The new Xe2 iGPU delivers up to 1.5X more graphics performance than Meteor Lake's Arc Graphics, with up to 67 TOPS of AI performance. Intel has also simplified the naming of its GPU architecture and will simply refer to it as Xe2 in all configurations, as opposed to the Xe-LP, Xe-HP, and Xe-HPG suffixes used with the prior-gen Xe architecture.
Intel’s Xe2 architecture will not only come in the Lunar Lake processors, but it will also be used in the upcoming Battlemage discreet gaming GPUs. However, while the architecture may be the same, Lunar Lake uses lower-power transistors while Battlemage will employ faster transistors to maximize performance. That means the Lunar Lake performance projections can’t be directly extrapolated to predict the performance of Battlemage GPUs — not to mention dedicated GPUs will have dedicated VRAM as well.
The Xe2 GPU architecture features Intel's second-gen Xe core, larger XMX engines that support more data types, enhanced vector engines, larger ray tracing units, and deeper caches. The GPU is broken down into second-generation Xe cores and render slices, along with fixed functions graphics hardware for tasks like geometry processing, texture sampling, and rasterization. These units are connected to a large cache and memory fabric, along with I/O accommodations that vary based upon the implementation. The design is inherently modular, so it can be easily scaled to either more or fewer units.
The second-gen Xe core can do eight 512-bit multiplies per clock in the XVE vector engines and eight 2048-bit vectors per clock in the XMX engines. Intel also increased the SIMD engine from 8 lanes wide to 16 lanes wide, which is a more common arrangement that will enhance compatibility. The core also has a 192KB shared L1.
The second-generation vector engine supports INT2, INT4, INT8, FP16 and BF16 for AI operations. You can also see a table that has the calculations for peak TOPS (Ops/clock) in the album above. Note that the previous Meteor Lake iGPU cut the XMX Engine from the design in order to reduce die area and power requirements, so laptops with Xe2 will see significant improvements in AI workloads included XeSS.
The render slice has also seen plenty of improvements, including a 3X vertex fetch throughput improvement by changing the vertices distribution across the pipeline, a tripling of mesh shading performance via vertex re-use, new support for out of order sampling, and twice the throughput for sampling without filtering, among other improvements. Intel also cites increased ray tracing performance due a reorganized pipeline in the new Xe Ray Tracing Unit (RTU).
These ingredients are used to create Lunar Lake’s specific iGPU hardware configuration. Lunar Lake comes armed with eight second-gen Xe cores, 64 vector engines, two geometry pipelines, eight ray-tracing units, and 8MB of L2 cache, among other ingredients.
Intel says the Lunar Lake iGPU delivers 1.5X more performance than Meteor Lake-U at the same power threshold. Moving to Meteor Lake-H, Lunar delivers “similarly higher” performance at the upper end of the power range. However, the Lunar Lake GPU is designed for performance-per-watt with lower power transistors.
The display engine has three display pipes, up to 8K60 HDR, three 4K60 HDR displays, and up to 1080p360 and 1440p360. Outputs include HDMI 2.1, DisplayPort 2.1, and eDP 1.5. You can see the details of the graphics engine pipeline in the slides above.
The memory side cache provides 8MB to store some of the media information to increase bandwidth and save power. The media engine supports up to 8K60 10-bit HDR decode and encode, along with support for all of the media standards, along with the new H.266/VVC codec — but only for decode.
And of course, all of the new graphics features are backed by the past couple of years of effort by Intel's GPU drivers team. Arc GPUs first arrived in 2022 and had plenty of early growing pains. The latest drivers have come a long way, and Xe2 should benefit from everything that came before, with some improvements in the core architecture to remove bottleneck and limitations present in the first generation of Xe Graphics.
