AMD Radeon HD 6970M vs AMD Radeon Pro WX 4130 Mobile
Grafikprozessor
| GPU Name | Blackcomb | Baffin |
|---|---|---|
| GPU Variante | Blackcomb XT (216-0811000) | Baffin LE |
| Architektur | TeraScale 2 | GCN 4.0 |
| Hersteller | TSMC | GlobalFoundries |
| Prozessgröße | 40 nm | 14 nm |
| Transistoren | 1,700 million | 3,000 million |
| Chipgröße | 212 mm² | 123 mm² |
Mobile Grafik
| Veröffentlichungsdatum | Jan 4th, 2011 | Mar 1st, 2017 |
|---|---|---|
| Generation | Vancouver (HD 6900M) | Radeon Pro Mobile (WX x100) |
| Produktion | End-of-life | Active |
| Businterface | MXM-B (3.0) | PCIe 3.0 x8 |
| Vorgänger | Manhattan | — |
| Nachfolger | London | — |
Takt-Geschwindigkeiten
| GPU-Taktung | 680 MHz | — |
|---|---|---|
| Speicher-Taktung | 900 MHz 3.6 Gbps effective | 1500 MHz 6 Gbps effective |
| Basis-Taktfrequenz | — | 1002 MHz |
| Boost-Takt | — | 1053 MHz |
Speicher
| Speichergröße | 1024 MB | 4 GB |
|---|---|---|
| Speichertyp | GDDR5 | GDDR5 |
| Speicherbus | 256 bit | 128 bit |
| Bandbreite | 115.2 GB/s | 96.00 GB/s |
Render-Konfiguration
| Shading-Einheiten | 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 |
Theoretische Leistung
| Pixelrate | 21.76 GPixel/s | 16.85 GPixel/s |
|---|---|---|
| Texturrate | 32.64 GTexel/s | 42.12 GTexel/s |
| FP32 (float) Leistung | 1,306 GFLOPS | 1,348 GFLOPS |
| FP16 (half) Leistung | — | 1,348 GFLOPS (1:1) |
| FP64 (double) Leistung | — | 84.24 GFLOPS (1:16) |
Boarddesign
| Steckplatzbreite | MXM Module | MXM Module |
|---|---|---|
| TDP | 75 W | 50 W |
| Ausgabe | No outputs | No outputs |
| Stromverbindung | None | None |
| Board-Nummer | C296 | — |
Grafik-Features
| DirectX | 11.2 (11_0) | 12 (12_0) |
|---|---|---|
| OpenGL | 4.4 | 4.6 |
| OpenCL | 1.2 | 2.1 |
| Vulkan | — | 1.2 |
| Shader-Modell | 5.0 | 6.4 |
