llvm-project/llvm/lib/IR/IRBuilder.cpp

417 lines
17 KiB
C++
Raw Normal View History

//===---- IRBuilder.cpp - Builder for LLVM Instrs -------------------------===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// 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/Function.h"
#include "llvm/IR/GlobalVariable.h"
#include "llvm/IR/IRBuilder.h"
Change memcpy/memset/memmove to have dest and source alignments. Note, this was reviewed (and more details are in) http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20151109/312083.html These intrinsics currently have an explicit alignment argument which is required to be a constant integer. It represents the alignment of the source and dest, and so must be the minimum of those. This change allows source and dest to each have their own alignments by using the alignment attribute on their arguments. The alignment argument itself is removed. There are a few places in the code for which the code needs to be checked by an expert as to whether using only src/dest alignment is safe. For those places, they currently take the minimum of src/dest alignments which matches the current behaviour. For example, code which used to read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 500, i32 8, i1 false) will now read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 8 %dest, i8* align 8 %src, i32 500, i1 false) For out of tree owners, I was able to strip alignment from calls using sed by replacing: (call.*llvm\.memset.*)i32\ [0-9]*\,\ i1 false\) with: $1i1 false) and similarly for memmove and memcpy. I then added back in alignment to test cases which needed it. A similar commit will be made to clang which actually has many differences in alignment as now IRBuilder can generate different source/dest alignments on calls. In IRBuilder itself, a new argument was added. Instead of calling: CreateMemCpy(Dst, Src, getInt64(Size), DstAlign, /* isVolatile */ false) you now call CreateMemCpy(Dst, Src, getInt64(Size), DstAlign, SrcAlign, /* isVolatile */ false) There is a temporary class (IntegerAlignment) which takes the source alignment and rejects implicit conversion from bool. This is to prevent isVolatile here from passing its default parameter to the source alignment. Note, changes in future can now be made to codegen. I didn't change anything here, but this change should enable better memcpy code sequences. Reviewed by Hal Finkel. llvm-svn: 253511
2015-11-19 06:17:24 +08:00
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/IR/Intrinsics.h"
#include "llvm/IR/LLVMContext.h"
#include "llvm/IR/Statepoint.h"
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) {
Constant *StrConstant = ConstantDataArray::getString(Context, Str);
Module &M = *BB->getParent()->getParent();
GlobalVariable *GV = new GlobalVariable(M, StrConstant->getType(),
true, GlobalValue::PrivateLinkage,
StrConstant, Name, nullptr,
GlobalVariable::NotThreadLocal,
AddressSpace);
GV->setUnnamedAddr(true);
return GV;
}
Type *IRBuilderBase::getCurrentFunctionReturnType() const {
assert(BB && BB->getParent() && "No current function!");
return BB->getParent()->getReturnType();
}
Value *IRBuilderBase::getCastedInt8PtrValue(Value *Ptr) {
PointerType *PT = cast<PointerType>(Ptr->getType());
if (PT->getElementType()->isIntegerTy(8))
return Ptr;
// Otherwise, we need to insert a bitcast.
PT = getInt8PtrTy(PT->getAddressSpace());
BitCastInst *BCI = new BitCastInst(Ptr, PT, "");
BB->getInstList().insert(InsertPt, BCI);
SetInstDebugLocation(BCI);
return BCI;
}
static CallInst *createCallHelper(Value *Callee, ArrayRef<Value *> Ops,
IRBuilderBase *Builder,
const Twine& Name="") {
CallInst *CI = CallInst::Create(Callee, Ops, Name);
Builder->GetInsertBlock()->getInstList().insert(Builder->GetInsertPoint(),CI);
Builder->SetInstDebugLocation(CI);
return CI;
}
static InvokeInst *createInvokeHelper(Value *Invokee, BasicBlock *NormalDest,
BasicBlock *UnwindDest,
ArrayRef<Value *> Ops,
IRBuilderBase *Builder,
const Twine &Name = "") {
InvokeInst *II =
InvokeInst::Create(Invokee, NormalDest, UnwindDest, Ops, Name);
Builder->GetInsertBlock()->getInstList().insert(Builder->GetInsertPoint(),
II);
Builder->SetInstDebugLocation(II);
return II;
}
CallInst *IRBuilderBase::
