summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
Diffstat
-rw-r--r--llvm/include/llvm/AsmParser/Parser.h16
-rw-r--r--llvm/include/llvm/IRReader/IRReader.h9
-rw-r--r--llvm/lib/AsmParser/LLParser.cpp12
-rw-r--r--llvm/lib/AsmParser/LLParser.h11
-rw-r--r--llvm/lib/AsmParser/Parser.cpp35
-rw-r--r--llvm/lib/CodeGen/MIRParser/MIRParser.cpp2
-rw-r--r--llvm/lib/IRReader/IRReader.cpp13
-rw-r--r--llvm/test/Assembler/datalayout-alloca-addrspace-mismatch-0.ll4
-rw-r--r--llvm/test/Assembler/datalayout-alloca-addrspace-mismatch-1.ll4
-rw-r--r--llvm/test/Assembler/datalayout-alloca-addrspace-mismatch-2.ll4
-rw-r--r--llvm/test/Assembler/drop-debug-info-nonzero-alloca.ll25
-rw-r--r--llvm/test/CodeGen/AMDGPU/alloca.ll12
-rw-r--r--llvm/test/CodeGen/AMDGPU/fence-barrier.ll35
-rw-r--r--llvm/test/CodeGen/AMDGPU/invalid-alloca.ll16
-rw-r--r--llvm/test/CodeGen/AMDGPU/sched-crash-dbg-value.mir26
-rw-r--r--llvm/tools/llc/llc.cpp23
-rw-r--r--llvm/tools/llvm-as/llvm-as.cpp9
-rw-r--r--llvm/tools/opt/opt.cpp12
18 files changed, 179 insertions, 89 deletions
diff --git a/llvm/include/llvm/AsmParser/Parser.h b/llvm/include/llvm/AsmParser/Parser.h
index 5f02e488e5b..4e2210192a0 100644
--- a/llvm/include/llvm/AsmParser/Parser.h
+++ b/llvm/include/llvm/AsmParser/Parser.h
@@ -39,9 +39,11 @@ class Type;
/// \param UpgradeDebugInfo Run UpgradeDebugInfo, which runs the Verifier.
/// This option should only be set to false by llvm-as
/// for use inside the LLVM testuite!
+/// \param DataLayoutString Override datalayout in the llvm assembly.
std::unique_ptr<Module>
parseAssemblyFile(StringRef Filename, SMDiagnostic &Error, LLVMContext &Context,
- SlotMapping *Slots = nullptr, bool UpgradeDebugInfo = true);
+ SlotMapping *Slots = nullptr, bool UpgradeDebugInfo = true,
+ StringRef DataLayoutString = "");
/// The function is a secondary interface to the LLVM Assembly Parser. It parses
/// an ASCII string that (presumably) contains LLVM Assembly code. It returns a
@@ -57,11 +59,13 @@ parseAssemblyFile(StringRef Filename, SMDiagnostic &Error, LLVMContext &Context,
/// \param UpgradeDebugInfo Run UpgradeDebugInfo, which runs the Verifier.
/// This option should only be set to false by llvm-as
/// for use inside the LLVM testuite!
+/// \param DataLayoutString Override datalayout in the llvm assembly.
std::unique_ptr<Module> parseAssemblyString(StringRef AsmString,
SMDiagnostic &Error,
LLVMContext &Context,
SlotMapping *Slots = nullptr,
- bool UpgradeDebugInfo = true);
+ bool UpgradeDebugInfo = true,
+ StringRef DataLayoutString = "");
/// parseAssemblyFile and parseAssemblyString are wrappers around this function.
/// \brief Parse LLVM Assembly from a MemoryBuffer.
@@ -72,10 +76,12 @@ std::unique_ptr<Module> parseAssemblyString(StringRef AsmString,
/// \param UpgradeDebugInfo Run UpgradeDebugInfo, which runs the Verifier.
/// This option should only be set to false by llvm-as
/// for use inside the LLVM testuite!
+/// \param DataLayoutString Override datalayout in the llvm assembly.
std::unique_ptr<Module> parseAssembly(MemoryBufferRef F, SMDiagnostic &Err,
LLVMContext &Context,
SlotMapping *Slots = nullptr,
- bool UpgradeDebugInfo = true);
+ bool UpgradeDebugInfo = true,
+ StringRef DataLayoutString = "");
/// This function is the low-level interface to the LLVM Assembly Parser.
/// This is kept as an independent function instead of being inlined into
@@ -91,9 +97,11 @@ std::unique_ptr<Module> parseAssembly(MemoryBufferRef F, SMDiagnostic &Err,
/// \param UpgradeDebugInfo Run UpgradeDebugInfo, which runs the Verifier.
/// This option should only be set to false by llvm-as
/// for use inside the LLVM testuite!
+/// \param DataLayoutString Override datalayout in the llvm assembly.
bool parseAssemblyInto(MemoryBufferRef F, Module &M, SMDiagnostic &Err,
SlotMapping *Slots = nullptr,
- bool UpgradeDebugInfo = true);
+ bool UpgradeDebugInfo = true,
+ StringRef DataLayoutString = "");
/// Parse a type and a constant value in the given string.
