1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-22 10:42:39 +01:00
llvm-mirror/lib/IR/IRBuilder.cpp

1213 lines
46 KiB
C++
Raw Normal View History

//===- IRBuilder.cpp - Builder for LLVM Instrs ----------------------------===//
//
// 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
//
//===----------------------------------------------------------------------===//
//
// This file implements the IRBuilder class, which is used as a convenient way
// to create LLVM instructions with a consistent and simplified interface.
//
//===----------------------------------------------------------------------===//
#include "llvm/IR/IRBuilder.h"
#include "llvm/ADT/ArrayRef.h"
#include "llvm/ADT/None.h"
#include "llvm/IR/Constant.h"
#include "llvm/IR/Constants.h"
#include "llvm/IR/DerivedTypes.h"
#include "llvm/IR/Function.h"
#include "llvm/IR/GlobalValue.h"
#include "llvm/IR/GlobalVariable.h"
Remove alignment argument from memcpy/memmove/memset in favour of alignment attributes (Step 1) Summary: This is a resurrection of work first proposed and discussed in Aug 2015: http://lists.llvm.org/pipermail/llvm-dev/2015-August/089384.html and initially landed (but then backed out) in Nov 2015: http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20151109/312083.html The @llvm.memcpy/memmove/memset intrinsics currently have an explicit argument which is required to be a constant integer. It represents the alignment of the dest (and source), and so must be the minimum of the actual alignment of the two. This change is the first in a series that allows source and dest to each have their own alignments by using the alignment attribute on their arguments. In this change we: 1) Remove the alignment argument. 2) Add alignment attributes to the source & dest arguments. We, temporarily, require that the alignments for source & dest be equal. For example, code which used to read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 100, i32 4, i1 false) will now read call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %dest, i8* align 4 %src, i32 100, i1 false) Downstream users may have to update their lit tests that check for @llvm.memcpy/memmove/memset call/declaration patterns. The following extended sed script may help with updating the majority of your tests, but it does not catch all possible patterns so some manual checking and updating will be required. s~declare void @llvm\.mem(set|cpy|move)\.p([^(]*)\((.*), i32, i1\)~declare void @llvm.mem\1.p\2(\3, i1)~g s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* \3, i8 \4, i8 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* \3, i8 \4, i16 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* \3, i8 \4, i32 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* \3, i8 \4, i64 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* \3, i8 \4, i128 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* align \6 \3, i8 \4, i8 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* align \6 \3, i8 \4, i16 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* align \6 \3, i8 \4, i32 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* align \6 \3, i8 \4, i64 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* align \6 \3, i8 \4, i128 \5, i1 \7)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* \4, i8\5* \6, i8 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* \4, i8\5* \6, i16 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* \4, i8\5* \6, i32 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* \4, i8\5* \6, i64 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* \4, i8\5* \6, i128 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* align \8 \4, i8\5* align \8 \6, i8 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* align \8 \4, i8\5* align \8 \6, i16 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* align \8 \4, i8\5* align \8 \6, i32 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* align \8 \4, i8\5* align \8 \6, i64 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* align \8 \4, i8\5* align \8 \6, i128 \7, i1 \9)~g The remaining changes in the series will: Step 2) Expand the IRBuilder API to allow creation of memcpy/memmove with differing source and dest alignments. Step 3) Update Clang to use the new IRBuilder API. Step 4) Update Polly to use the new IRBuilder API. Step 5) Update LLVM passes that create memcpy/memmove calls to use the new IRBuilder API, and those that use use MemIntrinsicInst::[get|set]Alignment() to use getDestAlignment() and getSourceAlignment() instead. Step 6) Remove the single-alignment IRBuilder API for memcpy/memmove, and the MemIntrinsicInst::[get|set]Alignment() methods. Reviewers: pete, hfinkel, lhames, reames, bollu Reviewed By: reames Subscribers: niosHD, reames, jholewinski, qcolombet, jfb, sanjoy, arsenm, dschuff, dylanmckay, mehdi_amini, sdardis, nemanjai, david2050, nhaehnle, javed.absar, sbc100, jgravelle-google, eraman, aheejin, kbarton, JDevlieghere, asb, rbar, johnrusso, simoncook, jordy.potman.lists, apazos, sabuasal, llvm-commits Differential Revision: https://reviews.llvm.org/D41675 llvm-svn: 322965
2018-01-19 18:13:12 +01:00
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/IR/Intrinsics.h"
#include "llvm/IR/LLVMContext.h"
Reapply "[IRBuilder] Virtualize IRBuilder" Relative to the original commit, this fixes some warnings, and is based on the deletion of the IRBuilder copy constructor in D74693. The automatic copy constructor would no longer be safe. ----- Related llvm-dev thread: http://lists.llvm.org/pipermail/llvm-dev/2020-February/138951.html This patch moves the IRBuilder from templating over the constant folder and inserter towards making both of these virtual. There are a couple of motivations for this: 1. It's not possible to share code between use-sites that use different IRBuilder folders/inserters (short of templating the code and moving it into headers). 2. Methods currently defined on IRBuilderBase (which is not templated) do not use the custom inserter, resulting in subtle bugs (e.g. incorrect InstCombine worklist management). It would be possible to move those into the templated IRBuilder, but... 3. The vast majority of the IRBuilder implementation has to live in the header, because it depends on the template arguments. 4. We have many unnecessary dependencies on IRBuilder.h, because it is not easy to forward-declare. (Significant parts of the backend depend on it via TargetLowering.h, for example.) This patch addresses the issue by making the following changes: * IRBuilderDefaultInserter::InsertHelper becomes virtual. IRBuilderBase accepts a reference to it. * IRBuilderFolder is introduced as a virtual base class. It is implemented by ConstantFolder (default), NoFolder and TargetFolder. IRBuilderBase has a reference to this as well. * All the logic is moved from IRBuilder to IRBuilderBase. This means that methods can in the future replace their IRBuilder<> & uses (or other specific IRBuilder types) with IRBuilderBase & and thus be usable with different IRBuilders. * The IRBuilder class is now a thin wrapper around IRBuilderBase. Essentially it only stores the folder and inserter and takes care of constructing the base builder. What this patch doesn't do, but should be simple followups after this change: * Fixing use of the inserter for creation methods originally defined on IRBuilderBase. * Replacing IRBuilder<> uses in arguments with IRBuilderBase, where useful. * Moving code from the IRBuilder header to the source file. From the user perspective, these changes should be mostly transparent: The only thing that consumers using a custom inserted may need to do is inherit from IRBuilderDefaultInserter publicly and mark their InsertHelper as public. Differential Revision: https://reviews.llvm.org/D73835
2020-02-16 17:10:09 +01:00
#include "llvm/IR/NoFolder.h"
#include "llvm/IR/Operator.h"
#include "llvm/IR/Statepoint.h"
#include "llvm/IR/Type.h"
#include "llvm/IR/Value.h"
#include "llvm/Support/Casting.h"
#include "llvm/Support/MathExtras.h"
#include <cassert>
#include <cstdint>
#include <vector>
using namespace llvm;
/// CreateGlobalString - Make a new global variable with an initializer that
/// has array of i8 type filled in with the nul terminated string value
/// specified. If Name is specified, it is the name of the global variable
/// created.
GlobalVariable *IRBuilderBase::CreateGlobalString(StringRef Str,
const Twine &Name,
unsigned AddressSpace,
Module *M) {
Constant *StrConstant = ConstantDataArray::getString(Context, Str);
if (!M)
M = BB->getParent()->getParent();
auto *GV = new GlobalVariable(
*M, StrConstant->getType(), true, GlobalValue::PrivateLinkage,
StrConstant, Name, nullptr, GlobalVariable::NotThreadLocal, AddressSpace);
IR: Introduce local_unnamed_addr attribute. If a local_unnamed_addr attribute is attached to a global, the address is known to be insignificant within the module. It is distinct from the existing unnamed_addr attribute in that it only describes a local property of the module rather than a global property of the symbol. This attribute is intended to be used by the code generator and LTO to allow the linker to decide whether the global needs to be in the symbol table. It is possible to exclude a global from the symbol table if three things are true: - This attribute is present on every instance of the global (which means that the normal rule that the global must have a unique address can be broken without being observable by the program by performing comparisons against the global's address) - The global has linkonce_odr linkage (which means that each linkage unit must have its own copy of the global if it requires one, and the copy in each linkage unit must be the same) - It is a constant or a function (which means that the program cannot observe that the unique-address rule has been broken by writing to the global) Although this attribute could in principle be computed from the module contents, LTO clients (i.e. linkers) will normally need to be able to compute this property as part of symbol resolution, and it would be inefficient to materialize every module just to compute it. See: http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20160509/356401.html http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20160516/356738.html for earlier discussion. Part of the fix for PR27553. Differential Revision: http://reviews.llvm.org/D20348 llvm-svn: 272709
2016-06-14 23:01:22 +02:00
GV->setUnnamedAddr(GlobalValue::UnnamedAddr::Global);
GV->setAlignment(Align(1));
return GV;
}
Type *IRBuilderBase::getCurrentFunctionReturnType() const {
assert(BB && BB->getParent() && "No current function!");
return BB->getParent()->getReturnType();
}
Value *IRBuilderBase::getCastedInt8PtrValue(Value *Ptr) {
auto *PT = cast<PointerType>(Ptr->getType());
if (PT->getElementType()->isIntegerTy(8))
return Ptr;
// Otherwise, we need to insert a bitcast.
return CreateBitCast(Ptr, getInt8PtrTy(PT->getAddressSpace()));
}
static CallInst *createCallHelper(Function *Callee, ArrayRef<Value *> Ops,
IRBuilderBase *Builder,
const Twine &Name = "",
Instruction *FMFSource = nullptr,
ArrayRef<OperandBundleDef> OpBundles = {}) {
CallInst *CI = Builder->CreateCall(Callee, Ops, OpBundles, Name);
if (FMFSource)
CI->copyFastMathFlags(FMFSource);
return CI;
}
Value *IRBuilderBase::CreateVScale(Constant *Scaling, const Twine &Name) {
assert(isa<ConstantInt>(Scaling) && "Expected constant integer");
if (cast<ConstantInt>(Scaling)->isZero())
return Scaling;
Module *M = GetInsertBlock()->getParent()->getParent();
Function *TheFn =
Intrinsic::getDeclaration(M, Intrinsic::vscale, {Scaling->getType()});
CallInst *CI = createCallHelper(TheFn, {}, this, Name);
return cast<ConstantInt>(Scaling)->getSExtValue() == 1
? CI
: CreateMul(CI, Scaling);
}
[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 16:46:24 +01:00
Value *IRBuilderBase::CreateStepVector(Type *DstType, const Twine &Name) {
if (isa<ScalableVectorType>(DstType))
return CreateIntrinsic(Intrinsic::experimental_stepvector, {DstType}, {},
nullptr, Name);
Type *STy = DstType->getScalarType();
unsigned NumEls = cast<FixedVectorType>(DstType)->getNumElements();
// Create a vector of consecutive numbers from zero to VF.
SmallVector<Constant *, 8> Indices;
for (unsigned i = 0; i < NumEls; ++i)
Indices.push_back(ConstantInt::get(STy, i));
// Add the consecutive indices to the vector value.
