2017-09-28 07:26:01 +08:00
|
|
|
//===- SelectionDAGBuilder.h - Selection-DAG building -----------*- C++ -*-===//
|
2008-09-04 00:12:24 +08:00
|
|
|
//
|
2019-01-19 16:50:56 +08:00
|
|
|
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
|
|
|
|
// See https://llvm.org/LICENSE.txt for license information.
|
|
|
|
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
|
2008-09-04 00:12:24 +08:00
|
|
|
//
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
//
|
|
|
|
// This implements routines for translating from LLVM IR into SelectionDAG IR.
|
|
|
|
//
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
|
2014-08-14 00:26:38 +08:00
|
|
|
#ifndef LLVM_LIB_CODEGEN_SELECTIONDAG_SELECTIONDAGBUILDER_H
|
|
|
|
#define LLVM_LIB_CODEGEN_SELECTIONDAG_SELECTIONDAGBUILDER_H
|
2008-09-04 00:12:24 +08:00
|
|
|
|
2015-01-14 19:23:27 +08:00
|
|
|
#include "StatepointLowering.h"
|
2017-09-28 07:26:01 +08:00
|
|
|
#include "llvm/ADT/ArrayRef.h"
|
2008-09-04 00:12:24 +08:00
|
|
|
#include "llvm/ADT/DenseMap.h"
|
2019-03-26 20:18:08 +08:00
|
|
|
#include "llvm/ADT/MapVector.h"
|
2017-09-28 07:26:01 +08:00
|
|
|
#include "llvm/ADT/SmallVector.h"
|
2021-09-26 13:55:37 +08:00
|
|
|
#include "llvm/CodeGen/CodeGenCommonISel.h"
|
2017-09-28 07:26:01 +08:00
|
|
|
#include "llvm/CodeGen/ISDOpcodes.h"
|
2008-09-04 00:12:24 +08:00
|
|
|
#include "llvm/CodeGen/SelectionDAGNodes.h"
|
2019-06-08 08:05:17 +08:00
|
|
|
#include "llvm/CodeGen/SwitchLoweringUtils.h"
|
2017-11-17 09:07:10 +08:00
|
|
|
#include "llvm/CodeGen/TargetLowering.h"
|
2018-03-30 01:21:10 +08:00
|
|
|
#include "llvm/CodeGen/ValueTypes.h"
|
2017-09-28 07:26:01 +08:00
|
|
|
#include "llvm/IR/DebugLoc.h"
|
|
|
|
#include "llvm/IR/Instruction.h"
|
|
|
|
#include "llvm/Support/BranchProbability.h"
|
|
|
|
#include "llvm/Support/CodeGen.h"
|
2009-07-12 04:10:48 +08:00
|
|
|
#include "llvm/Support/ErrorHandling.h"
|
2018-03-24 07:58:25 +08:00
|
|
|
#include "llvm/Support/MachineValueType.h"
|
2017-09-28 07:26:01 +08:00
|
|
|
#include <algorithm>
|
|
|
|
#include <cassert>
|
|
|
|
#include <cstdint>
|
2016-05-27 22:27:24 +08:00
|
|
|
#include <utility>
|
2008-09-04 00:12:24 +08:00
|
|
|
#include <vector>
|
|
|
|
|
|
|
|
namespace llvm {
|
|
|
|
|
2020-09-15 18:44:47 +08:00
|
|
|
class AAResults;
|
2008-09-04 00:12:24 +08:00
|
|
|
class AllocaInst;
|
2017-09-28 07:26:01 +08:00
|
|
|
class AtomicCmpXchgInst;
|
|
|
|
class AtomicRMWInst;
|
2008-09-04 00:12:24 +08:00
|
|
|
class BasicBlock;
|
|
|
|
class BranchInst;
|
|
|
|
class CallInst;
|
2019-02-09 04:48:56 +08:00
|
|
|
class CallBrInst;
|
2017-09-28 07:26:01 +08:00
|
|
|
class CatchPadInst;
|
|
|
|
class CatchReturnInst;
|
|
|
|
class CatchSwitchInst;
|
|
|
|
class CleanupPadInst;
|
|
|
|
class CleanupReturnInst;
|
|
|
|
class Constant;
|
|
|
|
class ConstrainedFPIntrinsic;
|
2010-08-27 07:35:15 +08:00
|
|
|
class DbgValueInst;
|
2017-09-28 07:26:01 +08:00
|
|
|
class DataLayout;
|
|
|
|
class DIExpression;
|
|
|
|
class DILocalVariable;
|
|
|
|
class DILocation;
|
|
|
|
class FenceInst;
|
2009-11-24 01:16:22 +08:00
|
|
|
class FunctionLoweringInfo;
|
2008-09-04 00:12:24 +08:00
|
|
|
class GCFunctionInfo;
|
2017-09-28 07:26:01 +08:00
|
|
|
class GCRelocateInst;
|
|
|
|
class GCResultInst;
|
2020-09-15 18:44:47 +08:00
|
|
|
class GCStatepointInst;
|
2009-10-28 08:19:10 +08:00
|
|
|
class IndirectBrInst;
|
2008-09-04 00:12:24 +08:00
|
|
|
class InvokeInst;
|
2017-09-28 07:26:01 +08:00
|
|
|
class LandingPadInst;
|
|
|
|
class LLVMContext;
|
2008-09-04 00:12:24 +08:00
|
|
|
class LoadInst;
|
|
|
|
class MachineBasicBlock;
|
|
|
|
class PHINode;
|
2017-09-28 07:26:01 +08:00
|
|
|
class ResumeInst;
|
2008-09-04 00:12:24 +08:00
|
|
|
class ReturnInst;
|
2010-07-16 08:02:08 +08:00
|
|
|
class SDDbgValue;
|
2020-04-19 19:38:41 +08:00
|
|
|
class SelectionDAG;
|
2008-09-04 00:12:24 +08:00
|
|
|
class StoreInst;
|
2019-05-24 16:39:43 +08:00
|
|
|
class SwiftErrorValueTracking;
|
2008-09-04 00:12:24 +08:00
|
|
|
class SwitchInst;
|
2011-12-09 06:15:21 +08:00
|
|
|
class TargetLibraryInfo;
|
2017-09-28 07:26:01 +08:00
|
|
|
class TargetMachine;
|
|
|
|
class Type;
|
2008-09-04 00:12:24 +08:00
|
|
|
class VAArgInst;
|
2017-09-28 07:26:01 +08:00
|
|
|
class UnreachableInst;
|
|
|
|
class Use;
|
|
|
|
class User;
|
|
|
|
class Value;
|
2008-09-04 00:12:24 +08:00
|
|
|
|
|
|
|
//===----------------------------------------------------------------------===//
|
2009-11-24 02:04:58 +08:00
|
|
|
/// SelectionDAGBuilder - This is the common target-independent lowering
|
2008-09-04 00:12:24 +08:00
|
|
|
/// implementation that is parameterized by a TargetLowering object.
|
|
|
|
///
|
2013-09-12 02:05:11 +08:00
|
|
|
class SelectionDAGBuilder {
|
2019-02-13 06:11:20 +08:00
|
|
|
/// The current instruction being visited.
|
2017-09-28 07:26:01 +08:00
|
|
|
const Instruction *CurInst = nullptr;
|
2009-01-31 10:22:37 +08:00
|
|
|
|
2008-09-04 00:12:24 +08:00
|
|
|
DenseMap<const Value*, SDValue> NodeMap;
|
2013-11-01 01:18:07 +08:00
|
|
|
|
2019-02-13 06:11:20 +08:00
|
|
|
/// Maps argument value for unused arguments. This is used
|
2010-06-02 03:59:01 +08:00
|
|
|
/// to preserve debug information for incoming arguments.
|
|
|
|
DenseMap<const Value*, SDValue> UnusedArgNodeMap;
|
2008-09-04 00:12:24 +08:00
|
|
|
|
2019-02-13 06:11:20 +08:00
|
|
|
/// Helper type for DanglingDebugInfoMap.
|
2010-07-16 08:02:08 +08:00
|
|
|
class DanglingDebugInfo {
|
2017-09-28 07:26:01 +08:00
|
|
|
const DbgValueInst* DI = nullptr;
|
2010-07-16 08:02:08 +08:00
|
|
|
DebugLoc dl;
|
2017-09-28 07:26:01 +08:00
|
|
|
unsigned SDNodeOrder = 0;
|
|
|
|
|
2010-07-16 08:02:08 +08:00
|
|
|
public:
|
2017-09-28 07:26:01 +08:00
|
|
|
DanglingDebugInfo() = default;
|
2016-05-27 22:27:24 +08:00
|
|
|
DanglingDebugInfo(const DbgValueInst *di, DebugLoc DL, unsigned SDNO)
|
|
|
|
: DI(di), dl(std::move(DL)), SDNodeOrder(SDNO) {}
|
2017-09-28 07:26:01 +08:00
|
|
|
|
2010-08-27 07:35:15 +08:00
|
|
|
const DbgValueInst* getDI() { return DI; }
|
2010-07-16 08:02:08 +08:00
|
|
|
DebugLoc getdl() { return dl; }
|
|
|
|
unsigned getSDNodeOrder() { return SDNodeOrder; }
|
|
|
|
};
|
|
|
|
|
2019-02-13 06:11:20 +08:00
|
|
|
/// Helper type for DanglingDebugInfoMap.
|
2018-03-21 17:44:34 +08:00
|
|
|
typedef std::vector<DanglingDebugInfo> DanglingDebugInfoVector;
|
|
|
|
|
2019-02-13 06:11:20 +08:00
|
|
|
/// Keeps track of dbg_values for which we have not yet seen the referent.
|
|
|
|
/// We defer handling these until we do see it.
|
2019-03-26 20:18:08 +08:00
|
|
|
MapVector<const Value*, DanglingDebugInfoVector> DanglingDebugInfoMap;
|
2010-07-16 08:02:08 +08:00
|
|
|
|
2009-12-24 08:37:38 +08:00
|
|
|
public:
|
2019-02-13 06:11:20 +08:00
|
|
|
/// Loads are not emitted to the program immediately. We bunch them up and
|
|
|
|
/// then emit token factor nodes when possible. This allows us to get simple
|
|
|
|
/// disambiguation between loads without worrying about alias analysis.
|
2008-09-04 00:12:24 +08:00
|
|
|
SmallVector<SDValue, 8> PendingLoads;
|
[Statepoints 3/4] Statepoint infrastructure for garbage collection: SelectionDAGBuilder
This is the third patch in a small series. It contains the CodeGen support for lowering the gc.statepoint intrinsic sequences (223078) to the STATEPOINT pseudo machine instruction (223085). The change also includes the set of helper routines and classes for working with gc.statepoints, gc.relocates, and gc.results since the lowering code uses them.
With this change, gc.statepoints should be functionally complete. The documentation will follow in the fourth change, and there will likely be some cleanup changes, but interested parties can start experimenting now.
