maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/lib/Target/AMDGPU/R600ISelLowering.h

113 lines
4.8 KiB
C
Raw Normal View History

Add R600 backend A new backend supporting AMD GPUs: Radeon HD2XXX - HD7XXX llvm-svn: 169915
2012-12-12 05:25:42 +08:00
//===-- R600ISelLowering.h - R600 DAG Lowering Interface -*- C++ -*--------===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
/// \file
Remove \brief commands from doxygen comments. We've been running doxygen with the autobrief option for a couple of years now. This makes the \brief markers into our comments redundant. Since they are a visual distraction and we don't want to encourage more \brief markers in new code either, this patch removes them all. Patch produced by for i in $(git grep -l '\\brief'); do perl -pi -e 's/\\brief //g' $i & done Differential Revision: https://reviews.llvm.org/D46290 llvm-svn: 331272
2018-05-01 23:54:18 +08:00
/// R600 DAG Lowering interface definition
Add R600 backend A new backend supporting AMD GPUs: Radeon HD2XXX - HD7XXX llvm-svn: 169915
2012-12-12 05:25:42 +08:00
//
//===----------------------------------------------------------------------===//
AMDGPU: R600 code splitting cleanup Move a few functions only used by R600 to R600 specific code, fix header macros to stop using R600, mark classes as final. llvm-svn: 263204
2016-03-11 16:00:27 +08:00
#ifndef LLVM_LIB_TARGET_AMDGPU_R600ISELLOWERING_H
#define LLVM_LIB_TARGET_AMDGPU_R600ISELLOWERING_H
Add R600 backend A new backend supporting AMD GPUs: Radeon HD2XXX - HD7XXX llvm-svn: 169915
2012-12-12 05:25:42 +08:00
#include "AMDGPUISelLowering.h"
namespace llvm {
class R600InstrInfo;
AMDGPU: Cleanup subtarget handling. Split AMDGPUSubtarget into amdgcn/r600 specific subclasses. This removes most of the static_casting of the basic codegen classes everywhere, and tries to restrict the features visible on the wrong target. llvm-svn: 273652
2016-06-24 14:30:11 +08:00
class R600Subtarget;
Add R600 backend A new backend supporting AMD GPUs: Radeon HD2XXX - HD7XXX llvm-svn: 169915
2012-12-12 05:25:42 +08:00
AMDGPU: R600 code splitting cleanup Move a few functions only used by R600 to R600 specific code, fix header macros to stop using R600, mark classes as final. llvm-svn: 263204
2016-03-11 16:00:27 +08:00
class R600TargetLowering final : public AMDGPUTargetLowering {
AMDGPU: Separate R600 and GCN TableGen files Summary: We now have two sets of generated TableGen files, one for R600 and one for GCN, so each sub-target now has its own tables of instructions, registers, ISel patterns, etc. This should help reduce compile time since each sub-target now only has to consider information that is specific to itself. This will also help prevent the R600 sub-target from slowing down new features for GCN, like disassembler support, GlobalISel, etc. Reviewers: arsenm, nhaehnle, jvesely Reviewed By: arsenm Subscribers: MatzeB, kzhuravl, wdng, mgorny, yaxunl, dstuttard, tpr, t-tye, javed.absar, llvm-commits Differential Revision: https://reviews.llvm.org/D46365 llvm-svn: 335942
2018-06-29 07:47:12 +08:00
const R600Subtarget *Subtarget;
Add R600 backend A new backend supporting AMD GPUs: Radeon HD2XXX - HD7XXX llvm-svn: 169915
2012-12-12 05:25:42 +08:00
public:
AMDGPU: Cleanup subtarget handling. Split AMDGPUSubtarget into amdgcn/r600 specific subclasses. This removes most of the static_casting of the basic codegen classes everywhere, and tries to restrict the features visible on the wrong target. llvm-svn: 273652
2016-06-24 14:30:11 +08:00
R600TargetLowering(const TargetMachine &TM, const R600Subtarget &STI);
const R600Subtarget *getSubtarget() const;
