Micron has announced the release of its HBM3E 12-Hi memory, boasting an impressive 36GB capacity and a bandwidth of 1.2TB/s. This powerful memory is designed to fuel the demands of artificial intelligence (AI) GPUs, enabling the processing of larger AI models and faster insights.
Rumors swirl about the launch of Nvidia’s highly anticipated RTX 50-series graphics cards, with whispers of a September release. However, the timeline contradicts past release patterns, leaving uncertainty surrounding the truth of these claims.
Intel’s new Lunar Lake Core Ultra processors are packing a serious graphics punch with the next-generation Xe2 ‘Battlemage’ integrated GPUs, boasting significant performance improvements over previous generations and even outperforming AMD’s Ryzen AI 300 series APUs in some games. These GPUs offer impressive ray tracing capabilities and support for Intel’s XeSS upscaling technology, resulting in smoother gameplay and enhanced visuals.
Intel’s new Core Ultra Series 2 processors, codenamed Lunar Lake, boast impressive integrated GPUs featuring the Xe2 architecture. These GPUs offer significant performance gains over previous generations, making them ideal for thin and light laptops. The integrated GPU’s capabilities extend to gaming, as demonstrated by the upcoming MSI Claw 8 AI+ gaming handheld. The new chips also showcase significant power efficiency improvements, making them a compelling option for consumers seeking a balance between performance and battery life.
The latest Steam Hardware & Software Survey reveals the GeForce RTX 3060 remains the most popular GPU among PC gamers, while the AMD Radeon 780M integrated graphics, powering popular handheld gaming devices like the ROG Ally and Steam Deck, makes a significant impact, signaling the growth of portable PC gaming.
NVIDIA’s Hopper H100 and H200 AI GPUs are getting even more powerful with new optimizations in the CUDA stack. The H200, featuring 80% more HBM memory and 40% higher bandwidth than the H100, delivers significant performance gains across a range of benchmarks, including Llama 2 and Mixtral 8x7B. These advancements highlight NVIDIA’s commitment to pushing the boundaries of AI computing.
AMD’s upcoming Radeon RX 8000 series, based on the RDNA 4 architecture, is rumored to focus on the mid-range market. This strategy mirrors the approach taken with the first-generation Radeon RX 5000 series, prioritizing cost-effectiveness over top-tier performance. The rumored Navi 44 and Navi 48 GPUs are expected to compete in the mid-range segment, potentially challenging NVIDIA’s offerings in that space.
AMD is set to release its new RDNA 4 GPU architecture later this year, with the mid-range Radeon RX 8600, powered by the Navi 44 XL GPU, being one of the key additions. This GPU has been spotted in a shipping manifest, confirming its existence and potentially its upcoming release.
AMD’s upcoming Radeon RX 8000 series graphics cards, built on the RDNA 4 architecture, are rumored to feature 48MB to 64MB of next-gen Infinity Cache. Leaks suggest three configurations, each with varying memory bus sizes, speeds, and Infinity Cache amounts. The RX 8800 XT is expected to have the highest specs, while the RX 8600 XT will offer a more budget-friendly option.
Leaks suggest AMD’s upcoming Navi 48 GPU, based on the RDNA 4 architecture, will offer performance comparable to the RTX 4080 at a lower price point. This could be a game-changer for AMD, aiming to dominate the sub-$600 market.