I'm not particularly happy with the amount of code or complexity involved with the lowering step, but at least it's fairly well isolated. The statepoint lowering code is split into it's own files and anyone not working on the statepoint support itself should be able to ignore it.
During the lowering process, we currently spill aggressively to stack. This is not entirely ideal (and we have plans to do better), but it's functional, relatively straight forward, and matches closely the implementations of the patchpoint intrinsics. Most of the complexity comes from trying to keep relocated copies of values in the same stack slots across statepoints. Doing so avoids the insertion of pointless load and store instructions to reshuffle the stack. The current implementation isn't as effective as I'd like, but it is functional and 'good enough' for many common use cases.
In the long term, I'd like to figure out how to integrate the statepoint lowering with the register allocator. In principal, we shouldn't need to eagerly spill at all. The register allocator should do any spilling required and the statepoint should simply record that fact. Depending on how challenging that turns out to be, we may invest in a smarter global stack slot assignment mechanism as a stop gap measure.
Reviewed by: atrick, ributzka
llvm-svn: 223137
2014-12-03 02:50:36 +08:00
|
|
|
|
|
|
|
/// State used while lowering a statepoint sequence (gc_statepoint,
|
|
|
|
/// gc_relocate, and gc_result). See StatepointLowering.hpp/cpp for details.
|
|
|
|
StatepointLoweringState StatepointLowering;
|
2008-09-04 00:12:24 +08:00
|
|
|
|
2017-09-28 07:26:01 +08:00
|
|
|
private:
|
2019-02-13 06:11:20 +08:00
|
|
|
/// CopyToReg nodes that copy values to virtual registers for export to other
|
|
|
|
/// blocks need to be emitted before any terminator instruction, but they have
|
|
|
|
/// no other ordering requirements. We bunch them up and the emit a single
|
|
|
|
/// tokenfactor for them just before terminator instructions.
|
2008-09-04 00:12:24 +08:00
|
|
|
SmallVector<SDValue, 8> PendingExports;
|
|
|
|
|
2020-01-13 21:37:07 +08:00
|
|
|
/// Similar to loads, nodes corresponding to constrained FP intrinsics are
|
|
|
|
/// bunched up and emitted when necessary. These can be moved across each
|
|
|
|
/// other and any (normal) memory operation (load or store), but not across
|
|
|
|
/// calls or instructions having unspecified side effects. As a special
|
|
|
|
/// case, constrained FP intrinsics using fpexcept.strict may not be deleted
|
|
|
|
/// even if otherwise unused, so they need to be chained before any
|
|
|
|
/// terminator instruction (like PendingExports). We track the latter
|
|
|
|
/// set of nodes in a separate list.
|
|
|
|
SmallVector<SDValue, 8> PendingConstrainedFP;
|
|
|
|
SmallVector<SDValue, 8> PendingConstrainedFPStrict;
|
|
|
|
|
2020-01-14 21:04:53 +08:00
|
|
|
/// Update root to include all chains from the Pending list.
|
|
|
|
SDValue updateRoot(SmallVectorImpl<SDValue> &Pending);
|
|
|
|
|
2019-02-13 06:11:20 +08:00
|
|
|
/// A unique monotonically increasing number used to order the SDNodes we
|
|
|
|
/// create.
|
2009-12-19 07:32:53 +08:00
|
|
|
unsigned SDNodeOrder;
|
|
|
|
|
Switch lowering: add heuristic for filling leaf nodes in the weight-balanced binary search tree
Sparse switches with profile info are lowered as weight-balanced BSTs. For
example, if the node weights are {1,1,1,1,1,1000}, the right-most node would
end up in a tree by itself, bringing it closer to the top.
However, a leaf in this BST can contain up to 3 cases, and having a single
case in a leaf node as in the example means the tree might become
unnecessarily high.
This patch adds a heauristic to the pivot selection algorithm that moves more
cases into leaf nodes unless that would lower their rank. It still doesn't
yield the optimal tree in every case, but I believe it's conservatibely correct.
llvm-svn: 240224
2015-06-21 01:14:07 +08:00
|
|
|
/// Determine the rank by weight of CC in [First,Last]. If CC has more weight
|
|
|
|
/// than each cluster in the range, its rank is 0.
|
2019-06-08 08:05:17 +08:00
|
|
|
unsigned caseClusterRank(const SwitchCG::CaseCluster &CC,
|
|
|
|
SwitchCG::CaseClusterIt First,
|
|
|
|
SwitchCG::CaseClusterIt Last);
|
Switch lowering: add heuristic for filling leaf nodes in the weight-balanced binary search tree
Sparse switches with profile info are lowered as weight-balanced BSTs. For
example, if the node weights are {1,1,1,1,1,1000}, the right-most node would
end up in a tree by itself, bringing it closer to the top.
However, a leaf in this BST can contain up to 3 cases, and having a single
case in a leaf node as in the example means the tree might become
unnecessarily high.
This patch adds a heauristic to the pivot selection algorithm that moves more
cases into leaf nodes unless that would lower their rank. It still doesn't
yield the optimal tree in every case, but I believe it's conservatibely correct.
llvm-svn: 240224
2015-06-21 01:14:07 +08:00
|
|
|
|
2015-04-24 00:45:24 +08:00
|
|
|
/// Emit comparison and split W into two subtrees.
|
2019-06-08 08:05:17 +08:00
|
|
|
void splitWorkItem(SwitchCG::SwitchWorkList &WorkList,
|
|
|
|
const SwitchCG::SwitchWorkListItem &W, Value *Cond,
|
|
|
|
MachineBasicBlock *SwitchMBB);
|
2015-04-24 00:45:24 +08:00
|
|
|
|
|
|
|
/// Lower W.
|
2019-06-08 08:05:17 +08:00
|
|
|
void lowerWorkItem(SwitchCG::SwitchWorkListItem W, Value *Cond,
|
2015-04-24 00:45:24 +08:00
|
|
|
MachineBasicBlock *SwitchMBB,
|
|
|
|
MachineBasicBlock *DefaultMBB);
|
|
|
|
|
2017-11-15 05:44:09 +08:00
|
|
|
/// Peel the top probability case if it exceeds the threshold
|
2019-06-08 08:05:17 +08:00
|
|
|
MachineBasicBlock *
|
|
|
|
peelDominantCaseCluster(const SwitchInst &SI,
|
|
|
|
SwitchCG::CaseClusterVector &Clusters,
|
|
|
|
BranchProbability &PeeledCaseProb);
|
2015-04-24 00:45:24 +08:00
|
|
|
|
2013-06-20 05:36:55 +08:00
|
|
|
private:
|
2010-04-20 03:05:59 +08:00
|
|
|
const TargetMachine &TM;
|
2017-09-28 07:26:01 +08:00
|
|
|
|
2013-06-20 05:36:55 +08:00
|
|
|
public:
|
2014-01-12 22:09:17 +08:00
|
|
|
/// Lowest valid SDNodeOrder. The special case 0 is reserved for scheduling
|
|
|
|
/// nodes without a corresponding SDNode.
|
|
|
|
static const unsigned LowestSDNodeOrder = 1;
|
|
|
|
|
2008-09-04 00:12:24 +08:00
|
|
|
SelectionDAG &DAG;
|
2020-09-15 18:44:47 +08:00
|
|
|
AAResults *AA = nullptr;
|
2011-12-09 06:15:21 +08:00
|
|
|
const TargetLibraryInfo *LibInfo;
|
2008-09-04 00:12:24 +08:00
|
|
|
|
2019-06-08 08:05:17 +08:00
|
|
|
class SDAGSwitchLowering : public SwitchCG::SwitchLowering {
|
|
|
|
public:
|
|
|
|
SDAGSwitchLowering(SelectionDAGBuilder *sdb, FunctionLoweringInfo &funcinfo)
|
|
|
|
: SwitchCG::SwitchLowering(funcinfo), SDB(sdb) {}
|
2017-09-28 07:26:01 +08:00
|
|
|
|
2022-07-26 14:00:59 +08:00
|
|
|
void addSuccessorWithProb(
|
2019-06-08 08:05:17 +08:00
|
|
|
MachineBasicBlock *Src, MachineBasicBlock *Dst,
|
|
|
|
BranchProbability Prob = BranchProbability::getUnknown()) override {
|
|
|
|
SDB->addSuccessorWithProb(Src, Dst, Prob);
|
|
|
|
}
|
|
|
|
|
|
|
|
private:
|
|
|
|
SelectionDAGBuilder *SDB;
|
|
|
|
};
|
2017-09-28 07:26:01 +08:00
|
|
|
|
2020-05-12 12:22:54 +08:00
|
|
|
// Data related to deferred switch lowerings. Used to construct additional
|
|
|
|
// Basic Blocks in SelectionDAGISel::FinishBasicBlock.
|
2019-06-08 08:05:17 +08:00
|
|
|
std::unique_ptr<SDAGSwitchLowering> SL;
|
2017-09-28 07:26:01 +08:00
|
|
|
|
Teach selectiondag how to handle the stackprotectorcheck intrinsic.
Previously, generation of stack protectors was done exclusively in the
pre-SelectionDAG Codegen LLVM IR Pass "Stack Protector". This necessitated
splitting basic blocks at the IR level to create the success/failure basic
blocks in the tail of the basic block in question. As a result of this,
calls that would have qualified for the sibling call optimization were no
longer eligible for optimization since said calls were no longer right in
the "tail position" (i.e. the immediate predecessor of a ReturnInst
instruction).
Then it was noticed that since the sibling call optimization causes the
callee to reuse the caller's stack, if we could delay the generation of
the stack protector check until later in CodeGen after the sibling call
decision was made, we get both the tail call optimization and the stack
protector check!
A few goals in solving this problem were:
1. Preserve the architecture independence of stack protector generation.
2. Preserve the normal IR level stack protector check for platforms like
OpenBSD for which we support platform specific stack protector
generation.
The main problem that guided the present solution is that one can not
solve this problem in an architecture independent manner at the IR level
only. This is because:
1. The decision on whether or not to perform a sibling call on certain
platforms (for instance i386) requires lower level information
related to available registers that can not be known at the IR level.
2. Even if the previous point were not true, the decision on whether to
perform a tail call is done in LowerCallTo in SelectionDAG which
occurs after the Stack Protector Pass. As a result, one would need to
put the relevant callinst into the stack protector check success
basic block (where the return inst is placed) and then move it back
later at SelectionDAG/MI time before the stack protector check if the
tail call optimization failed. The MI level option was nixed
immediately since it would require platform specific pattern
matching. The SelectionDAG level option was nixed because
SelectionDAG only processes one IR level basic block at a time
implying one could not create a DAG Combine to move the callinst.
To get around this problem a few things were realized:
1. While one can not handle multiple IR level basic blocks at the
SelectionDAG Level, one can generate multiple machine basic blocks
for one IR level basic block. This is how we handle bit tests and
switches.
