Nom du GPU | Navi 14 | GM107 |
---|---|---|
GPU variant | Navi 14 PRO XTM | N16P-Q3-A2 |
Architecture | RDNA 1.0 | Maxwell |
Fonderie | TSMC | TSMC |
Taille du processus | 7 nm | 28 nm |
Transistors | 6,400 million | 1,870 million |
Taille des matrices | 158 mm² | 148 mm² |
Date de publication | Feb 10th, 2020 | Dec 3rd, 2015 |
---|---|---|
Génération | Radeon Pro Mobile (W5x00M) | Quadro Mobile (Mx000M) |
Production | Active | End-of-life |
Bus interface | PCIe 4.0 x8 | MXM-A (3.0) |
Critiques | — | 26 in our database |
Base clock | 1000 MHz | 1029 MHz |
---|---|---|
Boost clock | 1700 MHz | 1098 MHz |
Mémoire clock | 1750 MHz 14 Gbps effective | 1253 MHz 5 Gbps effective |
Taille de la mémoire | 4 GB | 4 GB |
---|---|---|
Type de mémoire | GDDR6 | GDDR5 |
Bus mémoire | 128 bit | 128 bit |
Bande passante | 224.0 GB/s | 80.19 GB/s |
Shading units | 1408 | 640 |
---|---|---|
TMUs | 88 | 40 |
ROPs | 32 | 16 |
Compute units | 22 | — |
Cache L2 | 2 MB | 2 MB |
Comptage SMM | — | 5 |
Cache L1 | — | 64 KB (per SMM) |
Taux de pixel | 54.40 GPixel/s | 17.57 GPixel/s |
---|---|---|
Taux de texture | 149.6 GTexel/s | 43.92 GTexel/s |
FP16 (half) performance | 9.574 TFLOPS (2:1) | — |
FP32 (float) performance | 4.787 TFLOPS | 1,405 GFLOPS |
FP64 (double) performance | 299.2 GFLOPS (1:16) | 43.92 GFLOPS (1:32) |
TDP | 85 W | 55 W |
---|---|---|
Sorties | No outputs | No outputs |
Connecteurs de puissance | None | None |
Taille Slot | — | MXM Module |
DirectX | 12 (12_1) | 12 (11_0) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 2.1 | 3.0 |
Vulkan | 1.2 | 1.1 |
Shader model | 6.5 | 5.1 |
CUDA | — | 5.0 |