RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-22 02:33:06 +01:00
Code Issues Projects Releases Wiki Activity

Fix several accidental DOS line endings in source files

Browse Source 
Summary:
There are a number of files in the tree which have been accidentally checked in with DOS line endings.  Convert these to native line endings.

There are also a few files which have DOS line endings on purpose, and I have set the svn:eol-style property to 'CRLF' on those.

Reviewers: joerg, aaron.ballman

Subscribers: aaron.ballman, sanjoy, dsanders, llvm-commits

Differential Revision: http://reviews.llvm.org/D15848

llvm-svn: 256707
This commit is contained in:
Dimitry Andric 2016-01-03 17:22:03 +00:00
parent ad5c48e76d
commit 0614f2a55e
46 changed files with 1688 additions and 1688 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

360
docs/MCJITDesignAndImplementation.rst
View File

@ -1,180 +1,180 @@
===============================
MCJIT Design and Implementation
===============================
Introduction
============
This document describes the internal workings of the MCJIT execution
engine and the RuntimeDyld component. It is intended as a high level
overview of the implementation, showing the flow and interactions of
objects throughout the code generation and dynamic loading process.
Engine Creation
===============
In most cases, an EngineBuilder object is used to create an instance of
the MCJIT execution engine. The EngineBuilder takes an llvm::Module
object as an argument to its constructor. The client may then set various
options that we control the later be passed along to the MCJIT engine,
including the selection of MCJIT as the engine type to be created.
Of particular interest is the EngineBuilder::setMCJITMemoryManager
function. If the client does not explicitly create a memory manager at
this time, a default memory manager (specifically SectionMemoryManager)
will be created when the MCJIT engine is instantiated.
Once the options have been set, a client calls EngineBuilder::create to
create an instance of the MCJIT engine. If the client does not use the
form of this function that takes a TargetMachine as a parameter, a new
TargetMachine will be created based on the target triple associated with
the Module that was used to create the EngineBuilder.
.. image:: MCJIT-engine-builder.png
EngineBuilder::create will call the static MCJIT::createJIT function,
passing in its pointers to the module, memory manager and target machine
objects, all of which will subsequently be owned by the MCJIT object.
The MCJIT class has a member variable, Dyld, which contains an instance of
the RuntimeDyld wrapper class. This member will be used for
communications between MCJIT and the actual RuntimeDyldImpl object that
gets created when an object is loaded.
.. image:: MCJIT-creation.png
Upon creation, MCJIT holds a pointer to the Module object that it received
from EngineBuilder but it does not immediately generate code for this
module. Code generation is deferred until either the
MCJIT::finalizeObject method is called explicitly or a function such as
MCJIT::getPointerToFunction is called which requires the code to have been
generated.
Code Generation
===============
When code generation is triggered, as described above, MCJIT will first
attempt to retrieve an object image from its ObjectCache member, if one
has been set. If a cached object image cannot be retrieved, MCJIT will
call its emitObject method. MCJIT::emitObject uses a local PassManager
instance and creates a new ObjectBufferStream instance, both of which it
passes to TargetMachine::addPassesToEmitMC before calling PassManager::run
on the Module with which it was created.
.. image:: MCJIT-load.png
The PassManager::run call causes the MC code generation mechanisms to emit
a complete relocatable binary object image (either in either ELF or MachO
format, depending on the target) into the ObjectBufferStream object, which
is flushed to complete the process. If an ObjectCache is being used, the
image will be passed to the ObjectCache here.
At this point, the ObjectBufferStream contains the raw object image.
Before the code can be executed, the code and data sections from this
image must be loaded into suitable memory, relocations must be applied and
memory permission and code cache invalidation (if required) must be completed.
Object Loading
==============
Once an object image has been obtained, either through code generation or
having been retrieved from an ObjectCache, it is passed to RuntimeDyld to
be loaded. The RuntimeDyld wrapper class examines the object to determine
its file format and creates an instance of either RuntimeDyldELF or
RuntimeDyldMachO (both of which derive from the RuntimeDyldImpl base
class) and calls the RuntimeDyldImpl::loadObject method to perform that
actual loading.
.. image:: MCJIT-dyld-load.png
RuntimeDyldImpl::loadObject begins by creating an ObjectImage instance
from the ObjectBuffer it received. ObjectImage, which wraps the
ObjectFile class, is a helper class which parses the binary object image
and provides access to the information contained in the format-specific
headers, including section, symbol and relocation information.
RuntimeDyldImpl::loadObject then iterates through the symbols in the
image. Information about common symbols is collected for later use. For
each function or data symbol, the associated section is loaded into memory
and the symbol is stored in a symbol table map data structure. When the
iteration is complete, a section is emitted for the common symbols.
Next, RuntimeDyldImpl::loadObject iterates through the sections in the
object image and for each section iterates through the relocations for
that sections. For each relocation, it calls the format-specific
processRelocationRef method, which will examine the relocation and store
it in one of two data structures, a section-based relocation list map and
an external symbol relocation map.
.. image:: MCJIT-load-object.png
When RuntimeDyldImpl::loadObject returns, all of the code and data
sections for the object will have been loaded into memory allocated by the
memory manager and relocation information will have been prepared, but the
relocations have not yet been applied and the generated code is still not
ready to be executed.
[Currently (as of August 2013) the MCJIT engine will immediately apply
relocations when loadObject completes. However, this shouldn't be
happening. Because the code may have been generated for a remote target,
the client should be given a chance to re-map the section addresses before
relocations are applied. It is possible to apply relocations multiple
times, but in the case where addresses are to be re-mapped, this first
application is wasted effort.]
Address Remapping
=================
At any time after initial code has been generated and before
finalizeObject is called, the client can remap the address of sections in
the object. Typically this is done because the code was generated for an
external process and is being mapped into that process' address space.
The client remaps the section address by calling MCJIT::mapSectionAddress.
This should happen before the section memory is copied to its new
location.
When MCJIT::mapSectionAddress is called, MCJIT passes the call on to
RuntimeDyldImpl (via its Dyld member). RuntimeDyldImpl stores the new
address in an internal data structure but does not update the code at this
time, since other sections are likely to change.
When the client is finished remapping section addresses, it will call
MCJIT::finalizeObject to complete the remapping process.
Final Preparations
==================
When MCJIT::finalizeObject is called, MCJIT calls
RuntimeDyld::resolveRelocations. This function will attempt to locate any
external symbols and then apply all relocations for the object.
External symbols are resolved by calling the memory manager's
getPointerToNamedFunction method. The memory manager will return the
address of the requested symbol in the target address space. (Note, this
may not be a valid pointer in the host process.) RuntimeDyld will then
iterate through the list of relocations it has stored which are associated
with this symbol and invoke the resolveRelocation method which, through an
format-specific implementation, will apply the relocation to the loaded
section memory.
Next, RuntimeDyld::resolveRelocations iterates through the list of
sections and for each section iterates through a list of relocations that
have been saved which reference that symbol and call resolveRelocation for
each entry in this list. The relocation list here is a list of
relocations for which the symbol associated with the relocation is located
in the section associated with the list. Each of these locations will
have a target location at which the relocation will be applied that is
likely located in a different section.
.. image:: MCJIT-resolve-relocations.png
Once relocations have been applied as described above, MCJIT calls
RuntimeDyld::getEHFrameSection, and if a non-zero result is returned
passes the section data to the memory manager's registerEHFrames method.
This allows the memory manager to call any desired target-specific
functions, such as registering the EH frame information with a debugger.
Finally, MCJIT calls the memory manager's finalizeMemory method. In this
method, the memory manager will invalidate the target code cache, if
necessary, and apply final permissions to the memory pages it has
allocated for code and data memory.
===============================
MCJIT Design and Implementation
===============================
Introduction
============
This document describes the internal workings of the MCJIT execution
engine and the RuntimeDyld component. It is intended as a high level
overview of the implementation, showing the flow and interactions of
objects throughout the code generation and dynamic loading process.
Engine Creation
===============
In most cases, an EngineBuilder object is used to create an instance of
the MCJIT execution engine. The EngineBuilder takes an llvm::Module
object as an argument to its constructor. The client may then set various
options that we control the later be passed along to the MCJIT engine,
including the selection of MCJIT as the engine type to be created.
Of particular interest is the EngineBuilder::setMCJITMemoryManager
function. If the client does not explicitly create a memory manager at
this time, a default memory manager (specifically SectionMemoryManager)
will be created when the MCJIT engine is instantiated.
Once the options have been set, a client calls EngineBuilder::create to
create an instance of the MCJIT engine. If the client does not use the
form of this function that takes a TargetMachine as a parameter, a new
TargetMachine will be created based on the target triple associated with
the Module that was used to create the EngineBuilder.
.. image:: MCJIT-engine-builder.png
EngineBuilder::create will call the static MCJIT::createJIT function,
passing in its pointers to the module, memory manager and target machine
objects, all of which will subsequently be owned by the MCJIT object.
The MCJIT class has a member variable, Dyld, which contains an instance of
the RuntimeDyld wrapper class. This member will be used for
communications between MCJIT and the actual RuntimeDyldImpl object that
gets created when an object is loaded.
.. image:: MCJIT-creation.png
Upon creation, MCJIT holds a pointer to the Module object that it received
from EngineBuilder but it does not immediately generate code for this
module. Code generation is deferred until either the
MCJIT::finalizeObject method is called explicitly or a function such as
MCJIT::getPointerToFunction is called which requires the code to have been
generated.
Code Generation
===============
When code generation is triggered, as described above, MCJIT will first
attempt to retrieve an object image from its ObjectCache member, if one
has been set. If a cached object image cannot be retrieved, MCJIT will
call its emitObject method. MCJIT::emitObject uses a local PassManager
instance and creates a new ObjectBufferStream instance, both of which it
passes to TargetMachine::addPassesToEmitMC before calling PassManager::run
on the Module with which it was created.
.. image:: MCJIT-load.png
The PassManager::run call causes the MC code generation mechanisms to emit
a complete relocatable binary object image (either in either ELF or MachO
format, depending on the target) into the ObjectBufferStream object, which
is flushed to complete the process. If an ObjectCache is being used, the
image will be passed to the ObjectCache here.
At this point, the ObjectBufferStream contains the raw object image.
Before the code can be executed, the code and data sections from this
image must be loaded into suitable memory, relocations must be applied and
memory permission and code cache invalidation (if required) must be completed.
Object Loading
==============
Once an object image has been obtained, either through code generation or
having been retrieved from an ObjectCache, it is passed to RuntimeDyld to
be loaded. The RuntimeDyld wrapper class examines the object to determine
its file format and creates an instance of either RuntimeDyldELF or
RuntimeDyldMachO (both of which derive from the RuntimeDyldImpl base
class) and calls the RuntimeDyldImpl::loadObject method to perform that
actual loading.
.. image:: MCJIT-dyld-load.png
RuntimeDyldImpl::loadObject begins by creating an ObjectImage instance
from the ObjectBuffer it received. ObjectImage, which wraps the
ObjectFile class, is a helper class which parses the binary object image
and provides access to the information contained in the format-specific
headers, including section, symbol and relocation information.
RuntimeDyldImpl::loadObject then iterates through the symbols in the
image. Information about common symbols is collected for later use. For
each function or data symbol, the associated section is loaded into memory
and the symbol is stored in a symbol table map data structure. When the
iteration is complete, a section is emitted for the common symbols.
Next, RuntimeDyldImpl::loadObject iterates through the sections in the
object image and for each section iterates through the relocations for
that sections. For each relocation, it calls the format-specific
processRelocationRef method, which will examine the relocation and store
it in one of two data structures, a section-based relocation list map and
an external symbol relocation map.
.. image:: MCJIT-load-object.png
When RuntimeDyldImpl::loadObject returns, all of the code and data
sections for the object will have been loaded into memory allocated by the
memory manager and relocation information will have been prepared, but the
relocations have not yet been applied and the generated code is still not
ready to be executed.
[Currently (as of August 2013) the MCJIT engine will immediately apply
relocations when loadObject completes. However, this shouldn't be
happening. Because the code may have been generated for a remote target,
the client should be given a chance to re-map the section addresses before
relocations are applied. It is possible to apply relocations multiple
times, but in the case where addresses are to be re-mapped, this first
application is wasted effort.]
Address Remapping
=================
At any time after initial code has been generated and before
finalizeObject is called, the client can remap the address of sections in
the object. Typically this is done because the code was generated for an
external process and is being mapped into that process' address space.
The client remaps the section address by calling MCJIT::mapSectionAddress.
This should happen before the section memory is copied to its new
location.
When MCJIT::mapSectionAddress is called, MCJIT passes the call on to
RuntimeDyldImpl (via its Dyld member). RuntimeDyldImpl stores the new
address in an internal data structure but does not update the code at this
time, since other sections are likely to change.
When the client is finished remapping section addresses, it will call
MCJIT::finalizeObject to complete the remapping process.
Final Preparations
==================
When MCJIT::finalizeObject is called, MCJIT calls
RuntimeDyld::resolveRelocations. This function will attempt to locate any
external symbols and then apply all relocations for the object.
External symbols are resolved by calling the memory manager's
getPointerToNamedFunction method. The memory manager will return the
address of the requested symbol in the target address space. (Note, this
may not be a valid pointer in the host process.) RuntimeDyld will then
iterate through the list of relocations it has stored which are associated
with this symbol and invoke the resolveRelocation method which, through an
format-specific implementation, will apply the relocation to the loaded
section memory.
Next, RuntimeDyld::resolveRelocations iterates through the list of
sections and for each section iterates through a list of relocations that
have been saved which reference that symbol and call resolveRelocation for
each entry in this list. The relocation list here is a list of
relocations for which the symbol associated with the relocation is located
in the section associated with the list. Each of these locations will
have a target location at which the relocation will be applied that is
likely located in a different section.
.. image:: MCJIT-resolve-relocations.png
Once relocations have been applied as described above, MCJIT calls
RuntimeDyld::getEHFrameSection, and if a non-zero result is returned
passes the section data to the memory manager's registerEHFrames method.
This allows the memory manager to call any desired target-specific
functions, such as registering the EH frame information with a debugger.
Finally, MCJIT calls the memory manager's finalizeMemory method. In this
method, the memory manager will invalidate the target code cache, if
necessary, and apply final permissions to the memory pages it has
allocated for code and data memory.