2. At the MI level, tail calls are represented via a special return
MIInst called "tcreturn". Thus if we know the basic block in which we
wish to insert the stack protector check, we get the correct behavior
by always inserting the stack protector check right before the return
statement. This is a "magical transformation" since no matter where
the stack protector check intrinsic is, we always insert the stack
protector check code at the end of the BB.
Given the aforementioned constraints, the following solution was devised:
1. On platforms that do not support SelectionDAG stack protector check
generation, allow for the normal IR level stack protector check
generation to continue.
2. On platforms that do support SelectionDAG stack protector check
generation:
a. Use the IR level stack protector pass to decide if a stack
protector is required/which BB we insert the stack protector check
in by reusing the logic already therein. If we wish to generate a
stack protector check in a basic block, we place a special IR
intrinsic called llvm.stackprotectorcheck right before the BB's
returninst or if there is a callinst that could potentially be
sibling call optimized, before the call inst.
b. Then when a BB with said intrinsic is processed, we codegen the BB
normally via SelectBasicBlock. In said process, when we visit the
stack protector check, we do not actually emit anything into the
BB. Instead, we just initialize the stack protector descriptor
class (which involves stashing information/creating the success
mbbb and the failure mbb if we have not created one for this
function yet) and export the guard variable that we are going to
compare.
c. After we finish selecting the basic block, in FinishBasicBlock if
the StackProtectorDescriptor attached to the SelectionDAGBuilder is
initialized, we first find a splice point in the parent basic block
before the terminator and then splice the terminator of said basic
block into the success basic block. Then we code-gen a new tail for
the parent basic block consisting of the two loads, the comparison,
and finally two branches to the success/failure basic blocks. We
conclude by code-gening the failure basic block if we have not
code-gened it already (all stack protector checks we generate in
the same function, use the same failure basic block).
llvm-svn: 188755
2013-08-20 15:00:16 +08:00
|
|
|
/// A StackProtectorDescriptor structure used to communicate stack protector
|
|
|
|
/// information in between SelectBasicBlock and FinishBasicBlock.
|
|
|
|
StackProtectorDescriptor SPDescriptor;
|
2009-09-19 05:02:19 +08:00
|
|
|
|
2008-09-04 00:12:24 +08:00
|
|
|
// Emit PHI-node-operand constants only once even if used by multiple
|
|
|
|
// PHI nodes.
|
2010-04-15 09:51:59 +08:00
|
|
|
DenseMap<const Constant *, unsigned> ConstantsOut;
|
2008-09-04 00:12:24 +08:00
|
|
|
|
2019-02-13 06:11:20 +08:00
|
|
|
/// Information about the function as a whole.
|
2008-09-04 00:12:24 +08:00
|
|
|
FunctionLoweringInfo &FuncInfo;
|
2009-02-20 05:12:54 +08:00
|
|
|
|
2019-05-24 16:39:43 +08:00
|
|
|
/// Information about the swifterror values used throughout the function.
|
|
|
|
SwiftErrorValueTracking &SwiftError;
|
|
|
|
|
2019-02-13 06:11:20 +08:00
|
|
|
/// Garbage collection metadata for the function.
|
2008-09-04 00:12:24 +08:00
|
|
|
GCFunctionInfo *GFI;
|
|
|
|
|
2019-02-13 06:11:20 +08:00
|
|
|
/// Map a landing pad to the call site indexes.
|
2017-09-28 07:26:01 +08:00
|
|
|
DenseMap<MachineBasicBlock *, SmallVector<unsigned, 4>> LPadToCallSiteMap;
|
2011-10-05 06:00:35 +08:00
|
|
|
|
2019-02-13 06:11:20 +08:00
|
|
|
/// This is set to true if a call in the current block has been translated as
|
|
|
|
/// a tail call. In this case, no subsequent DAG nodes should be created.
|
2017-09-28 07:26:01 +08:00
|
|
|
bool HasTailCall = false;
|
Major calling convention code refactoring.
Instead of awkwardly encoding calling-convention information with ISD::CALL,
ISD::FORMAL_ARGUMENTS, ISD::RET, and ISD::ARG_FLAGS nodes, TargetLowering
provides three virtual functions for targets to override:
LowerFormalArguments, LowerCall, and LowerRet, which replace the custom
lowering done on the special nodes. They provide the same information, but
in a more immediately usable format.
This also reworks much of the target-independent tail call logic. The
decision of whether or not to perform a tail call is now cleanly split
between target-independent portions, and the target dependent portion
in IsEligibleForTailCallOptimization.
This also synchronizes all in-tree targets, to help enable future
refactoring and feature work.
llvm-svn: 78142
2009-08-05 09:29:28 +08:00
|
|
|
|
2009-07-13 12:09:18 +08:00
|
|
|
LLVMContext *Context;
|
|
|
|
|
2010-04-20 03:05:59 +08:00
|
|
|
SelectionDAGBuilder(SelectionDAG &dag, FunctionLoweringInfo &funcinfo,
|
2019-05-24 16:39:43 +08:00
|
|
|
SwiftErrorValueTracking &swifterror, CodeGenOpt::Level ol)
|
|
|
|
: SDNodeOrder(LowestSDNodeOrder), TM(dag.getTarget()), DAG(dag),
|
2019-08-15 23:54:37 +08:00
|
|
|
SL(std::make_unique<SDAGSwitchLowering>(this, funcinfo)), FuncInfo(funcinfo),
|
2019-06-08 08:05:17 +08:00
|
|
|
SwiftError(swifterror) {}
|
2008-09-04 00:12:24 +08:00
|
|
|
|
2020-09-15 18:44:47 +08:00
|
|
|
void init(GCFunctionInfo *gfi, AAResults *AA,
|
2011-12-09 06:15:21 +08:00
|
|
|
const TargetLibraryInfo *li);
|
2008-09-04 00:12:24 +08:00
|
|
|
|
2017-03-03 04:48:08 +08:00
|
|
|
/// Clear out the current SelectionDAG and the associated state and prepare
|
|
|
|
/// this SelectionDAGBuilder object to be used for a new block. This doesn't
|
|
|
|
/// clear out information about additional blocks that are needed to complete
|
|
|
|
/// switch lowering or PHI node updating; that information is cleared out as
|
|
|
|
/// it is consumed.
|
2008-09-04 00:12:24 +08:00
|
|
|
void clear();
|
|
|
|
|
2017-03-03 04:48:08 +08:00
|
|
|
/// Clear the dangling debug information map. This function is separated from
|
|
|
|
/// the clear so that debug information that is dangling in a basic block can
|
|
|
|
/// be properly resolved in a different basic block. This allows the
|
|
|
|
/// SelectionDAG to resolve dangling debug information attached to PHI nodes.
|
2011-05-24 01:44:13 +08:00
|
|
|
void clearDanglingDebugInfo();
|
|
|
|
|
2017-03-03 04:48:08 +08:00
|
|
|
/// Return the current virtual root of the Selection DAG, flushing any
|
|
|
|
/// PendingLoad items. This must be done before emitting a store or any other
|
2020-01-13 21:37:07 +08:00
|
|
|
/// memory node that may need to be ordered after any prior load instructions.
|
|
|
|
SDValue getMemoryRoot();
|
|
|
|
|
|
|
|
/// Similar to getMemoryRoot, but also flushes PendingConstrainedFP(Strict)
|
|
|
|
/// items. This must be done before emitting any call other any other node
|
|
|
|
/// that may need to be ordered after FP instructions due to other side
|
|
|
|
/// effects.
|
2008-09-04 00:12:24 +08:00
|
|
|
SDValue getRoot();
|
|
|
|
|
2017-03-03 04:48:08 +08:00
|
|
|
/// Similar to getRoot, but instead of flushing all the PendingLoad items,
|
2020-01-13 21:37:07 +08:00
|
|
|
/// flush all the PendingExports (and PendingConstrainedFPStrict) items.
|
|
|
|
/// It is necessary to do this before emitting a terminator instruction.
|
2008-09-04 00:12:24 +08:00
|
|
|
SDValue getControlRoot();
|
|
|
|
|
2013-05-25 10:20:36 +08:00
|
|
|
SDLoc getCurSDLoc() const {
|
|
|
|
return SDLoc(CurInst, SDNodeOrder);
|
|
|
|
}
|
|
|
|
|
|
|
|
DebugLoc getCurDebugLoc() const {
|
|
|
|
return CurInst ? CurInst->getDebugLoc() : DebugLoc();
|
|
|
|
}
|
2011-02-22 07:21:26 +08:00
|
|
|
|
2022-03-31 02:24:01 +08:00
|
|
|
void CopyValueToVirtualRegister(const Value *V, unsigned Reg,
|
|
|
|
ISD::NodeType ExtendType = ISD::ANY_EXTEND);
|
2008-09-04 00:12:24 +08:00
|
|
|
|
2010-04-15 09:51:59 +08:00
|
|
|
void visit(const Instruction &I);
|
2008-09-04 00:12:24 +08:00
|
|
|
|
2010-04-15 09:51:59 +08:00
|
|
|
void visit(unsigned Opcode, const User &I);
|
2008-09-04 00:12:24 +08:00
|
|
|
|
2019-02-07 01:36:18 +08:00
|
|
|
/// If there was virtual register allocated for the value V emit CopyFromReg
|
|
|
|
/// of the specified type Ty. Return empty SDValue() otherwise.
|
2015-03-11 00:26:48 +08:00
|
|
|
SDValue getCopyFromRegs(const Value *V, Type *Ty);
|
|
|
|
|
2020-09-29 22:43:21 +08:00
|
|
|
/// Register a dbg_value which relies on a Value which we have not yet seen.
|
|
|
|
void addDanglingDebugInfo(const DbgValueInst *DI, DebugLoc DL,
|
|
|
|
unsigned Order);
|
|
|
|
|
2018-03-13 02:02:39 +08:00
|
|
|
/// If we have dangling debug info that describes \p Variable, or an
|
|
|
|
/// overlapping part of variable considering the \p Expr, then this method
|
2019-02-13 06:11:20 +08:00
|
|
|
/// will drop that debug info as it isn't valid any longer.
|
2018-03-13 02:02:39 +08:00
|
|
|
void dropDanglingDebugInfo(const DILocalVariable *Variable,
|
|
|
|
const DIExpression *Expr);
|
|
|
|
|
2019-02-14 00:33:05 +08:00
|
|
|
/// If we saw an earlier dbg_value referring to V, generate the debug data
|
|
|
|
/// structures now that we've seen its definition.
|
2010-07-16 08:02:08 +08:00
|
|
|
void resolveDanglingDebugInfo(const Value *V, SDValue Val);
|
2017-09-28 07:26:01 +08:00
|
|
|
|
2019-02-14 00:33:05 +08:00
|
|
|
/// For the given dangling debuginfo record, perform last-ditch efforts to
|
|
|
|
/// resolve the debuginfo to something that is represented in this DAG. If
|
|
|
|
/// this cannot be done, produce an Undef debug value record.
