Nom du GPU | Baffin | GA100 |
---|---|---|
GPU variant | Baffin XT | — |
Architecture | GCN 4.0 | Ampere |
Fonderie | GlobalFoundries | TSMC |
Taille du processus | 14 nm | 7 nm |
Transistors | 3,000 million | 54,200 million |
Taille des matrices | 123 mm² | 826 mm² |
Date de publication | Mar 1st, 2017 | — |
---|---|---|
Génération | Radeon Pro Mobile (WX x100) | — |
Production | Active | — |
Bus interface | PCIe 3.0 x8 | — |
Base clock | 1002 MHz | 900 MHz |
---|---|---|
Boost clock | 1201 MHz | 1005 MHz |
Mémoire clock | 1500 MHz 6 Gbps effective | 1215 MHz 2.4 Gbps effective |
Taille de la mémoire | 4 GB | 48 GB |
---|---|---|
Type de mémoire | GDDR5 | HBM2E |
Bus mémoire | 128 bit | 6144 bit |
Bande passante | 96.00 GB/s | 1,866 GB/s |
Shading units | 1024 | 6912 |
---|---|---|
TMUs | 64 | 432 |
ROPs | 16 | 192 |
Compute units | 16 | — |
Cache L1 | 16 KB (per CU) | 192 KB (per SM) |
Cache L2 | 1024 KB | 48 MB |
Comptage SM | — | 108 |
Tensor cores | — | 432 |
Taux de pixel | 19.22 GPixel/s | 193.0 GPixel/s |
---|---|---|
Taux de texture | 76.86 GTexel/s | 434.2 GTexel/s |
FP16 (half) performance | 2.460 TFLOPS (1:1) | 55.57 TFLOPS (4:1) |
FP32 (float) performance | 2.460 TFLOPS | 13.89 TFLOPS |
FP64 (double) performance | 153.7 GFLOPS (1:16) | 6.947 TFLOPS (1:2) |
Taille Slot | MXM Module | IGP |
---|---|---|
TDP | 50 W | 400 W |
Sorties | No outputs | No outputs |
Connecteurs de puissance | None | None |
Suggestions pour le PSU | — | 800 W |
DirectX | 12 (12_0) | — |
---|---|---|
OpenGL | 4.6 | — |
OpenCL | 2.1 | 3.0 |
Vulkan | 1.2 | — |
Shader model | 6.4 | — |
CUDA | — | 8.0 |
Date de publication | — | May 14th, 2020 |
---|---|---|
Génération | — | GRID |
Production | — | Active |
Bus interface | — | PCIe 4.0 x16 |