return ConstantVector::get(Indices);
}
CallInst *IRBuilderBase::CreateMemSet(Value *Ptr, Value *Val, Value *Size,
MaybeAlign Align, bool isVolatile,
MDNode *TBAATag, MDNode *ScopeTag,
MDNode *NoAliasTag) {
Ptr = getCastedInt8PtrValue(Ptr);
Remove alignment argument from memcpy/memmove/memset in favour of alignment attributes (Step 1) Summary: This is a resurrection of work first proposed and discussed in Aug 2015: http://lists.llvm.org/pipermail/llvm-dev/2015-August/089384.html and initially landed (but then backed out) in Nov 2015: http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20151109/312083.html The @llvm.memcpy/memmove/memset intrinsics currently have an explicit argument which is required to be a constant integer. It represents the alignment of the dest (and source), and so must be the minimum of the actual alignment of the two. This change is the first in a series that allows source and dest to each have their own alignments by using the alignment attribute on their arguments. In this change we: 1) Remove the alignment argument. 2) Add alignment attributes to the source & dest arguments. We, temporarily, require that the alignments for source & dest be equal. For example, code which used to read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 100, i32 4, i1 false) will now read call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %dest, i8* align 4 %src, i32 100, i1 false) Downstream users may have to update their lit tests that check for @llvm.memcpy/memmove/memset call/declaration patterns. The following extended sed script may help with updating the majority of your tests, but it does not catch all possible patterns so some manual checking and updating will be required. s~declare void @llvm\.mem(set|cpy|move)\.p([^(]*)\((.*), i32, i1\)~declare void @llvm.mem\1.p\2(\3, i1)~g s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* \3, i8 \4, i8 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* \3, i8 \4, i16 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* \3, i8 \4, i32 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* \3, i8 \4, i64 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* \3, i8 \4, i128 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* align \6 \3, i8 \4, i8 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* align \6 \3, i8 \4, i16 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* align \6 \3, i8 \4, i32 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* align \6 \3, i8 \4, i64 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* align \6 \3, i8 \4, i128 \5, i1 \7)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* \4, i8\5* \6, i8 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* \4, i8\5* \6, i16 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* \4, i8\5* \6, i32 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* \4, i8\5* \6, i64 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* \4, i8\5* \6, i128 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* align \8 \4, i8\5* align \8 \6, i8 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* align \8 \4, i8\5* align \8 \6, i16 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* align \8 \4, i8\5* align \8 \6, i32 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* align \8 \4, i8\5* align \8 \6, i64 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* align \8 \4, i8\5* align \8 \6, i128 \7, i1 \9)~g The remaining changes in the series will: Step 2) Expand the IRBuilder API to allow creation of memcpy/memmove with differing source and dest alignments. Step 3) Update Clang to use the new IRBuilder API. Step 4) Update Polly to use the new IRBuilder API. Step 5) Update LLVM passes that create memcpy/memmove calls to use the new IRBuilder API, and those that use use MemIntrinsicInst::[get|set]Alignment() to use getDestAlignment() and getSourceAlignment() instead. Step 6) Remove the single-alignment IRBuilder API for memcpy/memmove, and the MemIntrinsicInst::[get|set]Alignment() methods. Reviewers: pete, hfinkel, lhames, reames, bollu Reviewed By: reames Subscribers: niosHD, reames, jholewinski, qcolombet, jfb, sanjoy, arsenm, dschuff, dylanmckay, mehdi_amini, sdardis, nemanjai, david2050, nhaehnle, javed.absar, sbc100, jgravelle-google, eraman, aheejin, kbarton, JDevlieghere, asb, rbar, johnrusso, simoncook, jordy.potman.lists, apazos, sabuasal, llvm-commits Differential Revision: https://reviews.llvm.org/D41675 llvm-svn: 322965
2018-01-19 18:13:12 +01:00
Value *Ops[] = {Ptr, Val, Size, getInt1(isVolatile)};
Type *Tys[] = { Ptr->getType(), Size->getType() };
Module *M = BB->getParent()->getParent();
Function *TheFn = Intrinsic::getDeclaration(M, Intrinsic::memset, Tys);
CallInst *CI = createCallHelper(TheFn, Ops, this);
Remove alignment argument from memcpy/memmove/memset in favour of alignment attributes (Step 1) Summary: This is a resurrection of work first proposed and discussed in Aug 2015: http://lists.llvm.org/pipermail/llvm-dev/2015-August/089384.html and initially landed (but then backed out) in Nov 2015: http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20151109/312083.html The @llvm.memcpy/memmove/memset intrinsics currently have an explicit argument which is required to be a constant integer. It represents the alignment of the dest (and source), and so must be the minimum of the actual alignment of the two. This change is the first in a series that allows source and dest to each have their own alignments by using the alignment attribute on their arguments. In this change we: 1) Remove the alignment argument. 2) Add alignment attributes to the source & dest arguments. We, temporarily, require that the alignments for source & dest be equal. For example, code which used to read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 100, i32 4, i1 false) will now read call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %dest, i8* align 4 %src, i32 100, i1 false) Downstream users may have to update their lit tests that check for @llvm.memcpy/memmove/memset call/declaration patterns. The following extended sed script may help with updating the majority of your tests, but it does not catch all possible patterns so some manual checking and updating will be required. s~declare void @llvm\.mem(set|cpy|move)\.p([^(]*)\((.*), i32, i1\)~declare void @llvm.mem\1.p\2(\3, i1)~g s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* \3, i8 \4, i8 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* \3, i8 \4, i16 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* \3, i8 \4, i32 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* \3, i8 \4, i64 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* \3, i8 \4, i128 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* align \6 \3, i8 \4, i8 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* align \6 \3, i8 \4, i16 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* align \6 \3, i8 \4, i32 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* align \6 \3, i8 \4, i64 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* align \6 \3, i8 \4, i128 \5, i1 \7)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* \4, i8\5* \6, i8 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* \4, i8\5* \6, i16 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* \4, i8\5* \6, i32 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* \4, i8\5* \6, i64 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* \4, i8\5* \6, i128 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* align \8 \4, i8\5* align \8 \6, i8 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* align \8 \4, i8\5* align \8 \6, i16 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* align \8 \4, i8\5* align \8 \6, i32 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* align \8 \4, i8\5* align \8 \6, i64 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* align \8 \4, i8\5* align \8 \6, i128 \7, i1 \9)~g The remaining changes in the series will: Step 2) Expand the IRBuilder API to allow creation of memcpy/memmove with differing source and dest alignments. Step 3) Update Clang to use the new IRBuilder API. Step 4) Update Polly to use the new IRBuilder API. Step 5) Update LLVM passes that create memcpy/memmove calls to use the new IRBuilder API, and those that use use MemIntrinsicInst::[get|set]Alignment() to use getDestAlignment() and getSourceAlignment() instead. Step 6) Remove the single-alignment IRBuilder API for memcpy/memmove, and the MemIntrinsicInst::[get|set]Alignment() methods. Reviewers: pete, hfinkel, lhames, reames, bollu Reviewed By: reames Subscribers: niosHD, reames, jholewinski, qcolombet, jfb, sanjoy, arsenm, dschuff, dylanmckay, mehdi_amini, sdardis, nemanjai, david2050, nhaehnle, javed.absar, sbc100, jgravelle-google, eraman, aheejin, kbarton, JDevlieghere, asb, rbar, johnrusso, simoncook, jordy.potman.lists, apazos, sabuasal, llvm-commits Differential Revision: https://reviews.llvm.org/D41675 llvm-svn: 322965
2018-01-19 18:13:12 +01:00
if (Align)
cast<MemSetInst>(CI)->setDestAlignment(Align->value());
Remove alignment argument from memcpy/memmove/memset in favour of alignment attributes (Step 1) Summary: This is a resurrection of work first proposed and discussed in Aug 2015: http://lists.llvm.org/pipermail/llvm-dev/2015-August/089384.html and initially landed (but then backed out) in Nov 2015: http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20151109/312083.html The @llvm.memcpy/memmove/memset intrinsics currently have an explicit argument which is required to be a constant integer. It represents the alignment of the dest (and source), and so must be the minimum of the actual alignment of the two. This change is the first in a series that allows source and dest to each have their own alignments by using the alignment attribute on their arguments. In this change we: 1) Remove the alignment argument. 2) Add alignment attributes to the source & dest arguments. We, temporarily, require that the alignments for source & dest be equal. For example, code which used to read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 100, i32 4, i1 false) will now read call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %dest, i8* align 4 %src, i32 100, i1 false) Downstream users may have to update their lit tests that check for @llvm.memcpy/memmove/memset call/declaration patterns. The following extended sed script may help with updating the majority of your tests, but it does not catch all possible patterns so some manual checking and updating will be required. s~declare void @llvm\.mem(set|cpy|move)\.p([^(]*)\((.*), i32, i1\)~declare void @llvm.mem\1.p\2(\3, i1)~g s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* \3, i8 \4, i8 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* \3, i8 \4, i16 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* \3, i8 \4, i32 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* \3, i8 \4, i64 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* \3, i8 \4, i128 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* align \6 \3, i8 \4, i8 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* align \6 \3, i8 \4, i16 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* align \6 \3, i8 \4, i32 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* align \6 \3, i8 \4, i64 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* align \6 \3, i8 \4, i128 \5, i1 \7)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* \4, i8\5* \6, i8 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* \4, i8\5* \6, i16 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* \4, i8\5* \6, i32 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* \4, i8\5* \6, i64 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* \4, i8\5* \6, i128 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* align \8 \4, i8\5* align \8 \6, i8 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* align \8 \4, i8\5* align \8 \6, i16 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* align \8 \4, i8\5* align \8 \6, i32 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* align \8 \4, i8\5* align \8 \6, i64 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* align \8 \4, i8\5* align \8 \6, i128 \7, i1 \9)~g The remaining changes in the series will: Step 2) Expand the IRBuilder API to allow creation of memcpy/memmove with differing source and dest alignments. Step 3) Update Clang to use the new IRBuilder API. Step 4) Update Polly to use the new IRBuilder API. Step 5) Update LLVM passes that create memcpy/memmove calls to use the new IRBuilder API, and those that use use MemIntrinsicInst::[get|set]Alignment() to use getDestAlignment() and getSourceAlignment() instead. Step 6) Remove the single-alignment IRBuilder API for memcpy/memmove, and the MemIntrinsicInst::[get|set]Alignment() methods. Reviewers: pete, hfinkel, lhames, reames, bollu Reviewed By: reames Subscribers: niosHD, reames, jholewinski, qcolombet, jfb, sanjoy, arsenm, dschuff, dylanmckay, mehdi_amini, sdardis, nemanjai, david2050, nhaehnle, javed.absar, sbc100, jgravelle-google, eraman, aheejin, kbarton, JDevlieghere, asb, rbar, johnrusso, simoncook, jordy.potman.lists, apazos, sabuasal, llvm-commits Differential Revision: https://reviews.llvm.org/D41675 llvm-svn: 322965
2018-01-19 18:13:12 +01:00
// Set the TBAA info if present.
if (TBAATag)
CI->setMetadata(LLVMContext::MD_tbaa, TBAATag);
Add scoped-noalias metadata This commit adds scoped noalias metadata. The primary motivations for this feature are: 1. To preserve noalias function attribute information when inlining 2. To provide the ability to model block-scope C99 restrict pointers Neither of these two abilities are added here, only the necessary infrastructure. In fact, there should be no change to existing functionality, only the addition of new features. The logic that converts noalias function parameters into this metadata during inlining will come in a follow-up commit. What is added here is the ability to generally specify noalias memory-access sets. Regarding the metadata, alias-analysis scopes are defined similar to TBAA nodes: !scope0 = metadata !{ metadata !"scope of foo()" } !scope1 = metadata !{ metadata !"scope 1", metadata !scope0 } !scope2 = metadata !{ metadata !"scope 2", metadata !scope0 } !scope3 = metadata !{ metadata !"scope 2.1", metadata !scope2 } !scope4 = metadata !{ metadata !"scope 2.2", metadata !scope2 } Loads and stores can be tagged with an alias-analysis scope, and also, with a noalias tag for a specific scope: ... = load %ptr1, !alias.scope !{ !scope1 } ... = load %ptr2, !alias.scope !{ !scope1, !scope2 }, !noalias !{ !scope1 } When evaluating an aliasing query, if one of the instructions is associated with an alias.scope id that is identical to the noalias scope associated with the other instruction, or is a descendant (in the scope hierarchy) of the noalias scope associated with the other instruction, then the two memory accesses are assumed not to alias. Note that is the first element of the scope metadata is a string, then it can be combined accross functions and translation units. The string can be replaced by a self-reference to create globally unqiue scope identifiers. [Note: This overview is slightly stylized, since the metadata nodes really need to just be numbers (!0 instead of !scope0), and the scope lists are also global unnamed metadata.] Existing noalias metadata in a callee is "cloned" for use by the inlined code. This is necessary because the aliasing scopes are unique to each call site (because of possible control dependencies on the aliasing properties). For example, consider a function: foo(noalias a, noalias b) { *a = *b; } that gets inlined into bar() { ... if (...) foo(a1, b1); ... if (...) foo(a2, b2); } -- now just because we know that a1 does not alias with b1 at the first call site, and a2 does not alias with b2 at the second call site, we cannot let inlining these functons have the metadata imply that a1 does not alias with b2. llvm-svn: 213864
2014-07-24 16:25:39 +02:00
if (ScopeTag)
CI->setMetadata(LLVMContext::MD_alias_scope, ScopeTag);
Add scoped-noalias metadata This commit adds scoped noalias metadata. The primary motivations for this feature are: 1. To preserve noalias function attribute information when inlining 2. To provide the ability to model block-scope C99 restrict pointers Neither of these two abilities are added here, only the necessary infrastructure. In fact, there should be no change to existing functionality, only the addition of new features. The logic that converts noalias function parameters into this metadata during inlining will come in a follow-up commit. What is added here is the ability to generally specify noalias memory-access sets. Regarding the metadata, alias-analysis scopes are defined similar to TBAA nodes: !scope0 = metadata !{ metadata !"scope of foo()" } !scope1 = metadata !{ metadata !"scope 1", metadata !scope0 } !scope2 = metadata !{ metadata !"scope 2", metadata !scope0 } !scope3 = metadata !{ metadata !"scope 2.1", metadata !scope2 } !scope4 = metadata !{ metadata !"scope 2.2", metadata !scope2 } Loads and stores can be tagged with an alias-analysis scope, and also, with a noalias tag for a specific scope: ... = load %ptr1, !alias.scope !{ !scope1 } ... = load %ptr2, !alias.scope !{ !scope1, !scope2 }, !noalias !{ !scope1 } When evaluating an aliasing query, if one of the instructions is associated with an alias.scope id that is identical to the noalias scope associated with the other instruction, or is a descendant (in the scope hierarchy) of the noalias scope associated with the other instruction, then the two memory accesses are assumed not to alias. Note that is the first element of the scope metadata is a string, then it can be combined accross functions and translation units. The string can be replaced by a self-reference to create globally unqiue scope identifiers. [Note: This overview is slightly stylized, since the metadata nodes really need to just be numbers (!0 instead of !scope0), and the scope lists are also global unnamed metadata.] Existing noalias metadata in a callee is "cloned" for use by the inlined code. This is necessary because the aliasing scopes are unique to each call site (because of possible control dependencies on the aliasing properties). For example, consider a function: foo(noalias a, noalias b) { *a = *b; } that gets inlined into bar() { ... if (...) foo(a1, b1); ... if (...) foo(a2, b2); } -- now just because we know that a1 does not alias with b1 at the first call site, and a2 does not alias with b2 at the second call site, we cannot let inlining these functons have the metadata imply that a1 does not alias with b2. llvm-svn: 213864
2014-07-24 16:25:39 +02:00
if (NoAliasTag)
CI->setMetadata(LLVMContext::MD_noalias, NoAliasTag);
Remove alignment argument from memcpy/memmove/memset in favour of alignment attributes (Step 1) Summary: This is a resurrection of work first proposed and discussed in Aug 2015: http://lists.llvm.org/pipermail/llvm-dev/2015-August/089384.html and initially landed (but then backed out) in Nov 2015: http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20151109/312083.html The @llvm.memcpy/memmove/memset intrinsics currently have an explicit argument which is required to be a constant integer. It represents the alignment of the dest (and source), and so must be the minimum of the actual alignment of the two. This change is the first in a series that allows source and dest to each have their own alignments by using the alignment attribute on their arguments. In this change we: 1) Remove the alignment argument. 2) Add alignment attributes to the source & dest arguments. We, temporarily, require that the alignments for source & dest be equal. For example, code which used to read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 100, i32 4, i1 false) will now read call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %dest, i8* align 4 %src, i32 100, i1 false) Downstream users may have to update their lit tests that check for @llvm.memcpy/memmove/memset call/declaration patterns. The following extended sed script may help with updating the majority of your tests, but it does not catch all possible patterns so some manual checking and updating will be required. s~declare void @llvm\.mem(set|cpy|move)\.p([^(]*)\((.*), i32, i1\)~declare void @llvm.mem\1.p\2(\3, i1)~g s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* \3, i8 \4, i8 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* \3, i8 \4, i16 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* \3, i8 \4, i32 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* \3, i8 \4, i64 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* \3, i8 \4, i128 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* align \6 \3, i8 \4, i8 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* align \6 \3, i8 \4, i16 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* align \6 \3, i8 \4, i32 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* align \6 \3, i8 \4, i64 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* align \6 \3, i8 \4, i128 \5, i1 \7)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* \4, i8\5* \6, i8 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* \4, i8\5* \6, i16 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* \4, i8\5* \6, i32 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* \4, i8\5* \6, i64 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* \4, i8\5* \6, i128 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* align \8 \4, i8\5* align \8 \6, i8 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* align \8 \4, i8\5* align \8 \6, i16 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* align \8 \4, i8\5* align \8 \6, i32 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* align \8 \4, i8\5* align \8 \6, i64 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* align \8 \4, i8\5* align \8 \6, i128 \7, i1 \9)~g The remaining changes in the series will: Step 2) Expand the IRBuilder API to allow creation of memcpy/memmove with differing source and dest alignments. Step 3) Update Clang to use the new IRBuilder API. Step 4) Update Polly to use the new IRBuilder API. Step 5) Update LLVM passes that create memcpy/memmove calls to use the new IRBuilder API, and those that use use MemIntrinsicInst::[get|set]Alignment() to use getDestAlignment() and getSourceAlignment() instead. Step 6) Remove the single-alignment IRBuilder API for memcpy/memmove, and the MemIntrinsicInst::[get|set]Alignment() methods. Reviewers: pete, hfinkel, lhames, reames, bollu Reviewed By: reames Subscribers: niosHD, reames, jholewinski, qcolombet, jfb, sanjoy, arsenm, dschuff, dylanmckay, mehdi_amini, sdardis, nemanjai, david2050, nhaehnle, javed.absar, sbc100, jgravelle-google, eraman, aheejin, kbarton, JDevlieghere, asb, rbar, johnrusso, simoncook, jordy.potman.lists, apazos, sabuasal, llvm-commits Differential Revision: https://reviews.llvm.org/D41675 llvm-svn: 322965
2018-01-19 18:13:12 +01:00
return CI;
}
CallInst *IRBuilderBase::CreateElementUnorderedAtomicMemSet(
Value *Ptr, Value *Val, Value *Size, Align Alignment, uint32_t ElementSize,
MDNode *TBAATag, MDNode *ScopeTag, MDNode *NoAliasTag) {
Ptr = getCastedInt8PtrValue(Ptr);
Value *Ops[] = {Ptr, Val, Size, getInt32(ElementSize)};
Type *Tys[] = {Ptr->getType(), Size->getType()};
Module *M = BB->getParent()->getParent();
Function *TheFn = Intrinsic::getDeclaration(
M, Intrinsic::memset_element_unordered_atomic, Tys);
CallInst *CI = createCallHelper(TheFn, Ops, this);
cast<AtomicMemSetInst>(CI)->setDestAlignment(Alignment);
// Set the TBAA info if present.