|
|
|
|
void salvageUnresolvedDbgValue(DanglingDebugInfo &DDI);
|
|
|
|
|
2020-09-29 22:43:21 +08:00
|
|
|
/// For a given list of Values, attempt to create and record a SDDbgValue in
|
|
|
|
/// the SelectionDAG.
|
|
|
|
bool handleDebugValue(ArrayRef<const Value *> Values, DILocalVariable *Var,
|
|
|
|
DIExpression *Expr, DebugLoc CurDL, DebugLoc InstDL,
|
|
|
|
unsigned Order, bool IsVariadic);
|
2019-02-13 23:53:10 +08:00
|
|
|
|
2019-02-14 00:33:05 +08:00
|
|
|
/// Evict any dangling debug information, attempting to salvage it first.
|
|
|
|
void resolveOrClearDbgInfo();
|
|
|
|
|
2008-09-04 00:12:24 +08:00
|
|
|
SDValue getValue(const Value *V);
|
2015-04-28 15:57:37 +08:00
|
|
|
|
2010-07-01 09:59:43 +08:00
|
|
|
SDValue getNonRegisterValue(const Value *V);
|
|
|
|
SDValue getValueImpl(const Value *V);
|
2008-09-04 00:12:24 +08:00
|
|
|
|
|
|
|
void setValue(const Value *V, SDValue NewN) {
|
|
|
|
SDValue &N = NodeMap[V];
|
2014-04-16 12:21:27 +08:00
|
|
|
assert(!N.getNode() && "Already set a value for this node!");
|
2008-09-04 00:12:24 +08:00
|
|
|
N = NewN;
|
|
|
|
}
|
2013-11-01 01:18:07 +08:00
|
|
|
|
2010-06-02 03:59:01 +08:00
|
|
|
void setUnusedArgValue(const Value *V, SDValue NewN) {
|
|
|
|
SDValue &N = UnusedArgNodeMap[V];
|
2014-04-16 12:21:27 +08:00
|
|
|
assert(!N.getNode() && "Already set a value for this node!");
|
2010-06-02 03:59:01 +08:00
|
|
|
N = NewN;
|
|
|
|
}
|
2008-09-04 00:12:24 +08:00
|
|
|
|
2010-04-15 09:51:59 +08:00
|
|
|
void FindMergedConditions(const Value *Cond, MachineBasicBlock *TBB,
|
2008-09-04 00:12:24 +08:00
|
|
|
MachineBasicBlock *FBB, MachineBasicBlock *CurBB,
|
2015-07-15 09:31:26 +08:00
|
|
|
MachineBasicBlock *SwitchBB,
|
2018-07-17 02:51:40 +08:00
|
|
|
Instruction::BinaryOps Opc, BranchProbability TProb,
|
|
|
|
BranchProbability FProb, bool InvertCond);
|
2010-04-15 09:51:59 +08:00
|
|
|
void EmitBranchForMergedCondition(const Value *Cond, MachineBasicBlock *TBB,
|
2008-10-18 05:16:08 +08:00
|
|
|
MachineBasicBlock *FBB,
|
2010-04-20 06:41:47 +08:00
|
|
|
MachineBasicBlock *CurBB,
|
2014-01-31 08:42:44 +08:00
|
|
|
MachineBasicBlock *SwitchBB,
|
2018-07-17 02:51:40 +08:00
|
|
|
BranchProbability TProb, BranchProbability FProb,
|
2017-01-25 00:36:07 +08:00
|
|
|
bool InvertCond);
|
2019-06-08 08:05:17 +08:00
|
|
|
bool ShouldEmitAsBranches(const std::vector<SwitchCG::CaseBlock> &Cases);
|
2010-04-15 09:51:59 +08:00
|
|
|
bool isExportableFromCurrentBlock(const Value *V, const BasicBlock *FromBB);
|
|
|
|
void CopyToExportRegsIfNeeded(const Value *V);
|
|
|
|
void ExportFromCurrentBlock(const Value *V);
|
2020-04-14 01:44:59 +08:00
|
|
|
void LowerCallTo(const CallBase &CB, SDValue Callee, bool IsTailCall,
|
2021-02-10 22:35:16 +08:00
|
|
|
bool IsMustTailCall, const BasicBlock *EHPadBB = nullptr);
|
2008-09-04 00:12:24 +08:00
|
|
|
|
2016-02-09 00:28:19 +08:00
|
|
|
// Lower range metadata from 0 to N to assert zext to an integer of nearest
|
|
|
|
// floor power of two.
|
|
|
|
SDValue lowerRangeToAssertZExt(SelectionDAG &DAG, const Instruction &I,
|
|
|
|
SDValue Op);
|
|
|
|
|
2016-03-17 04:49:31 +08:00
|
|
|
void populateCallLoweringInfo(TargetLowering::CallLoweringInfo &CLI,
|
2019-02-11 15:42:30 +08:00
|
|
|
const CallBase *Call, unsigned ArgIdx,
|
2016-03-17 04:49:31 +08:00
|
|
|
unsigned NumArgs, SDValue Callee,
|
|
|
|
Type *ReturnTy, bool IsPatchPoint);
|
|
|
|
|
|
|
|
std::pair<SDValue, SDValue>
|
|
|
|
lowerInvokable(TargetLowering::CallLoweringInfo &CLI,
|
|
|
|
const BasicBlock *EHPadBB = nullptr);
|
2013-11-01 01:18:24 +08:00
|
|
|
|
2019-02-13 06:11:20 +08:00
|
|
|
/// When an MBB was split during scheduling, update the
|
2014-01-11 22:01:43 +08:00
|
|
|
/// references that need to refer to the last resulting block.
|
2010-10-01 03:44:31 +08:00
|
|
|
void UpdateSplitBlock(MachineBasicBlock *First, MachineBasicBlock *Last);
|
|
|
|
|
2016-03-17 07:08:00 +08:00
|
|
|
/// Describes a gc.statepoint or a gc.statepoint like thing for the purposes
|
2016-03-23 10:28:35 +08:00
|
|
|
/// of lowering into a STATEPOINT node.
|
2016-03-17 07:08:00 +08:00
|
|
|
struct StatepointLoweringInfo {
|
|
|
|
/// Bases[i] is the base pointer for Ptrs[i]. Together they denote the set
|
|
|
|
/// of gc pointers this STATEPOINT has to relocate.
|
2016-03-23 10:24:07 +08:00
|
|
|
SmallVector<const Value *, 16> Bases;
|
|
|
|
SmallVector<const Value *, 16> Ptrs;
|
2016-03-17 07:08:00 +08:00
|
|
|
|
|
|
|
/// The set of gc.relocate calls associated with this gc.statepoint.
|
2016-03-23 10:24:07 +08:00
|
|
|
SmallVector<const GCRelocateInst *, 16> GCRelocates;
|
2016-03-17 07:08:00 +08:00
|
|
|
|
|
|
|
/// The full list of gc arguments to the gc.statepoint being lowered.
|
|
|
|
ArrayRef<const Use> GCArgs;
|
|
|
|
|
|
|
|
/// The gc.statepoint instruction.
|
|
|
|
const Instruction *StatepointInstr = nullptr;
|
|
|
|
|
|
|
|
/// The list of gc transition arguments present in the gc.statepoint being
|
|
|
|
/// lowered.
|
|
|
|
ArrayRef<const Use> GCTransitionArgs;
|
|
|
|
|
|
|
|
/// The ID that the resulting STATEPOINT instruction has to report.
|
|
|
|
unsigned ID = -1;
|
|
|
|
|
|
|
|
/// Information regarding the underlying call instruction.
|
|
|
|
TargetLowering::CallLoweringInfo CLI;
|
|
|
|
|
|
|
|
/// The deoptimization state associated with this gc.statepoint call, if
|
|
|
|
/// any.
|
|
|
|
ArrayRef<const Use> DeoptState;
|
|
|
|
|
|
|
|
/// Flags associated with the meta arguments being lowered.
|
|
|
|
uint64_t StatepointFlags = -1;
|
|
|
|
|
|
|
|
/// The number of patchable bytes the call needs to get lowered into.
|
|
|
|
unsigned NumPatchBytes = -1;
|
|
|
|
|
|
|
|
/// The exception handling unwind destination, in case this represents an
|
|
|
|
/// invoke of gc.statepoint.
|
|
|
|
const BasicBlock *EHPadBB = nullptr;
|
|
|
|
|
|
|
|
explicit StatepointLoweringInfo(SelectionDAG &DAG) : CLI(DAG) {}
|
|
|
|
};
|
|
|
|
|
|
|
|
/// Lower \p SLI into a STATEPOINT instruction.
|
2018-07-17 02:51:40 +08:00
|
|
|
SDValue LowerAsSTATEPOINT(StatepointLoweringInfo &SI);
|
2016-03-17 07:08:00 +08:00
|
|
|
|
2015-02-20 23:28:35 +08:00
|
|
|
// This function is responsible for the whole statepoint lowering process.
|
2015-03-11 00:26:48 +08:00
|
|
|
// It uniformly handles invoke and call statepoints.
|
2020-05-28 09:56:50 +08:00
|
|
|
void LowerStatepoint(const GCStatepointInst &I,
|
2015-09-09 07:28:38 +08:00
|
|
|
const BasicBlock *EHPadBB = nullptr);
|
2016-03-22 08:59:13 +08:00
|
|
|
|
2019-02-11 15:42:30 +08:00
|
|
|
void LowerCallSiteWithDeoptBundle(const CallBase *Call, SDValue Callee,
|
2016-03-22 08:59:13 +08:00
|
|
|
const BasicBlock *EHPadBB);
|
|
|
|
|
2016-03-25 04:23:29 +08:00
|
|
|
void LowerDeoptimizeCall(const CallInst *CI);
|
2016-04-06 09:33:49 +08:00
|
|
|
void LowerDeoptimizingReturn();
|
2016-03-25 04:23:29 +08:00
|
|
|
|
2019-02-11 15:42:30 +08:00
|
|
|
void LowerCallSiteWithDeoptBundleImpl(const CallBase *Call, SDValue Callee,
|
2016-03-25 06:51:49 +08:00
|
|
|
const BasicBlock *EHPadBB,
|
2016-04-06 09:33:49 +08:00
|
|
|
bool VarArgDisallowed,
|
|
|
|
bool ForceVoidReturnTy);
|
2016-03-25 06:51:49 +08:00
|
|
|
|
2017-04-28 01:17:16 +08:00
|
|
|
/// Returns the type of FrameIndex and TargetFrameIndex nodes.
|
|
|
|
MVT getFrameIndexTy() {
|
|
|
|
return DAG.getTargetLoweringInfo().getFrameIndexTy(DAG.getDataLayout());
|
|
|
|
}
|
|
|
|
|
2008-09-04 00:12:24 +08:00
|
|
|
private:
|
|
|
|
// Terminator instructions.
|
2010-04-15 09:51:59 +08:00
|
|
|
void visitRet(const ReturnInst &I);
|
|
|
|
void visitBr(const BranchInst &I);
|
|
|
|
void visitSwitch(const SwitchInst &I);
|
|
|
|
void visitIndirectBr(const IndirectBrInst &I);
|
2014-04-19 21:47:43 +08:00
|
|
|
void visitUnreachable(const UnreachableInst &I);
|
2015-08-01 01:58:14 +08:00
|
|
|
void visitCleanupRet(const CleanupReturnInst &I);
|
[IR] Reformulate LLVM's EH funclet IR
While we have successfully implemented a funclet-oriented EH scheme on
top of LLVM IR, our scheme has some notable deficiencies:
- catchendpad and cleanupendpad are necessary in the current design
but they are difficult to explain to others, even to seasoned LLVM
experts.
