Skip to main content

10 docs tagged with "patterns"

View all tags

Parallel Patterns

Almost every GPU kernel, however specialized, is built from a small set of recurring data-access shapes. Recognizing which pattern a problem is — before writing any code — tells you how parallelizable it is, what its likely performance limiter will be, and often points directly at a library implementation that already exists and is already tuned. This page names those shapes once, and every later applied-kernel page in this knowledge base assumes you already know these names — "this is a reduction" or "this needs a scan" is meant to carry full meaning by the time you reach folder 13.

Pattern flags

The pattern controls the line around your message — timestamp, level, logger name, thread id — and