///
diff --git a/llvm/include/llvm/IRReader/IRReader.h b/llvm/include/llvm/IRReader/IRReader.h
index f5621647db0..bedde8954fb 100644
--- a/llvm/include/llvm/IRReader/IRReader.h
+++ b/llvm/include/llvm/IRReader/IRReader.h
@@ -15,6 +15,7 @@
#ifndef LLVM_IRREADER_IRREADER_H
#define LLVM_IRREADER_IRREADER_H
+#include "llvm/ADT/StringRef.h"
#include <memory>
namespace llvm {
@@ -40,9 +41,11 @@ getLazyIRFileModule(StringRef Filename, SMDiagnostic &Err, LLVMContext &Context,
/// \param UpgradeDebugInfo Run UpgradeDebugInfo, which runs the Verifier.
/// This option should only be set to false by llvm-as
/// for use inside the LLVM testuite!
+/// \param DataLayoutString Override datalayout in the llvm assembly.
std::unique_ptr<Module> parseIR(MemoryBufferRef Buffer, SMDiagnostic &Err,
LLVMContext &Context,
- bool UpgradeDebugInfo = true);
+ bool UpgradeDebugInfo = true,
+ StringRef DataLayoutString = "");
/// If the given file holds a bitcode image, return a Module for it.
/// Otherwise, attempt to parse it as LLVM Assembly and return a Module
@@ -50,9 +53,11 @@ std::unique_ptr<Module> parseIR(MemoryBufferRef Buffer, SMDiagnostic &Err,
/// \param UpgradeDebugInfo Run UpgradeDebugInfo, which runs the Verifier.
/// This option should only be set to false by llvm-as
/// for use inside the LLVM testuite!
+/// \param DataLayoutString Override datalayout in the llvm assembly.
std::unique_ptr<Module> parseIRFile(StringRef Filename, SMDiagnostic &Err,
LLVMContext &Context,
- bool UpgradeDebugInfo = true);
+ bool UpgradeDebugInfo = true,
+ StringRef DataLayoutString = "");
}
#endif
diff --git a/llvm/lib/AsmParser/LLParser.cpp b/llvm/lib/AsmParser/LLParser.cpp
index 9bc34f927e8..226e4827968 100644
--- a/llvm/lib/AsmParser/LLParser.cpp
+++ b/llvm/lib/AsmParser/LLParser.cpp
@@ -327,7 +327,8 @@ bool LLParser::ParseTargetDefinition() {
if (ParseToken(lltok::equal, "expected '=' after target datalayout") ||
ParseStringConstant(Str))
return true;
- M->setDataLayout(Str);
+ if (DataLayoutStr.empty())
+ M->setDataLayout(Str);
return false;
}
}
@@ -6261,14 +6262,7 @@ int LLParser::ParseAlloc(Instruction *&Inst, PerFunctionState &PFS) {
if (Size && !Size->getType()->isIntegerTy())
return Error(SizeLoc, "element count must have integer type");
- const DataLayout &DL = M->getDataLayout();
- unsigned AS = DL.getAllocaAddrSpace();
- if (AS != AddrSpace) {
- // TODO: In the future it should be possible to specify addrspace per-alloca.
- return Error(ASLoc, "address space must match datalayout");
- }
-
- AllocaInst *AI = new AllocaInst(Ty, AS, Size, Alignment);
+ AllocaInst *AI = new AllocaInst(Ty, AddrSpace, Size, Alignment);
AI->setUsedWithInAlloca(IsInAlloca);
AI->setSwiftError(IsSwiftError);
Inst = AI;
diff --git a/llvm/lib/AsmParser/LLParser.h b/llvm/lib/AsmParser/LLParser.h
index 94e4c1ae96d..a3252ff5f19 100644
--- a/llvm/lib/AsmParser/LLParser.h
+++ b/llvm/lib/AsmParser/LLParser.h
@@ -143,12 +143,19 @@ namespace llvm {
/// UpgradeDebuginfo so it can generate broken bitcode.
bool UpgradeDebugInfo;
+ /// DataLayout string to override that in LLVM assembly.