- catchendpad and cleanupendpad are optimization barriers. They cannot
be split and force all potentially throwing call-sites to be invokes.
This has a noticable effect on the quality of our code generation.
- catchpad, while similar in some aspects to invoke, is fairly awkward.
It is unsplittable, starts a funclet, and has control flow to other
funclets.
- The nesting relationship between funclets is currently a property of
control flow edges. Because of this, we are forced to carefully
analyze the flow graph to see if there might potentially exist illegal
nesting among funclets. While we have logic to clone funclets when
they are illegally nested, it would be nicer if we had a
representation which forbade them upfront.
Let's clean this up a bit by doing the following:
- Instead, make catchpad more like cleanuppad and landingpad: no control
flow, just a bunch of simple operands; catchpad would be splittable.
- Introduce catchswitch, a control flow instruction designed to model
the constraints of funclet oriented EH.
- Make funclet scoping explicit by having funclet instructions consume
the token produced by the funclet which contains them.
- Remove catchendpad and cleanupendpad. Their presence can be inferred
implicitly using coloring information.
N.B. The state numbering code for the CLR has been updated but the
veracity of it's output cannot be spoken for. An expert should take a
look to make sure the results are reasonable.
Reviewers: rnk, JosephTremoulet, andrew.w.kaylor
Differential Revision: http://reviews.llvm.org/D15139
llvm-svn: 255422
2015-12-12 13:38:55 +08:00
|
|
|
void visitCatchSwitch(const CatchSwitchInst &I);
|
2015-08-01 01:58:14 +08:00
|
|
|
void visitCatchRet(const CatchReturnInst &I);
|
|
|
|
void visitCatchPad(const CatchPadInst &I);
|
|
|
|
void visitCleanupPad(const CleanupPadInst &CPI);
|
2008-09-04 00:12:24 +08:00
|
|
|
|
2015-11-24 16:51:23 +08:00
|
|
|
BranchProbability getEdgeProbability(const MachineBasicBlock *Src,
|
|
|
|
const MachineBasicBlock *Dst) const;
|
|
|
|
void addSuccessorWithProb(
|
|
|
|
MachineBasicBlock *Src, MachineBasicBlock *Dst,
|
|
|
|
BranchProbability Prob = BranchProbability::getUnknown());
|
|
|
|
|
2008-09-04 00:12:24 +08:00
|
|
|
public:
|
2019-06-08 08:05:17 +08:00
|
|
|
void visitSwitchCase(SwitchCG::CaseBlock &CB, MachineBasicBlock *SwitchBB);
|
Teach selectiondag how to handle the stackprotectorcheck intrinsic.
Previously, generation of stack protectors was done exclusively in the
pre-SelectionDAG Codegen LLVM IR Pass "Stack Protector". This necessitated
splitting basic blocks at the IR level to create the success/failure basic
blocks in the tail of the basic block in question. As a result of this,
calls that would have qualified for the sibling call optimization were no
longer eligible for optimization since said calls were no longer right in
the "tail position" (i.e. the immediate predecessor of a ReturnInst
instruction).
Then it was noticed that since the sibling call optimization causes the
callee to reuse the caller's stack, if we could delay the generation of
the stack protector check until later in CodeGen after the sibling call
decision was made, we get both the tail call optimization and the stack
protector check!
A few goals in solving this problem were:
1. Preserve the architecture independence of stack protector generation.
2. Preserve the normal IR level stack protector check for platforms like
OpenBSD for which we support platform specific stack protector
generation.
The main problem that guided the present solution is that one can not
solve this problem in an architecture independent manner at the IR level
only. This is because:
1. The decision on whether or not to perform a sibling call on certain
platforms (for instance i386) requires lower level information
related to available registers that can not be known at the IR level.
2. Even if the previous point were not true, the decision on whether to
perform a tail call is done in LowerCallTo in SelectionDAG which
occurs after the Stack Protector Pass. As a result, one would need to
put the relevant callinst into the stack protector check success
basic block (where the return inst is placed) and then move it back
later at SelectionDAG/MI time before the stack protector check if the
tail call optimization failed. The MI level option was nixed
immediately since it would require platform specific pattern
matching. The SelectionDAG level option was nixed because
SelectionDAG only processes one IR level basic block at a time
implying one could not create a DAG Combine to move the callinst.
To get around this problem a few things were realized:
1. While one can not handle multiple IR level basic blocks at the
SelectionDAG Level, one can generate multiple machine basic blocks
for one IR level basic block. This is how we handle bit tests and
switches.
2. At the MI level, tail calls are represented via a special return
MIInst called "tcreturn". Thus if we know the basic block in which we
wish to insert the stack protector check, we get the correct behavior
by always inserting the stack protector check right before the return
statement. This is a "magical transformation" since no matter where
the stack protector check intrinsic is, we always insert the stack
protector check code at the end of the BB.
Given the aforementioned constraints, the following solution was devised:
1. On platforms that do not support SelectionDAG stack protector check
generation, allow for the normal IR level stack protector check
generation to continue.
2. On platforms that do support SelectionDAG stack protector check
generation:
a. Use the IR level stack protector pass to decide if a stack
protector is required/which BB we insert the stack protector check
in by reusing the logic already therein. If we wish to generate a
stack protector check in a basic block, we place a special IR
intrinsic called llvm.stackprotectorcheck right before the BB's
returninst or if there is a callinst that could potentially be
sibling call optimized, before the call inst.
b. Then when a BB with said intrinsic is processed, we codegen the BB
normally via SelectBasicBlock. In said process, when we visit the
stack protector check, we do not actually emit anything into the
BB. Instead, we just initialize the stack protector descriptor
class (which involves stashing information/creating the success
mbbb and the failure mbb if we have not created one for this
function yet) and export the guard variable that we are going to
compare.
c. After we finish selecting the basic block, in FinishBasicBlock if
the StackProtectorDescriptor attached to the SelectionDAGBuilder is
initialized, we first find a splice point in the parent basic block
before the terminator and then splice the terminator of said basic
block into the success basic block. Then we code-gen a new tail for
the parent basic block consisting of the two loads, the comparison,
and finally two branches to the success/failure basic blocks. We
conclude by code-gening the failure basic block if we have not
code-gened it already (all stack protector checks we generate in
the same function, use the same failure basic block).
llvm-svn: 188755
2013-08-20 15:00:16 +08:00
|
|
|
void visitSPDescriptorParent(StackProtectorDescriptor &SPD,
|
|
|
|
MachineBasicBlock *ParentBB);
|
|
|
|
void visitSPDescriptorFailure(StackProtectorDescriptor &SPD);
|
2019-06-08 08:05:17 +08:00
|
|
|
void visitBitTestHeader(SwitchCG::BitTestBlock &B,
|
|
|
|
MachineBasicBlock *SwitchBB);
|
|
|
|
void visitBitTestCase(SwitchCG::BitTestBlock &BB, MachineBasicBlock *NextMBB,
|
|
|
|
BranchProbability BranchProbToNext, unsigned Reg,
|
|
|
|
SwitchCG::BitTestCase &B, MachineBasicBlock *SwitchBB);
|
|
|
|
void visitJumpTable(SwitchCG::JumpTable &JT);
|
|
|
|
void visitJumpTableHeader(SwitchCG::JumpTable &JT,
|
|
|
|
SwitchCG::JumpTableHeader &JTH,
|
2010-04-20 06:41:47 +08:00
|
|
|
MachineBasicBlock *SwitchBB);
|
2013-11-01 01:18:07 +08:00
|
|
|
|
2008-09-04 00:12:24 +08:00
|
|
|
private:
|
|
|
|
// These all get lowered before this pass.
|
2010-04-15 09:51:59 +08:00
|
|
|
void visitInvoke(const InvokeInst &I);
|
2019-02-09 04:48:56 +08:00
|
|
|
void visitCallBr(const CallBrInst &I);
|
2011-07-31 14:30:59 +08:00
|
|
|
void visitResume(const ResumeInst &I);
|
2010-04-15 09:51:59 +08:00
|
|
|
|
2018-11-14 02:15:47 +08:00
|
|
|
void visitUnary(const User &I, unsigned Opcode);
|
|
|
|
void visitFNeg(const User &I) { visitUnary(I, ISD::FNEG); }
|
|
|
|
|
2018-05-12 06:45:22 +08:00
|
|
|
void visitBinary(const User &I, unsigned Opcode);
|
2010-04-15 09:51:59 +08:00
|
|
|
void visitShift(const User &I, unsigned Opcode);
|
|
|
|
void visitAdd(const User &I) { visitBinary(I, ISD::ADD); }
|
|
|
|
void visitFAdd(const User &I) { visitBinary(I, ISD::FADD); }
|
|
|
|
void visitSub(const User &I) { visitBinary(I, ISD::SUB); }
|
2020-08-03 23:19:33 +08:00
|
|
|
void visitFSub(const User &I) { visitBinary(I, ISD::FSUB); }
|
2010-04-15 09:51:59 +08:00
|
|
|
void visitMul(const User &I) { visitBinary(I, ISD::MUL); }
|
|
|
|
void visitFMul(const User &I) { visitBinary(I, ISD::FMUL); }
|
|
|
|
void visitURem(const User &I) { visitBinary(I, ISD::UREM); }
|
|
|
|
void visitSRem(const User &I) { visitBinary(I, ISD::SREM); }
|
|
|
|
void visitFRem(const User &I) { visitBinary(I, ISD::FREM); }
|
|
|
|
void visitUDiv(const User &I) { visitBinary(I, ISD::UDIV); }
|
Emit a more efficient magic number multiplication for exact sdivs.
