Nom du GPU | Blackcomb | Baffin |
---|---|---|
GPU variant | Blackcomb XT (216-0811000) | Baffin LE |
Architecture | TeraScale 2 | GCN 4.0 |
Fonderie | TSMC | GlobalFoundries |
Taille du processus | 40 nm | 14 nm |
Transistors | 1,700 million | 3,000 million |
Taille des matrices | 212 mm² | 123 mm² |
Date de publication | Jan 4th, 2011 | — |
---|---|---|
Génération | Vancouver (HD 6900M) | — |
Production | End-of-life | — |
Bus interface | MXM-B (3.0) | — |
Prédécesseur | Manhattan | — |
Successeur | London | — |
GPU clock | 680 MHz | — |
---|---|---|
Mémoire clock | 900 MHz 3.6 Gbps effective | 1500 MHz 6 Gbps effective |
Base clock | — | 1019 MHz |
Boost clock | — | 1071 MHz |
Taille de la mémoire | 1024 MB | 2 GB |
---|---|---|
Type de mémoire | GDDR5 | GDDR5 |
Bus mémoire | 256 bit | 128 bit |
Bande passante | 115.2 GB/s | 96.00 GB/s |
Shading units | 960 | 640 |
---|---|---|
TMUs | 48 | 40 |
ROPs | 32 | 16 |
Compute units | 12 | 10 |
Cache L1 | 8 KB (per CU) | 16 KB (per CU) |
Cache L2 | 512 KB | 1024 KB |
Taux de pixel | 21.76 GPixel/s | 17.14 GPixel/s |
---|---|---|
Taux de texture | 32.64 GTexel/s | 42.84 GTexel/s |
FP32 (float) performance | 1,306 GFLOPS | 1,371 GFLOPS |
FP16 (half) performance | — | 1,371 GFLOPS (1:1) |
FP64 (double) performance | — | 85.68 GFLOPS (1:16) |
Taille Slot | MXM Module | Dual-slot |
---|---|---|
TDP | 75 W | 60 W |
Sorties | No outputs | 1x DVI1x HDMI1x DisplayPort |
Connecteurs de puissance | None | None |
Board number | C296 | D090-21 |
Longueur | — | 145 mm 5.7 inches |
Suggestions pour le PSU | — | 250 W |
DirectX | 11.2 (11_0) | 12 (12_0) |
---|---|---|
OpenGL | 4.4 | 4.6 |
OpenCL | 1.2 | 2.1 |
Vulkan | — | 1.2 |
Shader model | 5.0 | 6.4 |
Date de publication | — | Apr 11th, 2018 |
---|---|---|
Génération | — | Polaris |
Production | — | Active |
Bus interface | — | PCIe 3.0 x8 |
Prédécesseur | — | Polaris |
Successeur | — | Vega |