Halide
LowerWarpShuffles.h
Go to the documentation of this file.
1
#ifndef HALIDE_LOWER_WARP_SHUFFLES_H
2
#define HALIDE_LOWER_WARP_SHUFFLES_H
3
4
/** \file
5
* Defines the lowering pass that injects CUDA warp shuffle
6
* instructions to access storage outside of a GPULane loop.
7
*/
8
9
#include "
Expr.h
"
10
11
namespace
Halide
{
12
namespace
Internal
{
13
14
/** Rewrite access to things stored outside the loop over GPU lanes to
15
* use nvidia's warp shuffle instructions. */
16
Stmt
lower_warp_shuffles
(Stmt s,
const
Target &t);
17
18
}
// namespace Internal
19
}
// namespace Halide
20
21
#endif
Halide
This file defines the class FunctionDAG, which is our representation of a Halide pipeline,...
Definition:
AbstractGenerator.h:19
Halide::LinkageType::Internal
@ Internal
Not visible externally, similar to 'static' linkage in C.
Halide::Internal::lower_warp_shuffles
Stmt lower_warp_shuffles(Stmt s, const Target &t)
Rewrite access to things stored outside the loop over GPU lanes to use nvidia's warp shuffle instruct...
Expr.h
src
LowerWarpShuffles.h
Generated by
1.8.17