if (TBAATag)
CI->setMetadata(LLVMContext::MD_tbaa, TBAATag);
if (ScopeTag)
CI->setMetadata(LLVMContext::MD_alias_scope, ScopeTag);
if (NoAliasTag)
CI->setMetadata(LLVMContext::MD_noalias, NoAliasTag);
return CI;
}
CallInst *IRBuilderBase::CreateMemTransferInst(
Intrinsic::ID IntrID, Value *Dst, MaybeAlign DstAlign, Value *Src,
MaybeAlign SrcAlign, Value *Size, bool isVolatile, MDNode *TBAATag,
MDNode *TBAAStructTag, MDNode *ScopeTag, MDNode *NoAliasTag) {
Dst = getCastedInt8PtrValue(Dst);
Src = getCastedInt8PtrValue(Src);
Remove alignment argument from memcpy/memmove/memset in favour of alignment attributes (Step 1) Summary: This is a resurrection of work first proposed and discussed in Aug 2015: http://lists.llvm.org/pipermail/llvm-dev/2015-August/089384.html and initially landed (but then backed out) in Nov 2015: http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20151109/312083.html The @llvm.memcpy/memmove/memset intrinsics currently have an explicit argument which is required to be a constant integer. It represents the alignment of the dest (and source), and so must be the minimum of the actual alignment of the two. This change is the first in a series that allows source and dest to each have their own alignments by using the alignment attribute on their arguments. In this change we: 1) Remove the alignment argument. 2) Add alignment attributes to the source & dest arguments. We, temporarily, require that the alignments for source & dest be equal. For example, code which used to read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 100, i32 4, i1 false) will now read call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %dest, i8* align 4 %src, i32 100, i1 false) Downstream users may have to update their lit tests that check for @llvm.memcpy/memmove/memset call/declaration patterns. The following extended sed script may help with updating the majority of your tests, but it does not catch all possible patterns so some manual checking and updating will be required. s~declare void @llvm\.mem(set|cpy|move)\.p([^(]*)\((.*), i32, i1\)~declare void @llvm.mem\1.p\2(\3, i1)~g s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* \3, i8 \4, i8 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* \3, i8 \4, i16 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* \3, i8 \4, i32 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* \3, i8 \4, i64 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* \3, i8 \4, i128 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* align \6 \3, i8 \4, i8 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* align \6 \3, i8 \4, i16 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* align \6 \3, i8 \4, i32 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* align \6 \3, i8 \4, i64 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* align \6 \3, i8 \4, i128 \5, i1 \7)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* \4, i8\5* \6, i8 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* \4, i8\5* \6, i16 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* \4, i8\5* \6, i32 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* \4, i8\5* \6, i64 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* \4, i8\5* \6, i128 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* align \8 \4, i8\5* align \8 \6, i8 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* align \8 \4, i8\5* align \8 \6, i16 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* align \8 \4, i8\5* align \8 \6, i32 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* align \8 \4, i8\5* align \8 \6, i64 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* align \8 \4, i8\5* align \8 \6, i128 \7, i1 \9)~g The remaining changes in the series will: Step 2) Expand the IRBuilder API to allow creation of memcpy/memmove with differing source and dest alignments. Step 3) Update Clang to use the new IRBuilder API. Step 4) Update Polly to use the new IRBuilder API. Step 5) Update LLVM passes that create memcpy/memmove calls to use the new IRBuilder API, and those that use use MemIntrinsicInst::[get|set]Alignment() to use getDestAlignment() and getSourceAlignment() instead. Step 6) Remove the single-alignment IRBuilder API for memcpy/memmove, and the MemIntrinsicInst::[get|set]Alignment() methods. Reviewers: pete, hfinkel, lhames, reames, bollu Reviewed By: reames Subscribers: niosHD, reames, jholewinski, qcolombet, jfb, sanjoy, arsenm, dschuff, dylanmckay, mehdi_amini, sdardis, nemanjai, david2050, nhaehnle, javed.absar, sbc100, jgravelle-google, eraman, aheejin, kbarton, JDevlieghere, asb, rbar, johnrusso, simoncook, jordy.potman.lists, apazos, sabuasal, llvm-commits Differential Revision: https://reviews.llvm.org/D41675 llvm-svn: 322965
2018-01-19 18:13:12 +01:00
Value *Ops[] = {Dst, Src, Size, getInt1(isVolatile)};
Type *Tys[] = { Dst->getType(), Src->getType(), Size->getType() };
Module *M = BB->getParent()->getParent();
Function *TheFn = Intrinsic::getDeclaration(M, IntrID, Tys);
CallInst *CI = createCallHelper(TheFn, Ops, this);
Remove alignment argument from memcpy/memmove/memset in favour of alignment attributes (Step 1) Summary: This is a resurrection of work first proposed and discussed in Aug 2015: http://lists.llvm.org/pipermail/llvm-dev/2015-August/089384.html and initially landed (but then backed out) in Nov 2015: http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20151109/312083.html The @llvm.memcpy/memmove/memset intrinsics currently have an explicit argument which is required to be a constant integer. It represents the alignment of the dest (and source), and so must be the minimum of the actual alignment of the two. This change is the first in a series that allows source and dest to each have their own alignments by using the alignment attribute on their arguments. In this change we: 1) Remove the alignment argument. 2) Add alignment attributes to the source & dest arguments. We, temporarily, require that the alignments for source & dest be equal. For example, code which used to read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 100, i32 4, i1 false) will now read call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %dest, i8* align 4 %src, i32 100, i1 false) Downstream users may have to update their lit tests that check for @llvm.memcpy/memmove/memset call/declaration patterns. The following extended sed script may help with updating the majority of your tests, but it does not catch all possible patterns so some manual checking and updating will be required. s~declare void @llvm\.mem(set|cpy|move)\.p([^(]*)\((.*), i32, i1\)~declare void @llvm.mem\1.p\2(\3, i1)~g s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* \3, i8 \4, i8 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* \3, i8 \4, i16 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* \3, i8 \4, i32 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* \3, i8 \4, i64 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* \3, i8 \4, i128 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* align \6 \3, i8 \4, i8 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* align \6 \3, i8 \4, i16 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* align \6 \3, i8 \4, i32 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* align \6 \3, i8 \4, i64 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* align \6 \3, i8 \4, i128 \5, i1 \7)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* \4, i8\5* \6, i8 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* \4, i8\5* \6, i16 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* \4, i8\5* \6, i32 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* \4, i8\5* \6, i64 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* \4, i8\5* \6, i128 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* align \8 \4, i8\5* align \8 \6, i8 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* align \8 \4, i8\5* align \8 \6, i16 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* align \8 \4, i8\5* align \8 \6, i32 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* align \8 \4, i8\5* align \8 \6, i64 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* align \8 \4, i8\5* align \8 \6, i128 \7, i1 \9)~g The remaining changes in the series will: Step 2) Expand the IRBuilder API to allow creation of memcpy/memmove with differing source and dest alignments. Step 3) Update Clang to use the new IRBuilder API. Step 4) Update Polly to use the new IRBuilder API. Step 5) Update LLVM passes that create memcpy/memmove calls to use the new IRBuilder API, and those that use use MemIntrinsicInst::[get|set]Alignment() to use getDestAlignment() and getSourceAlignment() instead. Step 6) Remove the single-alignment IRBuilder API for memcpy/memmove, and the MemIntrinsicInst::[get|set]Alignment() methods. Reviewers: pete, hfinkel, lhames, reames, bollu Reviewed By: reames Subscribers: niosHD, reames, jholewinski, qcolombet, jfb, sanjoy, arsenm, dschuff, dylanmckay, mehdi_amini, sdardis, nemanjai, david2050, nhaehnle, javed.absar, sbc100, jgravelle-google, eraman, aheejin, kbarton, JDevlieghere, asb, rbar, johnrusso, simoncook, jordy.potman.lists, apazos, sabuasal, llvm-commits Differential Revision: https://reviews.llvm.org/D41675 llvm-svn: 322965
2018-01-19 18:13:12 +01:00
auto* MCI = cast<MemTransferInst>(CI);
if (DstAlign)
MCI->setDestAlignment(*DstAlign);
if (SrcAlign)
MCI->setSourceAlignment(*SrcAlign);
Remove alignment argument from memcpy/memmove/memset in favour of alignment attributes (Step 1) Summary: This is a resurrection of work first proposed and discussed in Aug 2015: http://lists.llvm.org/pipermail/llvm-dev/2015-August/089384.html and initially landed (but then backed out) in Nov 2015: http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20151109/312083.html The @llvm.memcpy/memmove/memset intrinsics currently have an explicit argument which is required to be a constant integer. It represents the alignment of the dest (and source), and so must be the minimum of the actual alignment of the two. This change is the first in a series that allows source and dest to each have their own alignments by using the alignment attribute on their arguments. In this change we: 1) Remove the alignment argument. 2) Add alignment attributes to the source & dest arguments. We, temporarily, require that the alignments for source & dest be equal. For example, code which used to read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 100, i32 4, i1 false) will now read call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %dest, i8* align 4 %src, i32 100, i1 false) Downstream users may have to update their lit tests that check for @llvm.memcpy/memmove/memset call/declaration patterns. The following extended sed script may help with updating the majority of your tests, but it does not catch all possible patterns so some manual checking and updating will be required. s~declare void @llvm\.mem(set|cpy|move)\.p([^(]*)\((.*), i32, i1\)~declare void @llvm.mem\1.p\2(\3, i1)~g s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* \3, i8 \4, i8 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* \3, i8 \4, i16 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* \3, i8 \4, i32 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* \3, i8 \4, i64 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* \3, i8 \4, i128 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* align \6 \3, i8 \4, i8 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* align \6 \3, i8 \4, i16 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* align \6 \3, i8 \4, i32 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* align \6 \3, i8 \4, i64 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* align \6 \3, i8 \4, i128 \5, i1 \7)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* \4, i8\5* \6, i8 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* \4, i8\5* \6, i16 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* \4, i8\5* \6, i32 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* \4, i8\5* \6, i64 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* \4, i8\5* \6, i128 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* align \8 \4, i8\5* align \8 \6, i8 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* align \8 \4, i8\5* align \8 \6, i16 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* align \8 \4, i8\5* align \8 \6, i32 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* align \8 \4, i8\5* align \8 \6, i64 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* align \8 \4, i8\5* align \8 \6, i128 \7, i1 \9)~g The remaining changes in the series will: Step 2) Expand the IRBuilder API to allow creation of memcpy/memmove with differing source and dest alignments. Step 3) Update Clang to use the new IRBuilder API. Step 4) Update Polly to use the new IRBuilder API. Step 5) Update LLVM passes that create memcpy/memmove calls to use the new IRBuilder API, and those that use use MemIntrinsicInst::[get|set]Alignment() to use getDestAlignment() and getSourceAlignment() instead. Step 6) Remove the single-alignment IRBuilder API for memcpy/memmove, and the MemIntrinsicInst::[get|set]Alignment() methods. Reviewers: pete, hfinkel, lhames, reames, bollu Reviewed By: reames Subscribers: niosHD, reames, jholewinski, qcolombet, jfb, sanjoy, arsenm, dschuff, dylanmckay, mehdi_amini, sdardis, nemanjai, david2050, nhaehnle, javed.absar, sbc100, jgravelle-google, eraman, aheejin, kbarton, JDevlieghere, asb, rbar, johnrusso, simoncook, jordy.potman.lists, apazos, sabuasal, llvm-commits Differential Revision: https://reviews.llvm.org/D41675 llvm-svn: 322965
2018-01-19 18:13:12 +01:00
// Set the TBAA info if present.
if (TBAATag)
CI->setMetadata(LLVMContext::MD_tbaa, TBAATag);
// Set the TBAA Struct info if present.