+ StringRef DataLayoutStr;
+
public:
LLParser(StringRef F, SourceMgr &SM, SMDiagnostic &Err, Module *M,
- SlotMapping *Slots = nullptr, bool UpgradeDebugInfo = true)
+ SlotMapping *Slots = nullptr, bool UpgradeDebugInfo = true,
+ StringRef DataLayoutString = "")
: Context(M->getContext()), Lex(F, SM, Err, M->getContext()), M(M),
Slots(Slots), BlockAddressPFS(nullptr),
- UpgradeDebugInfo(UpgradeDebugInfo) {}
+ UpgradeDebugInfo(UpgradeDebugInfo), DataLayoutStr(DataLayoutString) {
+ if (!DataLayoutStr.empty())
+ M->setDataLayout(DataLayoutStr);
+ }
bool Run();
bool parseStandaloneConstantValue(Constant *&C, const SlotMapping *Slots);
diff --git a/llvm/lib/AsmParser/Parser.cpp b/llvm/lib/AsmParser/Parser.cpp
index a43ae2b5577..37b97a17a53 100644
--- a/llvm/lib/AsmParser/Parser.cpp
+++ b/llvm/lib/AsmParser/Parser.cpp
@@ -23,31 +23,34 @@
using namespace llvm;
bool llvm::parseAssemblyInto(MemoryBufferRef F, Module &M, SMDiagnostic &Err,
- SlotMapping *Slots, bool UpgradeDebugInfo) {
+ SlotMapping *Slots, bool UpgradeDebugInfo,
+ StringRef DataLayoutString) {
SourceMgr SM;
std::unique_ptr<MemoryBuffer> Buf = MemoryBuffer::getMemBuffer(F);
SM.AddNewSourceBuffer(std::move(Buf), SMLoc());
- return LLParser(F.getBuffer(), SM, Err, &M, Slots, UpgradeDebugInfo).Run();
+ return LLParser(F.getBuffer(), SM, Err, &M, Slots, UpgradeDebugInfo,
+ DataLayoutString)
+ .Run();
}
std::unique_ptr<Module>
llvm::parseAssembly(MemoryBufferRef F, SMDiagnostic &Err, LLVMContext &Context,
- SlotMapping *Slots, bool UpgradeDebugInfo) {
+ SlotMapping *Slots, bool UpgradeDebugInfo,
+ StringRef DataLayoutString) {
std::unique_ptr<Module> M =
make_unique<Module>(F.getBufferIdentifier(), Context);
- if (parseAssemblyInto(F, *M, Err, Slots, UpgradeDebugInfo))
+ if (parseAssemblyInto(F, *M, Err, Slots, UpgradeDebugInfo, DataLayoutString))
return nullptr;
return M;
}
-std::unique_ptr<Module> llvm::parseAssemblyFile(StringRef Filename,
- SMDiagnostic &Err,
- LLVMContext &Context,
- SlotMapping *Slots,
- bool UpgradeDebugInfo) {
+std::unique_ptr<Module>
+llvm::parseAssemblyFile(StringRef Filename, SMDiagnostic &Err,
+ LLVMContext &Context, SlotMapping *Slots,
+ bool UpgradeDebugInfo, StringRef DataLayoutString) {
ErrorOr<std::unique_ptr<MemoryBuffer>> FileOrErr =
MemoryBuffer::getFileOrSTDIN(Filename);
if (std::error_code EC = FileOrErr.getError()) {
@@ -57,16 +60,16 @@ std::unique_ptr<Module> llvm::parseAssemblyFile(StringRef Filename,
}
return parseAssembly(FileOrErr.get()->getMemBufferRef(), Err, Context, Slots,
- UpgradeDebugInfo);
+ UpgradeDebugInfo, DataLayoutString);
}
-std::unique_ptr<Module> llvm::parseAssemblyString(StringRef AsmString,
- SMDiagnostic &Err,
- LLVMContext &Context,
- SlotMapping *Slots,
- bool UpgradeDebugInfo) {
+std::unique_ptr<Module>
+llvm::parseAssemblyString(StringRef AsmString, SMDiagnostic &Err,
+ LLVMContext &Context, SlotMapping *Slots,
+ bool UpgradeDebugInfo, StringRef DataLayoutString) {
MemoryBufferRef F(AsmString, "<string>");
- return parseAssembly(F, Err, Context, Slots, UpgradeDebugInfo);
+ return parseAssembly(F, Err, Context, Slots, UpgradeDebugInfo,
+ DataLayoutString);
}
Constant *llvm::parseConstantValue(StringRef Asm, SMDiagnostic &Err,
diff --git a/llvm/lib/CodeGen/MIRParser/MIRParser.cpp b/llvm/lib/CodeGen/MIRParser/MIRParser.cpp
index e4e3fbbd75d..52ac08cd2d3 100644
--- a/llvm/lib/CodeGen/MIRParser/MIRParser.cpp
+++ b/llvm/lib/CodeGen/MIRParser/MIRParser.cpp
@@ -237,7 +237,7 @@ std::unique_ptr<Module> MIRParserImpl::parseIRModule() {
dyn_cast_or_null<yaml::BlockScalarNode>(In.getCurrentNode())) {
SMDiagnostic Error;
M = parseAssembly(MemoryBufferRef(BSN->getValue(), Filename), Error,
- Context, &IRSlots);
+ Context, &IRSlots, /*UpgradeDebugInfo=*/false);
if (!M) {
reportDiagnostic(diagFromBlockStringDiag(Error, BSN->getSourceRange()));
return nullptr;
diff --git a/llvm/lib/IRReader/IRReader.cpp b/llvm/lib/IRReader/IRReader.cpp
index 999f11deb15..36bbf719bb6 100644
--- a/llvm/lib/IRReader/IRReader.cpp
+++ b/llvm/lib/IRReader/IRReader.cpp
@@ -68,7 +68,8 @@ std::unique_ptr<Module> llvm::getLazyIRFileModule(StringRef Filename,
std::unique_ptr<Module> llvm::parseIR(MemoryBufferRef Buffer, SMDiagnostic &Err,
LLVMContext &Context,
- bool UpgradeDebugInfo) {
+ bool UpgradeDebugInfo,
+ StringRef DataLayoutString) {
NamedRegionTimer T(TimeIRParsingName, TimeIRParsingDescription,
TimeIRParsingGroupName, TimeIRParsingGroupDescription,
TimePassesIsEnabled);
@@ -83,15 +84,19 @@ std::unique_ptr<Module> llvm::parseIR(MemoryBufferRef Buffer, SMDiagnostic &Err,
});
return nullptr;
}
+ if (!DataLayoutString.empty())
+ ModuleOrErr.get()->setDataLayout(DataLayoutString);
return std::move(ModuleOrErr.get());
}
- return parseAssembly(Buffer, Err, Context, nullptr, UpgradeDebugInfo);
+ return parseAssembly(Buffer, Err, Context, nullptr, UpgradeDebugInfo,
+ DataLayoutString);
}
std::unique_ptr<Module> llvm::parseIRFile(StringRef Filename, SMDiagnostic &Err,
LLVMContext &Context,
- bool UpgradeDebugInfo) {
+ bool UpgradeDebugInfo,
+ StringRef DataLayoutString) {
ErrorOr<std::unique_ptr<MemoryBuffer>> FileOrErr =
MemoryBuffer::getFileOrSTDIN(Filename);
if (std::error_code EC = FileOrErr.getError()) {
@@ -101,7 +106,7 @@ std::unique_ptr<Module> llvm::parseIRFile(StringRef Filename, SMDiagnostic &Err,
}
return parseIR(FileOrErr.get()->getMemBufferRef(), Err, Context,
- UpgradeDebugInfo);
+ UpgradeDebugInfo, DataLayoutString);
}
//===----------------------------------------------------------------------===//
diff --git a/llvm/test/Assembler/datalayout-alloca-addrspace-mismatch-0.ll b/llvm/test/Assembler/datalayout-alloca-addrspace-mismatch-0.ll
index 31920183c65..828aa133c76 100644
--- a/llvm/test/Assembler/datalayout-alloca-addrspace-mismatch-0.ll
+++ b/llvm/test/Assembler/datalayout-alloca-addrspace-mismatch-0.ll
@@ -2,7 +2,9 @@
target datalayout = "A1"
-; CHECK: :7:41: error: address space must match datalayout
+; CHECK: Allocation instruction pointer not in the stack address space!
