Technology
Intel will retire rarely-used 16x MSAA support on Xe3 GPUs — AI upscalers like XeSS, FSR, and DLSS provide better, more efficient results
Source
Tom's Hardware
Published
Similar Articles
Intel Panther Lake-H high-res die shot emerges — image show 18A compute tile, Xe3 GPU tile in new X-series processors
A die shot of Intel's Panther Lake-H processors has been revealed, showcasing the 18A compute tile and Xe3 GPU tile in the new X-series processors. The compute tile integrates high-performance Cougar Cove cores, Darkmont cores, and NPUs with cache slices for improved performance and flexibility. The memory controller includes an 8MB memory side cache to reduce latency and bandwidth pressure. The GPU tile features 12 Xe3 clusters and L2 cache for enhanced yield by allowing faulty clusters to be disabled. The I/O tile includes Thunderbolt 5 controller, Wi-Fi/Bluetooth controller, PCIe 5.0 x4 PHY, and USB PHYs, offering additional functionality to the processor.
Tom's Hardware•
New Panther Lake Core Ultra X7 358H leaks in new benchmark - Geekbench 6 result shows off 12 Xe3 Core iGPU's chops
A leak of Intel's upcoming Panther Lake mobile processor, the Core Ultra X7 358H, has surfaced through Geekbench 6 results. The chip features 16 CPU cores and a powerful integrated Xe3 GPU with 12 cores, showcasing impressive clock rates and performance potential. The GPU's maximum frequency is reported at 2.5 GHz, with benchmark scores surpassing some discrete graphics solutions. Panther Lake's integrated graphics are based on the Xe3 architecture, promising significant performance improvements over previous generations. Intel aims for over a 50% performance gain compared to the Lunar Lake series, hinting at a substantial leap in GPU capabilities.
Tom's Hardware•
Intel's Xe3 graphics architecture breaks cover — Panther Lake's 12 Xe Core iGPU promises 50+% better performance than Lunar Lake
Intel unveiled its Panther Lake SoCs featuring the Xe3 graphics architecture, promising over 50% better performance than Lunar Lake. The Xe3 architecture includes improvements for better resource utilization and scalability, with changes focused on continuous improvement rather than a completely new design. The Xe3 GPUs feature enhancements like variable register allocation, increased shared local memory, and a larger L2 cache for improved performance. Intel also introduced XeSS Multi Frame Generation for AI-accelerated frame generation, aiming to enhance image quality and game performance. Overall, Intel's Xe3 architecture shows promising improvements for future integrated GPU products.
Tom's Hardware•
Nvidia CEO Huang says upcoming DGX Spark systems are powered by N1 silicon — confirms GB10 Superchip and N1/N1X SoCs are identical
Nvidia CEO Jensen Huang confirmed that the upcoming N1 SoC is essentially the same as the existing GB10 Superchip, part of the DGX Spark lineup, designed for AI workloads. The N1/N1X SoCs were speculated upon following Nvidia's Project DIGITS announcement in collaboration with MediaTek. The N1 SoC is expected to feature 6,144 CUDA cores for its GPU and a 20-core CPU built using Nvidia's Grace architecture. Huang's statement suggests that the N1 and GB10 are closely linked, with the N1 possibly being a lower-binned version of the GB10. The N1's development is part of Nvidia's move towards mainstream CPU cores following Tegra, and its collaboration with Intel for ARM-based products is not expected to impact its roadmap.
Tom's Hardware•