Tag
Dmitry.GR criticizes RISC-V's design, arguing it is not optimal for all use cases, especially microcontrollers, due to issues with code density and interrupt latency.
Intel announced a $15B share offering to raise capital as AI-driven CPU demand outstrips manufacturing capacity, with 2026 capital spending increased from $18B to $20B.
NVIDIA highlights that AI agents operate in sequential loops where single-threaded speed matters more than core count, and introduces the Vera CPU designed to deliver maximum single-threaded performance across all 88 cores at scale.
An analytical critique of NVIDIA's Vera whitepaper, examining the Olympus core's impressive architecture while arguing that the paper's anti-x86 narrative and benchmark claims are overstated, with independent testing suggesting the hardware is genuinely strong.
AMD highlights that running cloud models for Blender and Hermes agent desktop still needs a powerful CPU, promoting Ryzen AI Agent Computers as the platform.
A game that lets players build a computer from scratch using logic gates, design circuits, construct a CPU, and run programs.
Liquid AI releases LFM2.5-Encoder-230M and LFM2.5-Encoder-350M, bidirectional encoders optimized for non-generative tasks like classification and retrieval, offering fast CPU inference at long context.
Microsoft announces general availability of Video Super Resolution for NPU and CPU, using on-device AI to enhance lower-resolution video quality.
A blog post by Mitchell Hashimoto arguing that SIMD (Single Instruction, Multiple Data) is simpler than often assumed, demonstrating a common pattern for using SIMD in loops with Zig examples.
Nvidia is promoting its new Vera Rubin chip system, which combines GPUs and CPUs, aiming to supply complete AI systems for data centers; OpenAI already has a rack in use.
A detailed technical explanation of how CPU caches work, covering the principle of locality, cache organization, indexing, and handling writes.
A review of the AMD Ryzen 7 7700X3D processor, highlighting its 3D V-Cache technology for improved gaming performance at a lower price point compared to higher-end X3D models.
A user released a BitNet trainer that Microsoft never published, along with custom kernels for training and inference, while also highlighting Microsoft's bitnet.cpp inference framework for fast 1-bit LLM inference on CPUs and GPUs.
cpu.land is a visual explainer that clarifies how CPUs work, multitasking, syscalls, and Linux program loading, aimed at filling knowledge gaps for self-taught programmers.
An analysis of whether AI agents are changing CPU recommendations for consumers.
NVIDIA introduces Vera, a new max single-threaded CPU designed for the agentic AI era, optimizing per-core performance to accelerate AI agent loops and maximize AI factory revenue.
User seeks advice on running llama.cpp with Gemma 4 E2B on an Intel N100 mini PC, asking whether to use CPU or iGPU and which backend to target.
An open-source tool converts PDFs, DOCX, PPTX, XLSX, EPUB, and images to markdown at 122 pages per second, supporting tables, equations, and forms on GPU, CPU, or Mac.
Hugging Face has added a new filter to its Models page that lets users filter by hardware compatibility (GPU, CPU, Apple Silicon), ensuring they only see models that can run on their machine. The filter stacks with other filters and is shareable via URL.
OpenAI co-founder Andrej Karpathy released llm.c, an open-source guide to training LLMs from scratch with simple code that runs on any hardware, including CPUs and MacBooks, and is 7% faster than standard approaches.