Nom du GPU | Vega 20 | GP107 |
---|---|---|
GPU variant | Vega 20 XT | N17P-G1-A1 |
Architecture | GCN 5.1 | Pascal |
Fonderie | TSMC | Samsung |
Taille du processus | 7 nm | 14 nm |
Transistors | 13,230 million | 3,300 million |
Taille des matrices | 331 mm² | 132 mm² |
Date de publication | Unknown | — |
---|---|---|
Génération | Radeon Pro Mac | — |
Production | Active | — |
Bus interface | PCIe 3.0 x16 | — |
Base clock | 1400 MHz | 1152 MHz |
---|---|---|
Boost clock | 1720 MHz | 1291 MHz |
Mémoire clock | 1000 MHz 2 Gbps effective | 1752 MHz 7 Gbps effective |
Taille de la mémoire | 32 GB | 4 GB |
---|---|---|
Type de mémoire | HBM2 | GDDR5 |
Bus mémoire | 4096 bit | 128 bit |
Bande passante | 1,024 GB/s | 112.1 GB/s |
Shading units | 4096 | 768 |
---|---|---|
TMUs | 256 | 48 |
ROPs | 64 | 32 |
Compute units | 64 | — |
Cache L1 | 16 KB (per CU) | 48 KB (per SM) |
Cache L2 | 4 MB | 1024 KB |
Comptage SM | — | 6 |
Taux de pixel | 110.1 GPixel/s | 41.31 GPixel/s |
---|---|---|
Taux de texture | 440.3 GTexel/s | 61.97 GTexel/s |
FP16 (half) performance | 28.18 TFLOPS (2:1) | 30.98 GFLOPS (1:64) |
FP32 (float) performance | 14.09 TFLOPS | 1.983 TFLOPS |
FP64 (double) performance | 880.6 GFLOPS (1:16) | 61.97 GFLOPS (1:32) |
Taille Slot | Quad-slot | — |
---|---|---|
TDP | 475 W | 75 W |
Suggestions pour le PSU | 850 W | — |
Sorties | 1x HDMI4x Thunderbolt | No outputs |
Connecteurs de puissance | None | None |
Board number | MW732ZM/A | E2904 SKU 1 |
DirectX | 12 (12_1) | 12 (12_1) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 2.1 | 3.0 |
Vulkan | 1.2 | 1.2 |
Shader model | 6.4 | 6.4 |
CUDA | — | 6.1 |
Date de publication | — | Jan 3rd, 2018 |
---|---|---|
Génération | — | GeForce 10 Mobile |
Production | — | End-of-life |
Bus interface | — | PCIe 3.0 x16 |
Critiques | — | 58 in our database |
Prédécesseur | — | GeForce 900M |
Successeur | — | GeForce 20 Mobile |