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

Mojo function

preferred_simd_width

def preferred_simd_width[dtype: DType]() -> Int

SIMD scalar count for fused GPU concat vectorization.

Uses 32-byte global loads on sm_100a; otherwise the target's native simd_width_of for dtype on the active GPU compilation target.

Returns:

Int