hardNewNVIDIAAMDOpenAI

A cp.async double-buffered kernel fails a handful of CI runs and never fails under -G. Find the race and fix it.

The kernel passes every test you write by hand, and the debug build hides the bug. The answer reads one rule out of the PTX ISA, builds a repro that never fails yet still trips the sanitizer, and fixes the one line that clean-looking pipelines get wrong.

Updated Oct 2026 · Worked answers on inference mechanisms, with calculations, implementation details, and follow-up questions.

10 answers per topic instead of 5, plus saved progress and bookmarks · costs nothingor unlock all 213 remaining answers · $25

Every worked answer and derivation in all 12 topics, every concept page, the full practice-test bank, and every code drill’s edge-case tests and reference solution.

6 months · One payment · No auto-renewal

UP NEXT ON YOUR JOURNEY

Next in this trackA kernel PR claims 12x over eager PyTorch on the SwiGLU activation and passes the tests. How do you decide whether it is real?Popular right nowWhy is batch-1 decode on a 70B model bandwidth-bound, and what is its latency floor on two H100s?Popular right nowDecode attention intensity is fixed at the query-to-KV head ratio. Derive that, then tell me what MLA does to it.

DISCUSSION · 0

Nobody has commented on this answer. Add a correction or another way to work it.