CodeGen: Use MachineInstr& in TargetLowering, NFC This is a mechanical change to make TargetLowering API take MachineInstr& (instead of MachineInstr*), since the argument is expected to be a valid MachineInstr. In one case, changed a parameter from MachineInstr* to MachineBasicBlock::iterator, since it was used as an insertion point. As a side effect, this removes a bunch of MachineInstr* to MachineBasicBlock::iterator implicit conversions, a necessary step toward fixing PR26753. llvm-svn: 274287
2016-07-01 06:52:52 +08:00
MachineBasicBlock *
EmitInstrWithCustomInserter(MachineInstr &MI,
MachineBasicBlock *BB) const override;
[C++11] Add 'override' keywords and remove 'virtual'. Additionally add 'final' and leave 'virtual' on some methods that are marked virtual without overriding anything and have no obvious overrides themselves. R600 edition llvm-svn: 207503
2014-04-29 15:57:24 +08:00
SDValue LowerOperation(SDValue Op, SelectionDAG &DAG) const override;
SDValue PerformDAGCombine(SDNode *N, DAGCombinerInfo &DCI) const override;
void ReplaceNodeResults(SDNode * N,
SmallVectorImpl<SDValue> &Results,
SelectionDAG &DAG) const override;
AMDGPU: Separate R600 and GCN TableGen files Summary: We now have two sets of generated TableGen files, one for R600 and one for GCN, so each sub-target now has its own tables of instructions, registers, ISel patterns, etc. This should help reduce compile time since each sub-target now only has to consider information that is specific to itself. This will also help prevent the R600 sub-target from slowing down new features for GCN, like disassembler support, GlobalISel, etc. Reviewers: arsenm, nhaehnle, jvesely Reviewed By: arsenm Subscribers: MatzeB, kzhuravl, wdng, mgorny, yaxunl, dstuttard, tpr, t-tye, javed.absar, llvm-commits Differential Revision: https://reviews.llvm.org/D46365 llvm-svn: 335942
2018-06-29 07:47:12 +08:00
CCAssignFn *CCAssignFnForCall(CallingConv::ID CC, bool IsVarArg) const;
Pass DebugLoc and SDLoc by const ref. This used to be free, copying and moving DebugLocs became expensive after the metadata rewrite. Passing by reference eliminates a ton of track/untrack operations. No functionality change intended. llvm-svn: 272512
2016-06-12 23:39:02 +08:00
SDValue LowerFormalArguments(SDValue Chain, CallingConv::ID CallConv,
bool isVarArg,
const SmallVectorImpl<ISD::InputArg> &Ins,
const SDLoc &DL, SelectionDAG &DAG,
SmallVectorImpl<SDValue> &InVals) const override;
Make TargetLowering::getPointerTy() taking DataLayout as an argument Summary: This change is part of a series of commits dedicated to have a single DataLayout during compilation by using always the one owned by the module. Reviewers: echristo Subscribers: jholewinski, ted, yaron.keren, rafael, llvm-commits Differential Revision: http://reviews.llvm.org/D11028 From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 241775
2015-07-09 10:09:04 +08:00
EVT getSetCCResultType(const DataLayout &DL, LLVMContext &,
EVT VT) const override;
AMDGPU/R600: Implement allowsMisalignedMemoryAccess This avoids some test regressions in a future commit when unaligned operations are expanded when they have custom lowering. llvm-svn: 261570
2016-02-23 05:04:16 +08:00
Add DAG argument to canMergeStoresTo NFC. llvm-svn: 307583
2017-07-11 04:25:54 +08:00
bool canMergeStoresTo(unsigned AS, EVT MemVT,
const SelectionDAG &DAG) const override;
[AMDGPU] Prevent too large store merges in AMDGPU Subtargets. NFCI. Various address spaces on the SI and R600 subtargets have stricter limits on memory access size that other address spaces. Use canMergeStoresTo predicate to prevent the DAGCombiner from creating these stores as they will be split up during legalization. llvm-svn: 303767
