Install
CPUs & Processors
Desktop, mobile, and server silicon — architectures, sockets, thermals, and tuning.
- 6 Subtopics
- 12 Tracked terms
- Last 30 days Feed window
Inside CPUs & Processors
What this topic collects on
An article joins this feed when it matches these terms. Each one is also a search of its own.
Related topics
- Accessories
- Computers
- Laptops
- Motherboards
- Memory & Storage
- GPUs & Graphics
- Monitors & Displays
- Cases & Builds
- Cooling & Power
- Peripherals & Input
- Networking & Wi‑Fi
- Printers & Scanners
- IoT & Embedded
- Enterprise
- AR/VR & XR
- Creator & Streaming Gear
- Repair & Maintenance
- Standards & Connectivity
- Sustainability & Right to Repair
Latest in CPUs & Processors
Intel Crescent Island Squeezes 1.3 PFLOPs Of FP8 Into Just 350W As D270 Targets The Competition With Value-Oriented LPDDR5X Up To 480 GB
2+ hour, 5+ min ago (999+ words) Intel is announcing its D-Series GPUs, formerly Crescent Island, as the next AI data center lineup based on the Xe3P architecture. The Intel Crescent Island GPU is based on the brand-new Xe3P architecture, which is the same graphics architecture that was teased…...
Intel CEO Lip-Bu Tan Warns AI Hardware Shortage Will Last Two To Three Years & Says Sector Has To Show Return On Investment
1+ hour, 31+ min ago (446+ words) Intel CEO Lip-Bu Tan believes that the AI industry will continue to experience a hardware shortage for the next two to three years. Tan made the remarks at a conference organized by DBS Bank in Singapore, where he commented on…...
Intel GPU D-Series Packs 480GB LPDDR5X and 1.3 PFLOPS FP8 into a 350W PCIe Card
46+ min ago (177+ words) Home » News » Intel GPU D-Series Packs 480GB LPDDR5X and 1.3 PFLOPS FP8 into a 350W PCIe Card Intel first described Crescent Island at OCP 2025 and detailed the silicon at Hot Chips in August: 32 Xe cores and 256 XMX engines on Xe3P, with LPDDR5X in place of HBM so…...
Microsoft Maia 300 Puts 288GB of HBM4 at 18TB/s on an N2P Chiplet and 96 Accelerators in a 167kW Rack
46+ min ago (178+ words) Home » News » Microsoft Maia 300 Puts 288GB of HBM4 at 18TB/s on an N2P Chiplet and 96 Accelerators in a 167kW Rack Microsoft’s rack diagram shows jobs sharded across racks over the scale-up fabric with expert-parallel traffic between shards, which is the traffic pattern that large…...
AMD's Next-Gen Radeon GPUs May Not Arrive Until Late 2027 or 2028, Leaker Says
3+ hour ago (655+ words) AMD's next-generation RDNA 5 graphics architecture may not reach consumers until late 2027 or 2028, according to leaker Kepler_L2 and supply chain reports. The earliest announcement window is Computex 2027 in June, though a later reveal appears more likely. Only one GPU, codenamed AT2, is expected…...
Sorry Radeon Fans, AMD May Hold RDNA 5 Until Late 2027
2+ hour, 2+ min ago (27+ words) Reputable leaker @Kepler_L2 insists that AMD RDNA 5 GPUs won't arrive until late next year. Sorry Radeon Fans, AMD May Hold RDNA 5 Until Late 2027...
Intel aims to boost AI turnaround with new GPU chips to take on Nvidia
2+ hour, 1+ min ago (336+ words) Intel's (INTC) turnaround effort is getting a strong boost from the global AI build-out, which is driving increased demand for its central processing units (CPUs). But the company is also expanding further into the graphics processing unit (GPU) market with…...
Maia 300: Microsoft Builds the Exit From a Compute Landlord Model It Helped Finance
2+ hour ago (699+ words) Yahoo Finance Oops, something went wrong Maia 300: Microsoft Builds the Exit From a Compute Landlord Model It Helped Finance The Shift From Borrower to Builder Microsoft is no longer content to finance the dominance of the chipmakers it depends on....
AMD Announces Helion Rack System for Agentic AI with 32768 EPYC Cores
1+ hour, 29+ min ago (136+ words) Technetbook AMD Announces Helion Rack System for Agentic AI with 32768 EPYC Cores AMD has announced Helion, an open rack compute solution designed specifically for agentic artificial intelligence workloads. The architecture allows data centers to combine CPU and GPU resources flexibly,…...
Intel begins customer sampling of D-Series GPUs, expands AI infrastructure
1+ hour, 50+ min ago (467+ words) Intel's D270 data center GPU, formerly codenamed Crescent Island, bets on memory capacity and efficiency over raw training muscle Intel has started putting its new D-Series data center GPUs into customers’ hands for testing. The chips mark the company’s latest attempt…...