We have to do this in DAGBuilder instead of DAGCombiner, because the exact bit is lost after building.
struct foo { char x[24]; };
long bar(struct foo *a, struct foo *b) { return a-b; }
is now compiled into
movl 4(%esp), %eax
subl 8(%esp), %eax
sarl $3, %eax
imull $-1431655765, %eax, %eax
instead of
movl 4(%esp), %eax
subl 8(%esp), %eax
movl $715827883, %ecx
imull %ecx
movl %edx, %eax
shrl $31, %eax
sarl $2, %edx
addl %eax, %edx
movl %edx, %eax
llvm-svn: 134695
2011-07-08 18:31:30 +08:00
|
|
|
void visitSDiv(const User &I);
|
2010-04-15 09:51:59 +08:00
|
|
|
void visitFDiv(const User &I) { visitBinary(I, ISD::FDIV); }
|
|
|
|
void visitAnd (const User &I) { visitBinary(I, ISD::AND); }
|
|
|
|
void visitOr (const User &I) { visitBinary(I, ISD::OR); }
|
|
|
|
void visitXor (const User &I) { visitBinary(I, ISD::XOR); }
|
|
|
|
void visitShl (const User &I) { visitShift(I, ISD::SHL); }
|
|
|
|
void visitLShr(const User &I) { visitShift(I, ISD::SRL); }
|
|
|
|
void visitAShr(const User &I) { visitShift(I, ISD::SRA); }
|
|
|
|
void visitICmp(const User &I);
|
|
|
|
void visitFCmp(const User &I);
|
2008-09-04 00:12:24 +08:00
|
|
|
// Visit the conversion instructions
|
2010-04-15 09:51:59 +08:00
|
|
|
void visitTrunc(const User &I);
|
|
|
|
void visitZExt(const User &I);
|
|
|
|
void visitSExt(const User &I);
|
|
|
|
void visitFPTrunc(const User &I);
|
|
|
|
void visitFPExt(const User &I);
|
|
|
|
void visitFPToUI(const User &I);
|
|
|
|
void visitFPToSI(const User &I);
|
|
|
|
void visitUIToFP(const User &I);
|
|
|
|
void visitSIToFP(const User &I);
|
|
|
|
void visitPtrToInt(const User &I);
|
|
|
|
void visitIntToPtr(const User &I);
|
|
|
|
void visitBitCast(const User &I);
|
2013-11-15 09:34:59 +08:00
|
|
|
void visitAddrSpaceCast(const User &I);
|
2010-04-15 09:51:59 +08:00
|
|
|
|
|
|
|
void visitExtractElement(const User &I);
|
|
|
|
void visitInsertElement(const User &I);
|
|
|
|
void visitShuffleVector(const User &I);
|
|
|
|
|
2022-06-29 16:42:46 +08:00
|
|
|
void visitExtractValue(const ExtractValueInst &I);
|
2022-06-28 17:25:54 +08:00
|
|
|
void visitInsertValue(const InsertValueInst &I);
|
2018-07-17 02:51:40 +08:00
|
|
|
void visitLandingPad(const LandingPadInst &LP);
|
2010-04-15 09:51:59 +08:00
|
|
|
|
|
|
|
void visitGetElementPtr(const User &I);
|
|
|
|
void visitSelect(const User &I);
|
|
|
|
|
|
|
|
void visitAlloca(const AllocaInst &I);
|
|
|
|
void visitLoad(const LoadInst &I);
|
|
|
|
void visitStore(const StoreInst &I);
|
2016-11-03 11:23:55 +08:00
|
|
|
void visitMaskedLoad(const CallInst &I, bool IsExpanding = false);
|
|
|
|
void visitMaskedStore(const CallInst &I, bool IsCompressing = false);
|
2015-04-28 15:57:37 +08:00
|
|
|
void visitMaskedGather(const CallInst &I);
|
|
|
|
void visitMaskedScatter(const CallInst &I);
|
2011-07-29 05:48:00 +08:00
|
|
|
void visitAtomicCmpXchg(const AtomicCmpXchgInst &I);
|
|
|
|
void visitAtomicRMW(const AtomicRMWInst &I);
|
2011-07-26 07:16:38 +08:00
|
|
|
void visitFence(const FenceInst &I);
|
2010-04-20 23:00:41 +08:00
|
|
|
void visitPHI(const PHINode &I);
|
2010-04-15 09:51:59 +08:00
|
|
|
void visitCall(const CallInst &I);
|
2020-09-25 23:54:21 +08:00
|
|
|
bool visitMemCmpBCmpCall(const CallInst &I);
|
2016-07-30 02:23:18 +08:00
|
|
|
bool visitMemPCpyCall(const CallInst &I);
|
2013-08-20 17:38:48 +08:00
|
|
|
bool visitMemChrCall(const CallInst &I);
|
2013-08-16 19:29:37 +08:00
|
|
|
bool visitStrCpyCall(const CallInst &I, bool isStpcpy);
|
2013-08-16 19:21:54 +08:00
|
|
|
bool visitStrCmpCall(const CallInst &I);
|
2013-08-16 19:41:43 +08:00
|
|
|
bool visitStrLenCall(const CallInst &I);
|
|
|
|
bool visitStrNLenCall(const CallInst &I);
|
2012-08-04 07:29:17 +08:00
|
|
|
bool visitUnaryFloatCall(const CallInst &I, unsigned Opcode);
|
2014-10-22 07:01:01 +08:00
|
|
|
bool visitBinaryFloatCall(const CallInst &I, unsigned Opcode);
|
2011-08-25 04:50:09 +08:00
|
|
|
void visitAtomicLoad(const LoadInst &I);
|
|
|
|
void visitAtomicStore(const StoreInst &I);
|
2016-04-06 02:13:16 +08:00
|
|
|
void visitLoadFromSwiftError(const LoadInst &I);
|
|
|
|
void visitStoreToSwiftError(const StoreInst &I);
|
[IR] Redefine Freeze instruction
Summary:
This patch redefines freeze instruction from being UnaryOperator to a subclass of UnaryInstruction.
ConstantExpr freeze is removed, as discussed in the previous review.
FreezeOperator is not added because there's no ConstantExpr freeze.
`freeze i8* null` test is added to `test/Bindings/llvm-c/freeze.ll` as well, because the null pointer-related bug in `tools/llvm-c/echo.cpp` is now fixed.
InstVisitor has visitFreeze now because freeze is not unaryop anymore.
Reviewers: whitequark, deadalnix, craig.topper, jdoerfert, lebedev.ri
Reviewed By: craig.topper, lebedev.ri
Subscribers: regehr, nlopes, mehdi_amini, hiraditya, steven_wu, dexonsmith, jfb, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D69932
2019-11-07 00:17:49 +08:00
|
|
|
void visitFreeze(const FreezeInst &I);
|
2011-08-25 04:50:09 +08:00
|
|
|
|
2021-05-14 02:05:11 +08:00
|
|
|
void visitInlineAsm(const CallBase &Call,
|
|
|
|
const BasicBlock *EHPadBB = nullptr);
|
2019-05-20 19:01:30 +08:00
|
|
|
void visitIntrinsicCall(const CallInst &I, unsigned Intrinsic);
|
2010-04-15 09:51:59 +08:00
|
|
|
void visitTargetIntrinsic(const CallInst &I, unsigned Intrinsic);
|
2017-05-26 05:31:00 +08:00
|
|
|
void visitConstrainedFPIntrinsic(const ConstrainedFPIntrinsic &FPI);
|
2021-08-31 23:01:32 +08:00
|
|
|
void visitVPLoadGather(const VPIntrinsic &VPIntrin, EVT VT,
|
2021-11-20 04:21:47 +08:00
|
|
|
SmallVector<SDValue, 7> &OpValues, bool IsGather);
|
2021-08-31 23:01:32 +08:00
|
|
|
void visitVPStoreScatter(const VPIntrinsic &VPIntrin,
|
2021-11-20 04:21:47 +08:00
|
|
|
SmallVector<SDValue, 7> &OpValues, bool IsScatter);
|
2022-03-10 23:39:12 +08:00
|
|
|
void visitVPStridedLoad(const VPIntrinsic &VPIntrin, EVT VT,
|
|
|
|
SmallVectorImpl<SDValue> &OpValues);
|
|
|
|
void visitVPStridedStore(const VPIntrinsic &VPIntrin,
|
|
|
|
SmallVectorImpl<SDValue> &OpValues);
|
2022-03-31 00:01:30 +08:00
|
|
|
void visitVPCmp(const VPCmpIntrinsic &VPIntrin);
|
2020-12-09 18:36:30 +08:00
|
|
|
void visitVectorPredicationIntrinsic(const VPIntrinsic &VPIntrin);
|
2010-04-15 09:51:59 +08:00
|
|
|
|
|
|
|
void visitVAStart(const CallInst &I);
|
|
|
|
void visitVAArg(const VAArgInst &I);
|
|
|
|
void visitVAEnd(const CallInst &I);
|
|
|
|
void visitVACopy(const CallInst &I);
|
2013-11-01 01:18:24 +08:00
|
|
|
void visitStackmap(const CallInst &I);
|
2020-04-11 14:12:07 +08:00
|
|
|
void visitPatchpoint(const CallBase &CB, const BasicBlock *EHPadBB = nullptr);
|
2010-04-15 09:51:59 +08:00
|
|
|
|
2016-03-17 08:47:14 +08:00
|
|
|
// These two are implemented in StatepointLowering.cpp
|
2018-07-17 02:51:40 +08:00
|
|
|
void visitGCRelocate(const GCRelocateInst &Relocate);
|
2016-04-13 02:05:10 +08:00
|
|
|
void visitGCResult(const GCResultInst &I);
|
[Statepoints 3/4] Statepoint infrastructure for garbage collection: SelectionDAGBuilder
This is the third patch in a small series. It contains the CodeGen support for lowering the gc.statepoint intrinsic sequences (223078) to the STATEPOINT pseudo machine instruction (223085). The change also includes the set of helper routines and classes for working with gc.statepoints, gc.relocates, and gc.results since the lowering code uses them.
With this change, gc.statepoints should be functionally complete. The documentation will follow in the fourth change, and there will likely be some cleanup changes, but interested parties can start experimenting now.
I'm not particularly happy with the amount of code or complexity involved with the lowering step, but at least it's fairly well isolated. The statepoint lowering code is split into it's own files and anyone not working on the statepoint support itself should be able to ignore it.
During the lowering process, we currently spill aggressively to stack. This is not entirely ideal (and we have plans to do better), but it's functional, relatively straight forward, and matches closely the implementations of the patchpoint intrinsics. Most of the complexity comes from trying to keep relocated copies of values in the same stack slots across statepoints. Doing so avoids the insertion of pointless load and store instructions to reshuffle the stack. The current implementation isn't as effective as I'd like, but it is functional and 'good enough' for many common use cases.
In the long term, I'd like to figure out how to integrate the statepoint lowering with the register allocator. In principal, we shouldn't need to eagerly spill at all. The register allocator should do any spilling required and the statepoint should simply record that fact. Depending on how challenging that turns out to be, we may invest in a smarter global stack slot assignment mechanism as a stop gap measure.
Reviewed by: atrick, ributzka
llvm-svn: 223137
2014-12-03 02:50:36 +08:00
|
|
|
|
2017-05-09 18:43:25 +08:00
|
|
|
void visitVectorReduce(const CallInst &I, unsigned Intrinsic);
|
2021-01-16 00:46:42 +08:00
|
|
|
void visitVectorReverse(const CallInst &I);
|
[IR] Introduce llvm.experimental.vector.splice intrinsic
This patch introduces a new intrinsic @llvm.experimental.vector.splice
that constructs a vector of the same type as the two input vectors,
based on a immediate where the sign of the immediate distinguishes two
variants. A positive immediate specifies an index into the first vector
and a negative immediate specifies the number of trailing elements to
extract from the first vector.
