Intel’s Meteor Lake notebook, stable Diffusion fast processing without dGPU-PC Viewing

COMPUTEX TAIPEI 2023 will be held at “Taipei Nangang Exhibition Hall 1 and 2” in Taipei, Taiwan for four days from May 30th to June 2nd (Taiwan time). In COMPUTEX TAIPEI before the corona wreckage, Intel sent a speaker to the keynote speech every year, but this year (2023) Intel will not officially participate in COMPUTEX TAIPEI, and will attend nearby locations. Participation is in the form of private meetings and exhibitions.

Meanwhile, Intel has held a press briefing for members of the press to share more details about the “Meteor Lake” that the company plans to announce and launch later this year, especially the NPU which has been built in this time. (Neural Processing Unit , a processor specialized for processing AI inferences was shown).

Meteor Lake to be launched later this year, hybrid architecture and improved power efficiency

Meteor Lake, which Intel plans to launch later this year (pictured at last year’s Intel Vision)

Meteor Lake, which Intel plans to announce and launch in the second half of this year, will be a next-generation client PC product that will succeed the current 13th generation Core (development codename: Raptor Lake). Intel already outlined Meteor Lake back in August last year.

As detailed in the article above, the biggest feature of Meteor Lake is that it is made by applying 3D chip technology, which Intel calls with the development codename Foveros. In Meteor Lake, Intel 4 (Intel process node formerly known as 7nm 4 tiles) is set in a 3D direction: a computer tile manufactured by a notebook that introduces EUV for the first time, a GPU tile manufactured by TSMC’s 5N, and a manufactured SoC tile. by TSMC’s 6N It becomes

Intel’s Roadmap for Client PCs

Overview of Meteor Lake

Intel has not revealed the details of the compute tiles or GPU tiles yet, but the CPUs were implemented with new power saving features and a hybrid architecture focused on improving performance (performance hybrid architecture). It only revealed that it has improved power efficiency compared to with the 12th generation Core (Alder Lake) and the 13th generation Core (Raptor Lake).

Details of the GPU tile have not been revealed, but this time it was explained that it will be based on Arc, which was introduced as a single GPU last year (2022). The built-in GPU from the 12th generation / 13th generation Core continues to be equipped with Intel Xe Graphics (Xe-LP) introduced in the 11th generation Core (Tiger Lake), and there is no GPU update. Since it will be based on Arc in Meteor Lake, the new functions introduced in the Arc generation such as XeSS (Xe Super Sampling), AI function (XMX), AV1 decoder / encoder, etc. Built-in GPU will also be supported.

Please refer to the previous article for details on the Arc architecture.

Meteor Lake will appear as a completely new architecture as a new product for client PCs, and in 2024, Arrow Lake will be introduced, where the node of the computer tile manufacturing process will be hooked to Intel 20A.

Additionally, Lunar Lake and its successor are designed as a version with further improved power efficiency, the compute tile has been refined to Intel 18A, and this is the Arm SoC for Arm Windows (WoA) version with further revision on power management. a product that realizes power efficiency similar to power efficiency As a result, it will be possible to realize notebook computers with x86 CPUs that are smaller and can run on batteries for a long time.

Intel’s plan is an ambitious manufacturing technology innovation to rapidly develop and deliver 5 goals in 4 years, which is scheduled for the “IDM 2.0” strategy promoted by the company’s CEO Pat Gelsinger. It depends on the strategy, and for Intel to deliver Arrow Lake and Lunar Lake on time, it depends on whether Intel’s manufacturing technology strategy can be executed as planned.

Meteor Lake makes it possible to generate images at high speed with Stable Diffusion without a single GPU

Hardware that realizes AI in Meteor Lake, it is possible to use not only NPU but also CPU / GPU

This time, Intel has revealed details about the NPU (Neural Processing Unit) that the company will present in Meteor Lake as a new detail of such Meteor Lake.

In 2016, Intel acquired Movidius, which developed the VPU, now known as the NPU, and has provided USB modules and other products. The characteristic of Movidius VPU is that it has a built-in memory inside the chip, and it is a mechanism that does not increase power consumption by not accessing external memory, enabling AI compilation with extremely low power consumption of 1 W or less. is a great feature to make.

However, after that, Intel stopped external sales of VPU derived from Movidius, and now it was in the form of providing a single VPU called Keem Bay to some PC manufacturers. By using Keem Bay, it is possible to implement Windows AI solutions promoted by Microsoft, such as Windows Studio Effects, which will be provided to some OEM manufacturers in the 13th generation Core generation that was in shape.

However, as Intel itself announced in September last year, Intel has revealed that it has integrated the Movidius-derived VPU into Meteor Lake as an NPU, and since Meteor Lake, the NPU will be standard equipment.

Mr. John Layfield, Intel Vice President and General Manager, Client AI Division

This time, Intel revealed details about the implementation of its Movidius-derived NPU. Intel Vice President and AI Client Business Division Manager John Layfield said, “The NPU installed in Meteor Lake is a product derived from Movidius’ VPU. If the first product is the 1st generation, it ‘is currently provided by Intel. Keem Bay, which is under development, is a product based on the 2nd generation architecture. In contrast, Meteor Lake will have the 3rd generation architecture developed in-house by Intel ,” said Meteor Lake He explained that the built NPU is a further evolved NPU from Keem Bay.

Using a specialized NPU for AI processing increases processing power by 10 times and power efficiency by 5 times

According to Layfield, the NPU installed in Meteor Lake has further improved performance compared to Keem Bay. Specifically, “The processing power is 10 times higher than when processing with a CPU or GPU, but the power efficiency is 5 times higher.” Layfield explained.

This time, Intel showed that it supports multiple functions in Windows Studio Effects, and also showed the generation of images using AI Stable Diffusion generation using Meteor Lake. Although the exact conditions are unknown, it has been confirmed that the image was generated in about 30 seconds without a standalone GPU.

Windows Studio Effects (auto framing, gaze setting, background blur) on a PC with Meteor Lake places a high load only on the CPU and GPU, but even if the load is not on the CPU and the GPU so high, it can be achieved with the NPU It has been made public how it can be processed.

When running Windows Studio Effects on a laptop with Meteor Lake, note that the load on the CPU and GPU has not changed much, but the load on the NPU has increased. It is labeled Movidius VPU, but it was explained that this was an engineering sample (meaning it could be branded differently).