3 Sources
[1]
The next Snapdragon flagship chip is getting Qualcomm's take on DLSS
Otherwise, you should expect a GPU with an even higher clock speed than the Snapdragon 8 Elite Gen 5 GPU. Qualcomm recently revealed the first details for its next-generation flagship processors, focusing on the CPU improvements. Now, the company has detailed what we should expect on the GPU front. Easily the most notable upgrade to the GPU is the addition of Adreno Matrix Cores, with a graphic below suggesting that there are three cores. These cores run AI workloads locally with lower latency and improved power consumption. These cores come a year after Qualcomm brought SME tech to accelerate AI workloads on the CPU. So what are the Adreno Matrix Cores actually used for, then? Qualcomm says the Adreno Matrix Cores help power Adreno Neural Fusion technology. At first glance, this sounds like a fancy name for the firm's existing suite of AI super-resolution and frame generation solutions. However, the company says Adreno Neural Fusion offers reduced visual artifacts (e.g., shimmering and ghosting), more stable performance, and sharp detail compared to previous solutions. It also boasts up to 40% power savings compared to the previous solution. We're guessing the "previous solution" is Qualcomm's Snapdragon Game Super Resolution feature. Either way, it sounds like you should expect improved frame generation and upscaling in supported games. Qualcomm also confirmed that both Unreal Engine and Unity support Adreno Neural Fusion. This suggests that you won't have a tough time finding compatible games. It's unclear if the Adreno Matrix Cores can be used for non-gaming tasks, though. News of this tech also comes after Xiaomi confirmed that the Arm G2-Ultra NX GPU in its XRing 03 chipset will have eight neural accelerators. So it looks like AI silicon in GPUs could be a theme for next-generation chipsets. What about the fundamental GPU specs? Qualcomm has announced that its next-generation smartphone processors will offer a three-slice GPU architecture. Previous leaks suggested that the Snapdragon 8 Elite Gen 6 series could have six slices, doubling the 8 Elite Gen 5 GPU, but it looks like this claim is wide of the mark. The sliced architecture sees the GPU's shader cores and other hardware blocks divided into "slices," allowing for more granular power control and performance balancing. Qualcomm says its new Adreno GPU is clocked at 1.45GHz. By contrast, the Snapdragon 8 Elite Gen 5 GPU ran at 1.2GHz. The new GPU still packs 18MB of Adreno High Performance Memory, but the Snapdragon maker says you should expect a 12% efficiency improvement. Otherwise, the chip designer says you can expect a Qualcomm X105 modem and a FastConnect 8800 connectivity suite. Qualcomm previously confirmed that its next-generation processors would also have a 5GHz Oryon CPU. This marks the first time that we've seen a 5GHz smartphone chipset. This is paired with the firm's FlexCache architecture, which promises to keep the CPU well-fed with instructions. Either way, it looks like the Snapdragon 8 Elite Gen 6 series could deliver a ton of horsepower. Here's hoping Qualcomm and OEM partners can keep it cool.
[2]
Qualcomm's upcoming premium chip has Adreno 'Neural Fusion' GPU
Following Qualcomm detailing the core Oryon CPU that would find itself on the next flagship Snapdragon chip, the chipmaker has announced its next-gen Adreno Neural Fusion GPU. Qualcomm's next SoC will be the first chipset to feature dedicated AI GPU cores in the graphics pipeline. These so-called "Matrix Cores" sit snugly in each of the three 1.45GHz GPU slices on the new Adreno GPU. Qualcomm says they act as dedicated local hardware to "run advanced AI models directly inside the graphics pipeline." The Snapdragon chip's Adreno GPU will also feature a dedicated 18MB HPM (High Performance Memory) cache. That capacity sounds humble, but Qualcomm says its HPM "provides large, low-latency memory directly to the GPU, allowing tile-based rendering, frame buffers, and compute workloads to remain local to the graphics subsystem." Both components in the new core architecture help make up the entirety of the Adreno Neural Fusion GPU. For the end user, it means a 40% power improvement with the technology enabled. The company detailed in its press release how developing an SoC with AI processing done in closer proximity to the GPU means less latency and better efficiency. The trick is keeping the work close to the silicon. Adreno Matrix Cores handle AI models right where the graphics happen, and the 18MB of Adreno High Performance Memory holds the heavy data -- tiles, frame buffers, compute -- on-chip so it isn't constantly shuffling back and forth to system memory. Less movement means lower latency and better efficiency, which translates into gaming sessions that last longer. For the time being, Unity and Unreal Engine have already integrated Qualcomm's Neural Fusion stack. The end result should be improved graphics quality with "upscaled images, stable frame rates, and improved efficiency through AI-enhanced rendering built directly into the Snapdragon graphics pipeline," as Qualcomm puts it. Snapdragon Summit is scheduled for September 22-24, and more is set to be announced regarding the new chip's NPU.
