GPU model | Coffee Lake GT2 | GF108 |
---|---|---|
Architecture | Generation 9.5 | Fermi |
Foundry | Intel | TSMC |
Manufacturing process | 14 nm+++ | 40 nm |
Number of transistors | unknown | 585 million |
Die size | unknown | 116 mm² |
Release date | Apr 3rd, 2018 | — |
---|---|---|
Generation | HD Graphics-M (Coffee Lake) | — |
Production | Active | — |
Interface | Ring Bus | — |
Reviews | 1 in our database | — |
Base clock | 350 MHz | — |
---|---|---|
Boost clock | 1000 MHz | — |
Memory clock | System Shared | 500 MHz 1000 Mbps effective |
GPU clock | — | 701 MHz |
Shader clock | — | 1402 MHz |
Memory size | System Shared | 2 GB |
---|---|---|
Memory type | System Shared | DDR3 |
Memory bus width | System Shared | 64 bit |
Bandwidth | System Dependent | 8.000 GB/s |
Shading units | 192 | 48 |
---|---|---|
TMUs | 24 | 8 |
ROPs | 3 | 2 |
Execution units | 24 | — |
SM count | — | 1 |
Cache L1 | — | 64 KB (per SM) |
Cache L2 | — | 128 KB |
Pixel rate | 3.000 GPixel/s | 1.402 GPixel/s |
---|---|---|
Texture rate | 24.00 GTexel/s | 5.608 GTexel/s |
FP16 (half) performance | 768.0 GFLOPS (2:1) | — |
FP32 (float) performance | 384.0 GFLOPS | 134.6 GFLOPS |
FP64 (double) performance | 96.00 GFLOPS (1:4) | 11.22 GFLOPS (1:12) |
Slot width | IGP | Single-slot |
---|---|---|
TDP | 15 W | 29 W |
Outputs | No outputs | 1x DVI1x HDMI1x VGA |
Length | — | 145 mm 5.7 inches |
Suggested PSU | — | 200 W |
Power connectors | — | None |
DirectX | 12 (12_1) | 12 (11_0) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 3.0 | 1.1 |
Vulkan | 1.2 | — |
Shader model | 6.4 | 5.1 |
CUDA | — | 2.1 |
Release date | — | Apr 2nd, 2016 |
---|---|---|
Generation | — | GeForce 600 |
Production | — | Active |
Interface | — | PCIe 2.0 x16 |
Predecessor | — | GeForce 500 |
Successor | — | GeForce 700 |