Change memcpy/memset/memmove to have dest and source alignments. Note, this was reviewed (and more details are in) http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20151109/312083.html These intrinsics currently have an explicit alignment argument which is required to be a constant integer. It represents the alignment of the source and dest, and so must be the minimum of those. This change allows source and dest to each have their own alignments by using the alignment attribute on their arguments. The alignment argument itself is removed. There are a few places in the code for which the code needs to be checked by an expert as to whether using only src/dest alignment is safe. For those places, they currently take the minimum of src/dest alignments which matches the current behaviour. For example, code which used to read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 500, i32 8, i1 false) will now read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 8 %dest, i8* align 8 %src, i32 500, i1 false) For out of tree owners, I was able to strip alignment from calls using sed by replacing: (call.*llvm\.memset.*)i32\ [0-9]*\,\ i1 false\) with: $1i1 false) and similarly for memmove and memcpy. I then added back in alignment to test cases which needed it. A similar commit will be made to clang which actually has many differences in alignment as now IRBuilder can generate different source/dest alignments on calls. In IRBuilder itself, a new argument was added. Instead of calling: CreateMemCpy(Dst, Src, getInt64(Size), DstAlign, /* isVolatile */ false) you now call CreateMemCpy(Dst, Src, getInt64(Size), DstAlign, SrcAlign, /* isVolatile */ false) There is a temporary class (IntegerAlignment) which takes the source alignment and rejects implicit conversion from bool. This is to prevent isVolatile here from passing its default parameter to the source alignment. Note, changes in future can now be made to codegen. I didn't change anything here, but this change should enable better memcpy code sequences. Reviewed by Hal Finkel. llvm-svn: 253511
2015-11-19 06:17:24 +08:00
CreateMemSet(Value *Ptr, Value *Val, Value *Size, unsigned DstAlign,
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 22:25:39 +08:00
bool isVolatile, MDNode *TBAATag, MDNode *ScopeTag,
MDNode *NoAliasTag) {
Ptr = getCastedInt8PtrValue(Ptr);
Change memcpy/memset/memmove to have dest and source alignments. Note, this was reviewed (and more details are in) http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20151109/312083.html These intrinsics currently have an explicit alignment argument which is required to be a constant integer. It represents the alignment of the source and dest, and so must be the minimum of those. This change allows source and dest to each have their own alignments by using the alignment attribute on their arguments. The alignment argument itself is removed. There are a few places in the code for which the code needs to be checked by an expert as to whether using only src/dest alignment is safe. For those places, they currently take the minimum of src/dest alignments which matches the current behaviour. For example, code which used to read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 500, i32 8, i1 false) will now read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 8 %dest, i8* align 8 %src, i32 500, i1 false) For out of tree owners, I was able to strip alignment from calls using sed by replacing: (call.*llvm\.memset.*)i32\ [0-9]*\,\ i1 false\) with: $1i1 false) and similarly for memmove and memcpy. I then added back in alignment to test cases which needed it. A similar commit will be made to clang which actually has many differences in alignment as now IRBuilder can generate different source/dest alignments on calls. In IRBuilder itself, a new argument was added. Instead of calling: CreateMemCpy(Dst, Src, getInt64(Size), DstAlign, /* isVolatile */ false) you now call CreateMemCpy(Dst, Src, getInt64(Size), DstAlign, SrcAlign, /* isVolatile */ false) There is a temporary class (IntegerAlignment) which takes the source alignment and rejects implicit conversion from bool. This is to prevent isVolatile here from passing its default parameter to the source alignment. Note, changes in future can now be made to codegen. I didn't change anything here, but this change should enable better memcpy code sequences. Reviewed by Hal Finkel. llvm-svn: 253511
2015-11-19 06:17:24 +08:00
Value *Ops[] = { Ptr, Val, Size, getInt1(isVolatile) };
Type *Tys[] = { Ptr->getType(), Size->getType() };
Module *M = BB->getParent()->getParent();
Value *TheFn = Intrinsic::getDeclaration(M, Intrinsic::memset, Tys);
CallInst *CI = createCallHelper(TheFn, Ops, this);
// 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 22:25:39 +08:00
if (ScopeTag)
CI->setMetadata(LLVMContext::MD_alias_scope, ScopeTag);
if (NoAliasTag)
CI->setMetadata(LLVMContext::MD_noalias, NoAliasTag);