[3]
Qualcomm Details Next-Gen Adreno GPU With Matrix Cores
Qualcomm says Adreno Neural Fusion tech improves AI-driven rendering Qualcomm is gearing up to introduce its next-generation flagship mobile processor at the Snapdragon Summit in Hawaii later this month. Ahead of the announcement, the US-based chipmaker has detailed the GPU upgrades that its chipset will have. The chip, widely referred to as the Snapdragon 8 Elite Gen 6, is confirmed to feature a new Adreno GPU featuring Adreno Matrix Cores for AI workloads, alongside a new rendering technology called Adreno Neural Fusion. Qualcomm Details New Adreno GPU Upgrades In a blog post, Qualcomm said that the most notable upgrade on its next-generation flagship chip will be the addition of Adreno Matrix Cores to the GPU. These are said to be dedicated to running AI workloads directly within the graphics pipeline. As per the company, keeping these workloads on the GPU will result in reduced latency and power consumption compared with moving AI processing between different parts of the platform. The Adreno Matrix Cores are designed to power Adreno Neural Fusion, which is Qualcomm's new AI-driven rendering technology. It is claimed to combine neural processing, AI super resolution and frame generation into a unified graphics pipeline. Qualcomm says the technology is designed to address common issues associated with upscaling, including shimmering, ghosting and loss of fine detail. This indicates Adreno Neural Fusion could be Qualcomm's take on Nvidia's Deep Learning Super Sampling (DLSS) technology, which also renders images at a lower resolution and then upscales them to a higher resolution using AI to deliver improved frame rates. The new Adreno GPU is clocked at 1.45GHz, compared with 1.2GHz on the Snapdragon 8 Elite Gen 5. Qualcomm claims a 12 percent improvement in efficiency for the new GPU architecture. The chipmaker also confirmed that its next-generation flagship Adreno GPU uses a three-slice architecture that divides shader cores and other graphics hardware into separate sections. Qualcomm claims this allows the platform to manage power and performance more granularly depending on the workload. This architecture will be paired with 18MB of Adreno High Performance Memory (HPM), which is integrated into the GPU subsystem. The company says the dedicated HPM is designed to keep tile-based rendering data, frame buffers and compute workloads closer to the GPU, effectively resulting in lower latency and improve efficiency during graphics-intensive workloads. For developers, Adreno Neural Fusion will be supported across major game engines, including Unity and Unreal Engine. The technology is said to be commercially available and can be integrated into existing development workflows. While Qualcomm did not explicitly name the upcoming SoC, previous leaks suggest that it will launch two flagship SoCs this year. The chipset with model number SM8950 could be branded as the Snapdragon 8 Elite Gen 6, while the one bearing the model number SM8975 may be marketed as Snapdragon 8 Elite Extreme Gen 6. We can expect more details about the next-generation Snapdragon processors to be revealed at the 2026 Snapdragon Summit, which is scheduled to take place from September 22 to September 24 in Maui, Hawaii.