+; CHECK-NEXT: %alloca_scalar_no_align = alloca i32, addrspace(2)
+
define void @use_alloca() {
%alloca_scalar_no_align = alloca i32, addrspace(2)
ret void
diff --git a/llvm/test/Assembler/datalayout-alloca-addrspace-mismatch-1.ll b/llvm/test/Assembler/datalayout-alloca-addrspace-mismatch-1.ll
index 8778a05291c..9f1b91aae61 100644
--- a/llvm/test/Assembler/datalayout-alloca-addrspace-mismatch-1.ll
+++ b/llvm/test/Assembler/datalayout-alloca-addrspace-mismatch-1.ll
@@ -2,7 +2,9 @@
target datalayout = "A1"
-; CHECK: :7:50: error: address space must match datalayout
+; CHECK: Allocation instruction pointer not in the stack address space!
+; CHECK-NEXT: %alloca_scalar_no_align = alloca i32, align 4, addrspace(2)
+
define void @use_alloca() {
%alloca_scalar_no_align = alloca i32, align 4, addrspace(2)
ret void
diff --git a/llvm/test/Assembler/datalayout-alloca-addrspace-mismatch-2.ll b/llvm/test/Assembler/datalayout-alloca-addrspace-mismatch-2.ll
index b6e2738a4f6..1e9d3cb959c 100644
--- a/llvm/test/Assembler/datalayout-alloca-addrspace-mismatch-2.ll
+++ b/llvm/test/Assembler/datalayout-alloca-addrspace-mismatch-2.ll
@@ -2,7 +2,9 @@
target datalayout = "A1"
-; CHECK: :7:50: error: address space must match datalayout
+; CHECK: Allocation instruction pointer not in the stack address space!
+; CHECK-NEXT: %alloca_scalar_no_align = alloca i32, align 4, addrspace(2), !foo !0
+
define void @use_alloca() {
%alloca_scalar_no_align = alloca i32, align 4, addrspace(2), !foo !0
ret void
diff --git a/llvm/test/Assembler/drop-debug-info-nonzero-alloca.ll b/llvm/test/Assembler/drop-debug-info-nonzero-alloca.ll
new file mode 100644
index 00000000000..739edbacde9
--- /dev/null
+++ b/llvm/test/Assembler/drop-debug-info-nonzero-alloca.ll
@@ -0,0 +1,25 @@
+; RUN: llvm-as < %s -o %t.bc -data-layout=A5 2>&1 | FileCheck -check-prefixes=COM,AS %s
+; RUN: llvm-dis < %t.bc | FileCheck -check-prefixes=COM,DIS %s
+; RUN: opt < %s -S -data-layout=A5 2>&1 | FileCheck -check-prefixes=COM,AS %s
+; RUN: opt < %t.bc -S | FileCheck -check-prefixes=COM,DIS %s
+
+define void @foo() {
+entry:
+; DIS: target datalayout = "A5"
+; DIS: %tmp = alloca i32, addrspace(5)
+ %tmp = alloca i32, addrspace(5)
+ call void @llvm.dbg.value(
+ metadata i8* undef,
+ metadata !DILocalVariable(scope: !1),
+ metadata !DIExpression())
+; COM-NOT: Allocation instruction pointer not in the stack address space!
