GPU Name | Coffee Lake GT2 | GP106 |
---|---|---|
Architektur | Generation 9.5 | Pascal |
Hersteller | Intel | TSMC |
Prozessgröße | 14 nm+++ | 16 nm |
Transistoren | unknown | 4,400 million |
Chipgröße | unknown | 200 mm² |
GPU Variante | — | GP106-875-A1 |
Veröffentlichungsdatum | Apr 3rd, 2018 | — |
---|---|---|
Generation | HD Graphics-M (Coffee Lake) | — |
Produktion | Active | — |
Businterface | Ring Bus | — |
Reviews | 1 in our database | — |
Basis-Taktfrequenz | 350 MHz | 1076 MHz |
---|---|---|
Boost-Takt | 1000 MHz | 1480 MHz |
Speicher-Taktung | System Shared | 1752 MHz 7 Gbps effective |
Speichergröße | System Shared | 5 GB |
---|---|---|
Speichertyp | System Shared | GDDR5 |
Speicherbus | System Shared | 160 bit |
Bandbreite | System Dependent | 140.2 GB/s |
Shading-Einheiten | 192 | 1024 |
---|---|---|
TMUs | 24 | 64 |
ROPs | 3 | 40 |
Execution Units | 24 | — |
Anzahl SM | — | 8 |
Cache L1 | — | 48 KB (per SM) |
Cache L2 | — | 1280 KB |
Pixelrate | 3.000 GPixel/s | 59.20 GPixel/s |
---|---|---|
Texturrate | 24.00 GTexel/s | 94.72 GTexel/s |
FP16 (half) Leistung | 768.0 GFLOPS (2:1) | 47.36 GFLOPS (1:64) |
FP32 (float) Leistung | 384.0 GFLOPS | 3.031 TFLOPS |
FP64 (double) Leistung | 96.00 GFLOPS (1:4) | 94.72 GFLOPS (1:32) |
Steckplatzbreite | IGP | Single-slot |
---|---|---|
TDP | 15 W | 75 W |
Ausgabe | No outputs | 4x DisplayPort |
Länge | — | 196 mm 7.7 inches |
Breite | — | 111 mm 4.4 inches |
Vorgeschlagenes Netzteil | — | 250 W |
Stromverbindung | — | None |
Board-Nummer | — | PG410 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 6th, 2017 |
---|---|---|
Generation | — | Quadro |
Produktion | — | End-of-life |
Businterface | — | PCIe 3.0 x16 |