Intel announces new Lunar Lake chips with improved AI processor
Intel lifted the curtain on its latest processor series, codenamed Lunar Lake, on Wednesday during Intel CEO Pat Gelsinger’s Computex Keynote. The new chip will launch later this year and will power thin and light laptops in time for the 2024 holiday season.
The new system-on-a-chip (SoC) introduces a number of innovations over the current generation of Meteor Lake SoCs such as the Intel Core and Core Ultra processors, with Intel claiming better energy efficiency, a fourfold increase in NPU processing power, a 50% faster Intel Arc GPU based on the next-generation Arc Battlemage architecture, and on-chip memory for a smaller footprint and faster memory access.
Lunar Lake is also the first series of Intel chips to meet the minimum requirements for Microsoft’s Copilot+ PC standards, including more than 40 trillion operations per second for the NPU (TOPS) and 16 GB of memory.
The new SoC features a vastly updated architecture that introduces a range of small changes to the way the processors function, which together deliver significant performance improvements while consuming no more power than current Intel Core Ultra chips, and are said to be able to achieve the same performance as Intel Meteor Lake chips with one-third the power, significantly extending the potential battery life of laptops equipped with the new chips.
I haven’t tested these claims myself, so they should all be taken with a grain of salt until reviewers can get their hands on new laptops with Lunar Lake chips, but during an extensive tech tour ahead of Computex In the announcement, Intel engineers presented a pretty thorough explanation of the changes Lunar Lake will introduce and they are quite far-reaching, even if individual changes don’t bring much of a change on their own.
New core architectures introduced
The biggest innovation in Lunar Lake is the introduction of a new hybrid core architecture with Lion Cove performance cores and Skymont efficiency cores. These cores are a key driver of the improved energy efficiency that Intel claims for Lunar Lake, with some minor changes to the way instructions are processed by the CPU, the introduction of a new layer of cache memory and a doubling of capacity. number of efficiency cores over Meteor Lake.
Another big change is the loss of hyperthreading capabilities. This is when a processing core can execute two instructions per clock cycle instead of one, although Intel says the optimization baked into Lunar Lake’s Lion Cove performance cores eliminates the loss of hyperthreading that comes with its own processing overhead.
Together, these changes mean that the efficiency cores will deliver the same performance as current generation Meteor Lake chips at one-third the power, and up to four times the performance at peak power thanks to the addition of two more efficiency cores, according to Intel. As for the performance core, Intel says that Lunar Lake’s Lion Cove performance cores can deliver 50% better performance for the same power as Meteor Lake’s Redwood Cove cores in single-threaded performance, and about 5% better performance with single-threaded performance. threaded Lion Cove core than Meteor Lake’s multi-threaded performance cores.
Additionally, Intel says its efficiency cores are mature enough to handle more demanding tasks than previous generations of efficiency cores, meaning workloads previously assigned to higher-power performance cores can now be assigned to lower-power efficiency cores. increasing the chip’s overall efficiency, which should help extend the battery life of a Lunar Lake-equipped laptop to be competitive with Arm-based laptops like those powered by Qualcomm’s new Snapdragon M4 chips.
Comprehensive NPU and next-generation Intel Arc graphics
Other notable improvements come from the other two key components of the Lunar Lake SoC, namely the Intel NPU 4 neural processor and Intel Xe2 graphics architecture, based on Intel Arc Battlemage.
Starting with the GPU, the next generation of Arc graphics comes with 8 Alchemist-based architecture of Meteor Lake.
The NPU, meanwhile, quadruples the performance of Intel Meteor Lake’s NPU 3 neural processor, from 12 TOPS to 48 TOPS thanks to four additional neural processing cores and other architectural refinements.
For those counting, this equates to a total platform TOPS of 120 between the GPU, NPU, and CPU, and when Lunar Lake laptops hit the market in the third and fourth quarters of this year, Windows Copilot+ Runtime and other Developer APIs allow apps creators to use all three processors when necessary to better optimize AI tasks.
Whether Intel Lunar Lake delivers on this year’s AI PC promise remains to be seen, but Intel is exuding plenty of confidence that it will take a commanding lead in the AI PC market by the end of the year, how that market will eventually develop. .