2017-05-24 23:59:09 +08:00
AMDGPU/R600: Implement allowsMisalignedMemoryAccess This avoids some test regressions in a future commit when unaligned operations are expanded when they have custom lowering. llvm-svn: 261570
2016-02-23 05:04:16 +08:00
bool allowsMisalignedMemoryAccesses(EVT VT, unsigned AS,
unsigned Align,
bool *IsFast) const override;
Make TargetLowering::getPointerTy() taking DataLayout as an argument Summary: This change is part of a series of commits dedicated to have a single DataLayout during compilation by using always the one owned by the module. Reviewers: echristo Subscribers: jholewinski, ted, yaron.keren, rafael, llvm-commits Differential Revision: http://reviews.llvm.org/D11028 From: Mehdi Amini <mehdi.amini@apple.com> llvm-svn: 241775
2015-07-09 10:09:04 +08:00
Add R600 backend A new backend supporting AMD GPUs: Radeon HD2XXX - HD7XXX llvm-svn: 169915
2012-12-12 05:25:42 +08:00
private:
R600: Use DAG lowering pass to handle fcos/fsin NOTE: This is a candidate for the stable branch. llvm-svn: 185940
2013-07-09 23:03:11 +08:00
unsigned Gen;
Add R600 backend A new backend supporting AMD GPUs: Radeon HD2XXX - HD7XXX llvm-svn: 169915
2012-12-12 05:25:42 +08:00
/// Each OpenCL kernel has nine implicit parameters that are stored in the
/// first nine dwords of a Vertex Buffer. These implicit parameters are
Fix known typos Sweep the codebase for common typos. Includes some changes to visible function names that were misspelt. llvm-svn: 200018
2014-01-25 01:20:08 +08:00
/// lowered to load instructions which retrieve the values from the Vertex
Add R600 backend A new backend supporting AMD GPUs: Radeon HD2XXX - HD7XXX llvm-svn: 169915
2012-12-12 05:25:42 +08:00
/// Buffer.
Pass DebugLoc and SDLoc by const ref. This used to be free, copying and moving DebugLocs became expensive after the metadata rewrite. Passing by reference eliminates a ton of track/untrack operations. No functionality change intended. llvm-svn: 272512
2016-06-12 23:39:02 +08:00
SDValue LowerImplicitParameter(SelectionDAG &DAG, EVT VT, const SDLoc &DL,
unsigned DwordOffset) const;
Add R600 backend A new backend supporting AMD GPUs: Radeon HD2XXX - HD7XXX llvm-svn: 169915
2012-12-12 05:25:42 +08:00
void lowerImplicitParameter(MachineInstr *MI, MachineBasicBlock &BB,
MachineRegisterInfo & MRI, unsigned dword_offset) const;
Reapply r235977 "[DebugInfo] Add debug locations to constant SD nodes" [DebugInfo] Add debug locations to constant SD nodes This adds debug location to constant nodes of Selection DAG and updates all places that create constants to pass debug locations (see PR13269). Can't guarantee that all locations are correct, but in a lot of cases choice is obvious, so most of them should be. At least all tests pass. Tests for these changes do not cover everything, instead just check it for SDNodes, ARM and AArch64 where it's easy to get incorrect locations on constants. This is not complete fix as FastISel contains workaround for wrong debug locations, which drops locations from instructions on processing constants, but there isn't currently a way to use debug locations from constants there as llvm::Constant doesn't cache it (yet). Although this is a bit different issue, not directly related to these changes. Differential Revision: http://reviews.llvm.org/D9084 llvm-svn: 235989
2015-04-28 22:05:47 +08:00
SDValue OptimizeSwizzle(SDValue BuildVector, SDValue Swz[], SelectionDAG &DAG,
Pass DebugLoc and SDLoc by const ref. This used to be free, copying and moving DebugLocs became expensive after the metadata rewrite. Passing by reference eliminates a ton of track/untrack operations. No functionality change intended. llvm-svn: 272512