118
include/llvm/DebugInfo/DWARF/DWARFDebugMacro.h
View File

@ -1,59 +1,59 @@
//===-- DWARFDebugMacro.h ---------------------------------------*- C++ -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
#ifndef LLVM_DEBUGINFO_DWARF_DWARFDEBUGMACRO_H
#define LLVM_DEBUGINFO_DWARF_DWARFDEBUGMACRO_H
#include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/StringRef.h"
#include "llvm/Support/DataExtractor.h"
#include "llvm/Support/Dwarf.h"
namespace llvm {
class raw_ostream;
class DWARFDebugMacro {
/// A single macro entry within a macro list.
struct Entry {
/// The type of the macro entry.
uint32_t Type;
union {
/// The source line where the macro is defined.
uint64_t Line;
/// Vendor extension constant value.
uint64_t ExtConstant;
};
union {
/// The string (name, value) of the macro entry.
const char *MacroStr;
// An unsigned integer indicating the identity of the source file.
uint64_t File;
/// Vendor extension string.
const char *ExtStr;
};
};
typedef SmallVector<Entry, 4> MacroList;
/// A list of all the macro entries in the debug_macinfo section.
MacroList Macros;
public:
DWARFDebugMacro() {}
/// Print the macro list found within the debug_macinfo section.
void dump(raw_ostream &OS) const;
/// Parse the debug_macinfo section accessible via the 'data' parameter.
void parse(DataExtractor data);
};
}
#endif
//===-- DWARFDebugMacro.h ---------------------------------------*- C++ -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
#ifndef LLVM_DEBUGINFO_DWARF_DWARFDEBUGMACRO_H
#define LLVM_DEBUGINFO_DWARF_DWARFDEBUGMACRO_H
#include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/StringRef.h"
#include "llvm/Support/DataExtractor.h"
#include "llvm/Support/Dwarf.h"
namespace llvm {
class raw_ostream;
class DWARFDebugMacro {
/// A single macro entry within a macro list.
struct Entry {
/// The type of the macro entry.
uint32_t Type;
union {
/// The source line where the macro is defined.
uint64_t Line;
/// Vendor extension constant value.
uint64_t ExtConstant;
};
union {
/// The string (name, value) of the macro entry.
const char *MacroStr;
// An unsigned integer indicating the identity of the source file.
uint64_t File;
/// Vendor extension string.
const char *ExtStr;
};
};
typedef SmallVector<Entry, 4> MacroList;
/// A list of all the macro entries in the debug_macinfo section.
MacroList Macros;
public:
DWARFDebugMacro() {}
/// Print the macro list found within the debug_macinfo section.
void dump(raw_ostream &OS) const;
/// Parse the debug_macinfo section accessible via the 'data' parameter.
void parse(DataExtractor data);
};
}
#endif

28
lib/DebugInfo/CodeView/Makefile
View File

@ -1,14 +1,14 @@
##===- lib/DebugInfo/CodeView/Makefile ---------------------*- Makefile -*-===##
#
# The LLVM Compiler Infrastructure
#
# This file is distributed under the University of Illinois Open Source
# License. See LICENSE.TXT for details.
#
##===----------------------------------------------------------------------===##
LEVEL = ../../..
LIBRARYNAME = LLVMDebugInfoCodeView
BUILD_ARCHIVE := 1
include $(LEVEL)/Makefile.common
##===- lib/DebugInfo/CodeView/Makefile ---------------------*- Makefile -*-===##
#
# The LLVM Compiler Infrastructure
#
# This file is distributed under the University of Illinois Open Source
# License. See LICENSE.TXT for details.
#
##===----------------------------------------------------------------------===##
LEVEL = ../../..
LIBRARYNAME = LLVMDebugInfoCodeView
BUILD_ARCHIVE := 1
include $(LEVEL)/Makefile.common

206
lib/DebugInfo/DWARF/DWARFDebugMacro.cpp
View File

@ -1,103 +1,103 @@
//===-- DWARFDebugMacro.cpp -----------------------------------------------===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
#include "SyntaxHighlighting.h"
#include "llvm/DebugInfo/DWARF/DWARFDebugMacro.h"
#include "llvm/Support/Compiler.h"
#include "llvm/Support/Dwarf.h"
#include "llvm/Support/Format.h"
#include "llvm/Support/raw_ostream.h"
using namespace llvm;
using namespace dwarf;
using namespace syntax;
void DWARFDebugMacro::dump(raw_ostream &OS) const {
unsigned IndLevel = 0;
for (const Entry &E : Macros) {
// There should not be DW_MACINFO_end_file when IndLevel is Zero. However,
// this check handles the case of corrupted ".debug_macinfo" section.
if (IndLevel > 0)
IndLevel -= (E.Type == DW_MACINFO_end_file);
// Print indentation.
for (unsigned I = 0; I < IndLevel; I++)
OS << " ";
IndLevel += (E.Type == DW_MACINFO_start_file);
WithColor(OS, syntax::Macro).get() << MacinfoString(E.Type);
switch (E.Type) {
default:
// Got a corrupted ".debug_macinfo" section (invalid macinfo type).
break;
case DW_MACINFO_define:
case DW_MACINFO_undef:
OS << " - lineno: " << E.Line;
OS << " macro: " << E.MacroStr;
break;
case DW_MACINFO_start_file:
OS << " - lineno: " << E.Line;
OS << " filenum: " << E.File;
break;
case DW_MACINFO_end_file:
break;
case DW_MACINFO_vendor_ext:
OS << " - constant: " << E.ExtConstant;
OS << " string: " << E.ExtStr;
break;
}
OS << "\n";
}
}
void DWARFDebugMacro::parse(DataExtractor data) {
uint32_t Offset = 0;
while (data.isValidOffset(Offset)) {
// A macro list entry consists of:
Entry E;
// 1. Macinfo type
E.Type = data.getULEB128(&Offset);
if (E.Type == 0) {
// Reached end of ".debug_macinfo" section.
return;
}
switch (E.Type) {
default:
// Got a corrupted ".debug_macinfo" section (invalid macinfo type).
// Push the corrupted entry to the list and halt parsing.
E.Type = DW_MACINFO_invalid;
Macros.push_back(E);
return;
case DW_MACINFO_define:
case DW_MACINFO_undef:
// 2. Source line
E.Line = data.getULEB128(&Offset);
// 3. Macro string
E.MacroStr = data.getCStr(&Offset);
break;
case DW_MACINFO_start_file:
// 2. Source line
E.Line = data.getULEB128(&Offset);
// 3. Source file id
E.File = data.getULEB128(&Offset);
break;
case DW_MACINFO_end_file:
break;
case DW_MACINFO_vendor_ext:
// 2. Vendor extension constant
E.ExtConstant = data.getULEB128(&Offset);
// 3. Vendor extension string
E.ExtStr = data.getCStr(&Offset);
break;
}
Macros.push_back(E);
}
}
//===-- DWARFDebugMacro.cpp -----------------------------------------------===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
#include "SyntaxHighlighting.h"
#include "llvm/DebugInfo/DWARF/DWARFDebugMacro.h"
#include "llvm/Support/Compiler.h"
#include "llvm/Support/Dwarf.h"
#include "llvm/Support/Format.h"
#include "llvm/Support/raw_ostream.h"
using namespace llvm;
using namespace dwarf;
using namespace syntax;
void DWARFDebugMacro::dump(raw_ostream &OS) const {
unsigned IndLevel = 0;
for (const Entry &E : Macros) {
// There should not be DW_MACINFO_end_file when IndLevel is Zero. However,
// this check handles the case of corrupted ".debug_macinfo" section.
if (IndLevel > 0)
IndLevel -= (E.Type == DW_MACINFO_end_file);
// Print indentation.
for (unsigned I = 0; I < IndLevel; I++)
OS << " ";
IndLevel += (E.Type == DW_MACINFO_start_file);
WithColor(OS, syntax::Macro).get() << MacinfoString(E.Type);
switch (E.Type) {
default:
// Got a corrupted ".debug_macinfo" section (invalid macinfo type).
break;
case DW_MACINFO_define:
case DW_MACINFO_undef:
OS << " - lineno: " << E.Line;
OS << " macro: " << E.MacroStr;
break;
case DW_MACINFO_start_file:
OS << " - lineno: " << E.Line;
OS << " filenum: " << E.File;
break;
case DW_MACINFO_end_file:
break;
case DW_MACINFO_vendor_ext:
OS << " - constant: " << E.ExtConstant;
OS << " string: " << E.ExtStr;
break;
}
OS << "\n";
}
}
void DWARFDebugMacro::parse(DataExtractor data) {
uint32_t Offset = 0;
while (data.isValidOffset(Offset)) {
// A macro list entry consists of:
Entry E;
// 1. Macinfo type
E.Type = data.getULEB128(&Offset);
if (E.Type == 0) {
// Reached end of ".debug_macinfo" section.
return;
}
switch (E.Type) {
default:
// Got a corrupted ".debug_macinfo" section (invalid macinfo type).
// Push the corrupted entry to the list and halt parsing.
E.Type = DW_MACINFO_invalid;
Macros.push_back(E);
return;
case DW_MACINFO_define:
case DW_MACINFO_undef:
// 2. Source line
E.Line = data.getULEB128(&Offset);
// 3. Macro string
E.MacroStr = data.getCStr(&Offset);
break;
case DW_MACINFO_start_file:
// 2. Source line
E.Line = data.getULEB128(&Offset);
// 3. Source file id
E.File = data.getULEB128(&Offset);
break;
case DW_MACINFO_end_file:
break;
case DW_MACINFO_vendor_ext:
// 2. Vendor extension constant
E.ExtConstant = data.getULEB128(&Offset);
// 3. Vendor extension string
E.ExtStr = data.getCStr(&Offset);
break;
}
Macros.push_back(E);
}
}

