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

verify_schedule

verify_schedule(program: PipelineProgram, config: PipelineConfig, lgkm_per_a: Int, lgkm_per_b: Int, wait_lgkm_first: Int, wait_vm_last: Int)

Verify structural invariants of a finalized pipeline schedule.

Runs at compile time — zero runtime cost. Catches bugs in schedule construction that would otherwise surface as silent GPU miscomputes.

Checks:

1. Block completeness: every block has exactly 1 MMA op
2. Wait count bounds: wait values are non-negative and bounded
3. Distribution invariant: uniform global loads when max_globals > 0
4. Stage consistency: fragment/global ops use correct stage for half
5. Prefetch coverage: at least one global is marked prefetch
6. Completion coverage: each half has a completion load
7. Warp stagger LDS safety: no cross-block prefetch/fragment race

Note: these are structural checks on the generated program. They do not verify that the execution ordering respects all LDG dependency edges — that is enforced by the scheduler (greedy_schedule / optimal_schedule) which only places ops whose d=0 predecessors are already scheduled.

Was this page helpful?

Thank you! We'll create more content like this.

Thank you for helping us improve!

😔 What went wrong?

Some code doesn’t work

It includes inaccurate information

It's missing information I need

It was difficult to understand

Other

Submit