#include "mlir/Dialect/AMDGPU/Transforms/Passes.h"
#include "mlir/Dialect/AMDGPU/IR/AMDGPUDialect.h"
#include "mlir/Dialect/Affine/IR/AffineOps.h"
#include "mlir/Dialect/Arith/IR/Arith.h"
#include "mlir/Dialect/MemRef/IR/MemRef.h"
#include "mlir/Dialect/MemRef/Utils/MemRefUtils.h"
#include "mlir/Dialect/SCF/IR/SCF.h"
#include "mlir/Dialect/Vector/IR/VectorOps.h"
#include "mlir/IR/BuiltinTypes.h"
#include "mlir/IR/OpDefinition.h"
#include "mlir/IR/PatternMatch.h"
#include "mlir/IR/TypeUtilities.h"
#include "mlir/Pass/Pass.h"
#include "mlir/Support/LogicalResult.h"
#include "mlir/Transforms/GreedyPatternRewriteDriver.h"
#include "llvm/Support/MathExtras.h"
#include "mlir/Dialect/AMDGPU/Transforms/Passes.h.inc"

Classes
struct	AmdgpuTransferReadToLoadPass

Namespaces
	mlir
	Include the generated interface declarations.

	mlir::amdgpu

Macros
#define	GEN_PASS_DEF_AMDGPUTRANSFERREADTOLOADPASS

Functions
static LogicalResult	transferPreconditions (PatternRewriter &rewriter, VectorTransferOpInterface xferOp, bool &requiresBroadcasting, VectorType &unbroadcastedVectorType)
	This pattern supports lowering of: `vector.transfer_read` to a combination of `vector.load`, `arith.select` and `vector.broadcast` if all of the following hold: More...

static Value	createVectorLoadForMaskedLoad (OpBuilder &builder, Location loc, vector::TransferReadOp readOp, bool requiresBroadcasting, VectorType unbroadcastedVectorType)

Variables
static constexpr char	kTransferReadNeedsMask []

Macro Definition Documentation

◆ GEN_PASS_DEF_AMDGPUTRANSFERREADTOLOADPASS

#define GEN_PASS_DEF_AMDGPUTRANSFERREADTOLOADPASS

Definition at line 28 of file TransferReadToLoad.cpp.

Function Documentation

◆ createVectorLoadForMaskedLoad()

static Value createVectorLoadForMaskedLoad	(	OpBuilder &	builder,
		Location	loc,
		vector::TransferReadOp	readOp,
		bool	requiresBroadcasting,
		VectorType	unbroadcastedVectorType
	)

static

Definition at line 114 of file TransferReadToLoad.cpp.

References mlir::OpBuilder::create().

◆ transferPreconditions()

static LogicalResult transferPreconditions	(	PatternRewriter &	rewriter,
		VectorTransferOpInterface	xferOp,
		bool &	requiresBroadcasting,
		VectorType &	unbroadcastedVectorType
	)

static

This pattern supports lowering of: vector.transfer_read to a combination of vector.load, arith.select and vector.broadcast if all of the following hold:

The transfer op is masked.
The memref is in buffer address space.
Stride of most minor memref dimension must be 1.
Out-of-bounds masking is not required.
If the memref's element type is a vector type then it coincides with the result type.
The permutation map doesn't perform permutation (broadcasting is allowed). Note: those conditions mostly come from TransferReadToVectorLoadLowering pass.

Definition at line 47 of file TransferReadToLoad.cpp.

References mlir::RewriterBase::notifyMatchFailure(), and vectorShape().

Variable Documentation

◆ kTransferReadNeedsMask

constexpr char kTransferReadNeedsMask[]

staticconstexpr

Initial value:

=

"amdgpu.buffer_transfer_read_needs_mask"

Definition at line 131 of file TransferReadToLoad.cpp.

Classes

Namespaces

Macros

Functions