+; AS: llvm.dbg.value intrinsic requires a !dbg attachment
+; AS: warning: ignoring invalid debug info in <stdin>
+ret void
+}
+
+declare void @llvm.dbg.value(metadata, metadata, metadata)
+
+!llvm.module.flags = !{!0}
+!0 = !{i32 2, !"Debug Info Version", i32 3}
+!1 = distinct !DISubprogram(name: "foo")
diff --git a/llvm/test/CodeGen/AMDGPU/alloca.ll b/llvm/test/CodeGen/AMDGPU/alloca.ll
new file mode 100644
index 00000000000..fd42e925f3a
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/alloca.ll
@@ -0,0 +1,12 @@
+; RUN: llvm-as -data-layout=A5 < %s | llvm-dis | FileCheck %s
+; RUN: llc -mtriple amdgcn-amd-amdhsa-amdgiz < %s
+; RUN: llvm-as -data-layout=A5 < %s | llc -mtriple amdgcn-amd-amdhsa-amdgiz
+; RUN: opt -data-layout=A5 -S < %s
+; RUN: llvm-as -data-layout=A5 < %s | opt -S
+
+; CHECK: %tmp = alloca i32, addrspace(5)
+define amdgpu_kernel void @test() {
+ %tmp = alloca i32, addrspace(5)
+ ret void
+}
+
diff --git a/llvm/test/CodeGen/AMDGPU/fence-barrier.ll b/llvm/test/CodeGen/AMDGPU/fence-barrier.ll
index f140a762942..8c6c17e5e57 100644
--- a/llvm/test/CodeGen/AMDGPU/fence-barrier.ll
+++ b/llvm/test/CodeGen/AMDGPU/fence-barrier.ll
@@ -1,4 +1,5 @@
-; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx803 -enable-si-insert-waitcnts=1 -verify-machineinstrs < %s | FileCheck --check-prefix=GCN %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa-amdgiz -mcpu=gfx803 -enable-si-insert-waitcnts=1 -verify-machineinstrs < %s | FileCheck --check-prefix=GCN %s
+; RUN: llvm-as -data-layout=A5 < %s | llc -mtriple=amdgcn-amd-amdhsa-amdgiz -mcpu=gfx803 -enable-si-insert-waitcnts=1 -verify-machineinstrs | FileCheck --check-prefix=GCN %s
declare i8 addrspace(2)* @llvm.amdgcn.dispatch.ptr()
declare i8 addrspace(2)* @llvm.amdgcn.implicitarg.ptr()
@@ -16,8 +17,8 @@ declare void @llvm.amdgcn.s.barrier()
; GCN-NEXT: s_barrier
; GCN: flat_store_dword
define amdgpu_kernel void @test_local(i32 addrspace(1)*) {
- %2 = alloca i32 addrspace(1)*, align 4
- store i32 addrspace(1)* %0, i32 addrspace(1)** %2, align 4
+ %2 = alloca i32 addrspace(1)*, align 4, addrspace(5)
+ store i32 addrspace(1)* %0, i32 addrspace(1)* addrspace(5)* %2, align 4
%3 = call i32 @llvm.amdgcn.workitem.id.x()
%4 = zext i32 %3 to i64
%5 = icmp eq i64 %4, 0
@@ -32,7 +33,7 @@ define amdgpu_kernel void @test_local(i32 addrspace(1)*) {
call void @llvm.amdgcn.s.barrier()
fence syncscope("workgroup") acquire
%8 = load i32, i32 addrspace(3)* getelementptr inbounds ([1 x i32], [1 x i32] addrspace(3)* @test_local.temp, i64 0, i64 0), align 4
- %9 = load i32 addrspace(1)*, i32 addrspace(1)** %2, align 4
+ %9 = load i32 addrspace(1)*, i32 addrspace(1)* addrspace(5)* %2, align 4
%10 = call i8 addrspace(2)* @llvm.amdgcn.dispatch.ptr()
%11 = call i32 @llvm.amdgcn.workitem.id.x()
%12 = call i32 @llvm.amdgcn.workgroup.id.x()
@@ -58,14 +59,14 @@ define amdgpu_kernel void @test_local(i32 addrspace(1)*) {
; GCN: s_waitcnt vmcnt(0) lgkmcnt(0){{$}}
; GCN-NEXT: s_barrier
define amdgpu_kernel void @test_global(i32 addrspace(1)*) {
- %2 = alloca i32 addrspace(1)*, align 4
- %3 = alloca i32, align 4
- store i32 addrspace(1)* %0, i32 addrspace(1)** %2, align 4
- store i32 0, i32* %3, align 4
+ %2 = alloca i32 addrspace(1)*, align 4, addrspace(5)
+ %3 = alloca i32, align 4, addrspace(5)
+ store i32 addrspace(1)* %0, i32 addrspace(1)* addrspace(5)* %2, align 4
+ store i32 0, i32 addrspace(5)* %3, align 4
br label %4
; <label>:4: ; preds = %58, %1
- %5 = load i32, i32* %3, align 4
+ %5 = load i32, i32 addrspace(5)* %3, align 4
%6 = sext i32 %5 to i64
%7 = call i8 addrspace(2)* @llvm.amdgcn.dispatch.ptr()
%8 = call i32 @llvm.amdgcn.workitem.id.x()
@@ -101,8 +102,8 @@ define amdgpu_kernel void @test_global(i32 addrspace(1)*) {
%36 = add i64 %35, %33
%37 = add i64 %36, 2184
%38 = trunc i64 %37 to i32
- %39 = load i32 addrspace(1)*, i32 addrspace(1)** %2, align 4
- %40 = load i32, i32* %3, align 4
+ %39 = load i32 addrspace(1)*, i32 addrspace(1)* addrspace(5)* %2, align 4
+ %40 = load i32, i32 addrspace(5)* %3, align 4
%41 = sext i32 %40 to i64
%42 = call i8 addrspace(2)* @llvm.amdgcn.dispatch.ptr()
%43 = call i32 @llvm.amdgcn.workitem.id.x()
@@ -127,9 +128,9 @@ define amdgpu_kernel void @test_global(i32 addrspace(1)*) {
