GPU Name | Kaby Lake GT2 | GK104 |
---|---|---|
Architektur | Generation 9.5 | Kepler |
Hersteller | Intel | TSMC |
Prozessgröße | 14 nm++ | 28 nm |
Transistoren | unknown | 3,540 million |
Chipgröße | unknown | 294 mm² |
Veröffentlichungsdatum | Sep 1st, 2017 | — |
---|---|---|
Generation | HD Graphics-M (Kaby Lake Refresh) | — |
Produktion | Active | — |
Businterface | Ring Bus | — |
Reviews | 1 in our database | — |
Basis-Taktfrequenz | 300 MHz | — |
---|---|---|
Boost-Takt | 1000 MHz | — |
Speicher-Taktung | System Shared | 1250 MHz 5 Gbps effective |
GPU-Taktung | — | 745 MHz |
Speichergröße | System Shared | 512 MB |
---|---|---|
Speichertyp | System Shared | GDDR5 |
Speicherbus | System Shared | 256 bit |
Bandbreite | System Dependent | 160.0 GB/s |
Shading-Einheiten | 192 | 1536 |
---|---|---|
TMUs | 24 | 128 |
ROPs | 3 | 32 |
Execution Units | 24 | — |
Anzahl SMX | — | 8 |
Cache L1 | — | 16 KB (per SMX) |
Cache L2 | — | 512 KB |
Pixelrate | 3.000 GPixel/s | 23.84 GPixel/s |
---|---|---|
Texturrate | 24.00 GTexel/s | 95.36 GTexel/s |
FP16 (half) Leistung | 768.0 GFLOPS (2:1) | — |
FP32 (float) Leistung | 384.0 GFLOPS | 2.289 TFLOPS |
FP64 (double) Leistung | 96.00 GFLOPS (1:4) | 95.36 GFLOPS (1:24) |
Steckplatzbreite | IGP | IGP |
---|---|---|
TDP | 15 W | 225 W |
Ausgabe | No outputs | No outputs |
Vorgeschlagenes Netzteil | — | 550 W |
DirectX | 12 (12_1) | 12 (11_0) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 3.0 | 3.0 |
Vulkan | 1.2 | 1.1 |
Shader-Modell | 6.4 | 5.1 |
CUDA | — | 3.0 |
Veröffentlichungsdatum | — | Jul 2nd, 2014 |
---|---|---|
Generation | — | GRID |
Produktion | — | End-of-life |
Originalpreis | — | 469 USD |
Businterface | — | PCIe 3.0 x16 |