s |
Shading units | 2560 | 3072 |
---|---|---|
TMUs | 160 | 192 |
ROPs | 64 | 64 |
Compute units | 40 | — |
Cache L2 | 4 MB | 4 MB |
Comptage SM | — | 48 |
Tensor cores | — | 384 |
RT cores | — | 48 |
Cache L1 | — | 64 KB (per SM) |
Taux de pixel | 95.94 GPixel/s | 113.3 GPixel/s |
---|---|---|
Taux de texture | 239.8 GTexel/s | 339.8 GTexel/s |
FP16 (half) performance | 15.35 TFLOPS (2:1) | 21.75 TFLOPS (2:1) |
FP32 (float) performance | 7.675 TFLOPS | 10.87 TFLOPS |
FP64 (double) performance | 479.7 GFLOPS (1:16) | 339.8 GFLOPS (1:32) |
Taille Slot | IGP | IGP |
---|---|---|
TDP | 130 W | 110 W |
Suggestions pour le PSU | 300 W | — |
Sorties | No outputs | No outputs |
Connecteurs de puissance | None | None |
DirectX | 12 (12_1) | 12 Ultimate (12_2) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 2.1 | 3.0 |
Vulkan | 1.2 | 1.2 |
Shader model | 6.5 | 6.6 |
CUDA | — | 7.5 |
Date de publication | — | May 27th, 2019 |
---|---|---|
Génération | — | Quadro Mobile (Tx000) |
Production | — | Active |
Bus interface | — | PCIe 3.0 x16 |