Skip to main content

__tile_dpbf8ps

core::arch::x86_64

Function __tile_dpbf8ps 

Source 
pub unsafe fn __tile_dpbf8ps(
    dst: *mut __tile1024i,
    a: __tile1024i,
    b: __tile1024i,
)
🔬This is a nightly-only experimental API. (x86_amx_intrinsics #126622)
Available on x86-64 and target feature amx-fp8 only.
Expand description

Compute dot-product of BF8 (8-bit E5M2) floating-point elements in tile a and BF8 (8-bit E5M2) floating-point elements in tile b, accumulating the intermediate single-precision (32-bit) floating-point elements with elements in dst, and store the 32-bit result back to tile dst. The shape of the tile is specified in the struct of __tile1024i. The register of the tile is allocated by the compiler.