home.social

#xdna2 — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #xdna2, aggregated by home.social.

  1. Hello XDNA!

    We're documenting how to program AMD's NPUs in Ryzen AI chips.

    Our website covers the ISA, register files, operation latencies, and hand-optimized assembly kernels for tensor contractions.

    Measured single-compute-tile throughput:
    • XDNA1 (Ryzen 7 8700G): 398 BF16 GFLOPS (86% of peak)
    • XDNA2 (Ryzen AI Max PRO 390): 1760 BFP16 GFLOPS (95% of peak)

    tnzr.org/xdna