For example:
@llvm.experimental.vector.splice(<A,B,C,D>, <E,F,G,H>, 1) ==> <B, C, D, E> ; index
@llvm.experimental.vector.splice(<A,B,C,D>, <E,F,G,H>, -3) ==> <B, C, D, E> ; trailing element count
These intrinsics support both fixed and scalable vectors, where the
former is lowered to a shufflevector to maintain existing behaviour,
although while marked as experimental the recommended way to express
this operation for fixed-width vectors is to use shufflevector. For
scalable vectors where it is not possible to express a shufflevector
mask for this operation, a new ISD node has been implemented.
This is one of the named shufflevector intrinsics proposed on the
mailing-list in the RFC at [1].
Patch by Paul Walker and Cullen Rhodes.
[1] https://lists.llvm.org/pipermail/llvm-dev/2020-November/146864.html
Reviewed By: sdesmalen
Differential Revision: https://reviews.llvm.org/D94708
2021-01-08 22:06:13 +08:00
|
|
|
void visitVectorSplice(const CallInst &I);
|
[IR][SVE] Add new llvm.experimental.stepvector intrinsic
This patch adds a new llvm.experimental.stepvector intrinsic,
which takes no arguments and returns a linear integer sequence of
values of the form <0, 1, ...>. It is primarily intended for
scalable vectors, although it will work for fixed width vectors
too. It is intended that later patches will make use of this
new intrinsic when vectorising induction variables, currently only
supported for fixed width. I've added a new CreateStepVector
method to the IRBuilder, which will generate a call to this
intrinsic for scalable vectors and fall back on creating a
ConstantVector for fixed width.
For scalable vectors this intrinsic is lowered to a new ISD node
called STEP_VECTOR, which takes a single constant integer argument
as the step. During lowering this argument is set to a value of 1.
The reason for this additional argument at the codegen level is
because in future patches we will introduce various generic DAG
combines such as
mul step_vector(1), 2 -> step_vector(2)
add step_vector(1), step_vector(1) -> step_vector(2)
shl step_vector(1), 1 -> step_vector(2)
etc.
that encourage a canonical format for all targets. This hopefully
means all other targets supporting scalable vectors can benefit
from this too.
I've added cost model tests for both fixed width and scalable
vectors:
llvm/test/Analysis/CostModel/AArch64/neon-stepvector.ll
llvm/test/Analysis/CostModel/AArch64/sve-stepvector.ll
as well as codegen lowering tests for fixed width and scalable
vectors:
llvm/test/CodeGen/AArch64/neon-stepvector.ll
llvm/test/CodeGen/AArch64/sve-stepvector.ll
See this thread for discussion of the intrinsic:
https://lists.llvm.org/pipermail/llvm-dev/2021-January/147943.html
2021-02-08 23:46:24 +08:00
|
|
|
void visitStepVector(const CallInst &I);
|
2017-05-09 18:43:25 +08:00
|
|
|
|
2010-04-15 09:51:59 +08:00
|
|
|
void visitUserOp1(const Instruction &I) {
|
2009-07-15 00:55:14 +08:00
|
|
|
llvm_unreachable("UserOp1 should not exist at instruction selection time!");
|
2008-09-04 00:12:24 +08:00
|
|
|
}
|
2010-04-15 09:51:59 +08:00
|
|
|
void visitUserOp2(const Instruction &I) {
|
2009-07-15 00:55:14 +08:00
|
|
|
llvm_unreachable("UserOp2 should not exist at instruction selection time!");
|
2008-09-04 00:12:24 +08:00
|
|
|
}
|
2010-04-23 04:55:53 +08:00
|
|
|
|
2013-08-16 18:55:47 +08:00
|
|
|
void processIntegerCallValue(const Instruction &I,
|
|
|
|
SDValue Value, bool IsSigned);
|
|
|
|
|
2020-09-25 05:35:15 +08:00
|
|
|
void HandlePHINodesInSuccessorBlocks(const BasicBlock *LLVMBB);
|
2010-04-29 07:08:54 +08:00
|
|
|
|
2020-04-11 09:29:02 +08:00
|
|
|
void emitInlineAsmError(const CallBase &Call, const Twine &Message);
|
2016-05-18 03:52:01 +08:00
|
|
|
|
2022-04-02 06:57:52 +08:00
|
|
|
/// An enum that states to emit func argument dbg value the kind of intrinsic
|
|
|
|
/// it originally had. This controls the internal behavior of
|
|
|
|
/// EmitFuncArgumentDbgValue.
|
|
|
|
enum class FuncArgumentDbgValueKind {
|
|
|
|
Value, // This was originally a llvm.dbg.value.
|
|
|
|
Addr, // This was originally a llvm.dbg.addr.
|
|
|
|
Declare, // This was originally a llvm.dbg.declare.
|
|
|
|
};
|
|
|
|
|
2017-07-29 05:27:35 +08:00
|
|
|
/// If V is an function argument then create corresponding DBG_VALUE machine
|
|
|
|
/// instruction for it now. At the end of instruction selection, they will be
|
|
|
|
/// inserted to the entry BB.
|
2015-04-30 00:38:44 +08:00
|
|
|
bool EmitFuncArgumentDbgValue(const Value *V, DILocalVariable *Variable,
|
|
|
|
DIExpression *Expr, DILocation *DL,
|
2022-04-02 06:57:52 +08:00
|
|
|
FuncArgumentDbgValueKind Kind,
|
|
|
|
const SDValue &N);
|
2015-03-20 04:41:48 +08:00
|
|
|
|
|
|
|
/// Return the next block after MBB, or nullptr if there is none.
|
|
|
|
MachineBasicBlock *NextBlock(MachineBasicBlock *MBB);
|
2015-04-14 01:16:45 +08:00
|
|
|
|
|
|
|
/// Update the DAG and DAG builder with the relevant information after
|
|
|
|
/// a new root node has been created which could be a tail call.
|
|
|
|
void updateDAGForMaybeTailCall(SDValue MaybeTC);
|
2016-08-16 02:18:26 +08:00
|
|
|
|
|
|
|
/// Return the appropriate SDDbgValue based on N.
|
|
|
|
SDDbgValue *getDbgValue(SDValue N, DILocalVariable *Variable,
|
2017-07-29 05:27:35 +08:00
|
|
|
DIExpression *Expr, const DebugLoc &dl,
|
|
|
|
unsigned DbgSDNodeOrder);
|
2019-05-20 19:01:30 +08:00
|
|
|
|
|
|
|
/// Lowers CallInst to an external symbol.
|
|
|
|
void lowerCallToExternalSymbol(const CallInst &I, const char *FunctionName);
|
2021-05-14 02:05:11 +08:00
|
|
|
|
|
|
|
SDValue lowerStartEH(SDValue Chain, const BasicBlock *EHPadBB,
|
|
|
|
MCSymbol *&BeginLabel);
|
|
|
|
SDValue lowerEndEH(SDValue Chain, const InvokeInst *II,
|
|
|
|
const BasicBlock *EHPadBB, MCSymbol *BeginLabel);
|
2008-09-04 00:12:24 +08:00
|
|
|
};
|
|
|
|
|
2019-02-13 06:11:20 +08:00
|
|
|
/// This struct represents the registers (physical or virtual)
|
2015-05-06 07:06:54 +08:00
|
|
|
/// that a particular set of values is assigned, and the type information about
|
|
|
|
/// the value. The most common situation is to represent one value at a time,
|
|
|
|
/// but struct or array values are handled element-wise as multiple values. The
|
|
|
|
/// splitting of aggregates is performed recursively, so that we never have
|
|
|
|
/// aggregate-typed registers. The values at this point do not necessarily have
|
|
|
|
/// legal types, so each value may require one or more registers of some legal
|
|
|
|
/// type.
|
|
|
|
///
|
|
|
|
struct RegsForValue {
|
2017-03-03 04:48:08 +08:00
|
|
|
/// The value types of the values, which may not be legal, and
|
2015-05-06 07:06:54 +08:00
|
|
|
/// may need be promoted or synthesized from one or more registers.
|
|
|
|
SmallVector<EVT, 4> ValueVTs;
|
|
|
|
|
2017-03-03 04:48:08 +08:00
|
|
|
/// The value types of the registers. This is the same size as ValueVTs and it
|
|
|
|
/// records, for each value, what the type of the assigned register or
|
|
|
|
/// registers are. (Individual values are never synthesized from more than one
|
|
|
|
/// type of register.)
|
2015-05-06 07:06:54 +08:00
|
|
|
///
|
|
|
|
/// With virtual registers, the contents of RegVTs is redundant with TLI's
|
|
|
|
/// getRegisterType member function, however when with physical registers
|
|
|
|
/// it is necessary to have a separate record of the types.
|
|
|
|
SmallVector<MVT, 4> RegVTs;
|
|
|
|
|
2017-03-03 04:48:08 +08:00
|
|
|
/// This list holds the registers assigned to the values.
|
2015-05-06 07:06:54 +08:00
|
|
|
/// Each legal or promoted value requires one register, and each
|
|
|
|
/// expanded value requires multiple registers.
|
|
|
|
SmallVector<unsigned, 4> Regs;
|
|
|
|
|
Reland "[SelectionDAG] Enable target specific vector scalarization of calls and returns"
By target hookifying getRegisterType, getNumRegisters, getVectorBreakdown,
backends can request that LLVM to scalarize vector types for calls
and returns.
The MIPS vector ABI requires that vector arguments and returns are passed in
integer registers. With SelectionDAG's new hooks, the MIPS backend can now
handle LLVM-IR with vector types in calls and returns. E.g.
'call @foo(<4 x i32> %4)'.
Previously these cases would be scalarized for the MIPS O32/N32/N64 ABI for
calls and returns if vector types were not legal. If vector types were legal,
a single 128bit vector argument would be assigned to a single 32 bit / 64 bit
integer register.
By teaching the MIPS backend to inspect the original types, it can now
implement the MIPS vector ABI which requires a particular method of
scalarizing vectors.
Previously, the MIPS backend relied on clang to scalarize types such as "call
@foo(<4 x float> %a) into "call @foo(i32 inreg %1, i32 inreg %2, i32 inreg %3,
i32 inreg %4)".
This patch enables the MIPS backend to take either form for vector types.
The previous version of this patch had a "conditional move or jump depends on
uninitialized value".