6
lib/Target/X86/X86FastISel.cpp
View File

@ -1098,9 +1098,9 @@ bool X86FastISel::X86SelectRet(const Instruction *I) {
RetRegs.push_back(VA.getLocReg());
}
// All x86 ABIs require that for returning structs by value we copy
// the sret argument into %rax/%eax (depending on ABI) for the return.
// We saved the argument into a virtual register in the entry block,
// All x86 ABIs require that for returning structs by value we copy
// the sret argument into %rax/%eax (depending on ABI) for the return.
// We saved the argument into a virtual register in the entry block,
// so now we copy the value out and into %rax/%eax.
if (F.hasStructRetAttr()) {
unsigned Reg = X86MFInfo->getSRetReturnReg();

54
test/CodeGen/AArch64/arm64-vector-ext.ll
View File

@ -1,27 +1,27 @@
; RUN: llc < %s -march=arm64 -aarch64-neon-syntax=apple | FileCheck %s
;CHECK: @func30
;CHECK: movi.4h v1, #0x1
;CHECK: and.8b v0, v0, v1
;CHECK: ushll.4s v0, v0, #0
;CHECK: str q0, [x0]
;CHECK: ret
%T0_30 = type <4 x i1>
%T1_30 = type <4 x i32>
define void @func30(%T0_30 %v0, %T1_30* %p1) {
%r = zext %T0_30 %v0 to %T1_30
store %T1_30 %r, %T1_30* %p1
ret void
}
; Extend from v1i1 was crashing things (PR20791). Make sure we do something
; sensible instead.
define <1 x i32> @autogen_SD7918() {
; CHECK-LABEL: autogen_SD7918
; CHECK: movi d0, #0000000000000000
; CHECK-NEXT: ret
%I29 = insertelement <1 x i1> zeroinitializer, i1 false, i32 0
%ZE = zext <1 x i1> %I29 to <1 x i32>
ret <1 x i32> %ZE
}
; RUN: llc < %s -march=arm64 -aarch64-neon-syntax=apple | FileCheck %s
;CHECK: @func30
;CHECK: movi.4h v1, #0x1
;CHECK: and.8b v0, v0, v1
;CHECK: ushll.4s v0, v0, #0
;CHECK: str q0, [x0]
;CHECK: ret
%T0_30 = type <4 x i1>
%T1_30 = type <4 x i32>
define void @func30(%T0_30 %v0, %T1_30* %p1) {
%r = zext %T0_30 %v0 to %T1_30
store %T1_30 %r, %T1_30* %p1
ret void
}
; Extend from v1i1 was crashing things (PR20791). Make sure we do something
; sensible instead.
define <1 x i32> @autogen_SD7918() {
; CHECK-LABEL: autogen_SD7918
; CHECK: movi d0, #0000000000000000
; CHECK-NEXT: ret
%I29 = insertelement <1 x i1> zeroinitializer, i1 false, i32 0
%ZE = zext <1 x i1> %I29 to <1 x i32>
ret <1 x i32> %ZE
}

34
test/CodeGen/ARM/debugtrap.ll
View File

@ -1,17 +1,17 @@
; This test ensures the @llvm.debugtrap() call is not removed when generating
; the 'pop' instruction to restore the callee saved registers on ARM.
; RUN: llc < %s -mtriple=armv7 -O0 -filetype=asm | FileCheck %s
declare void @llvm.debugtrap() nounwind
declare void @foo() nounwind
define void @test() nounwind {
entry:
; CHECK: bl foo
; CHECK-NEXT: pop
; CHECK-NEXT: trap
call void @foo()
call void @llvm.debugtrap()
ret void
}
; This test ensures the @llvm.debugtrap() call is not removed when generating
; the 'pop' instruction to restore the callee saved registers on ARM.
; RUN: llc < %s -mtriple=armv7 -O0 -filetype=asm | FileCheck %s
declare void @llvm.debugtrap() nounwind
declare void @foo() nounwind
define void @test() nounwind {
entry:
; CHECK: bl foo
; CHECK-NEXT: pop
; CHECK-NEXT: trap
call void @foo()
call void @llvm.debugtrap()
ret void
}

14
test/CodeGen/X86/2011-11-30-or.ll
View File

@ -2,13 +2,13 @@
target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:128:128-n8:16:32"
target triple = "x86_64-apple-macosx10.6.6"
; Test that the order of operands is correct
; CHECK: select_func
; CHECK: pblendvb {{LCPI0_[0-9]*}}(%rip), %xmm1
; CHECK: ret
define void @select_func(<8 x i16> %in) {
; Test that the order of operands is correct
; CHECK: select_func
; CHECK: pblendvb {{LCPI0_[0-9]*}}(%rip), %xmm1
; CHECK: ret
define void @select_func(<8 x i16> %in) {
entry:
%c.lobit.i.i.i = ashr <8 x i16> %in, <i16 15, i16 15, i16 15, i16 15, i16 15, i16 15, i16 15, i16 15>
%and.i56.i.i.i = and <8 x i16> %c.lobit.i.i.i, <i16 25, i16 8, i16 65, i16 25, i16 8, i16 95, i16 15, i16 45>

36
test/CodeGen/X86/avx512cd-intrinsics.ll
View File

@ -1,18 +1,18 @@
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=knl -mattr=+avx512cd | FileCheck %s
define <16 x i32> @test_x86_vbroadcastmw_512(i16 %a0) {
; CHECK: test_x86_vbroadcastmw_512
; CHECK: vpbroadcastmw2d %k0, %zmm0
%res = call <16 x i32> @llvm.x86.avx512.broadcastmw.512(i16 %a0) ;
ret <16 x i32> %res
}
declare <16 x i32> @llvm.x86.avx512.broadcastmw.512(i16)
define <8 x i64> @test_x86_broadcastmb_512(i8 %a0) {
; CHECK: test_x86_broadcastmb_512
; CHECK: vpbroadcastmb2q %k0, %zmm0
%res = call <8 x i64> @llvm.x86.avx512.broadcastmb.512(i8 %a0) ;
ret <8 x i64> %res
}
declare <8 x i64> @llvm.x86.avx512.broadcastmb.512(i8)
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=knl -mattr=+avx512cd | FileCheck %s
define <16 x i32> @test_x86_vbroadcastmw_512(i16 %a0) {
; CHECK: test_x86_vbroadcastmw_512
; CHECK: vpbroadcastmw2d %k0, %zmm0
%res = call <16 x i32> @llvm.x86.avx512.broadcastmw.512(i16 %a0) ;
ret <16 x i32> %res
}
declare <16 x i32> @llvm.x86.avx512.broadcastmw.512(i16)
define <8 x i64> @test_x86_broadcastmb_512(i8 %a0) {
; CHECK: test_x86_broadcastmb_512
; CHECK: vpbroadcastmb2q %k0, %zmm0
%res = call <8 x i64> @llvm.x86.avx512.broadcastmb.512(i8 %a0) ;
ret <8 x i64> %res
}
declare <8 x i64> @llvm.x86.avx512.broadcastmb.512(i8)

254
test/CodeGen/X86/fpcmp-soft-fp.ll
View File

@ -1,127 +1,127 @@
; RUN: llc < %s -march=x86 -mcpu=pentium -mtriple=x86-linux-gnu -float-abi=soft | FileCheck %s
define i1 @test1(double %d) #0 {
entry:
%cmp = fcmp ule double %d, 0.000000e+00
ret i1 %cmp
}
; CHECK-LABEL: test1:
; CHECK: calll __gtdf2
; CHECK: setle
; CHECK: retl
define i1 @test2(double %d) #0 {
entry:
%cmp = fcmp ult double %d, 0.000000e+00
ret i1 %cmp
}
; CHECK-LABEL: test2:
; CHECK: calll __gedf2
; CHECK: sets
; CHECK: retl
define i1 @test3(double %d) #0 {
entry:
%cmp = fcmp ugt double %d, 0.000000e+00
ret i1 %cmp
}
; CHECK-LABEL: test3:
; CHECK: calll __ledf2
; CHECK: setg
; CHECK: retl
define i1 @test4(double %d) #0 {
entry:
%cmp = fcmp uge double %d, 0.000000e+00
ret i1 %cmp
}
; CHECK-LABEL: test4:
; CHECK: calll __ltdf2
; CHECK: setns
; CHECK: retl
define i1 @test5(double %d) #0 {
entry:
%cmp = fcmp ole double %d, 0.000000e+00
ret i1 %cmp
}
; CHECK-LABEL: test5:
; CHECK: calll __ledf2
; CHECK: setle
; CHECK: retl
define i1 @test6(double %d) #0 {
entry:
%cmp = fcmp olt double %d, 0.000000e+00
ret i1 %cmp
}
; CHECK-LABEL: test6:
; CHECK: calll __ltdf2
; CHECK: sets
; CHECK: retl
define i1 @test7(double %d) #0 {
entry:
%cmp = fcmp ogt double %d, 0.000000e+00
ret i1 %cmp
}
; CHECK-LABEL: test7:
; CHECK: calll __gtdf2
; CHECK: setg
; CHECK: retl
define i1 @test8(double %d) #0 {
entry:
%cmp = fcmp oge double %d, 0.000000e+00
ret i1 %cmp
}
; CHECK-LABEL: test8:
; CHECK: calll __gedf2
; CHECK: setns
; CHECK: retl
define i1 @test9(double %d) #0 {
entry:
%cmp = fcmp oeq double %d, 0.000000e+00
ret i1 %cmp
}
; CHECK-LABEL: test9:
; CHECK: calll __eqdf2
; CHECK: sete
; CHECK: retl
define i1 @test10(double %d) #0 {
entry:
%cmp = fcmp ueq double %d, 0.000000e+00
ret i1 %cmp
}
; CHECK-LABEL: test10:
; CHECK: calll __eqdf2
; CHECK: sete
; CHECK: calll __unorddf2
; CHECK: setne
; CHECK: retl
define i1 @test11(double %d) #0 {
entry:
%cmp = fcmp one double %d, 0.000000e+00
ret i1 %cmp
}
; CHECK-LABEL: test11:
; CHECK: calll __gtdf2
; CHECK: setg
; CHECK: calll __ltdf2
; CHECK: sets
; CHECK: retl
define i1 @test12(double %d) #0 {
entry:
%cmp = fcmp une double %d, 0.000000e+00
ret i1 %cmp
}
; CHECK-LABEL: test12:
; CHECK: calll __nedf2
; CHECK: setne
; CHECK: retl
attributes #0 = { "use-soft-float"="true" }
; RUN: llc < %s -march=x86 -mcpu=pentium -mtriple=x86-linux-gnu -float-abi=soft | FileCheck %s
define i1 @test1(double %d) #0 {
entry:
%cmp = fcmp ule double %d, 0.000000e+00
ret i1 %cmp
}
; CHECK-LABEL: test1:
; CHECK: calll __gtdf2
; CHECK: setle
; CHECK: retl
define i1 @test2(double %d) #0 {
entry:
%cmp = fcmp ult double %d, 0.000000e+00
ret i1 %cmp
}
; CHECK-LABEL: test2:
; CHECK: calll __gedf2
; CHECK: sets
; CHECK: retl
define i1 @test3(double %d) #0 {
entry:
%cmp = fcmp ugt double %d, 0.000000e+00
ret i1 %cmp
}
; CHECK-LABEL: test3:
; CHECK: calll __ledf2
; CHECK: setg
; CHECK: retl
define i1 @test4(double %d) #0 {
entry:
%cmp = fcmp uge double %d, 0.000000e+00
ret i1 %cmp
}
; CHECK-LABEL: test4:
; CHECK: calll __ltdf2
; CHECK: setns
; CHECK: retl
define i1 @test5(double %d) #0 {
entry:
%cmp = fcmp ole double %d, 0.000000e+00
ret i1 %cmp
}
; CHECK-LABEL: test5:
; CHECK: calll __ledf2
; CHECK: setle
; CHECK: retl
define i1 @test6(double %d) #0 {
entry:
%cmp = fcmp olt double %d, 0.000000e+00
ret i1 %cmp
}
; CHECK-LABEL: test6:
; CHECK: calll __ltdf2
; CHECK: sets
; CHECK: retl
define i1 @test7(double %d) #0 {
entry:
%cmp = fcmp ogt double %d, 0.000000e+00
ret i1 %cmp
}
; CHECK-LABEL: test7:
; CHECK: calll __gtdf2
; CHECK: setg
; CHECK: retl
define i1 @test8(double %d) #0 {
entry:
%cmp = fcmp oge double %d, 0.000000e+00
ret i1 %cmp
}
; CHECK-LABEL: test8:
; CHECK: calll __gedf2
; CHECK: setns
; CHECK: retl
define i1 @test9(double %d) #0 {
entry:
%cmp = fcmp oeq double %d, 0.000000e+00
ret i1 %cmp
}
; CHECK-LABEL: test9:
; CHECK: calll __eqdf2
; CHECK: sete
; CHECK: retl
define i1 @test10(double %d) #0 {
entry:
%cmp = fcmp ueq double %d, 0.000000e+00
ret i1 %cmp
}
; CHECK-LABEL: test10:
; CHECK: calll __eqdf2
; CHECK: sete
; CHECK: calll __unorddf2
; CHECK: setne
; CHECK: retl
define i1 @test11(double %d) #0 {
entry:
%cmp = fcmp one double %d, 0.000000e+00
ret i1 %cmp
}
; CHECK-LABEL: test11:
; CHECK: calll __gtdf2
; CHECK: setg
; CHECK: calll __ltdf2
; CHECK: sets
; CHECK: retl
define i1 @test12(double %d) #0 {
entry:
%cmp = fcmp une double %d, 0.000000e+00
ret i1 %cmp
}
; CHECK-LABEL: test12:
; CHECK: calll __nedf2
; CHECK: setne
; CHECK: retl
attributes #0 = { "use-soft-float"="true" }