if (TBAAStructTag)
CI->setMetadata(LLVMContext::MD_tbaa_struct, TBAAStructTag);
Add scoped-noalias metadata This commit adds scoped noalias metadata. The primary motivations for this feature are: 1. To preserve noalias function attribute information when inlining 2. To provide the ability to model block-scope C99 restrict pointers Neither of these two abilities are added here, only the necessary infrastructure. In fact, there should be no change to existing functionality, only the addition of new features. The logic that converts noalias function parameters into this metadata during inlining will come in a follow-up commit. What is added here is the ability to generally specify noalias memory-access sets. Regarding the metadata, alias-analysis scopes are defined similar to TBAA nodes: !scope0 = metadata !{ metadata !"scope of foo()" } !scope1 = metadata !{ metadata !"scope 1", metadata !scope0 } !scope2 = metadata !{ metadata !"scope 2", metadata !scope0 } !scope3 = metadata !{ metadata !"scope 2.1", metadata !scope2 } !scope4 = metadata !{ metadata !"scope 2.2", metadata !scope2 } Loads and stores can be tagged with an alias-analysis scope, and also, with a noalias tag for a specific scope: ... = load %ptr1, !alias.scope !{ !scope1 } ... = load %ptr2, !alias.scope !{ !scope1, !scope2 }, !noalias !{ !scope1 } When evaluating an aliasing query, if one of the instructions is associated with an alias.scope id that is identical to the noalias scope associated with the other instruction, or is a descendant (in the scope hierarchy) of the noalias scope associated with the other instruction, then the two memory accesses are assumed not to alias. Note that is the first element of the scope metadata is a string, then it can be combined accross functions and translation units. The string can be replaced by a self-reference to create globally unqiue scope identifiers. [Note: This overview is slightly stylized, since the metadata nodes really need to just be numbers (!0 instead of !scope0), and the scope lists are also global unnamed metadata.] Existing noalias metadata in a callee is "cloned" for use by the inlined code. This is necessary because the aliasing scopes are unique to each call site (because of possible control dependencies on the aliasing properties). For example, consider a function: foo(noalias a, noalias b) { *a = *b; } that gets inlined into bar() { ... if (...) foo(a1, b1); ... if (...) foo(a2, b2); } -- now just because we know that a1 does not alias with b1 at the first call site, and a2 does not alias with b2 at the second call site, we cannot let inlining these functons have the metadata imply that a1 does not alias with b2. llvm-svn: 213864
2014-07-24 16:25:39 +02:00
if (ScopeTag)
CI->setMetadata(LLVMContext::MD_alias_scope, ScopeTag);
Add scoped-noalias metadata This commit adds scoped noalias metadata. The primary motivations for this feature are: 1. To preserve noalias function attribute information when inlining 2. To provide the ability to model block-scope C99 restrict pointers Neither of these two abilities are added here, only the necessary infrastructure. In fact, there should be no change to existing functionality, only the addition of new features. The logic that converts noalias function parameters into this metadata during inlining will come in a follow-up commit. What is added here is the ability to generally specify noalias memory-access sets. Regarding the metadata, alias-analysis scopes are defined similar to TBAA nodes: !scope0 = metadata !{ metadata !"scope of foo()" } !scope1 = metadata !{ metadata !"scope 1", metadata !scope0 } !scope2 = metadata !{ metadata !"scope 2", metadata !scope0 } !scope3 = metadata !{ metadata !"scope 2.1", metadata !scope2 } !scope4 = metadata !{ metadata !"scope 2.2", metadata !scope2 } Loads and stores can be tagged with an alias-analysis scope, and also, with a noalias tag for a specific scope: ... = load %ptr1, !alias.scope !{ !scope1 } ... = load %ptr2, !alias.scope !{ !scope1, !scope2 }, !noalias !{ !scope1 } When evaluating an aliasing query, if one of the instructions is associated with an alias.scope id that is identical to the noalias scope associated with the other instruction, or is a descendant (in the scope hierarchy) of the noalias scope associated with the other instruction, then the two memory accesses are assumed not to alias. Note that is the first element of the scope metadata is a string, then it can be combined accross functions and translation units. The string can be replaced by a self-reference to create globally unqiue scope identifiers. [Note: This overview is slightly stylized, since the metadata nodes really need to just be numbers (!0 instead of !scope0), and the scope lists are also global unnamed metadata.] Existing noalias metadata in a callee is "cloned" for use by the inlined code. This is necessary because the aliasing scopes are unique to each call site (because of possible control dependencies on the aliasing properties). For example, consider a function: foo(noalias a, noalias b) { *a = *b; } that gets inlined into bar() { ... if (...) foo(a1, b1); ... if (...) foo(a2, b2); } -- now just because we know that a1 does not alias with b1 at the first call site, and a2 does not alias with b2 at the second call site, we cannot let inlining these functons have the metadata imply that a1 does not alias with b2. llvm-svn: 213864
2014-07-24 16:25:39 +02:00
if (NoAliasTag)
CI->setMetadata(LLVMContext::MD_noalias, NoAliasTag);
Remove alignment argument from memcpy/memmove/memset in favour of alignment attributes (Step 1) Summary: This is a resurrection of work first proposed and discussed in Aug 2015: http://lists.llvm.org/pipermail/llvm-dev/2015-August/089384.html and initially landed (but then backed out) in Nov 2015: http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20151109/312083.html The @llvm.memcpy/memmove/memset intrinsics currently have an explicit argument which is required to be a constant integer. It represents the alignment of the dest (and source), and so must be the minimum of the actual alignment of the two. This change is the first in a series that allows source and dest to each have their own alignments by using the alignment attribute on their arguments. In this change we: 1) Remove the alignment argument. 2) Add alignment attributes to the source & dest arguments. We, temporarily, require that the alignments for source & dest be equal. For example, code which used to read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 100, i32 4, i1 false) will now read call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %dest, i8* align 4 %src, i32 100, i1 false) Downstream users may have to update their lit tests that check for @llvm.memcpy/memmove/memset call/declaration patterns. The following extended sed script may help with updating the majority of your tests, but it does not catch all possible patterns so some manual checking and updating will be required. s~declare void @llvm\.mem(set|cpy|move)\.p([^(]*)\((.*), i32, i1\)~declare void @llvm.mem\1.p\2(\3, i1)~g s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* \3, i8 \4, i8 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* \3, i8 \4, i16 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* \3, i8 \4, i32 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* \3, i8 \4, i64 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* \3, i8 \4, i128 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* align \6 \3, i8 \4, i8 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* align \6 \3, i8 \4, i16 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* align \6 \3, i8 \4, i32 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* align \6 \3, i8 \4, i64 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* align \6 \3, i8 \4, i128 \5, i1 \7)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* \4, i8\5* \6, i8 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* \4, i8\5* \6, i16 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* \4, i8\5* \6, i32 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* \4, i8\5* \6, i64 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* \4, i8\5* \6, i128 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* align \8 \4, i8\5* align \8 \6, i8 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* align \8 \4, i8\5* align \8 \6, i16 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* align \8 \4, i8\5* align \8 \6, i32 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* align \8 \4, i8\5* align \8 \6, i64 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* align \8 \4, i8\5* align \8 \6, i128 \7, i1 \9)~g The remaining changes in the series will: Step 2) Expand the IRBuilder API to allow creation of memcpy/memmove with differing source and dest alignments. Step 3) Update Clang to use the new IRBuilder API. Step 4) Update Polly to use the new IRBuilder API. Step 5) Update LLVM passes that create memcpy/memmove calls to use the new IRBuilder API, and those that use use MemIntrinsicInst::[get|set]Alignment() to use getDestAlignment() and getSourceAlignment() instead. Step 6) Remove the single-alignment IRBuilder API for memcpy/memmove, and the MemIntrinsicInst::[get|set]Alignment() methods. Reviewers: pete, hfinkel, lhames, reames, bollu Reviewed By: reames Subscribers: niosHD, reames, jholewinski, qcolombet, jfb, sanjoy, arsenm, dschuff, dylanmckay, mehdi_amini, sdardis, nemanjai, david2050, nhaehnle, javed.absar, sbc100, jgravelle-google, eraman, aheejin, kbarton, JDevlieghere, asb, rbar, johnrusso, simoncook, jordy.potman.lists, apazos, sabuasal, llvm-commits Differential Revision: https://reviews.llvm.org/D41675 llvm-svn: 322965
2018-01-19 18:13:12 +01:00
return CI;
}
CallInst *IRBuilderBase::CreateMemCpyInline(Value *Dst, MaybeAlign DstAlign,
Value *Src, MaybeAlign SrcAlign,
Value *Size) {
Dst = getCastedInt8PtrValue(Dst);
Src = getCastedInt8PtrValue(Src);
Value *IsVolatile = getInt1(false);
Value *Ops[] = {Dst, Src, Size, IsVolatile};
Type *Tys[] = {Dst->getType(), Src->getType(), Size->getType()};
Function *F = BB->getParent();
Module *M = F->getParent();
Function *TheFn = Intrinsic::getDeclaration(M, Intrinsic::memcpy_inline, Tys);
CallInst *CI = createCallHelper(TheFn, Ops, this);
auto *MCI = cast<MemCpyInlineInst>(CI);
if (DstAlign)
MCI->setDestAlignment(*DstAlign);
if (SrcAlign)
MCI->setSourceAlignment(*SrcAlign);
return CI;
}
CallInst *IRBuilderBase::CreateElementUnorderedAtomicMemCpy(
Value *Dst, Align DstAlign, Value *Src, Align SrcAlign, Value *Size,
uint32_t ElementSize, MDNode *TBAATag, MDNode *TBAAStructTag,
MDNode *ScopeTag, MDNode *NoAliasTag) {
assert(DstAlign >= ElementSize &&
"Pointer alignment must be at least element size");
assert(SrcAlign >= ElementSize &&
"Pointer alignment must be at least element size");
Dst = getCastedInt8PtrValue(Dst);
Src = getCastedInt8PtrValue(Src);
Value *Ops[] = {Dst, Src, Size, getInt32(ElementSize)};
Type *Tys[] = {Dst->getType(), Src->getType(), Size->getType()};
Module *M = BB->getParent()->getParent();
Function *TheFn = Intrinsic::getDeclaration(
M, Intrinsic::memcpy_element_unordered_atomic, Tys);
CallInst *CI = createCallHelper(TheFn, Ops, this);
// Set the alignment of the pointer args.
Remove alignment argument from memcpy/memmove/memset in favour of alignment attributes (Step 1) Summary: This is a resurrection of work first proposed and discussed in Aug 2015: http://lists.llvm.org/pipermail/llvm-dev/2015-August/089384.html and initially landed (but then backed out) in Nov 2015: http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20151109/312083.html The @llvm.memcpy/memmove/memset intrinsics currently have an explicit argument which is required to be a constant integer. It represents the alignment of the dest (and source), and so must be the minimum of the actual alignment of the two. This change is the first in a series that allows source and dest to each have their own alignments by using the alignment attribute on their arguments. In this change we: 1) Remove the alignment argument. 2) Add alignment attributes to the source & dest arguments. We, temporarily, require that the alignments for source & dest be equal. For example, code which used to read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 100, i32 4, i1 false) will now read call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %dest, i8* align 4 %src, i32 100, i1 false) Downstream users may have to update their lit tests that check for @llvm.memcpy/memmove/memset call/declaration patterns. The following extended sed script may help with updating the majority of your tests, but it does not catch all possible patterns so some manual checking and updating will be required. s~declare void @llvm\.mem(set|cpy|move)\.p([^(]*)\((.*), i32, i1\)~declare void @llvm.mem\1.p\2(\3, i1)~g s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* \3, i8 \4, i8 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* \3, i8 \4, i16 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* \3, i8 \4, i32 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* \3, i8 \4, i64 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* \3, i8 \4, i128 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* align \6 \3, i8 \4, i8 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* align \6 \3, i8 \4, i16 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* align \6 \3, i8 \4, i32 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* align \6 \3, i8 \4, i64 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* align \6 \3, i8 \4, i128 \5, i1 \7)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* \4, i8\5* \6, i8 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* \4, i8\5* \6, i16 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* \4, i8\5* \6, i32 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* \4, i8\5* \6, i64 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* \4, i8\5* \6, i128 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* align \8 \4, i8\5* align \8 \6, i8 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* align \8 \4, i8\5* align \8 \6, i16 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* align \8 \4, i8\5* align \8 \6, i32 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* align \8 \4, i8\5* align \8 \6, i64 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* align \8 \4, i8\5* align \8 \6, i128 \7, i1 \9)~g The remaining changes in the series will: Step 2) Expand the IRBuilder API to allow creation of memcpy/memmove with differing source and dest alignments. Step 3) Update Clang to use the new IRBuilder API. Step 4) Update Polly to use the new IRBuilder API. Step 5) Update LLVM passes that create memcpy/memmove calls to use the new IRBuilder API, and those that use use MemIntrinsicInst::[get|set]Alignment() to use getDestAlignment() and getSourceAlignment() instead. Step 6) Remove the single-alignment IRBuilder API for memcpy/memmove, and the MemIntrinsicInst::[get|set]Alignment() methods. Reviewers: pete, hfinkel, lhames, reames, bollu Reviewed By: reames Subscribers: niosHD, reames, jholewinski, qcolombet, jfb, sanjoy, arsenm, dschuff, dylanmckay, mehdi_amini, sdardis, nemanjai, david2050, nhaehnle, javed.absar, sbc100, jgravelle-google, eraman, aheejin, kbarton, JDevlieghere, asb, rbar, johnrusso, simoncook, jordy.potman.lists, apazos, sabuasal, llvm-commits Differential Revision: https://reviews.llvm.org/D41675 llvm-svn: 322965
2018-01-19 18:13:12 +01:00
auto *AMCI = cast<AtomicMemCpyInst>(CI);
AMCI->setDestAlignment(DstAlign);
AMCI->setSourceAlignment(SrcAlign);
// Set the TBAA info if present.
if (TBAATag)
CI->setMetadata(LLVMContext::MD_tbaa, TBAATag);
// Set the TBAA Struct info if present.
if (TBAAStructTag)
CI->setMetadata(LLVMContext::MD_tbaa_struct, TBAAStructTag);
if (ScopeTag)
CI->setMetadata(LLVMContext::MD_alias_scope, ScopeTag);
if (NoAliasTag)
CI->setMetadata(LLVMContext::MD_noalias, NoAliasTag);
return CI;
}
CallInst *IRBuilderBase::CreateMemMove(Value *Dst, MaybeAlign DstAlign,
Value *Src, MaybeAlign SrcAlign,
Value *Size, bool isVolatile,
MDNode *TBAATag, MDNode *ScopeTag,
MDNode *NoAliasTag) {
Dst = getCastedInt8PtrValue(Dst);
Src = getCastedInt8PtrValue(Src);
Remove alignment argument from memcpy/memmove/memset in favour of alignment attributes (Step 1) Summary: This is a resurrection of work first proposed and discussed in Aug 2015: http://lists.llvm.org/pipermail/llvm-dev/2015-August/089384.html and initially landed (but then backed out) in Nov 2015: http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20151109/312083.html The @llvm.memcpy/memmove/memset intrinsics currently have an explicit argument which is required to be a constant integer. It represents the alignment of the dest (and source), and so must be the minimum of the actual alignment of the two. This change is the first in a series that allows source and dest to each have their own alignments by using the alignment attribute on their arguments. In this change we: 1) Remove the alignment argument. 2) Add alignment attributes to the source & dest arguments. We, temporarily, require that the alignments for source & dest be equal. For example, code which used to read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 100, i32 4, i1 false) will now read call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %dest, i8* align 4 %src, i32 100, i1 false) Downstream users may have to update their lit tests that check for @llvm.memcpy/memmove/memset call/declaration patterns. The following extended sed script may help with updating the majority of your tests, but it does not catch all possible patterns so some manual checking and updating will be required. s~declare void @llvm\.mem(set|cpy|move)\.p([^(]*)\((.*), i32, i1\)~declare void @llvm.mem\1.p\2(\3, i1)~g s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* \3, i8 \4, i8 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* \3, i8 \4, i16 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* \3, i8 \4, i32 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* \3, i8 \4, i64 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* \3, i8 \4, i128 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* align \6 \3, i8 \4, i8 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* align \6 \3, i8 \4, i16 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* align \6 \3, i8 \4, i32 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* align \6 \3, i8 \4, i64 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* align \6 \3, i8 \4, i128 \5, i1 \7)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* \4, i8\5* \6, i8 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* \4, i8\5* \6, i16 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* \4, i8\5* \6, i32 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* \4, i8\5* \6, i64 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* \4, i8\5* \6, i128 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* align \8 \4, i8\5* align \8 \6, i8 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* align \8 \4, i8\5* align \8 \6, i16 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* align \8 \4, i8\5* align \8 \6, i32 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* align \8 \4, i8\5* align \8 \6, i64 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* align \8 \4, i8\5* align \8 \6, i128 \7, i1 \9)~g The remaining changes in the series will: Step 2) Expand the IRBuilder API to allow creation of memcpy/memmove with differing source and dest alignments. Step 3) Update Clang to use the new IRBuilder API. Step 4) Update Polly to use the new IRBuilder API. Step 5) Update LLVM passes that create memcpy/memmove calls to use the new IRBuilder API, and those that use use MemIntrinsicInst::[get|set]Alignment() to use getDestAlignment() and getSourceAlignment() instead. Step 6) Remove the single-alignment IRBuilder API for memcpy/memmove, and the MemIntrinsicInst::[get|set]Alignment() methods. Reviewers: pete, hfinkel, lhames, reames, bollu Reviewed By: reames Subscribers: niosHD, reames, jholewinski, qcolombet, jfb, sanjoy, arsenm, dschuff, dylanmckay, mehdi_amini, sdardis, nemanjai, david2050, nhaehnle, javed.absar, sbc100, jgravelle-google, eraman, aheejin, kbarton, JDevlieghere, asb, rbar, johnrusso, simoncook, jordy.potman.lists, apazos, sabuasal, llvm-commits Differential Revision: https://reviews.llvm.org/D41675 llvm-svn: 322965
