-
PremiumBehind the scenes of our massive CPU retest for Bench — testing at 1080p, choosing new apps, and gathering data for a decade of CPUs
-
-
PremiumISSCC 2026: AMD discloses how the Instinct MI355X doubled per-CU throughput despite lower compute unit count
-
PremiumAmazon invests $50 billion in OpenAI, comitting to 2 gigawatts of Trainium silicon
-
Access Bench to view a treasure trove of data and compare products
-
Leave your feedback on Tom's Hardware Premium
-
-
-
PremiumBehind the scenes of our massive CPU retest for Bench — testing at 1080p, choosing new apps, and gathering data for a decade of CPUs
-
PremiumThe great Bench GPU retest begins — how we're testing for our GPU Hierarchy in 2026, and why upscaling and framegen are still out
-
PremiumThe state of China's decade-long semiconductor push: still a decade behind, despite hundreds of billions spent and significant progress
-
PremiumWi-Fi 7 promises made, but not kept — the mysteries of MLO and AFC, and looking toward Wi-Fi 8
-
PremiumUltra Ethernet: The data-center interconnection of tomorrow detailed
-
PremiumCPU scaling with DLSS
-
-
-
PremiumUALink roadmap plots course to optimized AI data center interconnects
-
PremiumThe future of Quantum computing — the tech, companies, and roadmaps that map out a coherent quantum future
-
PremiumHuawei Ascend NPU roadmap examined — company targets 4 ZettaFLOPS FP4 performance by 2028, amid manufacturing constraints
-
PremiumInside the AI accelerator arms race: AMD, Nvidia, and hyperscalers commit to annual releases through the decade
-
PremiumThe future of DRAM: From DDR5 advancements to future ICs
-
PremiumDesktop GPU roadmap: Nvidia Rubin, AMD UDNA & Intel Xe3 Celestial
-
News AnalysisSilicon Motion announces new devices: PCIe 6.0 SSDs, 256 / 512 TB drives, and next-gen 16K LDPC
-
PremiumHBM roadmaps for Micron, Samsung, and SK hynix: To HBM4 and beyond
-
PremiumInside the future of 3D NAND: The roadmap to 500 layers
-
PremiumNvidia enterprise GPU and CPU roadmaps: Rubin, Rubin Ultra, Feynman, and silicon photonics
-
News AnalysisMicron details new U.S. fab projects — HBM production coming to America
-
TSMC to spend $42 billion on expansion in 2025 — ambitious plans detail nine production facilities
-
-
-
Premium
Amazon invests $50 billion in OpenAI, comitting to 2 gigawatts of Trainium silicon
-
Premium
ISSCC 2026: AMD discloses how the Instinct MI355X doubled per-CU throughput despite lower compute unit count
-
PremiumInside Meta and AMD's $100 billion deal, and why AMD is giving up a slice of the company in return for GPU orders
-
PremiumSambanova introduces new AI accelerator, partners with Intel to deploy Xeon CPUs for inferencing and agentic workloads
-
PremiumAI boosted US economy by 'basically zero' in 2025, says Goldman Sachs chief economist
-
PremiumOpenAI couldn’t finance its data centers, so it took control of the hardware instead
-
-
-
PremiumChina’s CXMT and YMTC to memory output
-
PremiumIntel is co-developing new Z-Angle Memory to compete with HBM used in AI data centers
-
PremiumPhotonics and high-speed data movement is the next big AI bottleneck
-
PremiumApple concedes it is constrained by TSMC's supply of advanced chips; storage and memory are also in short supply
-
Samsung, SK Hynix, Micron team up to block memory hoarding
-
PremiumChina moves into manufacturing disruptive new semiconductor glass substrates as processor packaging competition intensifies
-
PremiumThe Stout Owl: How I Built the Ultimate Noctua G2 PC
-
PremiumAMD CES 2026 gaming trends press Q&A roundtable transcript — 'we see a little bit of an uptick in the percentage of AM4 versus AM5 platforms'
-
PremiumOngoing trade war has TSMC and Taiwan stuck between a rock and a hard place
-
PremiumASML projects $71 billion in revenue by 2030, as demand for EUV lithography machines intensifies due to AI boom
-
PremiumSamsung's Taylor, Texas fab could herald a breakthrough for the chipmaker, company plans 2026 risk production
-
PremiumSK hynix invests $10 billion in creating a U.S.-based 'AI solutions' company
-