Change memcpy/memset/memmove to have dest and source alignments. Note, this was reviewed (and more details are in) http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20151109/312083.html These intrinsics currently have an explicit alignment argument which is required to be a constant integer. It represents the alignment of the source and dest, and so must be the minimum of those. This change allows source and dest to each have their own alignments by using the alignment attribute on their arguments. The alignment argument itself is removed. There are a few places in the code for which the code needs to be checked by an expert as to whether using only src/dest alignment is safe. For those places, they currently take the minimum of src/dest alignments which matches the current behaviour. For example, code which used to read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 500, i32 8, i1 false) will now read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 8 %dest, i8* align 8 %src, i32 500, i1 false) For out of tree owners, I was able to strip alignment from calls using sed by replacing: (call.*llvm\.memset.*)i32\ [0-9]*\,\ i1 false\) with: $1i1 false) and similarly for memmove and memcpy. I then added back in alignment to test cases which needed it. A similar commit will be made to clang which actually has many differences in alignment as now IRBuilder can generate different source/dest alignments on calls. In IRBuilder itself, a new argument was added. Instead of calling: CreateMemCpy(Dst, Src, getInt64(Size), DstAlign, /* isVolatile */ false) you now call CreateMemCpy(Dst, Src, getInt64(Size), DstAlign, SrcAlign, /* isVolatile */ false) There is a temporary class (IntegerAlignment) which takes the source alignment and rejects implicit conversion from bool. This is to prevent isVolatile here from passing its default parameter to the source alignment. Note, changes in future can now be made to codegen. I didn't change anything here, but this change should enable better memcpy code sequences. Reviewed by Hal Finkel. llvm-svn: 253511
2015-11-19 06:17:24 +08:00
cast<MemSetInst>(CI)->setDestAlignment(DstAlign);
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 22:25:39 +08:00
return CI;
}
CallInst *IRBuilderBase::
Change memcpy/memset/memmove to have dest and source alignments. Note, this was reviewed (and more details are in) http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20151109/312083.html These intrinsics currently have an explicit alignment argument which is required to be a constant integer. It represents the alignment of the source and dest, and so must be the minimum of those. This change allows source and dest to each have their own alignments by using the alignment attribute on their arguments. The alignment argument itself is removed. There are a few places in the code for which the code needs to be checked by an expert as to whether using only src/dest alignment is safe. For those places, they currently take the minimum of src/dest alignments which matches the current behaviour. For example, code which used to read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 500, i32 8, i1 false) will now read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 8 %dest, i8* align 8 %src, i32 500, i1 false) For out of tree owners, I was able to strip alignment from calls using sed by replacing: (call.*llvm\.memset.*)i32\ [0-9]*\,\ i1 false\) with: $1i1 false) and similarly for memmove and memcpy. I then added back in alignment to test cases which needed it. A similar commit will be made to clang which actually has many differences in alignment as now IRBuilder can generate different source/dest alignments on calls. In IRBuilder itself, a new argument was added. Instead of calling: CreateMemCpy(Dst, Src, getInt64(Size), DstAlign, /* isVolatile */ false) you now call CreateMemCpy(Dst, Src, getInt64(Size), DstAlign, SrcAlign, /* isVolatile */ false) There is a temporary class (IntegerAlignment) which takes the source alignment and rejects implicit conversion from bool. This is to prevent isVolatile here from passing its default parameter to the source alignment. Note, changes in future can now be made to codegen. I didn't change anything here, but this change should enable better memcpy code sequences. Reviewed by Hal Finkel. llvm-svn: 253511
2015-11-19 06:17:24 +08:00
CreateMemCpy(Value *Dst, Value *Src, Value *Size, unsigned DstAlign,
IntegerAlignment SrcAlign,
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 22:25:39 +08:00
bool isVolatile, MDNode *TBAATag, MDNode *TBAAStructTag,
MDNode *ScopeTag, MDNode *NoAliasTag) {
Dst = getCastedInt8PtrValue(Dst);
Src = getCastedInt8PtrValue(Src);