2018-01-19 18:13:12 +01:00
Value *Ops[] = {Dst, Src, Size, getInt1(isVolatile)};
Type *Tys[] = { Dst->getType(), Src->getType(), Size->getType() };
Module *M = BB->getParent()->getParent();
Function *TheFn = Intrinsic::getDeclaration(M, Intrinsic::memmove, Tys);
CallInst *CI = createCallHelper(TheFn, Ops, this);
Remove alignment argument from memcpy/memmove/memset in favour of alignment attributes (Step 1) Summary: This is a resurrection of work first proposed and discussed in Aug 2015: http://lists.llvm.org/pipermail/llvm-dev/2015-August/089384.html and initially landed (but then backed out) in Nov 2015: http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20151109/312083.html The @llvm.memcpy/memmove/memset intrinsics currently have an explicit argument which is required to be a constant integer. It represents the alignment of the dest (and source), and so must be the minimum of the actual alignment of the two. This change is the first in a series that allows source and dest to each have their own alignments by using the alignment attribute on their arguments. In this change we: 1) Remove the alignment argument. 2) Add alignment attributes to the source & dest arguments. We, temporarily, require that the alignments for source & dest be equal. For example, code which used to read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 100, i32 4, i1 false) will now read call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %dest, i8* align 4 %src, i32 100, i1 false) Downstream users may have to update their lit tests that check for @llvm.memcpy/memmove/memset call/declaration patterns. The following extended sed script may help with updating the majority of your tests, but it does not catch all possible patterns so some manual checking and updating will be required. s~declare void @llvm\.mem(set|cpy|move)\.p([^(]*)\((.*), i32, i1\)~declare void @llvm.mem\1.p\2(\3, i1)~g s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* \3, i8 \4, i8 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* \3, i8 \4, i16 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* \3, i8 \4, i32 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* \3, i8 \4, i64 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* \3, i8 \4, i128 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* align \6 \3, i8 \4, i8 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* align \6 \3, i8 \4, i16 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* align \6 \3, i8 \4, i32 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* align \6 \3, i8 \4, i64 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* align \6 \3, i8 \4, i128 \5, i1 \7)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* \4, i8\5* \6, i8 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* \4, i8\5* \6, i16 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* \4, i8\5* \6, i32 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* \4, i8\5* \6, i64 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* \4, i8\5* \6, i128 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* align \8 \4, i8\5* align \8 \6, i8 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* align \8 \4, i8\5* align \8 \6, i16 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* align \8 \4, i8\5* align \8 \6, i32 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* align \8 \4, i8\5* align \8 \6, i64 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* align \8 \4, i8\5* align \8 \6, i128 \7, i1 \9)~g The remaining changes in the series will: Step 2) Expand the IRBuilder API to allow creation of memcpy/memmove with differing source and dest alignments. Step 3) Update Clang to use the new IRBuilder API. Step 4) Update Polly to use the new IRBuilder API. Step 5) Update LLVM passes that create memcpy/memmove calls to use the new IRBuilder API, and those that use use MemIntrinsicInst::[get|set]Alignment() to use getDestAlignment() and getSourceAlignment() instead. Step 6) Remove the single-alignment IRBuilder API for memcpy/memmove, and the MemIntrinsicInst::[get|set]Alignment() methods. Reviewers: pete, hfinkel, lhames, reames, bollu Reviewed By: reames Subscribers: niosHD, reames, jholewinski, qcolombet, jfb, sanjoy, arsenm, dschuff, dylanmckay, mehdi_amini, sdardis, nemanjai, david2050, nhaehnle, javed.absar, sbc100, jgravelle-google, eraman, aheejin, kbarton, JDevlieghere, asb, rbar, johnrusso, simoncook, jordy.potman.lists, apazos, sabuasal, llvm-commits Differential Revision: https://reviews.llvm.org/D41675 llvm-svn: 322965
2018-01-19 18:13:12 +01:00
auto *MMI = cast<MemMoveInst>(CI);
if (DstAlign)
MMI->setDestAlignment(*DstAlign);
if (SrcAlign)
MMI->setSourceAlignment(*SrcAlign);
Remove alignment argument from memcpy/memmove/memset in favour of alignment attributes (Step 1) Summary: This is a resurrection of work first proposed and discussed in Aug 2015: http://lists.llvm.org/pipermail/llvm-dev/2015-August/089384.html and initially landed (but then backed out) in Nov 2015: http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20151109/312083.html The @llvm.memcpy/memmove/memset intrinsics currently have an explicit argument which is required to be a constant integer. It represents the alignment of the dest (and source), and so must be the minimum of the actual alignment of the two. This change is the first in a series that allows source and dest to each have their own alignments by using the alignment attribute on their arguments. In this change we: 1) Remove the alignment argument. 2) Add alignment attributes to the source & dest arguments. We, temporarily, require that the alignments for source & dest be equal. For example, code which used to read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 100, i32 4, i1 false) will now read call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 %dest, i8* align 4 %src, i32 100, i1 false) Downstream users may have to update their lit tests that check for @llvm.memcpy/memmove/memset call/declaration patterns. The following extended sed script may help with updating the majority of your tests, but it does not catch all possible patterns so some manual checking and updating will be required. s~declare void @llvm\.mem(set|cpy|move)\.p([^(]*)\((.*), i32, i1\)~declare void @llvm.mem\1.p\2(\3, i1)~g s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* \3, i8 \4, i8 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* \3, i8 \4, i16 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* \3, i8 \4, i32 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* \3, i8 \4, i64 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* \3, i8 \4, i128 \5, i1 \6)~g s~call void @llvm\.memset\.p([^(]*)i8\(i8([^*]*)\* (.*), i8 (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i8(i8\2* align \6 \3, i8 \4, i8 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i16\(i8([^*]*)\* (.*), i8 (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i16(i8\2* align \6 \3, i8 \4, i16 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i32\(i8([^*]*)\* (.*), i8 (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i32(i8\2* align \6 \3, i8 \4, i32 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i64\(i8([^*]*)\* (.*), i8 (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i64(i8\2* align \6 \3, i8 \4, i64 \5, i1 \7)~g s~call void @llvm\.memset\.p([^(]*)i128\(i8([^*]*)\* (.*), i8 (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.memset.p\1i128(i8\2* align \6 \3, i8 \4, i128 \5, i1 \7)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* \4, i8\5* \6, i8 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* \4, i8\5* \6, i16 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* \4, i8\5* \6, i32 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* \4, i8\5* \6, i64 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 [01], i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* \4, i8\5* \6, i128 \7, i1 \8)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i8\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i8 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i8(i8\3* align \8 \4, i8\5* align \8 \6, i8 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i16\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i16 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i16(i8\3* align \8 \4, i8\5* align \8 \6, i16 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i32\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i32 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i32(i8\3* align \8 \4, i8\5* align \8 \6, i32 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i64\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i64 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i64(i8\3* align \8 \4, i8\5* align \8 \6, i64 \7, i1 \9)~g s~call void @llvm\.mem(cpy|move)\.p([^(]*)i128\(i8([^*]*)\* (.*), i8([^*]*)\* (.*), i128 (.*), i32 ([0-9]*), i1 ([^)]*)\)~call void @llvm.mem\1.p\2i128(i8\3* align \8 \4, i8\5* align \8 \6, i128 \7, i1 \9)~g The remaining changes in the series will: Step 2) Expand the IRBuilder API to allow creation of memcpy/memmove with differing source and dest alignments. Step 3) Update Clang to use the new IRBuilder API. Step 4) Update Polly to use the new IRBuilder API. Step 5) Update LLVM passes that create memcpy/memmove calls to use the new IRBuilder API, and those that use use MemIntrinsicInst::[get|set]Alignment() to use getDestAlignment() and getSourceAlignment() instead. Step 6) Remove the single-alignment IRBuilder API for memcpy/memmove, and the MemIntrinsicInst::[get|set]Alignment() methods. Reviewers: pete, hfinkel, lhames, reames, bollu Reviewed By: reames Subscribers: niosHD, reames, jholewinski, qcolombet, jfb, sanjoy, arsenm, dschuff, dylanmckay, mehdi_amini, sdardis, nemanjai, david2050, nhaehnle, javed.absar, sbc100, jgravelle-google, eraman, aheejin, kbarton, JDevlieghere, asb, rbar, johnrusso, simoncook, jordy.potman.lists, apazos, sabuasal, llvm-commits Differential Revision: https://reviews.llvm.org/D41675 llvm-svn: 322965
2018-01-19 18:13:12 +01:00
// Set the TBAA info if present.
if (TBAATag)
CI->setMetadata(LLVMContext::MD_tbaa, TBAATag);
Add scoped-noalias metadata This commit adds scoped noalias metadata. The primary motivations for this feature are: 1. To preserve noalias function attribute information when inlining 2. To provide the ability to model block-scope C99 restrict pointers Neither of these two abilities are added here, only the necessary infrastructure. In fact, there should be no change to existing functionality, only the addition of new features. The logic that converts noalias function parameters into this metadata during inlining will come in a follow-up commit. What is added here is the ability to generally specify noalias memory-access sets. Regarding the metadata, alias-analysis scopes are defined similar to TBAA nodes: !scope0 = metadata !{ metadata !"scope of foo()" } !scope1 = metadata !{ metadata !"scope 1", metadata !scope0 } !scope2 = metadata !{ metadata !"scope 2", metadata !scope0 } !scope3 = metadata !{ metadata !"scope 2.1", metadata !scope2 } !scope4 = metadata !{ metadata !"scope 2.2", metadata !scope2 } Loads and stores can be tagged with an alias-analysis scope, and also, with a noalias tag for a specific scope: ... = load %ptr1, !alias.scope !{ !scope1 } ... = load %ptr2, !alias.scope !{ !scope1, !scope2 }, !noalias !{ !scope1 } When evaluating an aliasing query, if one of the instructions is associated with an alias.scope id that is identical to the noalias scope associated with the other instruction, or is a descendant (in the scope hierarchy) of the noalias scope associated with the other instruction, then the two memory accesses are assumed not to alias. Note that is the first element of the scope metadata is a string, then it can be combined accross functions and translation units. The string can be replaced by a self-reference to create globally unqiue scope identifiers. [Note: This overview is slightly stylized, since the metadata nodes really need to just be numbers (!0 instead of !scope0), and the scope lists are also global unnamed metadata.] Existing noalias metadata in a callee is "cloned" for use by the inlined code. This is necessary because the aliasing scopes are unique to each call site (because of possible control dependencies on the aliasing properties). For example, consider a function: foo(noalias a, noalias b) { *a = *b; } that gets inlined into bar() { ... if (...) foo(a1, b1); ... if (...) foo(a2, b2); } -- now just because we know that a1 does not alias with b1 at the first call site, and a2 does not alias with b2 at the second call site, we cannot let inlining these functons have the metadata imply that a1 does not alias with b2. llvm-svn: 213864
2014-07-24 16:25:39 +02:00
if (ScopeTag)
CI->setMetadata(LLVMContext::MD_alias_scope, ScopeTag);
Add scoped-noalias metadata This commit adds scoped noalias metadata. The primary motivations for this feature are: 1. To preserve noalias function attribute information when inlining 2. To provide the ability to model block-scope C99 restrict pointers Neither of these two abilities are added here, only the necessary infrastructure. In fact, there should be no change to existing functionality, only the addition of new features. The logic that converts noalias function parameters into this metadata during inlining will come in a follow-up commit. What is added here is the ability to generally specify noalias memory-access sets. Regarding the metadata, alias-analysis scopes are defined similar to TBAA nodes: !scope0 = metadata !{ metadata !"scope of foo()" } !scope1 = metadata !{ metadata !"scope 1", metadata !scope0 } !scope2 = metadata !{ metadata !"scope 2", metadata !scope0 } !scope3 = metadata !{ metadata !"scope 2.1", metadata !scope2 } !scope4 = metadata !{ metadata !"scope 2.2", metadata !scope2 } Loads and stores can be tagged with an alias-analysis scope, and also, with a noalias tag for a specific scope: ... = load %ptr1, !alias.scope !{ !scope1 } ... = load %ptr2, !alias.scope !{ !scope1, !scope2 }, !noalias !{ !scope1 } When evaluating an aliasing query, if one of the instructions is associated with an alias.scope id that is identical to the noalias scope associated with the other instruction, or is a descendant (in the scope hierarchy) of the noalias scope associated with the other instruction, then the two memory accesses are assumed not to alias. Note that is the first element of the scope metadata is a string, then it can be combined accross functions and translation units. The string can be replaced by a self-reference to create globally unqiue scope identifiers. [Note: This overview is slightly stylized, since the metadata nodes really need to just be numbers (!0 instead of !scope0), and the scope lists are also global unnamed metadata.] Existing noalias metadata in a callee is "cloned" for use by the inlined code. This is necessary because the aliasing scopes are unique to each call site (because of possible control dependencies on the aliasing properties). For example, consider a function: foo(noalias a, noalias b) { *a = *b; } that gets inlined into bar() { ... if (...) foo(a1, b1); ... if (...) foo(a2, b2); } -- now just because we know that a1 does not alias with b1 at the first call site, and a2 does not alias with b2 at the second call site, we cannot let inlining these functons have the metadata imply that a1 does not alias with b2. llvm-svn: 213864
2014-07-24 16:25:39 +02:00
if (NoAliasTag)
CI->setMetadata(LLVMContext::MD_noalias, NoAliasTag);
return CI;
}
CallInst *IRBuilderBase::CreateElementUnorderedAtomicMemMove(
Value *Dst, Align DstAlign, Value *Src, Align SrcAlign, Value *Size,
uint32_t ElementSize, MDNode *TBAATag, MDNode *TBAAStructTag,
MDNode *ScopeTag, MDNode *NoAliasTag) {
assert(DstAlign >= ElementSize &&
"Pointer alignment must be at least element size");
assert(SrcAlign >= ElementSize &&
"Pointer alignment must be at least element size");
Dst = getCastedInt8PtrValue(Dst);
Src = getCastedInt8PtrValue(Src);
Value *Ops[] = {Dst, Src, Size, getInt32(ElementSize)};
Type *Tys[] = {Dst->getType(), Src->getType(), Size->getType()};
Module *M = BB->getParent()->getParent();
Function *TheFn = Intrinsic::getDeclaration(
M, Intrinsic::memmove_element_unordered_atomic, Tys);
CallInst *CI = createCallHelper(TheFn, Ops, this);
// Set the alignment of the pointer args.
CI->addParamAttr(0, Attribute::getWithAlignment(CI->getContext(), DstAlign));
CI->addParamAttr(1, Attribute::getWithAlignment(CI->getContext(), SrcAlign));
// Set the TBAA info if present.
if (TBAATag)
CI->setMetadata(LLVMContext::MD_tbaa, TBAATag);
// Set the TBAA Struct info if present.