br label %58
; <label>:58: ; preds = %22
- %59 = load i32, i32* %3, align 4
+ %59 = load i32, i32 addrspace(5)* %3, align 4
%60 = add nsw i32 %59, 1
- store i32 %60, i32* %3, align 4
+ store i32 %60, i32 addrspace(5)* %3, align 4
br label %4
; <label>:61: ; preds = %4
@@ -143,9 +144,9 @@ define amdgpu_kernel void @test_global(i32 addrspace(1)*) {
; GCN-NEXT: s_barrier
; GCN: flat_store_dword
define amdgpu_kernel void @test_global_local(i32 addrspace(1)*) {
- %2 = alloca i32 addrspace(1)*, align 4
- store i32 addrspace(1)* %0, i32 addrspace(1)** %2, align 4
- %3 = load i32 addrspace(1)*, i32 addrspace(1)** %2, align 4
+ %2 = alloca i32 addrspace(1)*, align 4, addrspace(5)
+ store i32 addrspace(1)* %0, i32 addrspace(1)* addrspace(5)* %2, align 4
+ %3 = load i32 addrspace(1)*, i32 addrspace(1)* addrspace(5)* %2, align 4
%4 = call i8 addrspace(2)* @llvm.amdgcn.dispatch.ptr()
%5 = call i32 @llvm.amdgcn.workitem.id.x()
%6 = call i32 @llvm.amdgcn.workgroup.id.x()
@@ -176,7 +177,7 @@ define amdgpu_kernel void @test_global_local(i32 addrspace(1)*) {
call void @llvm.amdgcn.s.barrier()
fence syncscope("workgroup") acquire
%24 = load i32, i32 addrspace(3)* getelementptr inbounds ([1 x i32], [1 x i32] addrspace(3)* @test_global_local.temp, i64 0, i64 0), align 4
- %25 = load i32 addrspace(1)*, i32 addrspace(1)** %2, align 4
+ %25 = load i32 addrspace(1)*, i32 addrspace(1)* addrspace(5)* %2, align 4
%26 = call i8 addrspace(2)* @llvm.amdgcn.dispatch.ptr()
%27 = call i32 @llvm.amdgcn.workitem.id.x()
%28 = call i32 @llvm.amdgcn.workgroup.id.x()
diff --git a/llvm/test/CodeGen/AMDGPU/invalid-alloca.ll b/llvm/test/CodeGen/AMDGPU/invalid-alloca.ll
new file mode 100644
index 00000000000..043ab46716b
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/invalid-alloca.ll
@@ -0,0 +1,16 @@
+; RUN: not llvm-as -data-layout=A5 < %s 2>&1 | FileCheck -check-prefixes=COMMON,AS %s
+; RUN: not llc -mtriple amdgcn-amd-amdhsa-amdgiz < %s 2>&1 | FileCheck -check-prefixes=COMMON,LLC %s
+; RUN: llvm-as < %s | not llc -mtriple amdgcn-amd-amdhsa-amdgiz 2>&1 | FileCheck -check-prefixes=COMMON,LLC %s
+; RUN: not opt -data-layout=A5 -S < %s 2>&1 | FileCheck -check-prefixes=COMMON,LLC %s
+; RUN: llvm-as < %s | not opt -data-layout=A5 2>&1 | FileCheck -check-prefixes=COMMON,LLC %s
+
+; AS: assembly parsed, but does not verify as correct!
+; COMMON: Allocation instruction pointer not in the stack address space!
+; COMMON: %tmp = alloca i32
+; LLC: error: input module is broken!
+
+define amdgpu_kernel void @test() {
+ %tmp = alloca i32
+ ret void
+}
+
diff --git a/llvm/test/CodeGen/AMDGPU/sched-crash-dbg-value.mir b/llvm/test/CodeGen/AMDGPU/sched-crash-dbg-value.mir
index a89011a0cce..bf1fdca5a82 100644
--- a/llvm/test/CodeGen/AMDGPU/sched-crash-dbg-value.mir
+++ b/llvm/test/CodeGen/AMDGPU/sched-crash-dbg-value.mir
@@ -1,4 +1,4 @@
-# RUN: llc -mtriple=amdgcn-amd-amdhsa-opencl -verify-machineinstrs -run-pass=machine-scheduler -o - %s | FileCheck %s
+# RUN: llc -mtriple=amdgcn-amd-amdhsa-amdgizcl -verify-machineinstrs -run-pass=machine-scheduler -o - %s | FileCheck %s
--- |
%struct.widget.0 = type { float, i32, i32 }
@@ -14,7 +14,7 @@
define amdgpu_kernel void @sched_dbg_value_crash(i8 addrspace(1)* nocapture readonly %arg, i32 addrspace(1)* nocapture readonly %arg1, %struct.widget.0 addrspace(1)* nocapture readonly %arg2, %struct.baz addrspace(1)* nocapture readonly %arg3, %struct.snork addrspace(1)* nocapture %arg4) local_unnamed_addr #2 {
bb:
%0 = getelementptr i32, i32 addrspace(1)* %arg1, i64 0, !amdgpu.uniform !3, !amdgpu.noclobber !3
- %tmp5 = alloca %struct.wombat, align 16
+ %tmp5 = alloca %struct.wombat, align 16, addrspace(5)
%1 = call noalias nonnull dereferenceable(64) i8 addrspace(2)* @llvm.amdgcn.dispatch.ptr()
%2 = bitcast i8 addrspace(2)* %1 to i32 addrspace(2)*
%3 = getelementptr inbounds i32, i32 addrspace(2)* %2, i64 1
@@ -48,9 +48,9 @@
%tmp20 = shl nuw nsw i64 %tmp19, 2
%tmp21 = getelementptr inbounds i8, i8 addrspace(1)* %arg, i64 %tmp20
%tmp22 = bitcast i8 addrspace(1)* %tmp21 to %struct.wombat.1 addrspace(1)*
- %tmp23 = bitcast %struct.wombat* %tmp5 to i8*
- call void @llvm.lifetime.start.p0i8(i64 144, i8* nonnull %tmp23) #3