Change memcpy/memset/memmove to have dest and source alignments. Note, this was reviewed (and more details are in) http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20151109/312083.html These intrinsics currently have an explicit alignment argument which is required to be a constant integer. It represents the alignment of the source and dest, and so must be the minimum of those. This change allows source and dest to each have their own alignments by using the alignment attribute on their arguments. The alignment argument itself is removed. There are a few places in the code for which the code needs to be checked by an expert as to whether using only src/dest alignment is safe. For those places, they currently take the minimum of src/dest alignments which matches the current behaviour. For example, code which used to read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 500, i32 8, i1 false) will now read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 8 %dest, i8* align 8 %src, i32 500, i1 false) For out of tree owners, I was able to strip alignment from calls using sed by replacing: (call.*llvm\.memset.*)i32\ [0-9]*\,\ i1 false\) with: $1i1 false) and similarly for memmove and memcpy. I then added back in alignment to test cases which needed it. A similar commit will be made to clang which actually has many differences in alignment as now IRBuilder can generate different source/dest alignments on calls. In IRBuilder itself, a new argument was added. Instead of calling: CreateMemCpy(Dst, Src, getInt64(Size), DstAlign, /* isVolatile */ false) you now call CreateMemCpy(Dst, Src, getInt64(Size), DstAlign, SrcAlign, /* isVolatile */ false) There is a temporary class (IntegerAlignment) which takes the source alignment and rejects implicit conversion from bool. This is to prevent isVolatile here from passing its default parameter to the source alignment. Note, changes in future can now be made to codegen. I didn't change anything here, but this change should enable better memcpy code sequences. Reviewed by Hal Finkel. llvm-svn: 253511
2015-11-19 06:17:24 +08:00
Value *Ops[] = { Dst, Src, Size, getInt1(isVolatile) };
Type *Tys[] = { Dst->getType(), Src->getType(), Size->getType() };
Module *M = BB->getParent()->getParent();
Value *TheFn = Intrinsic::getDeclaration(M, Intrinsic::memcpy, Tys);
CallInst *CI = createCallHelper(TheFn, Ops, this);
// 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 22:25:39 +08:00
if (ScopeTag)
CI->setMetadata(LLVMContext::MD_alias_scope, ScopeTag);
if (NoAliasTag)
CI->setMetadata(LLVMContext::MD_noalias, NoAliasTag);
Change memcpy/memset/memmove to have dest and source alignments. Note, this was reviewed (and more details are in) http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20151109/312083.html These intrinsics currently have an explicit alignment argument which is required to be a constant integer. It represents the alignment of the source and dest, and so must be the minimum of those. This change allows source and dest to each have their own alignments by using the alignment attribute on their arguments. The alignment argument itself is removed. There are a few places in the code for which the code needs to be checked by an expert as to whether using only src/dest alignment is safe. For those places, they currently take the minimum of src/dest alignments which matches the current behaviour. For example, code which used to read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 500, i32 8, i1 false) will now read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 8 %dest, i8* align 8 %src, i32 500, i1 false) For out of tree owners, I was able to strip alignment from calls using sed by replacing: (call.*llvm\.memset.*)i32\ [0-9]*\,\ i1 false\) with: $1i1 false) and similarly for memmove and memcpy. I then added back in alignment to test cases which needed it. A similar commit will be made to clang which actually has many differences in alignment as now IRBuilder can generate different source/dest alignments on calls. In IRBuilder itself, a new argument was added. Instead of calling: CreateMemCpy(Dst, Src, getInt64(Size), DstAlign, /* isVolatile */ false) you now call CreateMemCpy(Dst, Src, getInt64(Size), DstAlign, SrcAlign, /* isVolatile */ false) There is a temporary class (IntegerAlignment) which takes the source alignment and rejects implicit conversion from bool. This is to prevent isVolatile here from passing its default parameter to the source alignment. Note, changes in future can now be made to codegen. I didn't change anything here, but this change should enable better memcpy code sequences. Reviewed by Hal Finkel. llvm-svn: 253511
2015-11-19 06:17:24 +08:00
auto *MCI = cast<MemCpyInst>(CI);
MCI->setDestAlignment(DstAlign);
MCI->setSrcAlignment(SrcAlign);
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 22:25:39 +08:00
return CI;
}
CallInst *IRBuilderBase::