50
test/CodeGen/X86/pku.ll
View File

@ -1,25 +1,25 @@
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=knl --show-mc-encoding| FileCheck %s
declare i32 @llvm.x86.rdpkru()
declare void @llvm.x86.wrpkru(i32)
define void @test_x86_wrpkru(i32 %src) {
; CHECK-LABEL: test_x86_wrpkru:
; CHECK: ## BB#0:
; CHECK-NEXT: xorl %ecx, %ecx
; CHECK-NEXT: xorl %edx, %edx
; CHECK-NEXT: movl %edi, %eax
; CHECK-NEXT: wrpkru
; CHECK-NEXT: retq
call void @llvm.x86.wrpkru(i32 %src)
ret void
}
define i32 @test_x86_rdpkru() {
; CHECK-LABEL: test_x86_rdpkru:
; CHECK: ## BB#0:
; CHECK-NEXT: xorl %ecx, %ecx
; CHECK-NEXT: rdpkru
; CHECK-NEXT: retq
%res = call i32 @llvm.x86.rdpkru()
ret i32 %res
}
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=knl --show-mc-encoding| FileCheck %s
declare i32 @llvm.x86.rdpkru()
declare void @llvm.x86.wrpkru(i32)
define void @test_x86_wrpkru(i32 %src) {
; CHECK-LABEL: test_x86_wrpkru:
; CHECK: ## BB#0:
; CHECK-NEXT: xorl %ecx, %ecx
; CHECK-NEXT: xorl %edx, %edx
; CHECK-NEXT: movl %edi, %eax
; CHECK-NEXT: wrpkru
; CHECK-NEXT: retq
call void @llvm.x86.wrpkru(i32 %src)
ret void
}
define i32 @test_x86_rdpkru() {
; CHECK-LABEL: test_x86_rdpkru:
; CHECK: ## BB#0:
; CHECK-NEXT: xorl %ecx, %ecx
; CHECK-NEXT: rdpkru
; CHECK-NEXT: retq
%res = call i32 @llvm.x86.rdpkru()
ret i32 %res
}

82
test/CodeGen/X86/pr21792.ll
View File

@ -1,41 +1,41 @@
; RUN: llc -mtriple=x86_64-linux -mcpu=corei7 < %s | FileCheck %s
; This fixes a missing cases in the MI scheduler's constrainLocalCopy exposed by
; PR21792
@stuff = external constant [256 x double], align 16
define void @func(<4 x float> %vx) {
entry:
%tmp2 = bitcast <4 x float> %vx to <2 x i64>
%and.i = and <2 x i64> %tmp2, <i64 8727373547504, i64 8727373547504>
%tmp3 = bitcast <2 x i64> %and.i to <4 x i32>
%index.sroa.0.0.vec.extract = extractelement <4 x i32> %tmp3, i32 0
%idx.ext = sext i32 %index.sroa.0.0.vec.extract to i64
%add.ptr = getelementptr inbounds i8, i8* bitcast ([256 x double]* @stuff to i8*), i64 %idx.ext
%tmp4 = bitcast i8* %add.ptr to double*
%index.sroa.0.4.vec.extract = extractelement <4 x i32> %tmp3, i32 1
%idx.ext5 = sext i32 %index.sroa.0.4.vec.extract to i64
%add.ptr6 = getelementptr inbounds i8, i8* bitcast ([256 x double]* @stuff to i8*), i64 %idx.ext5
%tmp5 = bitcast i8* %add.ptr6 to double*
%index.sroa.0.8.vec.extract = extractelement <4 x i32> %tmp3, i32 2
%idx.ext14 = sext i32 %index.sroa.0.8.vec.extract to i64
%add.ptr15 = getelementptr inbounds i8, i8* bitcast ([256 x double]* @stuff to i8*), i64 %idx.ext14
%tmp6 = bitcast i8* %add.ptr15 to double*
%index.sroa.0.12.vec.extract = extractelement <4 x i32> %tmp3, i32 3
%idx.ext19 = sext i32 %index.sroa.0.12.vec.extract to i64
%add.ptr20 = getelementptr inbounds i8, i8* bitcast ([256 x double]* @stuff to i8*), i64 %idx.ext19
%tmp7 = bitcast i8* %add.ptr20 to double*
%add.ptr46 = getelementptr inbounds i8, i8* bitcast (double* getelementptr inbounds ([256 x double], [256 x double]* @stuff, i64 0, i64 1) to i8*), i64 %idx.ext
%tmp16 = bitcast i8* %add.ptr46 to double*
%add.ptr51 = getelementptr inbounds i8, i8* bitcast (double* getelementptr inbounds ([256 x double], [256 x double]* @stuff, i64 0, i64 1) to i8*), i64 %idx.ext5
%tmp17 = bitcast i8* %add.ptr51 to double*
call void @toto(double* %tmp4, double* %tmp5, double* %tmp6, double* %tmp7, double* %tmp16, double* %tmp17)
ret void
; CHECK-LABEL: func:
; CHECK: pextrq $1, %xmm0,
; CHECK-NEXT: movd %xmm0, %r[[AX:..]]
; CHECK-NEXT: movslq %e[[AX]],
; CHECK-NEXT: sarq $32, %r[[AX]]
}
declare void @toto(double*, double*, double*, double*, double*, double*)
; RUN: llc -mtriple=x86_64-linux -mcpu=corei7 < %s | FileCheck %s
; This fixes a missing cases in the MI scheduler's constrainLocalCopy exposed by
; PR21792
@stuff = external constant [256 x double], align 16
define void @func(<4 x float> %vx) {
entry:
%tmp2 = bitcast <4 x float> %vx to <2 x i64>
%and.i = and <2 x i64> %tmp2, <i64 8727373547504, i64 8727373547504>
%tmp3 = bitcast <2 x i64> %and.i to <4 x i32>
%index.sroa.0.0.vec.extract = extractelement <4 x i32> %tmp3, i32 0
%idx.ext = sext i32 %index.sroa.0.0.vec.extract to i64
%add.ptr = getelementptr inbounds i8, i8* bitcast ([256 x double]* @stuff to i8*), i64 %idx.ext
%tmp4 = bitcast i8* %add.ptr to double*
%index.sroa.0.4.vec.extract = extractelement <4 x i32> %tmp3, i32 1
%idx.ext5 = sext i32 %index.sroa.0.4.vec.extract to i64
%add.ptr6 = getelementptr inbounds i8, i8* bitcast ([256 x double]* @stuff to i8*), i64 %idx.ext5
%tmp5 = bitcast i8* %add.ptr6 to double*
%index.sroa.0.8.vec.extract = extractelement <4 x i32> %tmp3, i32 2
%idx.ext14 = sext i32 %index.sroa.0.8.vec.extract to i64
%add.ptr15 = getelementptr inbounds i8, i8* bitcast ([256 x double]* @stuff to i8*), i64 %idx.ext14
%tmp6 = bitcast i8* %add.ptr15 to double*
%index.sroa.0.12.vec.extract = extractelement <4 x i32> %tmp3, i32 3
%idx.ext19 = sext i32 %index.sroa.0.12.vec.extract to i64
%add.ptr20 = getelementptr inbounds i8, i8* bitcast ([256 x double]* @stuff to i8*), i64 %idx.ext19
%tmp7 = bitcast i8* %add.ptr20 to double*
%add.ptr46 = getelementptr inbounds i8, i8* bitcast (double* getelementptr inbounds ([256 x double], [256 x double]* @stuff, i64 0, i64 1) to i8*), i64 %idx.ext
%tmp16 = bitcast i8* %add.ptr46 to double*
%add.ptr51 = getelementptr inbounds i8, i8* bitcast (double* getelementptr inbounds ([256 x double], [256 x double]* @stuff, i64 0, i64 1) to i8*), i64 %idx.ext5
%tmp17 = bitcast i8* %add.ptr51 to double*
call void @toto(double* %tmp4, double* %tmp5, double* %tmp6, double* %tmp7, double* %tmp16, double* %tmp17)
ret void
; CHECK-LABEL: func:
; CHECK: pextrq $1, %xmm0,
; CHECK-NEXT: movd %xmm0, %r[[AX:..]]
; CHECK-NEXT: movslq %e[[AX]],
; CHECK-NEXT: sarq $32, %r[[AX]]
}
declare void @toto(double*, double*, double*, double*, double*, double*)

