{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreigd7en2v5sw4lvn56mplsdw7bbp5tpqimaxj66czrcxwm5xub4niy",
    "uri": "at://did:plc:ax37ypwwfpozwkc552d7scv5/app.bsky.feed.post/3mlbm4sdmofe2"
  },
  "path": "/threads/new-dgf-supercompression-released-on-gpuopen.2634599/",
  "publishedAt": "2026-05-07T16:08:39.000Z",
  "site": "https://forums.anandtech.com",
  "tags": [
    "Graphics Cards",
    "Introducing AMD DGF SuperCompression - AMD GPUOpen",
    "Read more"
  ],
  "textContent": "###  \n\t\t\t\t\t\tIntroducing AMD DGF SuperCompression - AMD GPUOpen\n\t\t\t\t\t\n\nAMD DGF SuperCompression (DGFS) cuts DGF geometry file sizes while preserving exact block reconstruction and enabling fast decode to either DGF blocks or conventional meshlets for cross-device deployment.\n\ngpuopen.com\n\n\n\n\n> DGF was designed first and foremost as an efficient hardware format. Its design ensures that all of the information required for a particular triangle can be accessed using a single 128B aligned memory read. This property, although essential for efficient hardware ray traversal, has consequences which make it less appealing as a storage format. Vertex positions and compression parameters need to be duplicated across multiple blocks, and pad bits need to be inserted for data alignment, especially if blocks are not full.\n>\n> Click to expand...\n\n\n\n\n\n> We address this by introducing _DGF SuperCompression_ (DGFS), a software system which further compresses DGF data to reduce its storage cost. Geometry encoded with DGFS is no longer directly consumable by hardware, but can be made considerably smaller. DGFS is able to exactly reconstruct a given set of input DGF blocks, and also supports efficient decode to a conventional vertex...\n>\n> Click to expand...\n\n\nRead more",
  "title": "New DGF Supercompression released on GPUOpen"
}