Radeon RX 9070 gains 25% performance in synthetic benchmarks using RX 9070 XT vBIOS

Mobile RTX 2070 with shunt mod nearly eclipses desktop performance — 60W boost provides 15% performance uplift

A PC enthusiast successfully shunt modded their Nvidia GeForce RTX 2070 Mobile GPU, boosting performance by approximately 15%. By pushing the mobile GPU beyond its power limit to 175W, it nearly matches the performance of its desktop counterpart. Shunt mods involve changing a shunt resistor on the graphics card PCB to allow more current to reach the GPU without altering the vBIOS. The modder, HerrBolsch, conducted this modification as part of a project to re-house and water-cool a Zotac Mini PC. Post-modification assessments confirmed improved performance and manageable thermals, with the modded RTX 2070 Mobile keeping pace with a desktop card.

MSI Afterburner developer adding 'triple channel voltage' support for future MSI RTX 50 graphics cards

MSI Afterburner's developer is enhancing the app with "triple channel voltage" support for future MSI RTX 50 series graphics cards, enabling control over memory and auxiliary voltages in addition to core voltage. This upgrade surpasses Nvidia's default voltage controls, offering a wider voltage offset range for overclocking. While limited to upcoming MSI models due to Nvidia's restrictions on older cards, other GPU brands could adopt this feature with modified software. The addition of memory voltage control is particularly noteworthy for optimizing performance through overclocking. Overclockers may benefit from increased headroom for overclocking with this new feature.

AMD zapped with 16-pin power connector melting issue for the first time — Radeon RX 9070 XT paired with sub-par PSU gets singed

Dr. L.C. Lu on TSMC Advanced Technology Design Solutions

Dr. L.C. Lu, a key figure at TSMC, focuses on design-technology co-optimization, packaging innovations, and AI-driven methodologies for next-gen semiconductor systems. TSMC emphasizes DTCO and DDCL innovations for scaling from N5 to A14 nodes, with NanoFlex and NanoFlex Pro architectures offering efficiency gains. N2P and N2U nodes incorporate advanced DTCO and power delivery optimizations, with hybrid dual-rail architectures achieving significant energy savings. TSMC collaborates with EDA partners for AI integration, enhancing productivity and design quality. Advanced packaging technologies like CoWoS and SoIC play a crucial role in enabling AI scaling, with memory bandwidth and interconnect performance scaling aggressively. TSMC addresses power delivery and thermal management challenges in AI systems through advanced solutions. TSMC's advancements in design methodologies and AI-driven automation promise improved productivity and scalability in chip-package co-design.