On Tue, 2025-09-02 at 12:04 +0530, soum...@nvidia.com wrote: > From: Soumya AR <soum...@nvidia.com> > > This patch extends various compiler components to handle the newly > added > atomic fetch min/max builtins: >
[...] > > 3. Static Analyzer: Extended kf_atomic_fetch_op and > kf_atomic_op_fetch classes > to model the behavior of atomic min/max builtins. > Note: The analyzer currently doesn't recognize ternary operators > (e.g., i < j ? i : j) as MIN_EXPR/MAX_EXPR, so analyzer tests use > constants > to verify correct min/max computation in memory. I can't speak to the rest of the patch, but the analyzer parts look reasonable to me. [...] Thanks Dave
