GPU Name | DG1 | GP108 |
---|---|---|
Architektur | Generation 12.1 | Pascal |
Hersteller | Intel | Samsung |
Prozessgröße | 10 nm | 14 nm |
Transistoren | unknown | 1,800 million |
Chipgröße | 95 mm² | 74 mm² |
GPU Variante | — | GP108-655-A1 (N17S-G3-A1) |
Veröffentlichungsdatum | Oct 31st, 2020 | Feb 10th, 2020 |
---|---|---|
Generation | Iris Xe Graphics-M (Tiger Lake) | GeForce MX (3xx) |
Produktion | Active | End-of-life |
Businterface | PCIe 4.0 x4 | PCIe 3.0 x4 |
Reviews | 1 in our database | — |
Basis-Taktfrequenz | 300 MHz | 1531 MHz |
---|---|---|
Boost-Takt | 1650 MHz | 1594 MHz |
Speicher-Taktung | 2133 MHz 4.3 Gbps effective | 1752 MHz 7 Gbps effective |
Speichergröße | 4 GB | 2 GB |
---|---|---|
Speichertyp | LPDDR4X | GDDR5 |
Speicherbus | 128 bit | 64 bit |
Bandbreite | 68.26 GB/s | 56.06 GB/s |
Shading-Einheiten | 768 | 384 |
---|---|---|
TMUs | 48 | 24 |
ROPs | 24 | 16 |
Execution Units | 96 | — |
Cache L2 | 1024 KB | 512 KB |
gpu.details.l3-cache | 16 MB | — |
Anzahl SM | — | 3 |
Cache L1 | — | 48 KB (per SM) |
Pixelrate | 39.60 GPixel/s | 25.50 GPixel/s |
---|---|---|
Texturrate | 79.20 GTexel/s | 38.26 GTexel/s |
FP16 (half) Leistung | 5.069 TFLOPS (2:1) | 19.13 GFLOPS (1:64) |
FP32 (float) Leistung | 2.534 TFLOPS | 1,224 GFLOPS |
FP64 (double) Leistung | 633.6 GFLOPS (1:4) | 38.26 GFLOPS (1:32) |
Steckplatzbreite | IGP | IGP |
---|---|---|
TDP | 25 W | 10 W |
Ausgabe | No outputs | No outputs |
Stromverbindung | — | None |
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 |