Revision 3657cf5f363fd64aeaf06432e62e3960800927b0 authored by Andrew Adams on 26 January 2024, 17:26:12 UTC, committed by GitHub on 26 January 2024, 17:26:12 UTC
* Fix bounds_of_nested_lanes bounds_of_nested_lanes assumed that one layer of nested vectorization could be removed at a time. When faced with the expression: min(ramp(x8(a), x8(b), 5), x40(27)) It panicked, because on the left hand side it reduced the bounds to x8(a) ... x8(a) + x8(b) * 4, and on the right hand side it reduced the bounds to 27. It then attempted to take a min of mismatched types. In general we can't assume that binary operators on nested vectors have the same nesting structure on both sides, so I just rewrote it to reduce directly to a scalar. Fixes #8038
1 parent 4590a09
RebaseLoopsToZero.h
#ifndef HALIDE_REBASE_LOOPS_TO_ZERO_H
#define HALIDE_REBASE_LOOPS_TO_ZERO_H
/** \file
* Defines the lowering pass that rewrites loop mins to be 0.
*/
#include "Expr.h"
namespace Halide {
namespace Internal {
/** Rewrite the mins of most loops to 0. */
Stmt rebase_loops_to_zero(const Stmt &);
} // namespace Internal
} // namespace Halide
#endif
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...