Revision aa696b54a17d5939ebb61ff14965bf0ce16dcd7a authored by Volodymyr Kysenko on 27 February 2024, 22:28:14 UTC, committed by GitHub on 27 February 2024, 22:28:14 UTC
* [Xtensa codegen] Specializations for load/store and fma support * format
1 parent 85b6d7e
LowerWarpShuffles.h
#ifndef HALIDE_LOWER_WARP_SHUFFLES_H
#define HALIDE_LOWER_WARP_SHUFFLES_H
/** \file
* Defines the lowering pass that injects CUDA warp shuffle
* instructions to access storage outside of a GPULane loop.
*/
#include "Expr.h"
namespace Halide {
namespace Internal {
/** Rewrite access to things stored outside the loop over GPU lanes to
* use nvidia's warp shuffle instructions. */
Stmt lower_warp_shuffles(Stmt s, const Target &t);
} // namespace Internal
} // namespace Halide
#endif
Computing file changes ...