296
test/CodeGen/X86/pr24139.ll
View File

@ -1,148 +1,148 @@
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s
; Check that we do not get excessive spilling from splitting of constant live ranges.
; CHECK-LABEL: PR24139:
; CHECK: # 16-byte Spill
; CHECK-NOT: # 16-byte Spill
; CHECK: retq
define <2 x double> @PR24139(<2 x double> %arg, <2 x double> %arg1, <2 x double> %arg2) {
%tmp = bitcast <2 x double> %arg to <4 x float>
%tmp3 = fmul <4 x float> %tmp, <float 0x3FE45F3060000000, float 0x3FE45F3060000000, float 0x3FE45F3060000000, float 0x3FE45F3060000000>
%tmp4 = bitcast <2 x double> %arg to <4 x i32>
%tmp5 = and <4 x i32> %tmp4, <i32 -2147483648, i32 -2147483648, i32 -2147483648, i32 -2147483648>
%tmp6 = or <4 x i32> %tmp5, <i32 1056964608, i32 1056964608, i32 1056964608, i32 1056964608>
%tmp7 = bitcast <4 x i32> %tmp6 to <4 x float>
%tmp8 = fadd <4 x float> %tmp3, %tmp7
%tmp9 = tail call <4 x i32> @llvm.x86.sse2.cvttps2dq(<4 x float> %tmp8) #2
%tmp10 = bitcast <4 x i32> %tmp9 to <2 x i64>
%tmp11 = tail call <4 x float> @llvm.x86.sse2.cvtdq2ps(<4 x i32> %tmp9) #2
%tmp12 = fmul <4 x float> %tmp11, <float 0x3FF921FB40000000, float 0x3FF921FB40000000, float 0x3FF921FB40000000, float 0x3FF921FB40000000>
%tmp13 = fsub <4 x float> %tmp, %tmp12
%tmp14 = fmul <4 x float> %tmp11, <float 0x3E74442D00000000, float 0x3E74442D00000000, float 0x3E74442D00000000, float 0x3E74442D00000000>
%tmp15 = fsub <4 x float> %tmp13, %tmp14
%tmp16 = fmul <4 x float> %tmp15, %tmp15
%tmp17 = fmul <4 x float> %tmp15, %tmp16
%tmp18 = fmul <4 x float> %tmp16, <float 0xBF56493260000000, float 0xBF56493260000000, float 0xBF56493260000000, float 0xBF56493260000000>
%tmp19 = fadd <4 x float> %tmp18, <float 0x3FA55406C0000000, float 0x3FA55406C0000000, float 0x3FA55406C0000000, float 0x3FA55406C0000000>
%tmp20 = fmul <4 x float> %tmp16, <float 0xBF29918DC0000000, float 0xBF29918DC0000000, float 0xBF29918DC0000000, float 0xBF29918DC0000000>
%tmp21 = fadd <4 x float> %tmp20, <float 0x3F81106840000000, float 0x3F81106840000000, float 0x3F81106840000000, float 0x3F81106840000000>
%tmp22 = fmul <4 x float> %tmp16, %tmp19
%tmp23 = fadd <4 x float> %tmp22, <float 0xBFDFFFFBE0000000, float 0xBFDFFFFBE0000000, float 0xBFDFFFFBE0000000, float 0xBFDFFFFBE0000000>
%tmp24 = fmul <4 x float> %tmp16, %tmp21
%tmp25 = fadd <4 x float> %tmp24, <float 0xBFC5555420000000, float 0xBFC5555420000000, float 0xBFC5555420000000, float 0xBFC5555420000000>
%tmp26 = fmul <4 x float> %tmp16, %tmp23
%tmp27 = fadd <4 x float> %tmp26, <float 1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 1.000000e+00>
%tmp28 = fmul <4 x float> %tmp17, %tmp25
%tmp29 = fadd <4 x float> %tmp15, %tmp28
%tmp30 = and <2 x i64> %tmp10, <i64 4294967297, i64 4294967297>
%tmp31 = bitcast <2 x i64> %tmp30 to <4 x i32>
%tmp32 = icmp eq <4 x i32> %tmp31, zeroinitializer
%tmp33 = sext <4 x i1> %tmp32 to <4 x i32>
%tmp34 = bitcast <4 x i32> %tmp33 to <4 x float>
%tmp35 = tail call <4 x float> @llvm.x86.sse41.blendvps(<4 x float> %tmp27, <4 x float> %tmp29, <4 x float> %tmp34) #2
%tmp36 = and <2 x i64> %tmp10, <i64 8589934594, i64 8589934594>
%tmp37 = bitcast <2 x i64> %tmp36 to <4 x i32>
%tmp38 = icmp eq <4 x i32> %tmp37, zeroinitializer
%tmp39 = sext <4 x i1> %tmp38 to <4 x i32>
%tmp40 = bitcast <4 x float> %tmp35 to <4 x i32>
%tmp41 = xor <4 x i32> %tmp40, <i32 -2147483648, i32 -2147483648, i32 -2147483648, i32 -2147483648>
%tmp42 = bitcast <4 x i32> %tmp41 to <4 x float>
%tmp43 = bitcast <4 x i32> %tmp39 to <4 x float>
%tmp44 = tail call <4 x float> @llvm.x86.sse41.blendvps(<4 x float> %tmp42, <4 x float> %tmp35, <4 x float> %tmp43) #2
%tmp45 = bitcast <2 x double> %arg1 to <4 x float>
%tmp46 = fmul <4 x float> %tmp45, <float 0x3FE45F3060000000, float 0x3FE45F3060000000, float 0x3FE45F3060000000, float 0x3FE45F3060000000>
%tmp47 = bitcast <2 x double> %arg1 to <4 x i32>
%tmp48 = and <4 x i32> %tmp47, <i32 -2147483648, i32 -2147483648, i32 -2147483648, i32 -2147483648>
%tmp49 = or <4 x i32> %tmp48, <i32 1056964608, i32 1056964608, i32 1056964608, i32 1056964608>
%tmp50 = bitcast <4 x i32> %tmp49 to <4 x float>
%tmp51 = fadd <4 x float> %tmp46, %tmp50
%tmp52 = tail call <4 x i32> @llvm.x86.sse2.cvttps2dq(<4 x float> %tmp51) #2
%tmp53 = bitcast <4 x i32> %tmp52 to <2 x i64>
%tmp54 = tail call <4 x float> @llvm.x86.sse2.cvtdq2ps(<4 x i32> %tmp52) #2
%tmp55 = fmul <4 x float> %tmp54, <float 0x3FF921FB40000000, float 0x3FF921FB40000000, float 0x3FF921FB40000000, float 0x3FF921FB40000000>
%tmp56 = fsub <4 x float> %tmp45, %tmp55
%tmp57 = fmul <4 x float> %tmp54, <float 0x3E74442D00000000, float 0x3E74442D00000000, float 0x3E74442D00000000, float 0x3E74442D00000000>
%tmp58 = fsub <4 x float> %tmp56, %tmp57
%tmp59 = fmul <4 x float> %tmp58, %tmp58
%tmp60 = fmul <4 x float> %tmp58, %tmp59
%tmp61 = fmul <4 x float> %tmp59, <float 0xBF56493260000000, float 0xBF56493260000000, float 0xBF56493260000000, float 0xBF56493260000000>
%tmp62 = fadd <4 x float> %tmp61, <float 0x3FA55406C0000000, float 0x3FA55406C0000000, float 0x3FA55406C0000000, float 0x3FA55406C0000000>
%tmp63 = fmul <4 x float> %tmp59, <float 0xBF29918DC0000000, float 0xBF29918DC0000000, float 0xBF29918DC0000000, float 0xBF29918DC0000000>
%tmp64 = fadd <4 x float> %tmp63, <float 0x3F81106840000000, float 0x3F81106840000000, float 0x3F81106840000000, float 0x3F81106840000000>
%tmp65 = fmul <4 x float> %tmp59, %tmp62
%tmp66 = fadd <4 x float> %tmp65, <float 0xBFDFFFFBE0000000, float 0xBFDFFFFBE0000000, float 0xBFDFFFFBE0000000, float 0xBFDFFFFBE0000000>
%tmp67 = fmul <4 x float> %tmp59, %tmp64
%tmp68 = fadd <4 x float> %tmp67, <float 0xBFC5555420000000, float 0xBFC5555420000000, float 0xBFC5555420000000, float 0xBFC5555420000000>
%tmp69 = fmul <4 x float> %tmp59, %tmp66
%tmp70 = fadd <4 x float> %tmp69, <float 1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 1.000000e+00>
%tmp71 = fmul <4 x float> %tmp60, %tmp68
%tmp72 = fadd <4 x float> %tmp58, %tmp71
%tmp73 = and <2 x i64> %tmp53, <i64 4294967297, i64 4294967297>
%tmp74 = bitcast <2 x i64> %tmp73 to <4 x i32>
%tmp75 = icmp eq <4 x i32> %tmp74, zeroinitializer
%tmp76 = sext <4 x i1> %tmp75 to <4 x i32>
%tmp77 = bitcast <4 x i32> %tmp76 to <4 x float>
%tmp78 = tail call <4 x float> @llvm.x86.sse41.blendvps(<4 x float> %tmp70, <4 x float> %tmp72, <4 x float> %tmp77) #2
%tmp79 = and <2 x i64> %tmp53, <i64 8589934594, i64 8589934594>
%tmp80 = bitcast <2 x i64> %tmp79 to <4 x i32>
%tmp81 = icmp eq <4 x i32> %tmp80, zeroinitializer
%tmp82 = sext <4 x i1> %tmp81 to <4 x i32>
%tmp83 = bitcast <4 x float> %tmp78 to <4 x i32>
%tmp84 = xor <4 x i32> %tmp83, <i32 -2147483648, i32 -2147483648, i32 -2147483648, i32 -2147483648>
%tmp85 = bitcast <4 x i32> %tmp84 to <4 x float>
%tmp86 = bitcast <4 x i32> %tmp82 to <4 x float>
%tmp87 = tail call <4 x float> @llvm.x86.sse41.blendvps(<4 x float> %tmp85, <4 x float> %tmp78, <4 x float> %tmp86) #2
%tmp88 = fadd <4 x float> %tmp44, %tmp87
%tmp89 = bitcast <2 x double> %arg2 to <4 x float>
%tmp90 = fmul <4 x float> %tmp89, <float 0x3FE45F3060000000, float 0x3FE45F3060000000, float 0x3FE45F3060000000, float 0x3FE45F3060000000>
%tmp91 = bitcast <2 x double> %arg2 to <4 x i32>
%tmp92 = and <4 x i32> %tmp91, <i32 -2147483648, i32 -2147483648, i32 -2147483648, i32 -2147483648>
%tmp93 = or <4 x i32> %tmp92, <i32 1056964608, i32 1056964608, i32 1056964608, i32 1056964608>
%tmp94 = bitcast <4 x i32> %tmp93 to <4 x float>
%tmp95 = fadd <4 x float> %tmp90, %tmp94
%tmp96 = tail call <4 x i32> @llvm.x86.sse2.cvttps2dq(<4 x float> %tmp95) #2
%tmp97 = bitcast <4 x i32> %tmp96 to <2 x i64>
%tmp98 = tail call <4 x float> @llvm.x86.sse2.cvtdq2ps(<4 x i32> %tmp96) #2
%tmp99 = fmul <4 x float> %tmp98, <float 0x3FF921FB40000000, float 0x3FF921FB40000000, float 0x3FF921FB40000000, float 0x3FF921FB40000000>
%tmp100 = fsub <4 x float> %tmp89, %tmp99
%tmp101 = fmul <4 x float> %tmp98, <float 0x3E74442D00000000, float 0x3E74442D00000000, float 0x3E74442D00000000, float 0x3E74442D00000000>
%tmp102 = fsub <4 x float> %tmp100, %tmp101
%tmp103 = fmul <4 x float> %tmp102, %tmp102
%tmp104 = fmul <4 x float> %tmp102, %tmp103
%tmp105 = fmul <4 x float> %tmp103, <float 0xBF56493260000000, float 0xBF56493260000000, float 0xBF56493260000000, float 0xBF56493260000000>
%tmp106 = fadd <4 x float> %tmp105, <float 0x3FA55406C0000000, float 0x3FA55406C0000000, float 0x3FA55406C0000000, float 0x3FA55406C0000000>
%tmp107 = fmul <4 x float> %tmp103, <float 0xBF29918DC0000000, float 0xBF29918DC0000000, float 0xBF29918DC0000000, float 0xBF29918DC0000000>
%tmp108 = fadd <4 x float> %tmp107, <float 0x3F81106840000000, float 0x3F81106840000000, float 0x3F81106840000000, float 0x3F81106840000000>
%tmp109 = fmul <4 x float> %tmp103, %tmp106
%tmp110 = fadd <4 x float> %tmp109, <float 0xBFDFFFFBE0000000, float 0xBFDFFFFBE0000000, float 0xBFDFFFFBE0000000, float 0xBFDFFFFBE0000000>
%tmp111 = fmul <4 x float> %tmp103, %tmp108
%tmp112 = fadd <4 x float> %tmp111, <float 0xBFC5555420000000, float 0xBFC5555420000000, float 0xBFC5555420000000, float 0xBFC5555420000000>
%tmp113 = fmul <4 x float> %tmp103, %tmp110
%tmp114 = fadd <4 x float> %tmp113, <float 1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 1.000000e+00>
%tmp115 = fmul <4 x float> %tmp104, %tmp112
%tmp116 = fadd <4 x float> %tmp102, %tmp115
%tmp117 = and <2 x i64> %tmp97, <i64 4294967297, i64 4294967297>
%tmp118 = bitcast <2 x i64> %tmp117 to <4 x i32>
%tmp119 = icmp eq <4 x i32> %tmp118, zeroinitializer
%tmp120 = sext <4 x i1> %tmp119 to <4 x i32>
%tmp121 = bitcast <4 x i32> %tmp120 to <4 x float>
%tmp122 = tail call <4 x float> @llvm.x86.sse41.blendvps(<4 x float> %tmp114, <4 x float> %tmp116, <4 x float> %tmp121) #2
%tmp123 = and <2 x i64> %tmp97, <i64 8589934594, i64 8589934594>
%tmp124 = bitcast <2 x i64> %tmp123 to <4 x i32>
%tmp125 = icmp eq <4 x i32> %tmp124, zeroinitializer
%tmp126 = sext <4 x i1> %tmp125 to <4 x i32>
%tmp127 = bitcast <4 x float> %tmp122 to <4 x i32>
%tmp128 = xor <4 x i32> %tmp127, <i32 -2147483648, i32 -2147483648, i32 -2147483648, i32 -2147483648>
%tmp129 = bitcast <4 x i32> %tmp128 to <4 x float>
%tmp130 = bitcast <4 x i32> %tmp126 to <4 x float>
%tmp131 = tail call <4 x float> @llvm.x86.sse41.blendvps(<4 x float> %tmp129, <4 x float> %tmp122, <4 x float> %tmp130) #2
%tmp132 = fadd <4 x float> %tmp88, %tmp131
%tmp133 = bitcast <4 x float> %tmp132 to <2 x double>
ret <2 x double> %tmp133
}
declare <4 x i32> @llvm.x86.sse2.cvttps2dq(<4 x float>)
declare <4 x float> @llvm.x86.sse2.cvtdq2ps(<4 x i32>)
declare <4 x float> @llvm.x86.sse41.blendvps(<4 x float>, <4 x float>, <4 x float>)