if (TBAAStructTag)
CI->setMetadata(LLVMContext::MD_tbaa_struct, TBAAStructTag);
if (ScopeTag)
CI->setMetadata(LLVMContext::MD_alias_scope, ScopeTag);
if (NoAliasTag)
CI->setMetadata(LLVMContext::MD_noalias, NoAliasTag);
return CI;
}
static CallInst *getReductionIntrinsic(IRBuilderBase *Builder, Intrinsic::ID ID,
Value *Src) {
Module *M = Builder->GetInsertBlock()->getParent()->getParent();
Value *Ops[] = {Src};
Type *Tys[] = { Src->getType() };
auto Decl = Intrinsic::getDeclaration(M, ID, Tys);
return createCallHelper(Decl, Ops, Builder);
}
CallInst *IRBuilderBase::CreateFAddReduce(Value *Acc, Value *Src) {
Module *M = GetInsertBlock()->getParent()->getParent();
Value *Ops[] = {Acc, Src};
auto Decl = Intrinsic::getDeclaration(M, Intrinsic::vector_reduce_fadd,
{Src->getType()});
return createCallHelper(Decl, Ops, this);
}
CallInst *IRBuilderBase::CreateFMulReduce(Value *Acc, Value *Src) {
Module *M = GetInsertBlock()->getParent()->getParent();
Value *Ops[] = {Acc, Src};
auto Decl = Intrinsic::getDeclaration(M, Intrinsic::vector_reduce_fmul,
{Src->getType()});
return createCallHelper(Decl, Ops, this);
}
CallInst *IRBuilderBase::CreateAddReduce(Value *Src) {
return getReductionIntrinsic(this, Intrinsic::vector_reduce_add, Src);
}
CallInst *IRBuilderBase::CreateMulReduce(Value *Src) {
return getReductionIntrinsic(this, Intrinsic::vector_reduce_mul, Src);
}
CallInst *IRBuilderBase::CreateAndReduce(Value *Src) {
return getReductionIntrinsic(this, Intrinsic::vector_reduce_and, Src);
}
CallInst *IRBuilderBase::CreateOrReduce(Value *Src) {
return getReductionIntrinsic(this, Intrinsic::vector_reduce_or, Src);
}
CallInst *IRBuilderBase::CreateXorReduce(Value *Src) {
return getReductionIntrinsic(this, Intrinsic::vector_reduce_xor, Src);
}
CallInst *IRBuilderBase::CreateIntMaxReduce(Value *Src, bool IsSigned) {
auto ID =
IsSigned ? Intrinsic::vector_reduce_smax : Intrinsic::vector_reduce_umax;
return getReductionIntrinsic(this, ID, Src);
}
CallInst *IRBuilderBase::CreateIntMinReduce(Value *Src, bool IsSigned) {
auto ID =
IsSigned ? Intrinsic::vector_reduce_smin : Intrinsic::vector_reduce_umin;
return getReductionIntrinsic(this, ID, Src);
}
CallInst *IRBuilderBase::CreateFPMaxReduce(Value *Src) {
return getReductionIntrinsic(this, Intrinsic::vector_reduce_fmax, Src);
}
CallInst *IRBuilderBase::CreateFPMinReduce(Value *Src) {
return getReductionIntrinsic(this, Intrinsic::vector_reduce_fmin, Src);
}
CallInst *IRBuilderBase::CreateLifetimeStart(Value *Ptr, ConstantInt *Size) {
assert(isa<PointerType>(Ptr->getType()) &&
2012-07-19 02:11:40 +02:00
"lifetime.start only applies to pointers.");
Ptr = getCastedInt8PtrValue(Ptr);
if (!Size)
Size = getInt64(-1);
else
assert(Size->getType() == getInt64Ty() &&
2012-07-19 02:11:40 +02:00
"lifetime.start requires the size to be an i64");
Value *Ops[] = { Size, Ptr };
Module *M = BB->getParent()->getParent();
Function *TheFn =
Intrinsic::getDeclaration(M, Intrinsic::lifetime_start, {Ptr->getType()});
return createCallHelper(TheFn, Ops, this);
}
CallInst *IRBuilderBase::CreateLifetimeEnd(Value *Ptr, ConstantInt *Size) {
assert(isa<PointerType>(Ptr->getType()) &&
2012-07-19 02:11:40 +02:00
"lifetime.end only applies to pointers.");
Ptr = getCastedInt8PtrValue(Ptr);
if (!Size)
Size = getInt64(-1);
else
assert(Size->getType() == getInt64Ty() &&
2012-07-19 02:11:40 +02:00
"lifetime.end requires the size to be an i64");
Value *Ops[] = { Size, Ptr };
Module *M = BB->getParent()->getParent();
Function *TheFn =
Intrinsic::getDeclaration(M, Intrinsic::lifetime_end, {Ptr->getType()});
return createCallHelper(TheFn, Ops, this);
}
CallInst *IRBuilderBase::CreateInvariantStart(Value *Ptr, ConstantInt *Size) {
assert(isa<PointerType>(Ptr->getType()) &&
"invariant.start only applies to pointers.");
Ptr = getCastedInt8PtrValue(Ptr);
if (!Size)
Size = getInt64(-1);
else
assert(Size->getType() == getInt64Ty() &&
"invariant.start requires the size to be an i64");
Value *Ops[] = {Size, Ptr};
// Fill in the single overloaded type: memory object type.
Type *ObjectPtr[1] = {Ptr->getType()};
Module *M = BB->getParent()->getParent();
Function *TheFn =
Intrinsic::getDeclaration(M, Intrinsic::invariant_start, ObjectPtr);
return createCallHelper(TheFn, Ops, this);
}
CallInst *
IRBuilderBase::CreateAssumption(Value *Cond,
ArrayRef<OperandBundleDef> OpBundles) {
assert(Cond->getType() == getInt1Ty() &&
"an assumption condition must be of type i1");
Value *Ops[] = { Cond };
Module *M = BB->getParent()->getParent();
Function *FnAssume = Intrinsic::getDeclaration(M, Intrinsic::assume);
return createCallHelper(FnAssume, Ops, this, "", nullptr, OpBundles);
}
Instruction *IRBuilderBase::CreateNoAliasScopeDeclaration(Value *Scope) {
Module *M = BB->getModule();
auto *FnIntrinsic = Intrinsic::getDeclaration(
M, Intrinsic::experimental_noalias_scope_decl, {});
return createCallHelper(FnIntrinsic, {Scope}, this);
}
/// Create a call to a Masked Load intrinsic.
/// \p Ptr - base pointer for the load
/// \p Alignment - alignment of the source location
/// \p Mask - vector of booleans which indicates what vector lanes should
/// be accessed in memory
/// \p PassThru - pass-through value that is used to fill the masked-off lanes
/// of the result
/// \p Name - name of the result variable
CallInst *IRBuilderBase::CreateMaskedLoad(Value *Ptr, Align Alignment,
Value *Mask, Value *PassThru,
const Twine &Name) {
auto *PtrTy = cast<PointerType>(Ptr->getType());
Type *DataTy = PtrTy->getElementType();
assert(DataTy->isVectorTy() && "Ptr should point to a vector");
assert(Mask && "Mask should not be all-ones (null)");
if (!PassThru)
PassThru = UndefValue::get(DataTy);
Type *OverloadedTypes[] = { DataTy, PtrTy };
Value *Ops[] = {Ptr, getInt32(Alignment.value()), Mask, PassThru};
return CreateMaskedIntrinsic(Intrinsic::masked_load, Ops,
OverloadedTypes, Name);
}
/// Create a call to a Masked Store intrinsic.
/// \p Val - data to be stored,
/// \p Ptr - base pointer for the store
/// \p Alignment - alignment of the destination location
/// \p Mask - vector of booleans which indicates what vector lanes should
/// be accessed in memory
CallInst *IRBuilderBase::CreateMaskedStore(Value *Val, Value *Ptr,
Align Alignment, Value *Mask) {
auto *PtrTy = cast<PointerType>(Ptr->getType());
Type *DataTy = PtrTy->getElementType();
assert(DataTy->isVectorTy() && "Ptr should point to a vector");
assert(Mask && "Mask should not be all-ones (null)");
Type *OverloadedTypes[] = { DataTy, PtrTy };
Value *Ops[] = {Val, Ptr, getInt32(Alignment.value()), Mask};
return CreateMaskedIntrinsic(Intrinsic::masked_store, Ops, OverloadedTypes);
}
/// Create a call to a Masked intrinsic, with given intrinsic Id,
/// an array of operands - Ops, and an array of overloaded types -
/// OverloadedTypes.
CallInst *IRBuilderBase::CreateMaskedIntrinsic(Intrinsic::ID Id,
ArrayRef<Value *> Ops,
ArrayRef<Type *> OverloadedTypes,
const Twine &Name) {
Module *M = BB->getParent()->getParent();
Function *TheFn = Intrinsic::getDeclaration(M, Id, OverloadedTypes);
return createCallHelper(TheFn, Ops, this, Name);
}
/// Create a call to a Masked Gather intrinsic.
/// \p Ptrs - vector of pointers for loading
/// \p Align - alignment for one element
/// \p Mask - vector of booleans which indicates what vector lanes should
/// be accessed in memory
/// \p PassThru - pass-through value that is used to fill the masked-off lanes
/// of the result
/// \p Name - name of the result variable
CallInst *IRBuilderBase::CreateMaskedGather(Value *Ptrs, Align Alignment,
Value *Mask, Value *PassThru,
const Twine &Name) {
auto *PtrsTy = cast<VectorType>(Ptrs->getType());
auto *PtrTy = cast<PointerType>(PtrsTy->getElementType());
ElementCount NumElts = PtrsTy->getElementCount();
auto *DataTy = VectorType::get(PtrTy->getElementType(), NumElts);
if (!Mask)
Mask = Constant::getAllOnesValue(
VectorType::get(Type::getInt1Ty(Context), NumElts));
if (!PassThru)
PassThru = UndefValue::get(DataTy);
Type *OverloadedTypes[] = {DataTy, PtrsTy};
Value *Ops[] = {Ptrs, getInt32(Alignment.value()), Mask, PassThru};
// We specify only one type when we create this intrinsic. Types of other
// arguments are derived from this type.
return CreateMaskedIntrinsic(Intrinsic::masked_gather, Ops, OverloadedTypes,
Name);
}
/// Create a call to a Masked Scatter intrinsic.
/// \p Data - data to be stored,
/// \p Ptrs - the vector of pointers, where the \p Data elements should be
/// stored
/// \p Align - alignment for one element
/// \p Mask - vector of booleans which indicates what vector lanes should
/// be accessed in memory
CallInst *IRBuilderBase::CreateMaskedScatter(Value *Data, Value *Ptrs,
Align Alignment, Value *Mask) {
auto *PtrsTy = cast<VectorType>(Ptrs->getType());
auto *DataTy = cast<VectorType>(Data->getType());
ElementCount NumElts = PtrsTy->getElementCount();
#ifndef NDEBUG
auto PtrTy = cast<PointerType>(PtrsTy->getElementType());
assert(NumElts == DataTy->getElementCount() &&
PtrTy->getElementType() == DataTy->getElementType() &&
"Incompatible pointer and data types");
#endif
if (!Mask)
Mask = Constant::getAllOnesValue(
VectorType::get(Type::getInt1Ty(Context), NumElts));
Type *OverloadedTypes[] = {DataTy, PtrsTy};
Value *Ops[] = {Data, Ptrs, getInt32(Alignment.value()), Mask};
// We specify only one type when we create this intrinsic. Types of other
// arguments are derived from this type.
return CreateMaskedIntrinsic(Intrinsic::masked_scatter, Ops, OverloadedTypes);
}
template <typename T0>
static std::vector<Value *>
getStatepointArgs(IRBuilderBase &B, uint64_t ID, uint32_t NumPatchBytes,
Value *ActualCallee, uint32_t Flags, ArrayRef<T0> CallArgs) {
std::vector<Value *> Args;
Args.push_back(B.getInt64(ID));
Args.push_back(B.getInt32(NumPatchBytes));
Args.push_back(ActualCallee);
Args.push_back(B.getInt32(CallArgs.size()));
Args.push_back(B.getInt32(Flags));
2021-01-07 03:27:33 +01:00
llvm::append_range(Args, CallArgs);
// GC Transition and Deopt args are now always handled via operand bundle.
// They will be removed from the signature of gc.statepoint shortly.
Args.push_back(B.getInt32(0));
Args.push_back(B.getInt32(0));
// GC args are now encoded in the gc-live operand bundle
return Args;
}
template<typename T1, typename T2, typename T3>
static std::vector<OperandBundleDef>
getStatepointBundles(Optional<ArrayRef<T1>> TransitionArgs,
Optional<ArrayRef<T2>> DeoptArgs,
ArrayRef<T3> GCArgs) {
std::vector<OperandBundleDef> Rval;
if (DeoptArgs) {
SmallVector<Value*, 16> DeoptValues;
2021-01-07 03:27:33 +01:00
llvm::append_range(DeoptValues, *DeoptArgs);
Rval.emplace_back("deopt", DeoptValues);
}
if (TransitionArgs) {
SmallVector<Value*, 16> TransitionValues;
2021-01-07 03:27:33 +01:00
llvm::append_range(TransitionValues, *TransitionArgs);
Rval.emplace_back("gc-transition", TransitionValues);
}
if (GCArgs.size()) {
SmallVector<Value*, 16> LiveValues;
2021-01-07 03:27:33 +01:00
llvm::append_range(LiveValues, GCArgs);
Rval.emplace_back("gc-live", LiveValues);
}
return Rval;
}
template <typename T0, typename T1, typename T2, typename T3>
static CallInst *CreateGCStatepointCallCommon(
IRBuilderBase *Builder, uint64_t ID, uint32_t NumPatchBytes,
Value *ActualCallee, uint32_t Flags, ArrayRef<T0> CallArgs,
Optional<ArrayRef<T1>> TransitionArgs,
Optional<ArrayRef<T2>> DeoptArgs, ArrayRef<T3> GCArgs,
const Twine &Name) {
// Extract out the type of the callee.
auto *FuncPtrType = cast<PointerType>(ActualCallee->getType());
assert(isa<FunctionType>(FuncPtrType->getElementType()) &&
"actual callee must be a callable value");
Module *M = Builder->GetInsertBlock()->getParent()->getParent();
// Fill in the one generic type'd argument (the function is also vararg)
Type *ArgTypes[] = { FuncPtrType };
Function *FnStatepoint =
Intrinsic::getDeclaration(M, Intrinsic::experimental_gc_statepoint,
ArgTypes);
std::vector<Value *> Args =
getStatepointArgs(*Builder, ID, NumPatchBytes, ActualCallee, Flags,
CallArgs);
return Builder->CreateCall(FnStatepoint, Args,
getStatepointBundles(TransitionArgs, DeoptArgs,
GCArgs),
Name);
}
CallInst *IRBuilderBase::CreateGCStatepointCall(
uint64_t ID, uint32_t NumPatchBytes, Value *ActualCallee,
ArrayRef<Value *> CallArgs, Optional<ArrayRef<Value *>> DeoptArgs,
ArrayRef<Value *> GCArgs, const Twine &Name) {
return CreateGCStatepointCallCommon<Value *, Value *, Value *, Value *>(
this, ID, NumPatchBytes, ActualCallee, uint32_t(StatepointFlags::None),
CallArgs, None /* No Transition Args */, DeoptArgs, GCArgs, Name);
}
CallInst *IRBuilderBase::CreateGCStatepointCall(
uint64_t ID, uint32_t NumPatchBytes, Value *ActualCallee, uint32_t Flags,
ArrayRef<Value *> CallArgs, Optional<ArrayRef<Use>> TransitionArgs,
Optional<ArrayRef<Use>> DeoptArgs, ArrayRef<Value *> GCArgs,
const Twine &Name) {
return CreateGCStatepointCallCommon<Value *, Use, Use, Value *>(
this, ID, NumPatchBytes, ActualCallee, Flags, CallArgs, TransitionArgs,
DeoptArgs, GCArgs, Name);
}
CallInst *IRBuilderBase::CreateGCStatepointCall(
uint64_t ID, uint32_t NumPatchBytes, Value *ActualCallee,
ArrayRef<Use> CallArgs, Optional<ArrayRef<Value *>> DeoptArgs,
ArrayRef<Value *> GCArgs, const Twine &Name) {
return CreateGCStatepointCallCommon<Use, Value *, Value *, Value *>(
this, ID, NumPatchBytes, ActualCallee, uint32_t(StatepointFlags::None),
CallArgs, None, DeoptArgs, GCArgs, Name);
}
template <typename T0, typename T1, typename T2, typename T3>
static InvokeInst *CreateGCStatepointInvokeCommon(
IRBuilderBase *Builder, uint64_t ID, uint32_t NumPatchBytes,
Value *ActualInvokee, BasicBlock *NormalDest, BasicBlock *UnwindDest,
uint32_t Flags, ArrayRef<T0> InvokeArgs,
Optional<ArrayRef<T1>> TransitionArgs, Optional<ArrayRef<T2>> DeoptArgs,
ArrayRef<T3> GCArgs, const Twine &Name) {
// Extract out the type of the callee.
