GPU Name | Kaby Lake GT2 | GP107 |
---|---|---|
Architektur | Generation 9.5 | Pascal |
Hersteller | Intel | Samsung |
Prozessgröße | 14 nm++ | 14 nm |
Transistoren | unknown | 3,300 million |
Chipgröße | unknown | 132 mm² |
GPU Variante | — | GP107-860-A1 |
Veröffentlichungsdatum | Aug 30th, 2016 | — |
---|---|---|
Generation | HD Graphics-M (Kaby Lake) | — |
Produktion | Active | — |
Businterface | Ring Bus | — |
Reviews | 1 in our database | — |
Basis-Taktfrequenz | 350 MHz | 1354 MHz |
---|---|---|
Boost-Takt | 1000 MHz | 1392 MHz |
Speicher-Taktung | System Shared | 1502 MHz 6 Gbps effective |
Speichergröße | System Shared | 4 GB |
---|---|---|
Speichertyp | System Shared | GDDR5 |
Speicherbus | System Shared | 128 bit |
Bandbreite | System Dependent | 96.13 GB/s |
Shading-Einheiten | 192 | 512 |
---|---|---|
TMUs | 24 | 32 |
ROPs | 3 | 16 |
Execution Units | 24 | — |
Anzahl SM | — | 4 |
Cache L1 | — | 48 KB (per SM) |
Cache L2 | — | 1024 KB |
Pixelrate | 3.000 GPixel/s | 22.27 GPixel/s |
---|---|---|
Texturrate | 24.00 GTexel/s | 44.54 GTexel/s |
FP16 (half) Leistung | 768.0 GFLOPS (2:1) | 22.27 GFLOPS (1:64) |
FP32 (float) Leistung | 384.0 GFLOPS | 1,425 GFLOPS |
FP64 (double) Leistung | 96.00 GFLOPS (1:4) | 44.54 GFLOPS (1:32) |
Steckplatzbreite | IGP | Single-slot |
---|---|---|
TDP | 15 W | 47 W |
Ausgabe | No outputs | 4x mini-DisplayPort |
Länge | — | 150 mm 5.9 inches |
Breite | — | 69 mm 2.7 inches |
Vorgeschlagenes Netzteil | — | 200 W |
Stromverbindung | — | None |
Board-Nummer | — | PG212 SKU 502 |
DirectX | 12 (12_1) | 12 (12_1) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 3.0 | 3.0 |
Vulkan | 1.2 | 1.2 |
Shader-Modell | 6.4 | 6.4 |
CUDA | — | 6.1 |
Veröffentlichungsdatum | — | Feb 7th, 2017 |
---|---|---|
Generation | — | Quadro |
Produktion | — | End-of-life |
Businterface | — | PCIe 3.0 x16 |