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s
; Check that we do not get excessive spilling from splitting of constant live ranges.
; CHECK-LABEL: PR24139:
; CHECK: # 16-byte Spill
; CHECK-NOT: # 16-byte Spill
; CHECK: retq
define <2 x double> @PR24139(<2 x double> %arg, <2 x double> %arg1, <2 x double> %arg2) {
%tmp = bitcast <2 x double> %arg to <4 x float>
%tmp3 = fmul <4 x float> %tmp, <float 0x3FE45F3060000000, float 0x3FE45F3060000000, float 0x3FE45F3060000000, float 0x3FE45F3060000000>
%tmp4 = bitcast <2 x double> %arg to <4 x i32>
%tmp5 = and <4 x i32> %tmp4, <i32 -2147483648, i32 -2147483648, i32 -2147483648, i32 -2147483648>
%tmp6 = or <4 x i32> %tmp5, <i32 1056964608, i32 1056964608, i32 1056964608, i32 1056964608>
%tmp7 = bitcast <4 x i32> %tmp6 to <4 x float>
%tmp8 = fadd <4 x float> %tmp3, %tmp7
%tmp9 = tail call <4 x i32> @llvm.x86.sse2.cvttps2dq(<4 x float> %tmp8) #2
%tmp10 = bitcast <4 x i32> %tmp9 to <2 x i64>
%tmp11 = tail call <4 x float> @llvm.x86.sse2.cvtdq2ps(<4 x i32> %tmp9) #2
%tmp12 = fmul <4 x float> %tmp11, <float 0x3FF921FB40000000, float 0x3FF921FB40000000, float 0x3FF921FB40000000, float 0x3FF921FB40000000>
%tmp13 = fsub <4 x float> %tmp, %tmp12
%tmp14 = fmul <4 x float> %tmp11, <float 0x3E74442D00000000, float 0x3E74442D00000000, float 0x3E74442D00000000, float 0x3E74442D00000000>
%tmp15 = fsub <4 x float> %tmp13, %tmp14
%tmp16 = fmul <4 x float> %tmp15, %tmp15
%tmp17 = fmul <4 x float> %tmp15, %tmp16
%tmp18 = fmul <4 x float> %tmp16, <float 0xBF56493260000000, float 0xBF56493260000000, float 0xBF56493260000000, float 0xBF56493260000000>
%tmp19 = fadd <4 x float> %tmp18, <float 0x3FA55406C0000000, float 0x3FA55406C0000000, float 0x3FA55406C0000000, float 0x3FA55406C0000000>
%tmp20 = fmul <4 x float> %tmp16, <float 0xBF29918DC0000000, float 0xBF29918DC0000000, float 0xBF29918DC0000000, float 0xBF29918DC0000000>
%tmp21 = fadd <4 x float> %tmp20, <float 0x3F81106840000000, float 0x3F81106840000000, float 0x3F81106840000000, float 0x3F81106840000000>
%tmp22 = fmul <4 x float> %tmp16, %tmp19
%tmp23 = fadd <4 x float> %tmp22, <float 0xBFDFFFFBE0000000, float 0xBFDFFFFBE0000000, float 0xBFDFFFFBE0000000, float 0xBFDFFFFBE0000000>
%tmp24 = fmul <4 x float> %tmp16, %tmp21
%tmp25 = fadd <4 x float> %tmp24, <float 0xBFC5555420000000, float 0xBFC5555420000000, float 0xBFC5555420000000, float 0xBFC5555420000000>
%tmp26 = fmul <4 x float> %tmp16, %tmp23
%tmp27 = fadd <4 x float> %tmp26, <float 1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 1.000000e+00>
%tmp28 = fmul <4 x float> %tmp17, %tmp25
%tmp29 = fadd <4 x float> %tmp15, %tmp28
%tmp30 = and <2 x i64> %tmp10, <i64 4294967297, i64 4294967297>
%tmp31 = bitcast <2 x i64> %tmp30 to <4 x i32>
%tmp32 = icmp eq <4 x i32> %tmp31, zeroinitializer
%tmp33 = sext <4 x i1> %tmp32 to <4 x i32>
%tmp34 = bitcast <4 x i32> %tmp33 to <4 x float>
%tmp35 = tail call <4 x float> @llvm.x86.sse41.blendvps(<4 x float> %tmp27, <4 x float> %tmp29, <4 x float> %tmp34) #2
%tmp36 = and <2 x i64> %tmp10, <i64 8589934594, i64 8589934594>
%tmp37 = bitcast <2 x i64> %tmp36 to <4 x i32>
%tmp38 = icmp eq <4 x i32> %tmp37, zeroinitializer
%tmp39 = sext <4 x i1> %tmp38 to <4 x i32>
%tmp40 = bitcast <4 x float> %tmp35 to <4 x i32>
%tmp41 = xor <4 x i32> %tmp40, <i32 -2147483648, i32 -2147483648, i32 -2147483648, i32 -2147483648>
%tmp42 = bitcast <4 x i32> %tmp41 to <4 x float>
%tmp43 = bitcast <4 x i32> %tmp39 to <4 x float>
%tmp44 = tail call <4 x float> @llvm.x86.sse41.blendvps(<4 x float> %tmp42, <4 x float> %tmp35, <4 x float> %tmp43) #2
%tmp45 = bitcast <2 x double> %arg1 to <4 x float>
%tmp46 = fmul <4 x float> %tmp45, <float 0x3FE45F3060000000, float 0x3FE45F3060000000, float 0x3FE45F3060000000, float 0x3FE45F3060000000>
%tmp47 = bitcast <2 x double> %arg1 to <4 x i32>
%tmp48 = and <4 x i32> %tmp47, <i32 -2147483648, i32 -2147483648, i32 -2147483648, i32 -2147483648>
%tmp49 = or <4 x i32> %tmp48, <i32 1056964608, i32 1056964608, i32 1056964608, i32 1056964608>
%tmp50 = bitcast <4 x i32> %tmp49 to <4 x float>
%tmp51 = fadd <4 x float> %tmp46, %tmp50
%tmp52 = tail call <4 x i32> @llvm.x86.sse2.cvttps2dq(<4 x float> %tmp51) #2
%tmp53 = bitcast <4 x i32> %tmp52 to <2 x i64>
%tmp54 = tail call <4 x float> @llvm.x86.sse2.cvtdq2ps(<4 x i32> %tmp52) #2
%tmp55 = fmul <4 x float> %tmp54, <float 0x3FF921FB40000000, float 0x3FF921FB40000000, float 0x3FF921FB40000000, float 0x3FF921FB40000000>
%tmp56 = fsub <4 x float> %tmp45, %tmp55
%tmp57 = fmul <4 x float> %tmp54, <float 0x3E74442D00000000, float 0x3E74442D00000000, float 0x3E74442D00000000, float 0x3E74442D00000000>
%tmp58 = fsub <4 x float> %tmp56, %tmp57
%tmp59 = fmul <4 x float> %tmp58, %tmp58
%tmp60 = fmul <4 x float> %tmp58, %tmp59
%tmp61 = fmul <4 x float> %tmp59, <float 0xBF56493260000000, float 0xBF56493260000000, float 0xBF56493260000000, float 0xBF56493260000000>
%tmp62 = fadd <4 x float> %tmp61, <float 0x3FA55406C0000000, float 0x3FA55406C0000000, float 0x3FA55406C0000000, float 0x3FA55406C0000000>
%tmp63 = fmul <4 x float> %tmp59, <float 0xBF29918DC0000000, float 0xBF29918DC0000000, float 0xBF29918DC0000000, float 0xBF29918DC0000000>
%tmp64 = fadd <4 x float> %tmp63, <float 0x3F81106840000000, float 0x3F81106840000000, float 0x3F81106840000000, float 0x3F81106840000000>
%tmp65 = fmul <4 x float> %tmp59, %tmp62
%tmp66 = fadd <4 x float> %tmp65, <float 0xBFDFFFFBE0000000, float 0xBFDFFFFBE0000000, float 0xBFDFFFFBE0000000, float 0xBFDFFFFBE0000000>
%tmp67 = fmul <4 x float> %tmp59, %tmp64
%tmp68 = fadd <4 x float> %tmp67, <float 0xBFC5555420000000, float 0xBFC5555420000000, float 0xBFC5555420000000, float 0xBFC5555420000000>
%tmp69 = fmul <4 x float> %tmp59, %tmp66
%tmp70 = fadd <4 x float> %tmp69, <float 1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 1.000000e+00>
%tmp71 = fmul <4 x float> %tmp60, %tmp68
%tmp72 = fadd <4 x float> %tmp58, %tmp71
%tmp73 = and <2 x i64> %tmp53, <i64 4294967297, i64 4294967297>
%tmp74 = bitcast <2 x i64> %tmp73 to <4 x i32>
%tmp75 = icmp eq <4 x i32> %tmp74, zeroinitializer
%tmp76 = sext <4 x i1> %tmp75 to <4 x i32>
%tmp77 = bitcast <4 x i32> %tmp76 to <4 x float>
%tmp78 = tail call <4 x float> @llvm.x86.sse41.blendvps(<4 x float> %tmp70, <4 x float> %tmp72, <4 x float> %tmp77) #2
%tmp79 = and <2 x i64> %tmp53, <i64 8589934594, i64 8589934594>
%tmp80 = bitcast <2 x i64> %tmp79 to <4 x i32>
%tmp81 = icmp eq <4 x i32> %tmp80, zeroinitializer
%tmp82 = sext <4 x i1> %tmp81 to <4 x i32>
%tmp83 = bitcast <4 x float> %tmp78 to <4 x i32>
%tmp84 = xor <4 x i32> %tmp83, <i32 -2147483648, i32 -2147483648, i32 -2147483648, i32 -2147483648>
%tmp85 = bitcast <4 x i32> %tmp84 to <4 x float>
%tmp86 = bitcast <4 x i32> %tmp82 to <4 x float>
%tmp87 = tail call <4 x float> @llvm.x86.sse41.blendvps(<4 x float> %tmp85, <4 x float> %tmp78, <4 x float> %tmp86) #2
%tmp88 = fadd <4 x float> %tmp44, %tmp87
%tmp89 = bitcast <2 x double> %arg2 to <4 x float>
%tmp90 = fmul <4 x float> %tmp89, <float 0x3FE45F3060000000, float 0x3FE45F3060000000, float 0x3FE45F3060000000, float 0x3FE45F3060000000>
%tmp91 = bitcast <2 x double> %arg2 to <4 x i32>
%tmp92 = and <4 x i32> %tmp91, <i32 -2147483648, i32 -2147483648, i32 -2147483648, i32 -2147483648>
%tmp93 = or <4 x i32> %tmp92, <i32 1056964608, i32 1056964608, i32 1056964608, i32 1056964608>
%tmp94 = bitcast <4 x i32> %tmp93 to <4 x float>
%tmp95 = fadd <4 x float> %tmp90, %tmp94
%tmp96 = tail call <4 x i32> @llvm.x86.sse2.cvttps2dq(<4 x float> %tmp95) #2
%tmp97 = bitcast <4 x i32> %tmp96 to <2 x i64>
%tmp98 = tail call <4 x float> @llvm.x86.sse2.cvtdq2ps(<4 x i32> %tmp96) #2
%tmp99 = fmul <4 x float> %tmp98, <float 0x3FF921FB40000000, float 0x3FF921FB40000000, float 0x3FF921FB40000000, float 0x3FF921FB40000000>
%tmp100 = fsub <4 x float> %tmp89, %tmp99
%tmp101 = fmul <4 x float> %tmp98, <float 0x3E74442D00000000, float 0x3E74442D00000000, float 0x3E74442D00000000, float 0x3E74442D00000000>
%tmp102 = fsub <4 x float> %tmp100, %tmp101
%tmp103 = fmul <4 x float> %tmp102, %tmp102
%tmp104 = fmul <4 x float> %tmp102, %tmp103
%tmp105 = fmul <4 x float> %tmp103, <float 0xBF56493260000000, float 0xBF56493260000000, float 0xBF56493260000000, float 0xBF56493260000000>
%tmp106 = fadd <4 x float> %tmp105, <float 0x3FA55406C0000000, float 0x3FA55406C0000000, float 0x3FA55406C0000000, float 0x3FA55406C0000000>
%tmp107 = fmul <4 x float> %tmp103, <float 0xBF29918DC0000000, float 0xBF29918DC0000000, float 0xBF29918DC0000000, float 0xBF29918DC0000000>
%tmp108 = fadd <4 x float> %tmp107, <float 0x3F81106840000000, float 0x3F81106840000000, float 0x3F81106840000000, float 0x3F81106840000000>
%tmp109 = fmul <4 x float> %tmp103, %tmp106
%tmp110 = fadd <4 x float> %tmp109, <float 0xBFDFFFFBE0000000, float 0xBFDFFFFBE0000000, float 0xBFDFFFFBE0000000, float 0xBFDFFFFBE0000000>
%tmp111 = fmul <4 x float> %tmp103, %tmp108
%tmp112 = fadd <4 x float> %tmp111, <float 0xBFC5555420000000, float 0xBFC5555420000000, float 0xBFC5555420000000, float 0xBFC5555420000000>
%tmp113 = fmul <4 x float> %tmp103, %tmp110
%tmp114 = fadd <4 x float> %tmp113, <float 1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 1.000000e+00>
%tmp115 = fmul <4 x float> %tmp104, %tmp112
%tmp116 = fadd <4 x float> %tmp102, %tmp115
%tmp117 = and <2 x i64> %tmp97, <i64 4294967297, i64 4294967297>
%tmp118 = bitcast <2 x i64> %tmp117 to <4 x i32>
%tmp119 = icmp eq <4 x i32> %tmp118, zeroinitializer
%tmp120 = sext <4 x i1> %tmp119 to <4 x i32>
%tmp121 = bitcast <4 x i32> %tmp120 to <4 x float>
%tmp122 = tail call <4 x float> @llvm.x86.sse41.blendvps(<4 x float> %tmp114, <4 x float> %tmp116, <4 x float> %tmp121) #2
%tmp123 = and <2 x i64> %tmp97, <i64 8589934594, i64 8589934594>
%tmp124 = bitcast <2 x i64> %tmp123 to <4 x i32>
%tmp125 = icmp eq <4 x i32> %tmp124, zeroinitializer
%tmp126 = sext <4 x i1> %tmp125 to <4 x i32>
%tmp127 = bitcast <4 x float> %tmp122 to <4 x i32>
%tmp128 = xor <4 x i32> %tmp127, <i32 -2147483648, i32 -2147483648, i32 -2147483648, i32 -2147483648>
%tmp129 = bitcast <4 x i32> %tmp128 to <4 x float>
%tmp130 = bitcast <4 x i32> %tmp126 to <4 x float>
%tmp131 = tail call <4 x float> @llvm.x86.sse41.blendvps(<4 x float> %tmp129, <4 x float> %tmp122, <4 x float> %tmp130) #2
%tmp132 = fadd <4 x float> %tmp88, %tmp131
%tmp133 = bitcast <4 x float> %tmp132 to <2 x double>
ret <2 x double> %tmp133
}
declare <4 x i32> @llvm.x86.sse2.cvttps2dq(<4 x float>)
declare <4 x float> @llvm.x86.sse2.cvtdq2ps(<4 x i32>)
declare <4 x float> @llvm.x86.sse41.blendvps(<4 x float>, <4 x float>, <4 x float>)

