GPU Name | Baffin | GK106 |
---|---|---|
GPU Variante | Baffin LE | — |
Architektur | GCN 4.0 | Kepler |
Hersteller | GlobalFoundries | TSMC |
Prozessgröße | 14 nm | 28 nm |
Transistoren | 3,000 million | 2,540 million |
Chipgröße | 123 mm² | 221 mm² |
Veröffentlichungsdatum | Oct 13th, 2017 | Mar 1st, 2013 |
---|---|---|
Generation | Polaris | Quadro |
Vorgänger | Arctic Islands | — |
Nachfolger | Vega | — |
Produktion | Active | End-of-life |
Originalpreis | 79 USD | 1,269 USD |
Businterface | PCIe 3.0 x8 | PCIe 2.0 x16 |
Reviews | — | 26 in our database |
Basis-Taktfrequenz | 1019 MHz | — |
---|---|---|
Boost-Takt | 1071 MHz | — |
Speicher-Taktung | 1500 MHz 6 Gbps effective | 1404 MHz 5.6 Gbps effective |
GPU-Taktung | — | 810 MHz |
Speichergröße | 2 GB | 3 GB |
---|---|---|
Speichertyp | GDDR5 | GDDR5 |
Speicherbus | 128 bit | 192 bit |
Bandbreite | 96.00 GB/s | 134.8 GB/s |
Shading-Einheiten | 512 | 768 |
---|---|---|
TMUs | 32 | 64 |
ROPs | 16 | 24 |
Compute Units | 8 | — |
Cache L1 | 16 KB (per CU) | 16 KB (per SMX) |
Cache L2 | 512 KB | 384 KB |
Anzahl SMX | — | 4 |
Pixelrate | 17.14 GPixel/s | 12.96 GPixel/s |
---|---|---|
Texturrate | 34.27 GTexel/s | 51.84 GTexel/s |
FP16 (half) Leistung | 1,097 GFLOPS (1:1) | — |
FP32 (float) Leistung | 1,097 GFLOPS | 1,244 GFLOPS |
FP64 (double) Leistung | 68.54 GFLOPS (1:16) | 51.84 GFLOPS (1:24) |
Steckplatzbreite | Dual-slot | Single-slot |
---|---|---|
Länge | 145 mm 5.7 inches | 241 mm 9.5 inches |
TDP | 50 W | 80 W |
Vorgeschlagenes Netzteil | 250 W | 250 W |
Ausgabe | 1x DVI1x HDMI1x DisplayPort | 1x DVI2x DisplayPort |
Stromverbindung | None | 1x 6-pin |
Board-Nummer | D090-01 | P2030 |
Breite | — | 111 mm 4.4 inches |
DirectX | 12 (12_0) | 12 (11_0) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 2.1 | 3.0 |
Vulkan | 1.2 | 1.1 |
Shader-Modell | 6.4 | 5.1 |
CUDA | — | 3.0 |