For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /get-started.md).

Mojo function

tc_reduce_gevm_4x

def tc_reduce_gevm_4x[out_type: DType, in_type: DType, simd_width: Int](val1: SIMD[in_type, simd_width]) -> SIMD[out_type, simd_width]

Performs a 4x GEVM reduction using tensor cores.

Note: Currently only supports bfloat16 input to float32 output conversion. Uses tensor core matrix multiply-accumulate (MMA) operations for reduction.

Parameters:

out_type (DType): The output data type for the reduction result (must be float32).
in_type (DType): The input data type of the vector to reduce (must be bfloat16).
simd_width (Int): The width of the SIMD vector.

Args:

val1 (SIMD[in_type, simd_width]): Input SIMD vector to reduce.

Returns:

SIMD[out_type, simd_width]: SIMD vector containing the reduced result.