auto *FuncPtrType = cast<PointerType>(ActualInvokee->getType());
assert(isa<FunctionType>(FuncPtrType->getElementType()) &&
"actual callee must be a callable value");
Module *M = Builder->GetInsertBlock()->getParent()->getParent();
// Fill in the one generic type'd argument (the function is also vararg)
Function *FnStatepoint = Intrinsic::getDeclaration(
M, Intrinsic::experimental_gc_statepoint, {FuncPtrType});
std::vector<Value *> Args =
getStatepointArgs(*Builder, ID, NumPatchBytes, ActualInvokee, Flags,
InvokeArgs);
return Builder->CreateInvoke(FnStatepoint, NormalDest, UnwindDest, Args,
getStatepointBundles(TransitionArgs, DeoptArgs,
GCArgs),
Name);
}
InvokeInst *IRBuilderBase::CreateGCStatepointInvoke(
uint64_t ID, uint32_t NumPatchBytes, Value *ActualInvokee,
BasicBlock *NormalDest, BasicBlock *UnwindDest,
ArrayRef<Value *> InvokeArgs, Optional<ArrayRef<Value *>> DeoptArgs,
ArrayRef<Value *> GCArgs, const Twine &Name) {
return CreateGCStatepointInvokeCommon<Value *, Value *, Value *, Value *>(
this, ID, NumPatchBytes, ActualInvokee, NormalDest, UnwindDest,
uint32_t(StatepointFlags::None), InvokeArgs, None /* No Transition Args*/,
DeoptArgs, GCArgs, Name);
}
InvokeInst *IRBuilderBase::CreateGCStatepointInvoke(
uint64_t ID, uint32_t NumPatchBytes, Value *ActualInvokee,
BasicBlock *NormalDest, BasicBlock *UnwindDest, uint32_t Flags,
ArrayRef<Value *> InvokeArgs, Optional<ArrayRef<Use>> TransitionArgs,
Optional<ArrayRef<Use>> DeoptArgs, ArrayRef<Value *> GCArgs, const Twine &Name) {
return CreateGCStatepointInvokeCommon<Value *, Use, Use, Value *>(
this, ID, NumPatchBytes, ActualInvokee, NormalDest, UnwindDest, Flags,
InvokeArgs, TransitionArgs, DeoptArgs, GCArgs, Name);
}
InvokeInst *IRBuilderBase::CreateGCStatepointInvoke(
uint64_t ID, uint32_t NumPatchBytes, Value *ActualInvokee,
BasicBlock *NormalDest, BasicBlock *UnwindDest, ArrayRef<Use> InvokeArgs,
Optional<ArrayRef<Value *>> DeoptArgs, ArrayRef<Value *> GCArgs, const Twine &Name) {
return CreateGCStatepointInvokeCommon<Use, Value *, Value *, Value *>(
this, ID, NumPatchBytes, ActualInvokee, NormalDest, UnwindDest,
uint32_t(StatepointFlags::None), InvokeArgs, None, DeoptArgs, GCArgs,
Name);
}
CallInst *IRBuilderBase::CreateGCResult(Instruction *Statepoint,
Type *ResultType,
const Twine &Name) {
Intrinsic::ID ID = Intrinsic::experimental_gc_result;
Module *M = BB->getParent()->getParent();
Type *Types[] = {ResultType};
Function *FnGCResult = Intrinsic::getDeclaration(M, ID, Types);
Value *Args[] = {Statepoint};
return createCallHelper(FnGCResult, Args, this, Name);
}
CallInst *IRBuilderBase::CreateGCRelocate(Instruction *Statepoint,
int BaseOffset,
int DerivedOffset,
Type *ResultType,
const Twine &Name) {
Module *M = BB->getParent()->getParent();
Type *Types[] = {ResultType};
Function *FnGCRelocate =
Intrinsic::getDeclaration(M, Intrinsic::experimental_gc_relocate, Types);
Value *Args[] = {Statepoint,
getInt32(BaseOffset),
getInt32(DerivedOffset)};
return createCallHelper(FnGCRelocate, Args, this, Name);
}
CallInst *IRBuilderBase::CreateUnaryIntrinsic(Intrinsic::ID ID, Value *V,
Instruction *FMFSource,
const Twine &Name) {
Module *M = BB->getModule();
Function *Fn = Intrinsic::getDeclaration(M, ID, {V->getType()});
return createCallHelper(Fn, {V}, this, Name, FMFSource);
}
CallInst *IRBuilderBase::CreateBinaryIntrinsic(Intrinsic::ID ID, Value *LHS,
Value *RHS,
Instruction *FMFSource,
const Twine &Name) {
Module *M = BB->getModule();
Function *Fn = Intrinsic::getDeclaration(M, ID, { LHS->getType() });
return createCallHelper(Fn, {LHS, RHS}, this, Name, FMFSource);
}
CallInst *IRBuilderBase::CreateIntrinsic(Intrinsic::ID ID,
ArrayRef<Type *> Types,
ArrayRef<Value *> Args,
Instruction *FMFSource,
const Twine &Name) {
Module *M = BB->getModule();
Function *Fn = Intrinsic::getDeclaration(M, ID, Types);
return createCallHelper(Fn, Args, this, Name, FMFSource);
}
Reapply "[IRBuilder] Virtualize IRBuilder" Relative to the original commit, this fixes some warnings, and is based on the deletion of the IRBuilder copy constructor in D74693. The automatic copy constructor would no longer be safe. ----- Related llvm-dev thread: http://lists.llvm.org/pipermail/llvm-dev/2020-February/138951.html This patch moves the IRBuilder from templating over the constant folder and inserter towards making both of these virtual. There are a couple of motivations for this: 1. It's not possible to share code between use-sites that use different IRBuilder folders/inserters (short of templating the code and moving it into headers). 2. Methods currently defined on IRBuilderBase (which is not templated) do not use the custom inserter, resulting in subtle bugs (e.g. incorrect InstCombine worklist management). It would be possible to move those into the templated IRBuilder, but... 3. The vast majority of the IRBuilder implementation has to live in the header, because it depends on the template arguments. 4. We have many unnecessary dependencies on IRBuilder.h, because it is not easy to forward-declare. (Significant parts of the backend depend on it via TargetLowering.h, for example.) This patch addresses the issue by making the following changes: * IRBuilderDefaultInserter::InsertHelper becomes virtual. IRBuilderBase accepts a reference to it. * IRBuilderFolder is introduced as a virtual base class. It is implemented by ConstantFolder (default), NoFolder and TargetFolder. IRBuilderBase has a reference to this as well. * All the logic is moved from IRBuilder to IRBuilderBase. This means that methods can in the future replace their IRBuilder<> & uses (or other specific IRBuilder types) with IRBuilderBase & and thus be usable with different IRBuilders. * The IRBuilder class is now a thin wrapper around IRBuilderBase. Essentially it only stores the folder and inserter and takes care of constructing the base builder. What this patch doesn't do, but should be simple followups after this change: * Fixing use of the inserter for creation methods originally defined on IRBuilderBase. * Replacing IRBuilder<> uses in arguments with IRBuilderBase, where useful. * Moving code from the IRBuilder header to the source file. From the user perspective, these changes should be mostly transparent: The only thing that consumers using a custom inserted may need to do is inherit from IRBuilderDefaultInserter publicly and mark their InsertHelper as public. Differential Revision: https://reviews.llvm.org/D73835
2020-02-16 17:10:09 +01:00
CallInst *IRBuilderBase::CreateConstrainedFPBinOp(
Intrinsic::ID ID, Value *L, Value *R, Instruction *FMFSource,
const Twine &Name, MDNode *FPMathTag,
[FPEnv] Use single enum to represent rounding mode Now compiler defines 5 sets of constants to represent rounding mode. These are: 1. `llvm::APFloatBase::roundingMode`. It specifies all 5 rounding modes defined by IEEE-754 and is used in `APFloat` implementation. 2. `clang::LangOptions::FPRoundingModeKind`. It specifies 4 of 5 IEEE-754 rounding modes and a special value for dynamic rounding mode. It is used in clang frontend. 3. `llvm::fp::RoundingMode`. Defines the same values as `clang::LangOptions::FPRoundingModeKind` but in different order. It is used to specify rounding mode in in IR and functions that operate IR. 4. Rounding mode representation used by `FLT_ROUNDS` (C11, 5.2.4.2.2p7). Besides constants for rounding mode it also uses a special value to indicate error. It is convenient to use in intrinsic functions, as it represents platform-independent representation for rounding mode. In this role it is used in some pending patches. 5. Values like `FE_DOWNWARD` and other, which specify rounding mode in library calls `fesetround` and `fegetround`. Often they represent bits of some control register, so they are target-dependent. The same names (not values) and a special name `FE_DYNAMIC` are used in `#pragma STDC FENV_ROUND`. The first 4 sets of constants are target independent and could have the same numerical representation. It would simplify conversion between the representations. Also now `clang::LangOptions::FPRoundingModeKind` and `llvm::fp::RoundingMode` do not contain the value for IEEE-754 rounding direction `roundTiesToAway`, although it is supported natively on some targets. This change defines all the rounding mode type via one `llvm::RoundingMode`, which also contains rounding mode for IEEE rounding direction `roundTiesToAway`. Differential Revision: https://reviews.llvm.org/D77379
2020-03-26 08:51:09 +01:00
Optional<RoundingMode> Rounding,
Optional<fp::ExceptionBehavior> Except) {
Value *RoundingV = getConstrainedFPRounding(Rounding);
Value *ExceptV = getConstrainedFPExcept(Except);
FastMathFlags UseFMF = FMF;
if (FMFSource)
UseFMF = FMFSource->getFastMathFlags();
CallInst *C = CreateIntrinsic(ID, {L->getType()},
{L, R, RoundingV, ExceptV}, nullptr, Name);
setConstrainedFPCallAttr(C);
setFPAttrs(C, FPMathTag, UseFMF);
return C;
}
Value *IRBuilderBase::CreateNAryOp(unsigned Opc, ArrayRef<Value *> Ops,
const Twine &Name, MDNode *FPMathTag) {
if (Instruction::isBinaryOp(Opc)) {
assert(Ops.size() == 2 && "Invalid number of operands!");
return CreateBinOp(static_cast<Instruction::BinaryOps>(Opc),
Ops[0], Ops[1], Name, FPMathTag);
}
if (Instruction::isUnaryOp(Opc)) {
assert(Ops.size() == 1 && "Invalid number of operands!");
return CreateUnOp(static_cast<Instruction::UnaryOps>(Opc),
Ops[0], Name, FPMathTag);
}
llvm_unreachable("Unexpected opcode!");
}
CallInst *IRBuilderBase::CreateConstrainedFPCast(
Intrinsic::ID ID, Value *V, Type *DestTy,
Instruction *FMFSource, const Twine &Name, MDNode *FPMathTag,
[FPEnv] Use single enum to represent rounding mode Now compiler defines 5 sets of constants to represent rounding mode. These are: 1. `llvm::APFloatBase::roundingMode`. It specifies all 5 rounding modes defined by IEEE-754 and is used in `APFloat` implementation. 2. `clang::LangOptions::FPRoundingModeKind`. It specifies 4 of 5 IEEE-754 rounding modes and a special value for dynamic rounding mode. It is used in clang frontend. 3. `llvm::fp::RoundingMode`. Defines the same values as `clang::LangOptions::FPRoundingModeKind` but in different order. It is used to specify rounding mode in in IR and functions that operate IR. 4. Rounding mode representation used by `FLT_ROUNDS` (C11, 5.2.4.2.2p7). Besides constants for rounding mode it also uses a special value to indicate error. It is convenient to use in intrinsic functions, as it represents platform-independent representation for rounding mode. In this role it is used in some pending patches. 5. Values like `FE_DOWNWARD` and other, which specify rounding mode in library calls `fesetround` and `fegetround`. Often they represent bits of some control register, so they are target-dependent. The same names (not values) and a special name `FE_DYNAMIC` are used in `#pragma STDC FENV_ROUND`. The first 4 sets of constants are target independent and could have the same numerical representation. It would simplify conversion between the representations. Also now `clang::LangOptions::FPRoundingModeKind` and `llvm::fp::RoundingMode` do not contain the value for IEEE-754 rounding direction `roundTiesToAway`, although it is supported natively on some targets. This change defines all the rounding mode type via one `llvm::RoundingMode`, which also contains rounding mode for IEEE rounding direction `roundTiesToAway`. Differential Revision: https://reviews.llvm.org/D77379
2020-03-26 08:51:09 +01:00
Optional<RoundingMode> Rounding,
Optional<fp::ExceptionBehavior> Except) {
Value *ExceptV = getConstrainedFPExcept(Except);
FastMathFlags UseFMF = FMF;
if (FMFSource)
UseFMF = FMFSource->getFastMathFlags();
CallInst *C;
bool HasRoundingMD = false;
switch (ID) {
default:
break;
#define INSTRUCTION(NAME, NARG, ROUND_MODE, INTRINSIC) \
case Intrinsic::INTRINSIC: \
HasRoundingMD = ROUND_MODE; \
break;
#include "llvm/IR/ConstrainedOps.def"
}
if (HasRoundingMD) {
Value *RoundingV = getConstrainedFPRounding(Rounding);
C = CreateIntrinsic(ID, {DestTy, V->getType()}, {V, RoundingV, ExceptV},
nullptr, Name);
} else
C = CreateIntrinsic(ID, {DestTy, V->getType()}, {V, ExceptV}, nullptr,
Name);
setConstrainedFPCallAttr(C);
if (isa<FPMathOperator>(C))
setFPAttrs(C, FPMathTag, UseFMF);
return C;
}
Value *IRBuilderBase::CreateFCmpHelper(
CmpInst::Predicate P, Value *LHS, Value *RHS, const Twine &Name,
MDNode *FPMathTag, bool IsSignaling) {
if (IsFPConstrained) {
auto ID = IsSignaling ? Intrinsic::experimental_constrained_fcmps
: Intrinsic::experimental_constrained_fcmp;
return CreateConstrainedFPCmp(ID, P, LHS, RHS, Name);
}
if (auto *LC = dyn_cast<Constant>(LHS))
if (auto *RC = dyn_cast<Constant>(RHS))
return Insert(Folder.CreateFCmp(P, LC, RC), Name);
return Insert(setFPAttrs(new FCmpInst(P, LHS, RHS), FPMathTag, FMF), Name);
}
CallInst *IRBuilderBase::CreateConstrainedFPCmp(
Intrinsic::ID ID, CmpInst::Predicate P, Value *L, Value *R,
const Twine &Name, Optional<fp::ExceptionBehavior> Except) {
Value *PredicateV = getConstrainedFPPredicate(P);
Value *ExceptV = getConstrainedFPExcept(Except);
CallInst *C = CreateIntrinsic(ID, {L->getType()},
{L, R, PredicateV, ExceptV}, nullptr, Name);
setConstrainedFPCallAttr(C);
return C;
}
CallInst *IRBuilderBase::CreateConstrainedFPCall(
Function *Callee, ArrayRef<Value *> Args, const Twine &Name,
[FPEnv] Use single enum to represent rounding mode Now compiler defines 5 sets of constants to represent rounding mode. These are: 1. `llvm::APFloatBase::roundingMode`. It specifies all 5 rounding modes defined by IEEE-754 and is used in `APFloat` implementation. 2. `clang::LangOptions::FPRoundingModeKind`. It specifies 4 of 5 IEEE-754 rounding modes and a special value for dynamic rounding mode. It is used in clang frontend. 3. `llvm::fp::RoundingMode`. Defines the same values as `clang::LangOptions::FPRoundingModeKind` but in different order. It is used to specify rounding mode in in IR and functions that operate IR. 4. Rounding mode representation used by `FLT_ROUNDS` (C11, 5.2.4.2.2p7). Besides constants for rounding mode it also uses a special value to indicate error. It is convenient to use in intrinsic functions, as it represents platform-independent representation for rounding mode. In this role it is used in some pending patches. 5. Values like `FE_DOWNWARD` and other, which specify rounding mode in library calls `fesetround` and `fegetround`. Often they represent bits of some control register, so they are target-dependent. The same names (not values) and a special name `FE_DYNAMIC` are used in `#pragma STDC FENV_ROUND`. The first 4 sets of constants are target independent and could have the same numerical representation. It would simplify conversion between the representations. Also now `clang::LangOptions::FPRoundingModeKind` and `llvm::fp::RoundingMode` do not contain the value for IEEE-754 rounding direction `roundTiesToAway`, although it is supported natively on some targets. This change defines all the rounding mode type via one `llvm::RoundingMode`, which also contains rounding mode for IEEE rounding direction `roundTiesToAway`. Differential Revision: https://reviews.llvm.org/D77379
2020-03-26 08:51:09 +01:00
Optional<RoundingMode> Rounding,
Optional<fp::ExceptionBehavior> Except) {
llvm::SmallVector<Value *, 6> UseArgs;
2021-01-28 08:25:41 +01:00
append_range(UseArgs, Args);
bool HasRoundingMD = false;
switch (Callee->getIntrinsicID()) {
default:
break;
#define INSTRUCTION(NAME, NARG, ROUND_MODE, INTRINSIC) \
case Intrinsic::INTRINSIC: \
HasRoundingMD = ROUND_MODE; \
break;
#include "llvm/IR/ConstrainedOps.def"
}
if (HasRoundingMD)
UseArgs.push_back(getConstrainedFPRounding(Rounding));
UseArgs.push_back(getConstrainedFPExcept(Except));
CallInst *C = CreateCall(Callee, UseArgs, Name);
setConstrainedFPCallAttr(C);
return C;
}
Value *IRBuilderBase::CreateSelect(Value *C, Value *True, Value *False,
const Twine &Name, Instruction *MDFrom) {
if (auto *CC = dyn_cast<Constant>(C))
if (auto *TC = dyn_cast<Constant>(True))
if (auto *FC = dyn_cast<Constant>(False))
return Insert(Folder.CreateSelect(CC, TC, FC), Name);
SelectInst *Sel = SelectInst::Create(C, True, False);
if (MDFrom) {
MDNode *Prof = MDFrom->getMetadata(LLVMContext::MD_prof);
MDNode *Unpred = MDFrom->getMetadata(LLVMContext::MD_unpredictable);
Sel = addBranchMetadata(Sel, Prof, Unpred);
}
if (isa<FPMathOperator>(Sel))
setFPAttrs(Sel, nullptr /* MDNode* */, FMF);
return Insert(Sel, Name);
}
Value *IRBuilderBase::CreatePtrDiff(Value *LHS, Value *RHS,
const Twine &Name) {
assert(LHS->getType() == RHS->getType() &&
"Pointer subtraction operand types must match!");
auto *ArgType = cast<PointerType>(LHS->getType());
Value *LHS_int = CreatePtrToInt(LHS, Type::getInt64Ty(Context));
Value *RHS_int = CreatePtrToInt(RHS, Type::getInt64Ty(Context));
Value *Difference = CreateSub(LHS_int, RHS_int);
return CreateExactSDiv(Difference,
ConstantExpr::getSizeOf(ArgType->getElementType()),
Name);
}
Value *IRBuilderBase::CreateLaunderInvariantGroup(Value *Ptr) {
assert(isa<PointerType>(Ptr->getType()) &&
"launder.invariant.group only applies to pointers.");
// FIXME: we could potentially avoid casts to/from i8*.