44
test/CodeGen/X86/statepoint-far-call.ll
View File

@ -1,22 +1,22 @@
; RUN: llc < %s | FileCheck %s
; Test to check that Statepoints with X64 far-immediate targets
; are lowered correctly to an indirect call via a scratch register.
target datalayout = "e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-pc-win64"
define void @test_far_call() gc "statepoint-example" {
; CHECK-LABEL: test_far_call
; CHECK: pushq %rax
; CHECK: movabsq $140727162896504, %rax
; CHECK: callq *%rax
; CHECK: popq %rax
; CHECK: retq
entry:
%safepoint_token = call token (i64, i32, void ()*, i32, i32, ...) @llvm.experimental.gc.statepoint.p0f_isVoidf(i64 0, i32 0, void ()* inttoptr (i64 140727162896504 to void ()*), i32 0, i32 0, i32 0, i32 0)
ret void
}
declare token @llvm.experimental.gc.statepoint.p0f_isVoidf(i64, i32, void ()*, i32, i32, ...)
; RUN: llc < %s | FileCheck %s
; Test to check that Statepoints with X64 far-immediate targets
; are lowered correctly to an indirect call via a scratch register.
target datalayout = "e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-pc-win64"
define void @test_far_call() gc "statepoint-example" {
; CHECK-LABEL: test_far_call
; CHECK: pushq %rax
; CHECK: movabsq $140727162896504, %rax
; CHECK: callq *%rax
; CHECK: popq %rax
; CHECK: retq
entry:
%safepoint_token = call token (i64, i32, void ()*, i32, i32, ...) @llvm.experimental.gc.statepoint.p0f_isVoidf(i64 0, i32 0, void ()* inttoptr (i64 140727162896504 to void ()*), i32 0, i32 0, i32 0, i32 0)
ret void
}
declare token @llvm.experimental.gc.statepoint.p0f_isVoidf(i64, i32, void ()*, i32, i32, ...)

82
test/CodeGen/X86/system-intrinsics-64-xsave.ll
View File

@ -1,41 +1,41 @@
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+xsave | FileCheck %s
define void @test_xsave(i8* %ptr, i32 %hi, i32 %lo) {
; CHECK-LABEL: test_xsave
; CHECK: movl %edx, %eax
; CHECK: movl %esi, %edx
; CHECK: xsave (%rdi)
call void @llvm.x86.xsave(i8* %ptr, i32 %hi, i32 %lo)
ret void;
}
declare void @llvm.x86.xsave(i8*, i32, i32)
define void @test_xsave64(i8* %ptr, i32 %hi, i32 %lo) {
; CHECK-LABEL: test_xsave64
; CHECK: movl %edx, %eax
; CHECK: movl %esi, %edx
; CHECK: xsave64 (%rdi)
call void @llvm.x86.xsave64(i8* %ptr, i32 %hi, i32 %lo)
ret void;
}
declare void @llvm.x86.xsave64(i8*, i32, i32)
define void @test_xrstor(i8* %ptr, i32 %hi, i32 %lo) {
; CHECK-LABEL: test_xrstor
; CHECK: movl %edx, %eax
; CHECK: movl %esi, %edx
; CHECK: xrstor (%rdi)
call void @llvm.x86.xrstor(i8* %ptr, i32 %hi, i32 %lo)
ret void;
}
declare void @llvm.x86.xrstor(i8*, i32, i32)
define void @test_xrstor64(i8* %ptr, i32 %hi, i32 %lo) {
; CHECK-LABEL: test_xrstor64
; CHECK: movl %edx, %eax
; CHECK: movl %esi, %edx
; CHECK: xrstor64 (%rdi)
call void @llvm.x86.xrstor64(i8* %ptr, i32 %hi, i32 %lo)
ret void;
}
declare void @llvm.x86.xrstor64(i8*, i32, i32)
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+xsave | FileCheck %s
define void @test_xsave(i8* %ptr, i32 %hi, i32 %lo) {
; CHECK-LABEL: test_xsave
; CHECK: movl %edx, %eax
; CHECK: movl %esi, %edx
; CHECK: xsave (%rdi)
call void @llvm.x86.xsave(i8* %ptr, i32 %hi, i32 %lo)
ret void;
}
declare void @llvm.x86.xsave(i8*, i32, i32)
define void @test_xsave64(i8* %ptr, i32 %hi, i32 %lo) {
; CHECK-LABEL: test_xsave64
; CHECK: movl %edx, %eax
; CHECK: movl %esi, %edx
; CHECK: xsave64 (%rdi)
call void @llvm.x86.xsave64(i8* %ptr, i32 %hi, i32 %lo)
ret void;
}
declare void @llvm.x86.xsave64(i8*, i32, i32)
define void @test_xrstor(i8* %ptr, i32 %hi, i32 %lo) {
; CHECK-LABEL: test_xrstor
; CHECK: movl %edx, %eax
; CHECK: movl %esi, %edx
; CHECK: xrstor (%rdi)
call void @llvm.x86.xrstor(i8* %ptr, i32 %hi, i32 %lo)
ret void;
}
declare void @llvm.x86.xrstor(i8*, i32, i32)
define void @test_xrstor64(i8* %ptr, i32 %hi, i32 %lo) {
; CHECK-LABEL: test_xrstor64
; CHECK: movl %edx, %eax
; CHECK: movl %esi, %edx
; CHECK: xrstor64 (%rdi)
call void @llvm.x86.xrstor64(i8* %ptr, i32 %hi, i32 %lo)
ret void;
}
declare void @llvm.x86.xrstor64(i8*, i32, i32)

42
test/CodeGen/X86/system-intrinsics-64-xsavec.ll
View File

@ -1,21 +1,21 @@
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+xsave,+xsavec | FileCheck %s
define void @test_xsavec(i8* %ptr, i32 %hi, i32 %lo) {
; CHECK-LABEL: test_xsavec
; CHECK: movl %edx, %eax
; CHECK: movl %esi, %edx
; CHECK: xsavec (%rdi)
call void @llvm.x86.xsavec(i8* %ptr, i32 %hi, i32 %lo)
ret void;
}
declare void @llvm.x86.xsavec(i8*, i32, i32)
define void @test_xsavec64(i8* %ptr, i32 %hi, i32 %lo) {
; CHECK-LABEL: test_xsavec64
; CHECK: movl %edx, %eax
; CHECK: movl %esi, %edx
; CHECK: xsavec64 (%rdi)
call void @llvm.x86.xsavec64(i8* %ptr, i32 %hi, i32 %lo)
ret void;
}
declare void @llvm.x86.xsavec64(i8*, i32, i32)
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+xsave,+xsavec | FileCheck %s
define void @test_xsavec(i8* %ptr, i32 %hi, i32 %lo) {
; CHECK-LABEL: test_xsavec
; CHECK: movl %edx, %eax
; CHECK: movl %esi, %edx
; CHECK: xsavec (%rdi)
call void @llvm.x86.xsavec(i8* %ptr, i32 %hi, i32 %lo)
ret void;
}
declare void @llvm.x86.xsavec(i8*, i32, i32)
define void @test_xsavec64(i8* %ptr, i32 %hi, i32 %lo) {
; CHECK-LABEL: test_xsavec64
; CHECK: movl %edx, %eax
; CHECK: movl %esi, %edx
; CHECK: xsavec64 (%rdi)
call void @llvm.x86.xsavec64(i8* %ptr, i32 %hi, i32 %lo)
ret void;
}
declare void @llvm.x86.xsavec64(i8*, i32, i32)

