Files
clang-p2996/llvm/lib/Target/AMDGPU/AMDGPUInstrInfo.h
Nicolai Haehnle 2f5a73820c AMDGPU: Dimension-aware image intrinsics
Summary:
These new image intrinsics contain the texture type as part of
their name and have each component of the address/coordinate as
individual parameters.

This is a preparatory step for implementing the A16 feature, where
coordinates are passed as half-floats or -ints, but the Z compare
value and texel offsets are still full dwords, making it difficult
or impossible to distinguish between A16 on or off in the old-style
intrinsics.

Additionally, these intrinsics pass the 'texfailpolicy' and
'cachectrl' as i32 bit fields to reduce operand clutter and allow
for future extensibility.

v2:
- gather4 supports 2darray images
- fix a bug with 1D images on SI

Change-Id: I099f309e0a394082a5901ea196c3967afb867f04

Reviewers: arsenm, rampitec, b-sumner

Subscribers: kzhuravl, wdng, yaxunl, dstuttard, tpr, llvm-commits, t-tye

Differential Revision: https://reviews.llvm.org/D44939

llvm-svn: 329166
2018-04-04 10:58:54 +00:00

76 lines
2.0 KiB
C++

//===-- AMDGPUInstrInfo.h - AMDGPU Instruction Information ------*- C++ -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
/// \file
/// \brief Contains the definition of a TargetInstrInfo class that is common
/// to all AMD GPUs.
//
//===----------------------------------------------------------------------===//
#ifndef LLVM_LIB_TARGET_AMDGPU_AMDGPUINSTRINFO_H
#define LLVM_LIB_TARGET_AMDGPU_AMDGPUINSTRINFO_H
#include "AMDGPU.h"
#include "Utils/AMDGPUBaseInfo.h"
#include "llvm/CodeGen/TargetInstrInfo.h"
#define GET_INSTRINFO_HEADER
#include "AMDGPUGenInstrInfo.inc"
#undef GET_INSTRINFO_HEADER
namespace llvm {
class AMDGPUSubtarget;
class MachineFunction;
class MachineInstr;
class MachineInstrBuilder;
class AMDGPUInstrInfo : public AMDGPUGenInstrInfo {
private:
const AMDGPUSubtarget &ST;
virtual void anchor();
protected:
AMDGPUAS AMDGPUASI;
public:
explicit AMDGPUInstrInfo(const AMDGPUSubtarget &st);
bool shouldScheduleLoadsNear(SDNode *Load1, SDNode *Load2,
int64_t Offset1, int64_t Offset2,
unsigned NumLoads) const override;
/// \brief Return a target-specific opcode if Opcode is a pseudo instruction.
/// Return -1 if the target-specific opcode for the pseudo instruction does
/// not exist. If Opcode is not a pseudo instruction, this is identity.
int pseudoToMCOpcode(int Opcode) const;
static bool isUniformMMO(const MachineMemOperand *MMO);
};
namespace AMDGPU {
struct RsrcIntrinsic {
unsigned Intr;
uint8_t RsrcArg;
bool IsImage;
};
const RsrcIntrinsic *lookupRsrcIntrinsicByIntr(unsigned Intr);
struct D16ImageDimIntrinsic {
unsigned Intr;
unsigned D16HelperIntr;
};
const D16ImageDimIntrinsic *lookupD16ImageDimIntrinsicByIntr(unsigned Intr);
} // end AMDGPU namespace
} // End llvm namespace
#endif