2016-06-12 23:39:02 +08:00
const SDLoc &DL) const;
R600: Use LDS and vectors for private memory llvm-svn: 211110
2014-06-18 00:53:14 +08:00
SDValue vectorToVerticalVector(SelectionDAG &DAG, SDValue Vector) const;
Add R600 backend A new backend supporting AMD GPUs: Radeon HD2XXX - HD7XXX llvm-svn: 169915
2012-12-12 05:25:42 +08:00
AMDGPU: Move function only used by R600 llvm-svn: 262853
2016-03-08 05:10:13 +08:00
SDValue lowerFrameIndex(SDValue Op, SelectionDAG &DAG) const;
R600: Use LDS and vectors for private memory llvm-svn: 211110
2014-06-18 00:53:14 +08:00
SDValue LowerEXTRACT_VECTOR_ELT(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerINSERT_VECTOR_ELT(SDValue Op, SelectionDAG &DAG) const;
AMDGPU: Move R600 specific code out of AMDGPUISelLowering.cpp Reviewers: arsenm Subscribers: jvesely, arsenm, llvm-commits Differential Revision: http://reviews.llvm.org/D19736 llvm-svn: 268267
2016-05-03 02:05:17 +08:00
SDValue LowerGlobalAddress(AMDGPUMachineFunction *MFI, SDValue Op,
Fix instance of -Winconsistent-missing-override in AMDGPU code llvm-svn: 268289
2016-05-03 03:45:10 +08:00
SelectionDAG &DAG) const override;
Add R600 backend A new backend supporting AMD GPUs: Radeon HD2XXX - HD7XXX llvm-svn: 169915
2012-12-12 05:25:42 +08:00
SDValue LowerSELECT_CC(SDValue Op, SelectionDAG &DAG) const;
AMDGPU: Split R600 and SI store lowering These were only sharing some somewhat incorrect logic for when to scalarize or split vectors. llvm-svn: 260490
2016-02-11 13:32:46 +08:00
SDValue lowerPrivateTruncStore(StoreSDNode *Store, SelectionDAG &DAG) const;
Add R600 backend A new backend supporting AMD GPUs: Radeon HD2XXX - HD7XXX llvm-svn: 169915
2012-12-12 05:25:42 +08:00
SDValue LowerSTORE(SDValue Op, SelectionDAG &DAG) const;
AMDGPU: Fix i1 fp_to_int R600's i1 fp_to_uint selected but was incorrect according to what instcombine constant folds to. llvm-svn: 276435
2016-07-23 01:01:21 +08:00
SDValue lowerFP_TO_UINT(SDValue Op, SelectionDAG &DAG) const;
SDValue lowerFP_TO_SINT(SDValue Op, SelectionDAG &DAG) const;
AMDGPU: Split R600 and SI load lowering These weren't actually sharing anything in the common LowerLOAD. llvm-svn: 260398
2016-02-11 02:21:39 +08:00
SDValue lowerPrivateExtLoad(SDValue Op, SelectionDAG &DAG) const;
R600: rework handling of the constants Remove Cxxx registers, add new special register - "ALU_CONST" and new operand for each alu src - "sel". ALU_CONST is used to designate that the new operand contains the value to override src.sel, src.kc_bank, src.chan for constants in the driver. Patch by: Vadim Girlin Vincent Lejeune: - Use pointers for constants - Fold CONST_ADDRESS when possible Tom Stellard: - Give CONSTANT_BUFFER_0 its own address space - Use integer types for constant loads Reviewed-by: Tom Stellard <thomas.stellard@amd.com> llvm-svn: 173222
2013-01-23 10:09:06 +08:00
SDValue LowerLOAD(SDValue Op, SelectionDAG &DAG) const;
R600: Remove AMDILISelLowering llvm-svn: 211519
2014-06-24 02:00:55 +08:00
SDValue LowerBRCOND(SDValue Op, SelectionDAG &DAG) const;
R600: Use DAG lowering pass to handle fcos/fsin NOTE: This is a candidate for the stable branch. llvm-svn: 185940
2013-07-09 23:03:11 +08:00
SDValue LowerTrig(SDValue Op, SelectionDAG &DAG) const;
R600: Implement 64bit SHL v2: Use c++ style comment Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> llvm-svn: 211157
2014-06-18 20:27:13 +08:00
SDValue LowerSHLParts(SDValue Op, SelectionDAG &DAG) const;
R600: Implement 64bit SRL v2: use C++ style comment Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu> llvm-svn: 211158
2014-06-18 20:27:15 +08:00