Share
Copy Link
Qualcomm has revealed its next-generation Adreno GPU featuring dedicated AI Matrix Cores and Neural Fusion technology for the upcoming Snapdragon 8 Elite Gen 6 chipset. The GPU clocked at 1.45GHz promises 40% power savings and improved frame generation with reduced visual artifacts, marking a significant leap in AI-driven mobile gaming performance.
Qualcomm has unveiled major AI-driven GPU improvements for its next-generation Snapdragon processors ahead of the Snapdragon Summit scheduled for September 22-24 in Maui, Hawaii
1
3
. The most significant upgrade comes in the form of Adreno Matrix Cores—dedicated AI-accelerated cores integrated directly into the graphics pipeline2
. These cores sit within each of the three GPU slices clocked at 1.45GHz, representing a substantial jump from the Snapdragon 8 Elite Gen 5's 1.2GHz1
. The chipmaker designed these Matrix Cores to run advanced AI models locally, resulting in reduced latency and improved power consumption compared to moving AI processing between different platform components3
. This marks the first time a flagship chipset will feature dedicated AI silicon directly embedded in the GPU architecture2
.
Source: Android Authority
The Adreno Matrix Cores power Qualcomm's new Adreno Neural Fusion technology, which combines neural processing, AI super resolution, and frame generation into a unified rendering technology
3
. Qualcomm claims this AI-driven approach delivers up to 40% power savings compared to previous solutions like Snapdragon Game Super Resolution1
. The technology specifically addresses common upscaling issues including shimmering, ghosting, and loss of fine detail—problems that have plagued AI-enhanced mobile gaming experiences3
. According to Qualcomm, keeping AI workloads close to the silicon dramatically improves efficiency. The company explained that Matrix Cores handle AI models right where graphics rendering happens, while 18MB of Adreno High Performance Memory holds critical data on-chip, eliminating constant data shuffling to system memory2
. This architectural approach translates into extended gaming sessions with stable frame rates and enhanced visual quality2
.The next-generation Adreno GPU utilizes a three-slice architecture that divides shader cores and graphics hardware into separate sections, enabling more granular power control and performance balancing
3
. Previous speculation suggested the Snapdragon 8 Elite Gen 6 series might feature six slices, but Qualcomm confirmed the three-slice design1
. Each slice operates at 1.45GHz and contains dedicated Matrix Cores for AI processing2
. The GPU maintains 18MB of High Performance Memory integrated directly into the subsystem, designed to keep tile-based rendering data, frame buffers, and compute workloads closer to processing units3
. Qualcomm reports a 12% efficiency improvement with this new architecture1
. The chipset will also feature a Qualcomm X105 modem and FastConnect 8800 connectivity suite, paired with a 5GHz Oryon CPU—marking the first time a smartphone chipset has reached this clock speed1
.
Source: 9to5Google
Related Stories
Both Unity and Unreal Engine have already integrated Adreno Neural Fusion into their development workflows, suggesting widespread game compatibility at launch
1
2
. This developer support positions Qualcomm's technology for rapid adoption across mobile gaming titles. The technology is commercially available and can be integrated into existing development pipelines3
. Qualcomm's move comes shortly after Xiaomi confirmed its XRing 03 chipset would feature eight neural accelerators in the Arm G2-Ultra NX GPU, indicating AI silicon in GPUs is becoming a defining trend for next-generation mobile processors1
. While Qualcomm hasn't explicitly confirmed whether Matrix Cores can handle non-gaming AI tasks, the architecture suggests potential applications beyond mobile gaming1
. Industry observers speculate that this integrated AI approach could set new standards for power efficiency in mobile devices, though thermal management remains a critical challenge given the combined horsepower of the 5GHz CPU and enhanced GPU1
. Previous leaks suggest Qualcomm may launch two flagship variants—the Snapdragon 8 Elite Gen 6 (SM8950) and a possible Snapdragon 8 Elite Extreme Gen 6 (SM8975)3
.Summarized by
Navi
[1]
[3]
21 Aug 2026•Technology

24 Sept 2025•Technology

26 Nov 2025•Technology