- %tmp24 = getelementptr inbounds %struct.wombat, %struct.wombat* %tmp5, i32 0, i32 6
+ %tmp23 = bitcast %struct.wombat addrspace(5)* %tmp5 to i8 addrspace(5)*
+ call void @llvm.lifetime.start.p5i8(i64 144, i8 addrspace(5)* nonnull %tmp23) #3
+ %tmp24 = getelementptr inbounds %struct.wombat, %struct.wombat addrspace(5)* %tmp5, i32 0, i32 6
%tmp25 = getelementptr i32, i32 addrspace(1)* %arg1, i64 3, !amdgpu.uniform !3, !amdgpu.noclobber !3
%tmp26 = load i32, i32 addrspace(1)* %tmp25, align 4
%tmp27 = zext i32 %tmp26 to i64
@@ -103,7 +103,7 @@
%tmp74 = insertelement <4 x float> <float undef, float undef, float undef, float 0.000000e+00>, float %tmp69, i32 0
%tmp75 = insertelement <4 x float> %tmp74, float %tmp71, i32 1
%tmp76 = insertelement <4 x float> %tmp75, float %tmp73, i32 2
- store <4 x float> %tmp76, <4 x float>* %tmp24, align 16
+ store <4 x float> %tmp76, <4 x float> addrspace(5)* %tmp24, align 16
%tmp77 = fsub float undef, %tmp60
%tmp78 = fsub float undef, %tmp61
%tmp79 = extractelement <4 x float> %tmp66, i32 2
@@ -125,26 +125,26 @@
%tmp94 = call float @llvm.fmuladd.f32(float %tmp92, float %tmp36, float %tmp93)
%tmp95 = call float @llvm.fmuladd.f32(float %tmp48, float undef, float %tmp94)
%tmp96 = fsub float extractelement (<2 x float> fadd (<2 x float> fmul (<2 x float> undef, <2 x float> undef), <2 x float> undef), i64 1), %tmp95
- %tmp97 = getelementptr inbounds %struct.wombat, %struct.wombat* %tmp5, i32 0, i32 8, i32 1
- call void @func(float %tmp96, i64 0, i16* nonnull %tmp97) #3
+ %tmp97 = getelementptr inbounds %struct.wombat, %struct.wombat addrspace(5)* %tmp5, i32 0, i32 8, i32 1
+ call void @func(float %tmp96, i64 0, i16 addrspace(5)* nonnull %tmp97) #3
%tmp984 = bitcast [16 x i8] addrspace(3)* %17 to i8 addrspace(3)*
%tmp99 = getelementptr inbounds %struct.snork, %struct.snork addrspace(1)* %arg4, i64 %tmp12, i32 8, i32 1, i64 0
call void @llvm.memcpy.p1i8.p3i8.i64(i8 addrspace(1)* %tmp99, i8 addrspace(3)* %tmp984, i64 16, i32 16, i1 false)
- call void @llvm.lifetime.end.p0i8(i64 144, i8* nonnull %tmp23) #3
+ call void @llvm.lifetime.end.p5i8(i64 144, i8 addrspace(5)* nonnull %tmp23) #3
ret void
}
- declare void @func(float, i64, i16*)
- declare void @llvm.lifetime.start.p0i8(i64, i8* nocapture) #0
+ declare void @func(float, i64, i16 addrspace(5)*)
+ declare void @llvm.lifetime.start.p5i8(i64, i8 addrspace(5)* nocapture) #0
declare float @llvm.fmuladd.f32(float, float, float) #1
- declare void @llvm.lifetime.end.p0i8(i64, i8* nocapture) #0
+ declare void @llvm.lifetime.end.p5i8(i64, i8 addrspace(5)* nocapture) #0
declare <2 x float> @llvm.fmuladd.v2f32(<2 x float>, <2 x float>, <2 x float>) #1
declare i32 @llvm.amdgcn.workitem.id.x() #1
declare void @llvm.dbg.value(metadata, metadata, metadata) #1
declare i8 addrspace(2)* @llvm.amdgcn.dispatch.ptr() #1
declare i32 @llvm.amdgcn.workitem.id.y() #1
declare i32 @llvm.amdgcn.workitem.id.z() #1
- declare void @llvm.memcpy.p1i8.p0i8.i64(i8 addrspace(1)* nocapture writeonly, i8* nocapture readonly, i64, i32, i1) #0
+ declare void @llvm.memcpy.p1i8.p5i8.i64(i8 addrspace(1)* nocapture writeonly, i8 addrspace(5)* nocapture readonly, i64, i32, i1) #0
declare void @llvm.memcpy.p1i8.p3i8.i64(i8 addrspace(1)* nocapture writeonly, i8 addrspace(3)* nocapture readonly, i64, i32, i1) #0
attributes #0 = { argmemonly nounwind }
diff --git a/llvm/tools/llc/llc.cpp b/llvm/tools/llc/llc.cpp
index a4810890f9b..1639b46ec79 100644
--- a/llvm/tools/llc/llc.cpp
+++ b/llvm/tools/llc/llc.cpp
@@ -24,6 +24,7 @@
#include "llvm/CodeGen/MachineModuleInfo.h"
#include "llvm/CodeGen/TargetPassConfig.h"
#include "llvm/CodeGen/TargetSubtargetInfo.h"
+#include "llvm/IR/AutoUpgrade.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/DiagnosticInfo.h"
#include "llvm/IR/DiagnosticPrinter.h"
@@ -395,20 +396,12 @@ static int compileModule(char **argv, LLVMContext &Context) {
if (MIR)
M = MIR->parseIRModule();
} else
- M = parseIRFile(InputFilename, Err, Context);
+ M = parseIRFile(InputFilename, Err, Context, false);
if (!M) {
Err.print(argv[0], errs());
return 1;
}
- // Verify module immediately to catch problems before doInitialization() is
- // called on any passes.
