{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreiar5zaoacv4xnlcf2dmmkpck4t46vgbjjo7ogblmju7xwyrmbn35m",
    "uri": "at://did:plc:qzjwstutqk2cy7df7jbzd2hx/app.bsky.feed.post/3ml2xnihxwem2"
  },
  "coverImage": {
    "$type": "blob",
    "ref": {
      "$link": "bafkreiemkcn7supj5byvf77hpyfoqagsm6wuypac7ztsbl7cxecrpu752m"
    },
    "mimeType": "image/jpeg",
    "size": 6043366
  },
  "path": "/article/4166785/amd-and-intel-partner-to-deliver-ai-performance-advancement.html",
  "publishedAt": "2026-05-04T21:05:45.000Z",
  "site": "https://www.networkworld.com",
  "tags": [
    "CPUs and Processors, Industry, Markets, Technology Industry",
    "x86 Ecosystem Advisory Group (EAG",
    "AI workloads on x86 CPUs",
    "CPU and GPU",
    "Jim McGregor, principal analyst with TIRIAS Research.",
    "established in 2024"
  ],
  "textContent": "The first major fruits of the x86 Ecosystem Advisory Group (EAG) have come in the form of ACE, a new set of matrix instructions from Intel and AMD that the two claim deliver a massive AI performance leap over current instructions built into modern processors instruction such as Advanced Vector Extensions (AVX).\n\nACE, short for AI Compute Extensions, aims to unify AI workloads on x86 CPUs, enhancing energy efficiency and software compatibility so applications will run without breaking across both x86 platforms.\n\nACE offers a significant increase in the performance of matrix multiplication performance while offering scalability and energy efficiency. Matrix multiplication is a core math operation in AI where two grids of numbers are combined to produce a new grid of numbers. In AI, it’s the main way neural networks transform inputs into outputs, so it shows up throughout training and inference in deep learning models.\n\nCurrent Single Instruction, Multiple Data (SIMD) extensions, such as AVX used by both Intel and AMD, can do matrix multiplication, but their math multiplication is nowhere near that of GPUs, which are built for it. So ACE brings that same technology to the x86 CPU. ACE is not a replacement for AVX, but an extension of the instruction set.\n\nBut while this closes the gap between CPU and GPU for both inference and training, it still doesn’t make the CPU truly competitive with the GPU, says Jim McGregor, principal analyst with TIRIAS Research.\n\n“The CPU will never be more efficient than the GPU/AI accelerator,” he said. “However, it does allow you to offload some AI workloads to the CPU and/or use the CPU for AI workloads in applications that may not have a GPU or AI accelerator, such as embedded/edge applications.”\n\nThe EAG was established in 2024 to blunt the increasing competitiveness of the ARM architecture in the desktop and server environment. The goal was to end fragmentation between the two X86 architectures, and in that regard, this move succeeds. Even though Intel and AMD both make X86 chips, there is some fragmentation and incompatibility between the two lines, so this working together of the two companies is a positive sign. It ensures applications will run on either platform without requiring a recompile or change.\n\n“I’m pleased to see the partnership between the two companies finally paying off,” said McGregor. “As expected, changes to the instruction set can take a generation or two to filter through the product lines of both companies. However, working together is a huge advantage for the x86 architecture.”\n\nThe two firms did not announce any product, and there are no indications when they will be releasing products with ACE anytime soon.",
  "title": "AMD and Intel partner to deliver AI performance advancement"
}