Intel details new Lunar Lake CPUs that will take on AMD, Qualcomm and Apple

Considering recent production issues, AMD’s resurgence, Qualcomm’s entry, and Apple’s shift from customer to competitor, it’s been a rough few years for Intel processors. Computer buyers have more viable options than they have in many years, and in many ways the company’s Meteor Lake architecture was more interesting as a technical achievement than as an upgrade for previous-generation Raptor Lake processors.

But despite all that, Intel still supplies the vast majority of PC CPUs; nearly four-fifths of all computer CPUs sold are from Intel, according to recent estimates from Canalys analysts. The company still casts a long shadow, and what it does still sets the pace for the rest of the industry.

Enter the next generation CPU architecture, codenamed Lunar Lake. We’ve known about Lunar Lake for a while – Intel reminded everyone it was coming when Qualcomm touted it during Microsoft’s Copilot+ PC reveal – but this month at Computex the company is going into more detail about its availability sometime in the third quarter of 2024.

Lunar Lake will be Intel’s first processor with a neural processing unit (NPU) that meets Microsoft’s Copilot+ PC requirements. But looking beyond the endless stream of AI news, it also includes upgraded architectures for its P-cores and E-cores, a next-generation GPU architecture, and some packaging changes that simultaneously build on many of the dramatic changes that Intel has implemented and is undoing this. Meteor lake.

Intel didn’t have more information to share about Arrow Lake, the architecture that will bring Meteor Lake’s big changes to socketed desktop motherboards for the first time. But Intel says Arrow Lake is still on track for release in the fourth quarter of 2024, and could be announced at Intel’s annual Innovation event in late September.

Building on Meteor Lake

Lunar Lake has a number of things in common with Meteor Lake, including a chiplet-based design that combines multiple silicon chips into one large one using Intel’s Foveros packaging technology. But in some ways Lunar Lake is simpler and less weird than Meteor Lake, with fewer chiplets and a more conventional design.

Meteor Lake’s components were spread across four tiles: a compute tile that was mainly for the CPU cores, a TSMC-made graphics tile for the GPU rendering hardware, an IO tile for things like PCI Express and Thunderbolt connectivity, and a grab bag “SoC” tile with a few extra CPU cores, the media encoding and decoding engine, display connectivity and the NPU.

Lunar Lake only has two functional tiles, plus a small “filler” tile that appears to exist exclusively so that Lunar Lake’s silicon die can be a perfect rectangle once everything is packed together. The compute tile combines all P-cores and E-cores of the processor, the GPU, the NPU, the display outputs, and the media encoding and decoding engine. And the platform controller tile provides wired and wireless connectivity, including PCIe and USB, Thunderbolt 4 and Wi-Fi 7, and Bluetooth 5.4.

This is essentially the same division that Intel has used for laptop chips for years and years: one chipset chip and one chip for the CPU, GPU and everything else. It’s just that these two chips are now part of the same silicon chip, rather than separate chips on the same processor package. In retrospect, it seems that some of Meteor Lake’s most notable design deviations (the distribution of GPU-related features across different tiles, the presence of additional CPU cores in the SoC tile) were things that Intel had to do to overcome the fact bypassing the fact that another company actually produced most of the GPU. Given the opportunity, Intel has returned to a more recognizable assembly of components.

Another big packaging change is that Intel is integrating RAM into the CPU package for Lunar Lake, rather than having it installed separately on the motherboard. Intel says this uses 40 percent less power because it shortens the distance data has to travel. It also saves motherboard space, which can be used for other components, to make systems smaller or to make more room for the battery. Apple also uses on-pack memory for its M-series chips.

Intel says Lunar Lake chips can include up to 32 GB of LPDDR5x memory. The downside is that this built-in memory precludes the use of separate Compression-Attached Memory Modules, which combine many of the benefits of traditional expandable DIMM modules and soldered-in laptop memory.