SDValue LowerSRXParts(SDValue Op, SelectionDAG &DAG) const;
Reinstate revisions r234755, r234759, r234760 changes: Don't apply on hexagon and NVPTX since they no longer claim to support UADDO/USUBO Add location to getConstant Drop comment about the ops being turned into expand llvm-svn: 236240
2015-05-01 01:15:56 +08:00
SDValue LowerUADDSUBO(SDValue Op, SelectionDAG &DAG,
unsigned mainop, unsigned ovf) const;
R600: Support for indirect addressing v4 Only implemented for R600 so far. SI is missing implementations of a few callbacks used by the Indirect Addressing pass and needs code to handle frame indices. At the moment R600 only supports array sizes of 16 dwords or less. Register packing of vector types is currently disabled, which means that a vec4 is stored in T0_X, T1_X, T2_X, T3_X, rather than T0_XYZW. In order to correctly pack registers in all cases, we will need to implement an analysis pass for R600 that determines the correct vector width for each array. v2: - Add support for i8 zext load from stack. - Coding style fixes v3: - Don't reserve registers for indirect addressing when it isn't being used. - Fix bug caused by LLVM limiting the number of SubRegIndex declarations. v4: - Fix 64-bit defines llvm-svn: 174525
2013-02-07 01:32:29 +08:00
SDValue stackPtrToRegIndex(SDValue Ptr, unsigned StackWidth,
SelectionDAG &DAG) const;
void getStackAddress(unsigned StackWidth, unsigned ElemIdx,
unsigned &Channel, unsigned &PtrIncr) const;
Add R600 backend A new backend supporting AMD GPUs: Radeon HD2XXX - HD7XXX llvm-svn: 169915
2012-12-12 05:25:42 +08:00
bool isZero(SDValue Op) const;
AMDGPU: R600 code splitting cleanup Move a few functions only used by R600 to R600 specific code, fix header macros to stop using R600, mark classes as final. llvm-svn: 263204
2016-03-11 16:00:27 +08:00
bool isHWTrueValue(SDValue Op) const;
bool isHWFalseValue(SDValue Op) const;
AMDGPU/R600: Convert kernel param loads to use PARAM_I_ADDRESS Non ext aligned i32 loads are still optimized to use CONSTANT_BUFFER (AS 8) llvm-svn: 338610
2018-08-02 02:36:07 +08:00
bool FoldOperand(SDNode *ParentNode, unsigned SrcIdx, SDValue &Src,
SDValue &Neg, SDValue &Abs, SDValue &Sel, SDValue &Imm,
SelectionDAG &DAG) const;
SDValue constBufferLoad(LoadSDNode *LoadNode, int Block,
SelectionDAG &DAG) const;
AMDGPU: Cleanup subtarget handling. Split AMDGPUSubtarget into amdgcn/r600 specific subclasses. This removes most of the static_casting of the basic codegen classes everywhere, and tries to restrict the features visible on the wrong target. llvm-svn: 273652
2016-06-24 14:30:11 +08:00
[C++11] Add 'override' keywords and remove 'virtual'. Additionally add 'final' and leave 'virtual' on some methods that are marked virtual without overriding anything and have no obvious overrides themselves. R600 edition llvm-svn: 207503
2014-04-29 15:57:24 +08:00
SDNode *PostISelFolding(MachineSDNode *N, SelectionDAG &DAG) const override;
Add R600 backend A new backend supporting AMD GPUs: Radeon HD2XXX - HD7XXX llvm-svn: 169915
2012-12-12 05:25:42 +08:00
};
Revert r240137 (Fixed/added namespace ending comments using clang-tidy. NFC) Apparently, the style needs to be agreed upon first. llvm-svn: 240390
2015-06-23 17:49:53 +08:00
} // End namespace llvm;
Add R600 backend A new backend supporting AMD GPUs: Radeon HD2XXX - HD7XXX llvm-svn: 169915
2012-12-12 05:25:42 +08:00
Canonicalize header guards into a common format. Add header guards to files that were missing guards. Remove #endif comments as they don't seem common in LLVM (we can easily add them back if we decide they're useful) Changes made by clang-tidy with minor tweaks. llvm-svn: 215558
2014-08-14 00:26:38 +08:00
#endif