Xe-LP: Integrated and Entry-Level
On the consumer side, Intel focused most of their architectural discussion on the aforementioned Xe-LP graphics to be found in Tiger Lake.
Xe-LP is Intel’s most efficient architecture for PC and mobile computing platforms with up to 96 EUs, and comes with new architecture designs including asynchronous compute, view instancing, sampler feedback, updated media engine with AV1 and updated display engine. This will enable new end-user features with instant game tuning, capture, and stream-and-image sharpening. On software optimization, Xe-LP will have driver improvements with a new DX11 path and optimized compiler.
Xe-LP is a 1.5x larger engine, offering up to 96 execution units compared to 64 EUs with Gen11. Based on the new 10nm SuperFin technology, Xe-LP provides what Intel is calling “significant performance-per-watt efficiency improvements”, and offers up to 48 texels and 24 pixels per clock, with 1536 flops per clock.