home.social

#processors — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #processors, aggregated by home.social.

fetched live
  1. SPIR-V on ROCm: A Portable IR for AMD GPUs:

    "ROCm has compiled GPU code ahead of time (AOT), once per target architecture, since its first release. CPU software shifted to runtime just-in-time (JIT) compilation in the 1990s — Java HotSpot, V8, LuaJIT, .NET RyuJIT, PyPy — once the matrix of target × workload × deployment became too large to enumerate at build time. With its adoption of SPIR-V, ROCm now brings the compile-once, specialize-on-device model to AMD GPUs.
    This post covers what SPIR-V is, why AMD adopted it, the compilation model and its trade-offs, and a reproducible single-kernel HIP example with measurements on MI350X (CDNA4), spot-checked on RX 9070 XT (RDNA4). A FAQ and status section at the end cover common questions and what is shipping, in flight, and not yet solved.

    A follow-up post will discuss a real-world SPIR-V deployment at scale: PyTorch."

    rocm.blogs.amd.com/software-to

    #cybersecurity #informationsecurity #processors #architecture #infosec

  2. For #intel #processors If the 586 is the #pentium then:

    286 Duonium
    386 Trium
    486 Tetrium
    686 Hexium
    786 Heptium

    And the Pentium Pro is 686, then the proper name of the Pentium 2 is actually the Hexium 2, as it's the second 686 chip!

    Pentium 4 was netburst, so it would be the Heptium 1.

    #biblicallyaccuratecpunaming

  3. winbuzzer.com/2026/06/01/nvidi

    Nvidia has unveiled its RTX Spark superchip for Windows PCs, pairing GB10 Grace Blackwell hardware with local AI features, unified memory and OEM launches later in 2026.

    #AI #DGXSpark #NVIDIA #WindowsOnARM #WindowsPCs #ARM #AIChips #OnDeviceAI #Semiconductors #Processors #Laptops

  4. winbuzzer.com/2026/05/27/nvidi

    Early public Vera benchmark results put Nvidia's in-house server CPU ahead of compared AMD EPYC and Intel Xeon parts, but only inside a workload set Nvidia controlled.

    #AI #VeraCPU #AMDEPYC #IntelXeon #Xeon #Benchmarks #NVIDIA #AMD #Intel #Processors #CPUs

  5. winbuzzer.com/2026/05/25/samsu

    Samsung is reportedly using its memory-chip leverage to try to pry MediaTek's Dimensity foundry business away from TSMC, with Chairman Lee Jae-yong personally pitching the bundle in a discreet May 21 Taiwan visit.

    #MediaTek #Samsung #TSMC #Qualcomm #SamsungFoundry #Snapdragon #Memory #Processors #Semiconductors #ChipIndustry

  6. AMD’s push to bring dedicated AI acceleration to desktops signals that “AI PCs” are becoming a standard expectation, not just a premium feature. However, the real value will depend on how widely software developers adopt and optimize applications for these on-device AI capabilities.

    amd.com/en/blogs/2026/amd-ryze

    #AMD #Ryzen #AIPC #ArtificialIntelligence #TechInnovation #Processors #PCGaming #EnterpriseTech #technology