auto *PtrType = Ptr->getType();
auto *Int8PtrTy = getInt8PtrTy(PtrType->getPointerAddressSpace());
if (PtrType != Int8PtrTy)
Ptr = CreateBitCast(Ptr, Int8PtrTy);
Module *M = BB->getParent()->getParent();
Function *FnLaunderInvariantGroup = Intrinsic::getDeclaration(
M, Intrinsic::launder_invariant_group, {Int8PtrTy});
assert(FnLaunderInvariantGroup->getReturnType() == Int8PtrTy &&
FnLaunderInvariantGroup->getFunctionType()->getParamType(0) ==
Int8PtrTy &&
"LaunderInvariantGroup should take and return the same type");
CallInst *Fn = CreateCall(FnLaunderInvariantGroup, {Ptr});
if (PtrType != Int8PtrTy)
return CreateBitCast(Fn, PtrType);
return Fn;
}
Value *IRBuilderBase::CreateStripInvariantGroup(Value *Ptr) {
assert(isa<PointerType>(Ptr->getType()) &&
"strip.invariant.group only applies to pointers.");
// FIXME: we could potentially avoid casts to/from i8*.
auto *PtrType = Ptr->getType();
auto *Int8PtrTy = getInt8PtrTy(PtrType->getPointerAddressSpace());
if (PtrType != Int8PtrTy)
Ptr = CreateBitCast(Ptr, Int8PtrTy);
Module *M = BB->getParent()->getParent();
Function *FnStripInvariantGroup = Intrinsic::getDeclaration(
M, Intrinsic::strip_invariant_group, {Int8PtrTy});
assert(FnStripInvariantGroup->getReturnType() == Int8PtrTy &&
FnStripInvariantGroup->getFunctionType()->getParamType(0) ==
Int8PtrTy &&
"StripInvariantGroup should take and return the same type");
CallInst *Fn = CreateCall(FnStripInvariantGroup, {Ptr});
if (PtrType != Int8PtrTy)
return CreateBitCast(Fn, PtrType);
return Fn;
}
Value *IRBuilderBase::CreateVectorReverse(Value *V, const Twine &Name) {
auto *Ty = cast<VectorType>(V->getType());
if (isa<ScalableVectorType>(Ty)) {
Module *M = BB->getParent()->getParent();
Function *F = Intrinsic::getDeclaration(
M, Intrinsic::experimental_vector_reverse, Ty);
return Insert(CallInst::Create(F, V), Name);
}
// Keep the original behaviour for fixed vector
SmallVector<int, 8> ShuffleMask;
int NumElts = Ty->getElementCount().getKnownMinValue();
for (int i = 0; i < NumElts; ++i)
ShuffleMask.push_back(NumElts - i - 1);
return CreateShuffleVector(V, ShuffleMask, Name);
}
Value *IRBuilderBase::CreateVectorSplice(Value *V1, Value *V2, int64_t Imm,
const Twine &Name) {
assert(isa<VectorType>(V1->getType()) && "Unexpected type");
assert(V1->getType() == V2->getType() &&
"Splice expects matching operand types!");
if (auto *VTy = dyn_cast<ScalableVectorType>(V1->getType())) {
Module *M = BB->getParent()->getParent();
Function *F = Intrinsic::getDeclaration(
M, Intrinsic::experimental_vector_splice, VTy);
Value *Ops[] = {V1, V2, getInt32(Imm)};
return Insert(CallInst::Create(F, Ops), Name);
}
unsigned NumElts = cast<FixedVectorType>(V1->getType())->getNumElements();
assert(((-Imm <= NumElts) || (Imm < NumElts)) &&
"Invalid immediate for vector splice!");
// Keep the original behaviour for fixed vector
unsigned Idx = (NumElts + Imm) % NumElts;
SmallVector<int, 8> Mask;
for (unsigned I = 0; I < NumElts; ++I)
Mask.push_back(Idx + I);
return CreateShuffleVector(V1, V2, Mask);
}
Value *IRBuilderBase::CreateVectorSplat(unsigned NumElts, Value *V,
const Twine &Name) {
auto EC = ElementCount::getFixed(NumElts);
return CreateVectorSplat(EC, V, Name);
}
Value *IRBuilderBase::CreateVectorSplat(ElementCount EC, Value *V,
const Twine &Name) {
assert(EC.isNonZero() && "Cannot splat to an empty vector!");
// First insert it into a poison vector so we can shuffle it.
Type *I32Ty = getInt32Ty();
Value *Poison = PoisonValue::get(VectorType::get(V->getType(), EC));
V = CreateInsertElement(Poison, V, ConstantInt::get(I32Ty, 0),
Name + ".splatinsert");
// Shuffle the value across the desired number of elements.
SmallVector<int, 16> Zeros;
Zeros.resize(EC.getKnownMinValue());
return CreateShuffleVector(V, Zeros, Name + ".splat");
}
Value *IRBuilderBase::CreateExtractInteger(
const DataLayout &DL, Value *From, IntegerType *ExtractedTy,
uint64_t Offset, const Twine &Name) {
auto *IntTy = cast<IntegerType>(From->getType());
assert(DL.getTypeStoreSize(ExtractedTy) + Offset <=
DL.getTypeStoreSize(IntTy) &&
"Element extends past full value");
uint64_t ShAmt = 8 * Offset;
Value *V = From;
if (DL.isBigEndian())
ShAmt = 8 * (DL.getTypeStoreSize(IntTy) -
DL.getTypeStoreSize(ExtractedTy) - Offset);
if (ShAmt) {
V = CreateLShr(V, ShAmt, Name + ".shift");
}
assert(ExtractedTy->getBitWidth() <= IntTy->getBitWidth() &&
"Cannot extract to a larger integer!");
if (ExtractedTy != IntTy) {
V = CreateTrunc(V, ExtractedTy, Name + ".trunc");
}
return V;
}
Value *IRBuilderBase::CreatePreserveArrayAccessIndex(
Type *ElTy, Value *Base, unsigned Dimension, unsigned LastIndex,
MDNode *DbgInfo) {
assert(isa<PointerType>(Base->getType()) &&
"Invalid Base ptr type for preserve.array.access.index.");
auto *BaseType = Base->getType();
Value *LastIndexV = getInt32(LastIndex);
Constant *Zero = ConstantInt::get(Type::getInt32Ty(Context), 0);
SmallVector<Value *, 4> IdxList(Dimension, Zero);
IdxList.push_back(LastIndexV);
Type *ResultType =
GetElementPtrInst::getGEPReturnType(ElTy, Base, IdxList);
Module *M = BB->getParent()->getParent();
Function *FnPreserveArrayAccessIndex = Intrinsic::getDeclaration(
M, Intrinsic::preserve_array_access_index, {ResultType, BaseType});
Value *DimV = getInt32(Dimension);
CallInst *Fn =
CreateCall(FnPreserveArrayAccessIndex, {Base, DimV, LastIndexV});
if (DbgInfo)
Fn->setMetadata(LLVMContext::MD_preserve_access_index, DbgInfo);
return Fn;
}
Value *IRBuilderBase::CreatePreserveUnionAccessIndex(
Value *Base, unsigned FieldIndex, MDNode *DbgInfo) {
assert(isa<PointerType>(Base->getType()) &&
"Invalid Base ptr type for preserve.union.access.index.");
auto *BaseType = Base->getType();
Module *M = BB->getParent()->getParent();
Function *FnPreserveUnionAccessIndex = Intrinsic::getDeclaration(
M, Intrinsic::preserve_union_access_index, {BaseType, BaseType});
Value *DIIndex = getInt32(FieldIndex);
CallInst *Fn =
CreateCall(FnPreserveUnionAccessIndex, {Base, DIIndex});
if (DbgInfo)
Fn->setMetadata(LLVMContext::MD_preserve_access_index, DbgInfo);
return Fn;
}
Value *IRBuilderBase::CreatePreserveStructAccessIndex(
Type *ElTy, Value *Base, unsigned Index, unsigned FieldIndex,
MDNode *DbgInfo) {
assert(isa<PointerType>(Base->getType()) &&
"Invalid Base ptr type for preserve.struct.access.index.");
auto *BaseType = Base->getType();
Value *GEPIndex = getInt32(Index);
Constant *Zero = ConstantInt::get(Type::getInt32Ty(Context), 0);
Type *ResultType =
GetElementPtrInst::getGEPReturnType(ElTy, Base, {Zero, GEPIndex});
Module *M = BB->getParent()->getParent();
Function *FnPreserveStructAccessIndex = Intrinsic::getDeclaration(
M, Intrinsic::preserve_struct_access_index, {ResultType, BaseType});
Value *DIIndex = getInt32(FieldIndex);
CallInst *Fn = CreateCall(FnPreserveStructAccessIndex,
{Base, GEPIndex, DIIndex});
if (DbgInfo)
Fn->setMetadata(LLVMContext::MD_preserve_access_index, DbgInfo);
return Fn;
}
CallInst *IRBuilderBase::CreateAlignmentAssumptionHelper(const DataLayout &DL,
Value *PtrValue,
Value *AlignValue,
Value *OffsetValue) {
SmallVector<Value *, 4> Vals({PtrValue, AlignValue});
if (OffsetValue)
Vals.push_back(OffsetValue);
OperandBundleDefT<Value *> AlignOpB("align", Vals);
return CreateAssumption(ConstantInt::getTrue(getContext()), {AlignOpB});
}
CallInst *IRBuilderBase::CreateAlignmentAssumption(const DataLayout &DL,
Value *PtrValue,
unsigned Alignment,
Value *OffsetValue) {
assert(isa<PointerType>(PtrValue->getType()) &&
"trying to create an alignment assumption on a non-pointer?");
assert(Alignment != 0 && "Invalid Alignment");
auto *PtrTy = cast<PointerType>(PtrValue->getType());
Type *IntPtrTy = getIntPtrTy(DL, PtrTy->getAddressSpace());
Value *AlignValue = ConstantInt::get(IntPtrTy, Alignment);
return CreateAlignmentAssumptionHelper(DL, PtrValue, AlignValue, OffsetValue);
}
CallInst *IRBuilderBase::CreateAlignmentAssumption(const DataLayout &DL,
Value *PtrValue,
Value *Alignment,
Value *OffsetValue) {
assert(isa<PointerType>(PtrValue->getType()) &&
"trying to create an alignment assumption on a non-pointer?");
return CreateAlignmentAssumptionHelper(DL, PtrValue, Alignment, OffsetValue);
}
Reapply "[IRBuilder] Virtualize IRBuilder" Relative to the original commit, this fixes some warnings, and is based on the deletion of the IRBuilder copy constructor in D74693. The automatic copy constructor would no longer be safe. ----- Related llvm-dev thread: http://lists.llvm.org/pipermail/llvm-dev/2020-February/138951.html This patch moves the IRBuilder from templating over the constant folder and inserter towards making both of these virtual. There are a couple of motivations for this: 1. It's not possible to share code between use-sites that use different IRBuilder folders/inserters (short of templating the code and moving it into headers). 2. Methods currently defined on IRBuilderBase (which is not templated) do not use the custom inserter, resulting in subtle bugs (e.g. incorrect InstCombine worklist management). It would be possible to move those into the templated IRBuilder, but... 3. The vast majority of the IRBuilder implementation has to live in the header, because it depends on the template arguments. 4. We have many unnecessary dependencies on IRBuilder.h, because it is not easy to forward-declare. (Significant parts of the backend depend on it via TargetLowering.h, for example.) This patch addresses the issue by making the following changes: * IRBuilderDefaultInserter::InsertHelper becomes virtual. IRBuilderBase accepts a reference to it. * IRBuilderFolder is introduced as a virtual base class. It is implemented by ConstantFolder (default), NoFolder and TargetFolder. IRBuilderBase has a reference to this as well. * All the logic is moved from IRBuilder to IRBuilderBase. This means that methods can in the future replace their IRBuilder<> & uses (or other specific IRBuilder types) with IRBuilderBase & and thus be usable with different IRBuilders. * The IRBuilder class is now a thin wrapper around IRBuilderBase. Essentially it only stores the folder and inserter and takes care of constructing the base builder. What this patch doesn't do, but should be simple followups after this change: * Fixing use of the inserter for creation methods originally defined on IRBuilderBase. * Replacing IRBuilder<> uses in arguments with IRBuilderBase, where useful. * Moving code from the IRBuilder header to the source file. From the user perspective, these changes should be mostly transparent: The only thing that consumers using a custom inserted may need to do is inherit from IRBuilderDefaultInserter publicly and mark their InsertHelper as public. Differential Revision: https://reviews.llvm.org/D73835
2020-02-16 17:10:09 +01:00
IRBuilderDefaultInserter::~IRBuilderDefaultInserter() {}
IRBuilderCallbackInserter::~IRBuilderCallbackInserter() {}
IRBuilderFolder::~IRBuilderFolder() {}
void ConstantFolder::anchor() {}
void NoFolder::anchor() {}