Samsung's Gaia AI accelerator enters testing with HP and Lenovo for next-generation AI PCs

Samsung readies Gaia AI accelerator for client devices -- HP and Lenovo are reportedly validating the NPU

Samsung is reportedly sampling its dedicated AI processor for next-generation AI PCs with leading PC makers, such as HP and Lenovo. The chip, codenamed Gaia, was developed by the company's System LSI business unit, and it is designed to offload AI-related workloads from the CPU and GPU, reports Chosun. Samsung's Gaia is designed to accelerate generative AI workloads on PCs and is made using the company's 4nm-class fabrication process. The chip, which is essentially a neural processing unit (NPU), is currently being evaluated by HP in the U.S. and Lenovo in China to verify its performance and evaluate whether it makes sense to integrate Gaia into their systems due in late 2027 or early 2028. The report does not detail how Gaia differs from NPUs that are integrated into AMD's Ryzen, Intel's Core, or Qualcomm's Snapdragon X processors as well as whether it can offer significant performance advantages. Meanwhile, the report implies that the NPU (or perhaps its derivatives based on the same architecture) could be used for Samsung's next-generation implementations of its processing-in-memory (PIM) technology. Samsung's original PIM was designed to embed compute logic directly within the HBM memory array and reduce data movement between HBM memory modules and host processors. PIM was aimed to accelerate select workloads, but did not take off because AI and HPC GPUs became very efficient and were supported by mature ecosystems, unlike PIM. Perhaps if Samsung's upcoming Gaia NPU gains support from hardware makers and ecosystem partners, then this will give a boost to Samsung's next-generation PIM implementation as well. However, standalone NPUs and PIM are so fundamentally different that we can barely imagine that they can share a common architecture. Yet, PIM logic can be a subset of an NPU in terms of supported instructions and data formats and they can certainly share a common software framework. One of the interesting things to note about Gaia is that it was reportedly developed by Samsung's LSI division, the same business unit at the company that is responsible for Exynos processors, automotive solutions, connectivity chips, ISPs, DSPs, display drivers, and image sensors. Given the multi-faceted nature of Samsung's LSI unit, as well as its strategic importance for the company, Samsung must be pinning some hopes on Gaia. We have contacted Samsung and asked for a comment about the report, but we yet have to hear back from the company. Follow Tom's Hardware on Google News, or add us as a preferred source, to get our latest news, analysis, & reviews in your feeds.

Samsung wants to put its own chip in your next PC and it's all about speeding up AI chores

Samsung may be plotting a new entry into the PC chip business. A new report from the Korea Economic Daily says Samsung's System LSI division is developing a dedicated AI accelerator for PCs called Gaia. The company has reportedly supplied early samples to Lenovo and HP for performance testing, with mass production potentially beginning as early as 2027. Prominent Samsung leaker Ice Universe described the project as the company's return to the PC processor market after roughly 13 years. However, the details point toward something slightly different from a traditional laptop processor. Gaia might be a specialized companion chip designed to handle artificial intelligence workloads rather than a complete replacement for an Intel, AMD, or Qualcomm CPU. Gaia would sit beside your PC's main processor Samsung will reportedly manufacture Gaia using a 4-nanometer process. Its architecture centers on an optimized neural processing unit, or NPU, capable of accelerating generative AI and other on-device workloads without having to constantly rely on cloud servers. The company is also exploring integration with processing-in-memory technology. PIM basically enables certain calculations to happen directly inside memory, reducing the amount of data shuffled between the processor and RAM. So Samsung could potentially pair Gaia with its own memory products, giving it greater control over several important parts of the AI computing pipeline. Recommended Videos Plenty of major details remain unknown. The report does not reveal Gaia's AI performance, power consumption, or any other key information. Meaning, we can't exactly compare it to Qualcomm's Snapdragon X2 processors or Nvidia's far more powerful RTX Spark platform. Regardless, a dedicated discrete accelerator could allow PC manufacturers to add stronger local AI capabilities without rebuilding an entire laptop around a new processor architecture. This is not the first time Samsung has made PC chips Aside from being a chip manufacturer for tech giants like Nvidia and AMD, Samsung's history in PC silicon stretches back more than a decade. The company had its Exynos 5 chips power some Chromebooks in the early 2010s. Today, Samsung's Galaxy Book laptops largely rely on processors from Intel and Qualcomm. The recently announced Galaxy Book6 Edge, for example, uses Qualcomm's Snapdragon X2 Elite. Gaia could eventually give Samsung a proprietary piece of that hardware stack once again.