Change memcpy/memset/memmove to have dest and source alignments. Note, this was reviewed (and more details are in) http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20151109/312083.html These intrinsics currently have an explicit alignment argument which is required to be a constant integer. It represents the alignment of the source and dest, and so must be the minimum of those. This change allows source and dest to each have their own alignments by using the alignment attribute on their arguments. The alignment argument itself is removed. There are a few places in the code for which the code needs to be checked by an expert as to whether using only src/dest alignment is safe. For those places, they currently take the minimum of src/dest alignments which matches the current behaviour. For example, code which used to read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 500, i32 8, i1 false) will now read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 8 %dest, i8* align 8 %src, i32 500, i1 false) For out of tree owners, I was able to strip alignment from calls using sed by replacing: (call.*llvm\.memset.*)i32\ [0-9]*\,\ i1 false\) with: $1i1 false) and similarly for memmove and memcpy. I then added back in alignment to test cases which needed it. A similar commit will be made to clang which actually has many differences in alignment as now IRBuilder can generate different source/dest alignments on calls. In IRBuilder itself, a new argument was added. Instead of calling: CreateMemCpy(Dst, Src, getInt64(Size), DstAlign, /* isVolatile */ false) you now call CreateMemCpy(Dst, Src, getInt64(Size), DstAlign, SrcAlign, /* isVolatile */ false) There is a temporary class (IntegerAlignment) which takes the source alignment and rejects implicit conversion from bool. This is to prevent isVolatile here from passing its default parameter to the source alignment. Note, changes in future can now be made to codegen. I didn't change anything here, but this change should enable better memcpy code sequences. Reviewed by Hal Finkel. llvm-svn: 253511
2015-11-19 06:17:24 +08:00
CreateMemMove(Value *Dst, Value *Src, Value *Size, unsigned DstAlign,
IntegerAlignment SrcAlign,
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 22:25:39 +08:00
bool isVolatile, MDNode *TBAATag, MDNode *ScopeTag,
MDNode *NoAliasTag) {
Dst = getCastedInt8PtrValue(Dst);
Src = getCastedInt8PtrValue(Src);
Change memcpy/memset/memmove to have dest and source alignments. Note, this was reviewed (and more details are in) http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20151109/312083.html These intrinsics currently have an explicit alignment argument which is required to be a constant integer. It represents the alignment of the source and dest, and so must be the minimum of those. This change allows source and dest to each have their own alignments by using the alignment attribute on their arguments. The alignment argument itself is removed. There are a few places in the code for which the code needs to be checked by an expert as to whether using only src/dest alignment is safe. For those places, they currently take the minimum of src/dest alignments which matches the current behaviour. For example, code which used to read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 500, i32 8, i1 false) will now read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 8 %dest, i8* align 8 %src, i32 500, i1 false) For out of tree owners, I was able to strip alignment from calls using sed by replacing: (call.*llvm\.memset.*)i32\ [0-9]*\,\ i1 false\) with: $1i1 false) and similarly for memmove and memcpy. I then added back in alignment to test cases which needed it. A similar commit will be made to clang which actually has many differences in alignment as now IRBuilder can generate different source/dest alignments on calls. In IRBuilder itself, a new argument was added. Instead of calling: CreateMemCpy(Dst, Src, getInt64(Size), DstAlign, /* isVolatile */ false) you now call CreateMemCpy(Dst, Src, getInt64(Size), DstAlign, SrcAlign, /* isVolatile */ false) There is a temporary class (IntegerAlignment) which takes the source alignment and rejects implicit conversion from bool. This is to prevent isVolatile here from passing its default parameter to the source alignment. Note, changes in future can now be made to codegen. I didn't change anything here, but this change should enable better memcpy code sequences. Reviewed by Hal Finkel. llvm-svn: 253511
2015-11-19 06:17:24 +08:00
Value *Ops[] = { Dst, Src, Size, getInt1(isVolatile) };
Type *Tys[] = { Dst->getType(), Src->getType(), Size->getType() };
Module *M = BB->getParent()->getParent();
Value *TheFn = Intrinsic::getDeclaration(M, Intrinsic::memmove, Tys);
CallInst *CI = createCallHelper(TheFn, Ops, this);
// 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 22:25:39 +08:00
if (ScopeTag)
CI->setMetadata(LLVMContext::MD_alias_scope, ScopeTag);
if (NoAliasTag)
