Skip to content
  • NVIDIA L40S (Driver Version: 570.133.20 CUDA Version: 12.8. SM89)

    ** LOADED DATA **
    LO_LEN 1073741824
    ** LOADED DATA TO GPU **
    TILING + LOCAL + COALESCING (CRYSTAL)
            {"final_count":966259449(89.9899%),"R111":13.2487}
            {"final_count":966259449(89.9899%),"R111":13.1103}
            {"final_count":966259449(89.9899%),"R111":13.1348}
    TILING + LOCAL + LINEAR
            {"final_count":966259449(89.9899%),"R110":12.4592}
            {"final_count":966259449(89.9899%),"R110":12.4684}
            {"final_count":966259449(89.9899%),"R110":12.4359}
    TILING + GLOBAL + COALESCING
            {"final_count":966259449(89.9899%),"R101":12.294}
            {"final_count":966259449(89.9899%),"R101":12.2763}
            {"final_count":966259449(89.9899%),"R101":12.3054}
    TILING + GLOBAL + LINEAR
            {"final_count":966259449(89.9899%),"R100":13.2651}
            {"final_count":966259449(89.9899%),"R100":13.3097}
            {"final_count":966259449(89.9899%),"R100":13.238}
    DIRECT + LOCAL + COALESCING
            {"final_count":966259449(89.9899%),"R011":13.0392}
            {"final_count":966259449(89.9899%),"R011":12.9193}
            {"final_count":966259449(89.9899%),"R011":12.9459}
    DIRECT + LOCAL + LINEAR
            {"final_count":966259449(89.9899%),"R010":12.9164}
            {"final_count":966259449(89.9899%),"R010":12.8506}
            {"final_count":966259449(89.9899%),"R010":12.8806}
    DIRECT + GLOBAL + COALESCING
            {"final_count":966259449(89.9899%),"R001":12.9909}
            {"final_count":966259449(89.9899%),"R001":12.9593}
            {"final_count":966259449(89.9899%),"R001":12.9022}
    DIRECT + GLOBAL + LINEAR
            {"final_count":966259449(89.9899%),"R000":12.9106}
            {"final_count":966259449(89.9899%),"R000":12.9319}
            {"final_count":966259449(89.9899%),"R000":12.8446}
    ```
    Edited by Ivan Kabadzhov
  • NVIDIA GeForce RTX 2080 Ti (Driver Version: 560.35.05 CUDA Version: 12.6. SM75)

    ** LOADED DATA **
    LO_LEN 1073741824
    ** LOADED DATA TO GPU **
    TILING + LOCAL + COALESCING (CRYSTAL)
            {"final_count":966259449(89.9899%),"R111":16.2938}
            {"final_count":966259449(89.9899%),"R111":16.2958}
            {"final_count":966259449(89.9899%),"R111":16.3005}
    TILING + LOCAL + LINEAR
            {"final_count":966259449(89.9899%),"R110":16.1162}
            {"final_count":966259449(89.9899%),"R110":16.117}
            {"final_count":966259449(89.9899%),"R110":16.117}
    TILING + GLOBAL + COALESCING
            {"final_count":966259449(89.9899%),"R101":16.0997}
            {"final_count":966259449(89.9899%),"R101":16.0932}
            {"final_count":966259449(89.9899%),"R101":16.1033}
    TILING + GLOBAL + LINEAR
            {"final_count":966259449(89.9899%),"R100":16.1029}
            {"final_count":966259449(89.9899%),"R100":16.1004}
            {"final_count":966259449(89.9899%),"R100":16.1034}
    DIRECT + LOCAL + COALESCING
            {"final_count":966259449(89.9899%),"R011":16.0996}
            {"final_count":966259449(89.9899%),"R011":16.0954}
            {"final_count":966259449(89.9899%),"R011":16.0958}
    DIRECT + LOCAL + LINEAR
            {"final_count":966259449(89.9899%),"R010":16.0954}
            {"final_count":966259449(89.9899%),"R010":16.0911}
            {"final_count":966259449(89.9899%),"R010":16.096}
    DIRECT + GLOBAL + COALESCING
            {"final_count":966259449(89.9899%),"R001":16.0925}
            {"final_count":966259449(89.9899%),"R001":16.0921}
            {"final_count":966259449(89.9899%),"R001":16.0933}
    DIRECT + GLOBAL + LINEAR
            {"final_count":966259449(89.9899%),"R000":16.0932}
            {"final_count":966259449(89.9899%),"R000":16.0928}
            {"final_count":966259449(89.9899%),"R000":16.0938}
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Please register or to comment