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
lane_group_sum
def lane_group_sum[val_type: DType, simd_width: SIMDLength, //, num_lanes: Int, stride: Int = Int(1)](val: SIMD[val_type, simd_width]) -> SIMD[val_type, simd_width]
Computes the sum of values across a group of lanes and broadcasts to all lanes.
This function performs a parallel reduction across a group of lanes to compute their sum. The result is broadcast to all participating lanes using optimized hardware-specific paths (AMD DPP, Blackwell redux, or butterfly shuffle pattern).
Parameters:
- val_type (
DType): The data type of the SIMD elements (e.g. float32, int32). - simd_width (
SIMDLength): The number of elements in the SIMD vector. - num_lanes (
Int): The number of threads participating in the reduction. - stride (
Int): The stride between lanes participating in the reduction.
Args:
- val (
SIMD[val_type, simd_width]): The SIMD value to reduce. Each lane contributes its value to the sum.
Returns:
SIMD[val_type, simd_width]: A SIMD value where all participating lanes contain the sum found across the lane group.
Non-participating lanes (lane_id >= num_lanes) retain their original values.