Insufficient capacity?Intel DG2 GPU will use TSMC’s 7nm process

Intel’s return to the discrete graphics card market can be said to be highly anticipated, but the progress is really not fast, and different product lines are also fast and slow. At present, Intel has announced the DG1 of the Xe LP architecture for the mobile notebook field, which will be launched later this year. Recently, it is reported that the DG2 for the gaming market will be released by 2022 and will be manufactured by TSMC’s 7nm process.

According to AdoredTV, the Intel DG2 GPU uses TSMC’s 7nm process, not Intel’s own 7nm process, and the new GPU will be launched in 2022.

According to Intel’s process roadmap, the 7nm process will be ready in the fourth quarter of next year. It is rare for Intel to suddenly change its foundry direction at this node and seek help from TSMC. The report pointed out that Intel’s decision may consider its 7nm production capacity. In addition, since the cost of the new node is higher than that of the old node, and the GPU used for the game cannot be too expensive, the cost issue is also considered. It may also have something to do with Intel’s crazy hiring of former AMD and Radeon employees who are familiar with TSMC’s process.

In addition, Intel chose the TSMC standard 7nm instead of the second-generation 7nm+ EUV, which should also take into account cost and production capacity.

Related Posts