Samsung is reportedly working on a new AI chip called Gaia

Samsung hasn't built a chip for PCs in over a decade. According to a new report from Korean outlet News1, that's about to change. The Samsung Gaia AI chip is reportedly in development as a dedicated AI accelerator for PCs, built on a 4nm process. Unlike a typical processor that runs your whole system, Gaia is said to focus purely on AI tasks. Reports point to an optimized neural processing unit built for generative AI workloads. The goal is handling those tasks on the device itself, without leaning on cloud servers for every request. Samsung is also said to be exploring processing-in-memory tech for the chip. That's a method that lets memory handle some calculations on its own. Data doesn't need to travel back and forth to a separate processor as often. According to the report, Samsung's System LSI division has already sent Samsung Gaia AI chip prototypes to Lenovo and HP for testing. Mass production could reportedly begin as soon as next year, though Samsung hasn't confirmed a timeline. Details on performance and power draw haven't surfaced yet. That means there's no way to stack Gaia up against Qualcomm's Snapdragon X2 or Nvidia's RTX Spark chips just yet. Samsung's Broader Push Into AI Chips Samsung's laptops, including its latest Galaxy Book 6 lineup, currently run on Intel and Qualcomm silicon. A homegrown AI chip would give Samsung a way to compete without waiting on outside suppliers. That instinct isn't new. Samsung's Exynos 2600 already made a similar push for phones. It packs in an 80 TOPS NPU built to handle AI features without hurting battery life. Gaia looks like that same strategy applied to laptops and PCs instead. There's an obvious catch here too. Nvidia and Qualcomm both rely on Samsung's foundries for parts of their own chip production. A Samsung Gaia AI chip competing directly with them could complicate those relationships. That's especially true if either company decides to shift work elsewhere. For now, Samsung appears willing to take that risk.

AI Catapulted Samsung's Memory Business To New Heights; Now, It's Pushing The Development Of A 4nm AI Accelerator SoC For PCs To Take On Qualcomm

* 0-20%: Unlikely - Lacks credible sources * 21-40%: Questionable - Some concerns remain * 41-60%: Plausible - Reasonable evidence * 61-80%: Probable - Strong evidence * 81-100%: Highly Likely - Multiple reliable sources The AI boom has favored Samsung like no other event, but this phase has also given the Korean giant motivation to challenge competitors it would typically steer clear of. Likely driven by a new confidence wave, a new report states that the Korean giant is now developing an AI accelerator using its 4nm process called "Gaia" and will enter the PC market by taking on Qualcomm and NVIDIA. Prototypes of Gaia have already been shipped to potential customers, with the possibility that this AI accelerator is paired with Samsung's next-generation DRAM Sporting an optimized internal structure for its NPU, Samsung's AI accelerator will be tailor-made for edge computing. According to Korea Economic Daily, prototypes of Gaia are already being tested by major companies like HP and Lenovo for verification, with mass production expected to begin as early as next year. With the improved 4nm lithography paired with Samsung's next-generation DRAM technology called PIM (Processing-in-Memory), increased 'performance per watt' and increased AI performance of this SoC will be its forte. Unlike traditional processors, Gaia is designed for generative AI tasks and can become the cornerstone for powering AI agents and LLMs. It also marks the first time that Samsung has entered the PC market in 14 years. The last time this attempt was made, the chip giant introduced its Exynos range of chipsets to Chromebooks. Sadly, it couldn't create the necessary dent to stay in competition for long. However, with the AI boom, Samsung isn't just benefiting from increased DRAM and NAND prices, but specifically-designed SoCs could be its next calling. In short, Gaia will now take on the likes of Qualcomm's Snapdragon X2 Elite Extreme and NVIDIA's RTX Spark, and if successful, Samsung's LSI division could have a new growth driver. Entering the AI PC race could create conflicts with NVIDIA and Qualcomm, who are Samsung's customers While certain clients and businesses are also rivals in other segments, Samsung should consider its position carefully. After all, its foundry sector only just started gaining momentum thanks to orders from NVIDIA and Qualcomm, and with the Korean titan's AI accelerator seemingly in development, it could lead to a conflict of interest. Qualcomm and NVIDIA could easily turn the tables by switching to TSMC as their exclusive foundry, cutting Samsung out of billions in earnings. Fortunately, there's no confirmation that Gaia has been greenlit to enter mass production, and whatever the company's plans are for its AI accelerator, we'll update readers in due time. News Source: Korea Economic Daily Follow Wccftech on Google to get more of our news coverage in your feeds.