Revision 799236949867b6a2be0d492137b36a0b67011622 authored by Andrew Adams on 07 December 2021, 16:16:50 UTC, committed by GitHub on 07 December 2021, 16:16:50 UTC
* Add a version of fast_integer_divide that rounds towards zero * clang-format * Fix test condition * Clean up debugging code * Add explanatory comment to performance test * Pacify clang tidy
1 parent fb305fd
LoopCarry.h
#ifndef HALIDE_LOOP_CARRY_H
#define HALIDE_LOOP_CARRY_H
#include "Expr.h"
namespace Halide {
namespace Internal {
/** Reuse loads done on previous loop iterations by stashing them in
* induction variables instead of redoing the load. If the loads are
* predicated, the predicates need to match. Can be an optimization or
* pessimization depending on how good the L1 cache is on the architecture
* and how many memory issue slots there are. Currently only intended
* for Hexagon. */
Stmt loop_carry(Stmt, int max_carried_values = 8);
} // namespace Internal
} // namespace Halide
#endif
Computing file changes ...
