IMPORTANT: To view this page as Markdown, append `.md` to the URL (e.g. /docs/manual/basics.md). For the complete Mojo documentation index, see llms.txt.
Skip to main content
Version: Nightly
For the complete Mojo documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /docs/manual/basics.md).

build_edge_mask

def build_edge_mask(index: Int32, lower_bound: Int32, upper_bound: Int32) -> Int16

Computes the per-lane edge mask for a vector access (Apple M5 only).

Bit i of the result is set when element index + i lies in [lower_bound, upper_bound). Pass it as an *edge_masked_load mask. Emits the AGX3 edgecheck instruction.

Args:

  • ​index (Int32): Linear element index of lane 0.
  • ​lower_bound (Int32): Inclusive lower bound of the valid range.
  • ​upper_bound (Int32): Exclusive upper bound of the valid range.

Returns:

Int16: A 16-bit per-lane mask (up to 4 lanes).

View source