- if (!NoVerify && verifyModule(*M, &errs())) {
- errs() << argv[0] << ": " << InputFilename
- << ": error: input module is broken!\n";
- return 1;
- }
-
// If we are supposed to override the target triple, do so now.
if (!TargetTriple.empty())
M->setTargetTriple(Triple::normalize(TargetTriple));
@@ -487,6 +480,18 @@ static int compileModule(char **argv, LLVMContext &Context) {
// Add the target data from the target machine, if it exists, or the module.
M->setDataLayout(Target->createDataLayout());
+ // This needs to be done after setting datalayout since it calls verifier
+ // to check debug info whereas verifier relies on correct datalayout.
+ UpgradeDebugInfo(*M);
+
+ // Verify module immediately to catch problems before doInitialization() is
+ // called on any passes.
+ if (!NoVerify && verifyModule(*M, &errs())) {
+ errs() << argv[0] << ": " << InputFilename
+ << ": error: input module is broken!\n";
+ return 1;
+ }
+
// Override function attributes based on CPUStr, FeaturesStr, and command line
// flags.
setFunctionAttributes(CPUStr, FeaturesStr, *M);
diff --git a/llvm/tools/llvm-as/llvm-as.cpp b/llvm/tools/llvm-as/llvm-as.cpp
index 9f0f162b74f..7d04b4ddc8e 100644
--- a/llvm/tools/llvm-as/llvm-as.cpp
+++ b/llvm/tools/llvm-as/llvm-as.cpp
@@ -59,6 +59,11 @@ static cl::opt<bool> PreserveBitcodeUseListOrder(
cl::desc("Preserve use-list order when writing LLVM bitcode."),
cl::init(true), cl::Hidden);
+static cl::opt<std::string> ClDataLayout("data-layout",
+ cl::desc("data layout string to use"),
+ cl::value_desc("layout-string"),
+ cl::init(""));
+
static void WriteOutputFile(const Module *M) {
// Infer the output filename if needed.
if (OutputFilename.empty()) {
@@ -97,8 +102,8 @@ int main(int argc, char **argv) {
// Parse the file now...
SMDiagnostic Err;
- std::unique_ptr<Module> M =
- parseAssemblyFile(InputFilename, Err, Context, nullptr, !DisableVerify);
+ std::unique_ptr<Module> M = parseAssemblyFile(
+ InputFilename, Err, Context, nullptr, !DisableVerify, ClDataLayout);
if (!M.get()) {
Err.print(argv[0], errs());
return 1;
diff --git a/llvm/tools/opt/opt.cpp b/llvm/tools/opt/opt.cpp
index e03f6cee39f..236c9022587 100644
--- a/llvm/tools/opt/opt.cpp
+++ b/llvm/tools/opt/opt.cpp
@@ -458,7 +458,7 @@ int main(int argc, char **argv) {
// Load the input module...
std::unique_ptr<Module> M =
- parseIRFile(InputFilename, Err, Context, !NoVerify);
+ parseIRFile(InputFilename, Err, Context, !NoVerify, ClDataLayout);
if (!M) {
Err.print(argv[0], errs());
@@ -469,6 +469,10 @@ int main(int argc, char **argv) {
if (StripDebug)
StripDebugInfo(*M);
+ // If we are supposed to override the target triple or data layout, do so now.
+ if (!TargetTriple.empty())
+ M->setTargetTriple(Triple::normalize(TargetTriple));
+
// Immediately run the verifier to catch any problems before starting up the
// pass pipelines. Otherwise we can crash on broken code during
// doInitialization().
@@ -478,12 +482,6 @@ int main(int argc, char **argv) {
return 1;
}
- // If we are supposed to override the target triple or data layout, do so now.
- if (!TargetTriple.empty())
- M->setTargetTriple(Triple::normalize(TargetTriple));
- if (!ClDataLayout.empty())
- M->setDataLayout(ClDataLayout);
-
// Figure out what stream we are supposed to write to...
std::unique_ptr<ToolOutputFile> Out;
std::unique_ptr<ToolOutputFile> ThinLinkOut;
OpenPOWER on IntegriCloud