GPU model | Amber Lake GT2 | GP108 |
---|---|---|
Architecture | Generation 9.5 | Pascal |
Foundry | Intel | Samsung |
Manufacturing process | 14 nm | 14 nm |
Number of transistors | unknown | 1,800 million |
Die size | unknown | 74 mm² |
GPU variant | — | GP108-655-A1 (N17S-G3-A1) |
Release date | Aug 21st, 2019 | — |
---|---|---|
Generation | HD Graphics-T (Amber Lake) | — |
Production | Active | — |
Interface | Ring Bus | — |
Reviews | 1 in our database | — |
Base clock | 300 MHz | 1531 MHz |
---|---|---|
Boost clock | 1050 MHz | 1594 MHz |
Memory clock | System Shared | 1752 MHz 7 Gbps effective |
Memory size | System Shared | 2 GB |
---|---|---|
Memory type | System Shared | GDDR5 |
Memory bus width | System Shared | 64 bit |
Bandwidth | System Dependent | 56.06 GB/s |
Shading units | 192 | 384 |
---|---|---|
TMUs | 24 | 24 |
ROPs | 3 | 16 |
Execution units | 24 | — |
SM count | — | 3 |
Cache L1 | — | 48 KB (per SM) |
Cache L2 | — | 512 KB |
Pixel rate | 3.150 GPixel/s | 25.50 GPixel/s |
---|---|---|
Texture rate | 25.20 GTexel/s | 38.26 GTexel/s |
FP16 (half) performance | 806.4 GFLOPS (2:1) | 19.13 GFLOPS (1:64) |
FP32 (float) performance | 403.2 GFLOPS | 1,224 GFLOPS |
FP64 (double) performance | 100.8 GFLOPS (1:4) | 38.26 GFLOPS (1:32) |
Slot width | IGP | IGP |
---|---|---|
TDP | 15 W | 10 W |
Outputs | No outputs | No outputs |
Power connectors | — | None |
DirectX | 12 (12_1) | 12 (12_1) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 3.0 | 3.0 |
Vulkan | 1.2 | 1.2 |
Shader model | 6.4 | 6.4 |
CUDA | — | 6.1 |
Release date | — | Feb 10th, 2020 |
---|---|---|
Generation | — | GeForce MX (3xx) |
Production | — | End-of-life |
Interface | — | PCIe 3.0 x4 |