CI->setMetadata(LLVMContext::MD_noalias, NoAliasTag);
Change memcpy/memset/memmove to have dest and source alignments. Note, this was reviewed (and more details are in) http://lists.llvm.org/pipermail/llvm-commits/Week-of-Mon-20151109/312083.html These intrinsics currently have an explicit alignment argument which is required to be a constant integer. It represents the alignment of the source and dest, and so must be the minimum of those. This change allows source and dest to each have their own alignments by using the alignment attribute on their arguments. The alignment argument itself is removed. There are a few places in the code for which the code needs to be checked by an expert as to whether using only src/dest alignment is safe. For those places, they currently take the minimum of src/dest alignments which matches the current behaviour. For example, code which used to read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 500, i32 8, i1 false) will now read: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 8 %dest, i8* align 8 %src, i32 500, i1 false) For out of tree owners, I was able to strip alignment from calls using sed by replacing: (call.*llvm\.memset.*)i32\ [0-9]*\,\ i1 false\) with: $1i1 false) and similarly for memmove and memcpy. I then added back in alignment to test cases which needed it. A similar commit will be made to clang which actually has many differences in alignment as now IRBuilder can generate different source/dest alignments on calls. In IRBuilder itself, a new argument was added. Instead of calling: CreateMemCpy(Dst, Src, getInt64(Size), DstAlign, /* isVolatile */ false) you now call CreateMemCpy(Dst, Src, getInt64(Size), DstAlign, SrcAlign, /* isVolatile */ false) There is a temporary class (IntegerAlignment) which takes the source alignment and rejects implicit conversion from bool. This is to prevent isVolatile here from passing its default parameter to the source alignment. Note, changes in future can now be made to codegen. I didn't change anything here, but this change should enable better memcpy code sequences. Reviewed by Hal Finkel. llvm-svn: 253511
2015-11-19 06:17:24 +08:00
auto *MMI = cast<MemMoveInst>(CI);
MMI->setDestAlignment(DstAlign);
MMI->setSrcAlignment(SrcAlign);
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 22:25:39 +08:00
return CI;
}
CallInst *IRBuilderBase::CreateLifetimeStart(Value *Ptr, ConstantInt *Size) {
assert(isa<PointerType>(Ptr->getType()) &&
2012-07-19 08:11:40 +08:00
"lifetime.start only applies to pointers.");
Ptr = getCastedInt8PtrValue(Ptr);
if (!Size)
Size = getInt64(-1);
else
assert(Size->getType() == getInt64Ty() &&
2012-07-19 08:11:40 +08:00
"lifetime.start requires the size to be an i64");
Value *Ops[] = { Size, Ptr };
Module *M = BB->getParent()->getParent();
Value *TheFn = Intrinsic::getDeclaration(M, Intrinsic::lifetime_start);
return createCallHelper(TheFn, Ops, this);
}
CallInst *IRBuilderBase::CreateLifetimeEnd(Value *Ptr, ConstantInt *Size) {
assert(isa<PointerType>(Ptr->getType()) &&
2012-07-19 08:11:40 +08:00
"lifetime.end only applies to pointers.");
Ptr = getCastedInt8PtrValue(Ptr);
if (!Size)
Size = getInt64(-1);
else
assert(Size->getType() == getInt64Ty() &&
2012-07-19 08:11:40 +08:00
"lifetime.end requires the size to be an i64");
Value *Ops[] = { Size, Ptr };
Module *M = BB->getParent()->getParent();
Value *TheFn = Intrinsic::getDeclaration(M, Intrinsic::lifetime_end);
return createCallHelper(TheFn, Ops, this);
}
CallInst *IRBuilderBase::CreateAssumption(Value *Cond) {
assert(Cond->getType() == getInt1Ty() &&
"an assumption condition must be of type i1");
Value *Ops[] = { Cond };
Module *M = BB->getParent()->getParent();
Value *FnAssume = Intrinsic::getDeclaration(M, Intrinsic::assume);
return createCallHelper(FnAssume, Ops, this);
}
/// Create a call to a Masked Load intrinsic.
/// Ptr - the base pointer for the load
/// Align - alignment of the source location
/// Mask - an vector of booleans which indicates what vector lanes should
/// be accessed in memory
/// PassThru - a pass-through value that is used to fill the masked-off lanes
/// of the result
/// Name - name of the result variable
CallInst *IRBuilderBase::CreateMaskedLoad(Value *Ptr, unsigned Align,
Value *Mask, Value *PassThru,
const Twine &Name) {
assert(Ptr->getType()->isPointerTy() && "Ptr must be of pointer type");
// DataTy is the overloaded type
Type *DataTy = cast<PointerType>(Ptr->getType())->getElementType();
assert(DataTy->isVectorTy() && "Ptr should point to a vector");
if (!PassThru)
PassThru = UndefValue::get(DataTy);
Value *Ops[] = { Ptr, getInt32(Align), Mask, PassThru};
return CreateMaskedIntrinsic(Intrinsic::masked_load, Ops, DataTy, Name);
}
/// Create a call to a Masked Store intrinsic.