Reviewers: zoran.jovanovic, jaydeep, vkalintiris, slthakur
Differential Revision: https://reviews.llvm.org/D27845
llvm-svn: 305083
2017-06-09 22:37:08 +08:00
|
|
|
/// This list holds the number of registers for each value.
|
|
|
|
SmallVector<unsigned, 4> RegCount;
|
|
|
|
|
|
|
|
/// Records if this value needs to be treated in an ABI dependant manner,
|
|
|
|
/// different to normal type legalization.
|
2018-07-28 21:25:19 +08:00
|
|
|
Optional<CallingConv::ID> CallConv;
|
2015-05-06 07:06:54 +08:00
|
|
|
|
2017-09-28 07:26:01 +08:00
|
|
|
RegsForValue() = default;
|
Reland "[SelectionDAG] Enable target specific vector scalarization of calls and returns"
By target hookifying getRegisterType, getNumRegisters, getVectorBreakdown,
backends can request that LLVM to scalarize vector types for calls
and returns.
The MIPS vector ABI requires that vector arguments and returns are passed in
integer registers. With SelectionDAG's new hooks, the MIPS backend can now
handle LLVM-IR with vector types in calls and returns. E.g.
'call @foo(<4 x i32> %4)'.
Previously these cases would be scalarized for the MIPS O32/N32/N64 ABI for
calls and returns if vector types were not legal. If vector types were legal,
a single 128bit vector argument would be assigned to a single 32 bit / 64 bit
integer register.
By teaching the MIPS backend to inspect the original types, it can now
implement the MIPS vector ABI which requires a particular method of
scalarizing vectors.
Previously, the MIPS backend relied on clang to scalarize types such as "call
@foo(<4 x float> %a) into "call @foo(i32 inreg %1, i32 inreg %2, i32 inreg %3,
i32 inreg %4)".
This patch enables the MIPS backend to take either form for vector types.
The previous version of this patch had a "conditional move or jump depends on
uninitialized value".
Reviewers: zoran.jovanovic, jaydeep, vkalintiris, slthakur
Differential Revision: https://reviews.llvm.org/D27845
llvm-svn: 305083
2017-06-09 22:37:08 +08:00
|
|
|
RegsForValue(const SmallVector<unsigned, 4> ®s, MVT regvt, EVT valuevt,
|
2018-07-28 21:25:19 +08:00
|
|
|
Optional<CallingConv::ID> CC = None);
|
2015-07-09 09:57:34 +08:00
|
|
|
RegsForValue(LLVMContext &Context, const TargetLowering &TLI,
|
Reland "[SelectionDAG] Enable target specific vector scalarization of calls and returns"
By target hookifying getRegisterType, getNumRegisters, getVectorBreakdown,
backends can request that LLVM to scalarize vector types for calls
and returns.
The MIPS vector ABI requires that vector arguments and returns are passed in
integer registers. With SelectionDAG's new hooks, the MIPS backend can now
handle LLVM-IR with vector types in calls and returns. E.g.
'call @foo(<4 x i32> %4)'.
Previously these cases would be scalarized for the MIPS O32/N32/N64 ABI for
calls and returns if vector types were not legal. If vector types were legal,
a single 128bit vector argument would be assigned to a single 32 bit / 64 bit
integer register.
By teaching the MIPS backend to inspect the original types, it can now
implement the MIPS vector ABI which requires a particular method of
scalarizing vectors.
Previously, the MIPS backend relied on clang to scalarize types such as "call
@foo(<4 x float> %a) into "call @foo(i32 inreg %1, i32 inreg %2, i32 inreg %3,
i32 inreg %4)".
This patch enables the MIPS backend to take either form for vector types.
The previous version of this patch had a "conditional move or jump depends on
uninitialized value".
Reviewers: zoran.jovanovic, jaydeep, vkalintiris, slthakur
Differential Revision: https://reviews.llvm.org/D27845
llvm-svn: 305083
2017-06-09 22:37:08 +08:00
|
|
|
const DataLayout &DL, unsigned Reg, Type *Ty,
|
2018-07-28 21:25:19 +08:00
|
|
|
Optional<CallingConv::ID> CC);
|
|
|
|
|
2022-06-21 11:26:05 +08:00
|
|
|
bool isABIMangled() const { return CallConv.has_value(); }
|
2015-05-06 07:06:54 +08:00
|
|
|
|
2017-03-03 04:48:08 +08:00
|
|
|
/// Add the specified values to this one.
|
2015-05-06 07:06:54 +08:00
|
|
|
void append(const RegsForValue &RHS) {
|
|
|
|
ValueVTs.append(RHS.ValueVTs.begin(), RHS.ValueVTs.end());
|
|
|
|
RegVTs.append(RHS.RegVTs.begin(), RHS.RegVTs.end());
|
|
|
|
Regs.append(RHS.Regs.begin(), RHS.Regs.end());
|
Reland "[SelectionDAG] Enable target specific vector scalarization of calls and returns"
By target hookifying getRegisterType, getNumRegisters, getVectorBreakdown,
backends can request that LLVM to scalarize vector types for calls
and returns.
The MIPS vector ABI requires that vector arguments and returns are passed in
integer registers. With SelectionDAG's new hooks, the MIPS backend can now
handle LLVM-IR with vector types in calls and returns. E.g.
'call @foo(<4 x i32> %4)'.
Previously these cases would be scalarized for the MIPS O32/N32/N64 ABI for
calls and returns if vector types were not legal. If vector types were legal,
a single 128bit vector argument would be assigned to a single 32 bit / 64 bit
integer register.
By teaching the MIPS backend to inspect the original types, it can now
implement the MIPS vector ABI which requires a particular method of
scalarizing vectors.
Previously, the MIPS backend relied on clang to scalarize types such as "call
@foo(<4 x float> %a) into "call @foo(i32 inreg %1, i32 inreg %2, i32 inreg %3,
i32 inreg %4)".
This patch enables the MIPS backend to take either form for vector types.
The previous version of this patch had a "conditional move or jump depends on
uninitialized value".
Reviewers: zoran.jovanovic, jaydeep, vkalintiris, slthakur
Differential Revision: https://reviews.llvm.org/D27845
llvm-svn: 305083
2017-06-09 22:37:08 +08:00
|
|
|
RegCount.push_back(RHS.Regs.size());
|
2015-05-06 07:06:54 +08:00
|
|
|
}
|
|
|
|
|
2017-03-03 04:48:08 +08:00
|
|
|
/// Emit a series of CopyFromReg nodes that copies from this value and returns
|
|
|
|
/// the result as a ValueVTs value. This uses Chain/Flag as the input and
|
|
|
|
/// updates them for the output Chain/Flag. If the Flag pointer is NULL, no
|
|
|
|
/// flag is used.
|
2015-05-06 07:06:54 +08:00
|
|
|
SDValue getCopyFromRegs(SelectionDAG &DAG, FunctionLoweringInfo &FuncInfo,
|
2016-06-12 23:39:02 +08:00
|
|
|
const SDLoc &dl, SDValue &Chain, SDValue *Flag,
|
2015-05-06 07:06:54 +08:00
|
|
|
const Value *V = nullptr) const;
|
|
|
|
|
2017-03-03 04:48:08 +08:00
|
|
|
/// Emit a series of CopyToReg nodes that copies the specified value into the
|
|
|
|
/// registers specified by this object. This uses Chain/Flag as the input and
|
|
|
|
/// updates them for the output Chain/Flag. If the Flag pointer is nullptr, no
|
|
|
|
/// flag is used. If V is not nullptr, then it is used in printing better
|
|
|
|
/// diagnostic messages on error.
|
2016-06-12 23:39:02 +08:00
|
|
|
void getCopyToRegs(SDValue Val, SelectionDAG &DAG, const SDLoc &dl,
|
|
|
|
SDValue &Chain, SDValue *Flag, const Value *V = nullptr,
|
|
|
|
ISD::NodeType PreferredExtendType = ISD::ANY_EXTEND) const;
|
2015-05-06 07:06:54 +08:00
|
|
|
|
2017-03-03 04:48:08 +08:00
|
|
|
/// Add this value to the specified inlineasm node operand list. This adds the
|
|
|
|
/// code marker, matching input operand index (if applicable), and includes
|
|
|
|
/// the number of values added into it.
|
2018-07-17 02:51:40 +08:00
|
|
|
void AddInlineAsmOperands(unsigned Code, bool HasMatching,
|
2016-06-12 23:39:02 +08:00
|
|
|
unsigned MatchingIdx, const SDLoc &dl,
|
|
|
|
SelectionDAG &DAG, std::vector<SDValue> &Ops) const;
|
Reapply "[SelectionDAG] Selection of DBG_VALUE using a PHI node result (pt 2)"
Summary:
This reverts SVN r331441 (reapplies r331337), together with a fix
in to handle an already existing fragment expression in the
dbg.value that must be fragmented due to a split PHI node.
This should solve the problem seen in PR37321, which was the
reason for the revert of r331337.
The situation in PR37321 is that we have a PHI node like this
%u.sroa = phi i80 [ %u.sroa.x, %if.x ],
[ %u.sroa.y, %if.y ],
[ %u.sroa.z, %if.z ]
and a dbg.value like this
call void @llvm.dbg.value(metadata i80 %u.sroa,
metadata !13,
metadata !DIExpression(DW_OP_LLVM_fragment, 0, 80))
The phi node is split into three 32-bit PHI nodes
%30:gr32 = PHI %11:gr32, %bb.4, %14:gr32, %bb.5, %27:gr32, %bb.8
%31:gr32 = PHI %12:gr32, %bb.4, %15:gr32, %bb.5, %28:gr32, %bb.8
%32:gr32 = PHI %13:gr32, %bb.4, %16:gr32, %bb.5, %29:gr32, %bb.8
but since the original value only is 80 bits we need to adjust the size
of the last fragment expression, and with this patch we get
DBG_VALUE debug-use %30:gr32, debug-use $noreg, !"u", !DIExpression(DW_OP_LLVM_fragment, 0, 32)
DBG_VALUE debug-use %31:gr32, debug-use $noreg, !"u", !DIExpression(DW_OP_LLVM_fragment, 32, 32)
DBG_VALUE debug-use %32:gr32, debug-use $noreg, !"u", !DIExpression(DW_OP_LLVM_fragment, 64, 16)
Reviewers: vsk, aprantl, mstorsjo
Reviewed By: aprantl
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D46384
llvm-svn: 331464
2018-05-04 01:04:16 +08:00
|
|
|
|
|
|
|
/// Check if the total RegCount is greater than one.
|
|
|
|
bool occupiesMultipleRegs() const {
|
|
|
|
return std::accumulate(RegCount.begin(), RegCount.end(), 0) > 1;
|
|
|
|
}
|
2018-05-04 16:50:48 +08:00
|
|
|
|
|
|
|
/// Return a list of registers and their sizes.
|
2020-12-01 01:30:11 +08:00
|
|
|
SmallVector<std::pair<unsigned, TypeSize>, 4> getRegsAndSizes() const;
|
2015-05-06 07:06:54 +08:00
|
|
|
};
|
|
|
|
|
2008-09-04 00:12:24 +08:00
|
|
|
} // end namespace llvm
|
|
|
|
|
2017-09-28 07:26:01 +08:00
|
|
|
#endif // LLVM_LIB_CODEGEN_SELECTIONDAG_SELECTIONDAGBUILDER_H
|