Nom du GPU | Thames | Vega 10 |
---|---|---|
GPU variant | Thames XTX | Vega 10 XL (215-0894216) |
Architecture | TeraScale 2 | GCN 5.0 |
Fonderie | TSMC | GlobalFoundries |
Taille du processus | 40 nm | 14 nm |
Transistors | 716 million | 12,500 million |
Taille des matrices | 104 mm² | 495 mm² |
Date de publication | Jan 7th, 2013 | Jun 1st, 2018 |
---|---|---|
Génération | London (HD 7600M) | Mobility Radeon (Vega) |
Production | End-of-life | Active |
Bus interface | PCIe 2.0 x16 | PCIe 3.0 x16 |
Prédécesseur | Vancouver | Crystal System |
Successeur | Solar System | — |
Critiques | — | 23 in our database |
GPU clock | 725 MHz | — |
---|---|---|
Mémoire clock | 900 MHz 3.6 Gbps effective | 800 MHz 1600 Mbps effective |
Base clock | — | 1138 MHz |
Boost clock | — | 1301 MHz |
Taille de la mémoire | 2 GB | 8 GB |
---|---|---|
Type de mémoire | GDDR5 | HBM2 |
Bus mémoire | 128 bit | 2048 bit |
Bande passante | 57.60 GB/s | 409.6 GB/s |
Shading units | 480 | 3584 |
---|---|---|
TMUs | 24 | 224 |
ROPs | 8 | 64 |
Compute units | 6 | 56 |
Cache L1 | 8 KB (per CU) | 16 KB (per CU) |
Cache L2 | 256 KB | 4 MB |
Taux de pixel | 5.800 GPixel/s | 83.26 GPixel/s |
---|---|---|
Taux de texture | 17.40 GTexel/s | 291.4 GTexel/s |
FP32 (float) performance | 696.0 GFLOPS | 9.326 TFLOPS |
FP16 (half) performance | — | 18.65 TFLOPS (2:1) |
FP64 (double) performance | — | 582.8 GFLOPS (1:16) |
TDP | 25 W | 120 W |
---|---|---|
Sorties | No outputs | 1x HDMI3x DisplayPort |
Taille Slot | — | MXM Module |
Longueur | — | 105 mm 4.1 inches |
Connecteurs de puissance | — | None |
DirectX | 11.2 (11_0) | 12 (12_1) |
---|---|---|
OpenGL | 4.4 | 4.6 |
OpenCL | 1.2 | 2.1 |
Vulkan | — | 1.2 |
Shader model | 5.0 | 6.4 |