/// Val - the data to be stored,
/// Ptr - the base pointer for the store
/// Align - alignment of the destination location
/// Mask - an vector of booleans which indicates what vector lanes should
/// be accessed in memory
CallInst *IRBuilderBase::CreateMaskedStore(Value *Val, Value *Ptr,
unsigned Align, Value *Mask) {
Value *Ops[] = { Val, Ptr, getInt32(Align), Mask };
// Type of the data to be stored - the only one overloaded type
return CreateMaskedIntrinsic(Intrinsic::masked_store, Ops, Val->getType());
}
/// Create a call to a Masked intrinsic, with given intrinsic Id,
/// an array of operands - Ops, and one overloaded type - DataTy
CallInst *IRBuilderBase::CreateMaskedIntrinsic(Intrinsic::ID Id,
ArrayRef<Value *> Ops,
Type *DataTy,
const Twine &Name) {
Module *M = BB->getParent()->getParent();
Type *OverloadedTypes[] = { DataTy };
Value *TheFn = Intrinsic::getDeclaration(M, Id, OverloadedTypes);
return createCallHelper(TheFn, Ops, this, Name);
}
template <typename T0, typename T1, typename T2, typename T3>
static std::vector<Value *>
getStatepointArgs(IRBuilderBase &B, uint64_t ID, uint32_t NumPatchBytes,
Value *ActualCallee, uint32_t Flags, ArrayRef<T0> CallArgs,
ArrayRef<T1> TransitionArgs, ArrayRef<T2> DeoptArgs,
ArrayRef<T3> GCArgs) {
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));
Args.insert(Args.end(), CallArgs.begin(), CallArgs.end());
Args.push_back(B.getInt32(TransitionArgs.size()));
Args.insert(Args.end(), TransitionArgs.begin(), TransitionArgs.end());
Args.push_back(B.getInt32(DeoptArgs.size()));
Args.insert(Args.end(), DeoptArgs.begin(), DeoptArgs.end());
Args.insert(Args.end(), GCArgs.begin(), GCArgs.end());
return Args;
}
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,
ArrayRef<T1> TransitionArgs, ArrayRef<T2> DeoptArgs, ArrayRef<T3> GCArgs,
const Twine &Name) {
// Extract out the type of the callee.
PointerType *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<llvm::Value *> Args =
getStatepointArgs(*Builder, ID, NumPatchBytes, ActualCallee, Flags,
CallArgs, TransitionArgs, DeoptArgs, GCArgs);
return createCallHelper(FnStatepoint, Args, Builder, Name);
}
CallInst *IRBuilderBase::CreateGCStatepointCall(
uint64_t ID, uint32_t NumPatchBytes, Value *ActualCallee,
ArrayRef<Value *> CallArgs, 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<Use> CallArgs, ArrayRef<Use> TransitionArgs,
ArrayRef<Use> DeoptArgs, ArrayRef<Value *> GCArgs, const Twine &Name) {
return CreateGCStatepointCallCommon<Use, 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, 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, ArrayRef<T1> TransitionArgs,
ArrayRef<T2> DeoptArgs, ArrayRef<T3> GCArgs, const Twine &Name) {
// Extract out the type of the callee.
PointerType *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<llvm::Value *> Args =
getStatepointArgs(*Builder, ID, NumPatchBytes, ActualInvokee, Flags,
InvokeArgs, TransitionArgs, DeoptArgs, GCArgs);
return createInvokeHelper(FnStatepoint, NormalDest, UnwindDest, Args, Builder,
Name);
}
InvokeInst *IRBuilderBase::CreateGCStatepointInvoke(
uint64_t ID, uint32_t NumPatchBytes, Value *ActualInvokee,
BasicBlock *NormalDest, BasicBlock *UnwindDest,
ArrayRef<Value *> InvokeArgs, 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<Use> InvokeArgs, ArrayRef<Use> TransitionArgs,
ArrayRef<Use> DeoptArgs, ArrayRef<Value *> GCArgs, const Twine &Name) {
return CreateGCStatepointInvokeCommon<Use, 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,
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};
Value *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};
Value *FnGCRelocate =
Intrinsic::getDeclaration(M, Intrinsic::experimental_gc_relocate, Types);
Value *Args[] = {Statepoint,
getInt32(BaseOffset),
getInt32(DerivedOffset)};
return createCallHelper(FnGCRelocate, Args, this, Name);
}