42
test/CodeGen/X86/system-intrinsics-64-xsaveopt.ll
View File

@ -1,21 +1,21 @@
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+xsaveopt | FileCheck %s
define void @test_xsaveopt(i8* %ptr, i32 %hi, i32 %lo) {
; CHECK-LABEL: test_xsaveopt
; CHECK: movl %edx, %eax
; CHECK: movl %esi, %edx
; CHECK: xsaveopt (%rdi)
call void @llvm.x86.xsaveopt(i8* %ptr, i32 %hi, i32 %lo)
ret void;
}
declare void @llvm.x86.xsaveopt(i8*, i32, i32)
define void @test_xsaveopt64(i8* %ptr, i32 %hi, i32 %lo) {
; CHECK-LABEL: test_xsaveopt64
; CHECK: movl %edx, %eax
; CHECK: movl %esi, %edx
; CHECK: xsaveopt64 (%rdi)
call void @llvm.x86.xsaveopt64(i8* %ptr, i32 %hi, i32 %lo)
ret void;
}
declare void @llvm.x86.xsaveopt64(i8*, i32, i32)
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+xsaveopt | FileCheck %s
define void @test_xsaveopt(i8* %ptr, i32 %hi, i32 %lo) {
; CHECK-LABEL: test_xsaveopt
; CHECK: movl %edx, %eax
; CHECK: movl %esi, %edx
; CHECK: xsaveopt (%rdi)
call void @llvm.x86.xsaveopt(i8* %ptr, i32 %hi, i32 %lo)
ret void;
}
declare void @llvm.x86.xsaveopt(i8*, i32, i32)
define void @test_xsaveopt64(i8* %ptr, i32 %hi, i32 %lo) {
; CHECK-LABEL: test_xsaveopt64
; CHECK: movl %edx, %eax
; CHECK: movl %esi, %edx
; CHECK: xsaveopt64 (%rdi)
call void @llvm.x86.xsaveopt64(i8* %ptr, i32 %hi, i32 %lo)
ret void;
}
declare void @llvm.x86.xsaveopt64(i8*, i32, i32)

82
test/CodeGen/X86/system-intrinsics-64-xsaves.ll
View File

@ -1,41 +1,41 @@
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+xsave,+xsaves | FileCheck %s
define void @test_xsaves(i8* %ptr, i32 %hi, i32 %lo) {
; CHECK-LABEL: test_xsaves
; CHECK: movl %edx, %eax
; CHECK: movl %esi, %edx
; CHECK: xsaves (%rdi)
call void @llvm.x86.xsaves(i8* %ptr, i32 %hi, i32 %lo)
ret void;
}
declare void @llvm.x86.xsaves(i8*, i32, i32)
define void @test_xsaves64(i8* %ptr, i32 %hi, i32 %lo) {
; CHECK-LABEL: test_xsaves64
; CHECK: movl %edx, %eax
; CHECK: movl %esi, %edx
; CHECK: xsaves64 (%rdi)
call void @llvm.x86.xsaves64(i8* %ptr, i32 %hi, i32 %lo)
ret void;
}
declare void @llvm.x86.xsaves64(i8*, i32, i32)
define void @test_xrstors(i8* %ptr, i32 %hi, i32 %lo) {
; CHECK-LABEL: test_xrstors
; CHECK: movl %edx, %eax
; CHECK: movl %esi, %edx
; CHECK: xrstors (%rdi)
call void @llvm.x86.xrstors(i8* %ptr, i32 %hi, i32 %lo)
ret void;
}
declare void @llvm.x86.xrstors(i8*, i32, i32)
define void @test_xrstors64(i8* %ptr, i32 %hi, i32 %lo) {
; CHECK-LABEL: test_xrstors64
; CHECK: movl %edx, %eax
; CHECK: movl %esi, %edx
; CHECK: xrstors64 (%rdi)
call void @llvm.x86.xrstors64(i8* %ptr, i32 %hi, i32 %lo)
ret void;
}
declare void @llvm.x86.xrstors64(i8*, i32, i32)
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+xsave,+xsaves | FileCheck %s
define void @test_xsaves(i8* %ptr, i32 %hi, i32 %lo) {
; CHECK-LABEL: test_xsaves
; CHECK: movl %edx, %eax
; CHECK: movl %esi, %edx
; CHECK: xsaves (%rdi)
call void @llvm.x86.xsaves(i8* %ptr, i32 %hi, i32 %lo)
ret void;
}
declare void @llvm.x86.xsaves(i8*, i32, i32)
define void @test_xsaves64(i8* %ptr, i32 %hi, i32 %lo) {
; CHECK-LABEL: test_xsaves64
; CHECK: movl %edx, %eax
; CHECK: movl %esi, %edx
; CHECK: xsaves64 (%rdi)
call void @llvm.x86.xsaves64(i8* %ptr, i32 %hi, i32 %lo)
ret void;
}
declare void @llvm.x86.xsaves64(i8*, i32, i32)
define void @test_xrstors(i8* %ptr, i32 %hi, i32 %lo) {
; CHECK-LABEL: test_xrstors
; CHECK: movl %edx, %eax
; CHECK: movl %esi, %edx
; CHECK: xrstors (%rdi)
call void @llvm.x86.xrstors(i8* %ptr, i32 %hi, i32 %lo)
ret void;
}
declare void @llvm.x86.xrstors(i8*, i32, i32)
define void @test_xrstors64(i8* %ptr, i32 %hi, i32 %lo) {
; CHECK-LABEL: test_xrstors64
; CHECK: movl %edx, %eax
; CHECK: movl %esi, %edx
; CHECK: xrstors64 (%rdi)
call void @llvm.x86.xrstors64(i8* %ptr, i32 %hi, i32 %lo)
ret void;
}
declare void @llvm.x86.xrstors64(i8*, i32, i32)

46
test/CodeGen/X86/system-intrinsics-xsave.ll
View File

@ -1,23 +1,23 @@
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+xsave | FileCheck %s
define void @test_xsave(i8* %ptr, i32 %hi, i32 %lo) {
; CHECK-LABEL: test_xsave
; CHECK: movl 8(%esp), %edx
; CHECK: movl 12(%esp), %eax
; CHECK: movl 4(%esp), %ecx
; CHECK: xsave (%ecx)
call void @llvm.x86.xsave(i8* %ptr, i32 %hi, i32 %lo)
ret void;
}
declare void @llvm.x86.xsave(i8*, i32, i32)
define void @test_xrstor(i8* %ptr, i32 %hi, i32 %lo) {
; CHECK-LABEL: test_xrstor
; CHECK: movl 8(%esp), %edx
; CHECK: movl 12(%esp), %eax
; CHECK: movl 4(%esp), %ecx
; CHECK: xrstor (%ecx)
call void @llvm.x86.xrstor(i8* %ptr, i32 %hi, i32 %lo)
ret void;
}
declare void @llvm.x86.xrstor(i8*, i32, i32)
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+xsave | FileCheck %s
define void @test_xsave(i8* %ptr, i32 %hi, i32 %lo) {
; CHECK-LABEL: test_xsave
; CHECK: movl 8(%esp), %edx
; CHECK: movl 12(%esp), %eax
; CHECK: movl 4(%esp), %ecx
; CHECK: xsave (%ecx)
call void @llvm.x86.xsave(i8* %ptr, i32 %hi, i32 %lo)
ret void;
}
declare void @llvm.x86.xsave(i8*, i32, i32)
define void @test_xrstor(i8* %ptr, i32 %hi, i32 %lo) {
; CHECK-LABEL: test_xrstor
; CHECK: movl 8(%esp), %edx
; CHECK: movl 12(%esp), %eax
; CHECK: movl 4(%esp), %ecx
; CHECK: xrstor (%ecx)
call void @llvm.x86.xrstor(i8* %ptr, i32 %hi, i32 %lo)
ret void;
}
declare void @llvm.x86.xrstor(i8*, i32, i32)

24
test/CodeGen/X86/system-intrinsics-xsavec.ll
View File

@ -1,12 +1,12 @@
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+xsave,+xsavec | FileCheck %s
define void @test_xsavec(i8* %ptr, i32 %hi, i32 %lo) {
; CHECK-LABEL: test_xsavec
; CHECK: movl 8(%esp), %edx
; CHECK: movl 12(%esp), %eax
; CHECK: movl 4(%esp), %ecx
; CHECK: xsavec (%ecx)
call void @llvm.x86.xsavec(i8* %ptr, i32 %hi, i32 %lo)
ret void;
}
declare void @llvm.x86.xsavec(i8*, i32, i32)
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+xsave,+xsavec | FileCheck %s
define void @test_xsavec(i8* %ptr, i32 %hi, i32 %lo) {
; CHECK-LABEL: test_xsavec
; CHECK: movl 8(%esp), %edx
; CHECK: movl 12(%esp), %eax
; CHECK: movl 4(%esp), %ecx
; CHECK: xsavec (%ecx)
call void @llvm.x86.xsavec(i8* %ptr, i32 %hi, i32 %lo)
ret void;
}
declare void @llvm.x86.xsavec(i8*, i32, i32)

24
test/CodeGen/X86/system-intrinsics-xsaveopt.ll
View File

@ -1,12 +1,12 @@
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+xsave,+xsaveopt | FileCheck %s
define void @test_xsaveopt(i8* %ptr, i32 %hi, i32 %lo) {
; CHECK-LABEL: test_xsaveopt
; CHECK: movl 8(%esp), %edx
; CHECK: movl 12(%esp), %eax
; CHECK: movl 4(%esp), %ecx
; CHECK: xsaveopt (%ecx)
call void @llvm.x86.xsaveopt(i8* %ptr, i32 %hi, i32 %lo)
ret void;
}
declare void @llvm.x86.xsaveopt(i8*, i32, i32)
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+xsave,+xsaveopt | FileCheck %s
define void @test_xsaveopt(i8* %ptr, i32 %hi, i32 %lo) {
; CHECK-LABEL: test_xsaveopt
; CHECK: movl 8(%esp), %edx
; CHECK: movl 12(%esp), %eax
; CHECK: movl 4(%esp), %ecx
; CHECK: xsaveopt (%ecx)
call void @llvm.x86.xsaveopt(i8* %ptr, i32 %hi, i32 %lo)
ret void;
}
declare void @llvm.x86.xsaveopt(i8*, i32, i32)

46
test/CodeGen/X86/system-intrinsics-xsaves.ll
View File

@ -1,23 +1,23 @@
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+xsave,+xsaves | FileCheck %s
define void @test_xsaves(i8* %ptr, i32 %hi, i32 %lo) {
; CHECK-LABEL: test_xsaves
; CHECK: movl 8(%esp), %edx
; CHECK: movl 12(%esp), %eax
; CHECK: movl 4(%esp), %ecx
; CHECK: xsaves (%ecx)
call void @llvm.x86.xsaves(i8* %ptr, i32 %hi, i32 %lo)
ret void;
}
declare void @llvm.x86.xsaves(i8*, i32, i32)
define void @test_xrstors(i8* %ptr, i32 %hi, i32 %lo) {
; CHECK-LABEL: test_xrstors
; CHECK: movl 8(%esp), %edx
; CHECK: movl 12(%esp), %eax
; CHECK: movl 4(%esp), %ecx
; CHECK: xrstors (%ecx)
call void @llvm.x86.xrstors(i8* %ptr, i32 %hi, i32 %lo)
ret void;
}
declare void @llvm.x86.xrstors(i8*, i32, i32)
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+xsave,+xsaves | FileCheck %s
define void @test_xsaves(i8* %ptr, i32 %hi, i32 %lo) {
; CHECK-LABEL: test_xsaves
; CHECK: movl 8(%esp), %edx
; CHECK: movl 12(%esp), %eax
; CHECK: movl 4(%esp), %ecx
; CHECK: xsaves (%ecx)
call void @llvm.x86.xsaves(i8* %ptr, i32 %hi, i32 %lo)
ret void;
}
declare void @llvm.x86.xsaves(i8*, i32, i32)
define void @test_xrstors(i8* %ptr, i32 %hi, i32 %lo) {
; CHECK-LABEL: test_xrstors
; CHECK: movl 8(%esp), %edx
; CHECK: movl 12(%esp), %eax
; CHECK: movl 4(%esp), %ecx
; CHECK: xrstors (%ecx)
call void @llvm.x86.xrstors(i8* %ptr, i32 %hi, i32 %lo)
ret void;
}
declare void @llvm.x86.xrstors(i8*, i32, i32)

64
test/CodeGen/X86/vec_partial.ll
View File

@ -1,32 +1,32 @@
; RUN: llc < %s -mtriple=x86_64-unknown-unknown | FileCheck %s
; PR11580
define <3 x float> @addf3(<3 x float> %x) {
; CHECK-LABEL: addf3
; CHECK: # BB#0:
; CHECK-NEXT: addps .LCPI0_0(%rip), %xmm0
; CHECK-NEXT: retq
entry:
%add = fadd <3 x float> %x, <float 1.000000e+00, float 1.000000e+00, float 1.000000e+00>
ret <3 x float> %add
}
; PR11580
define <4 x float> @cvtf3_f4(<3 x float> %x) {
; CHECK-LABEL: cvtf3_f4
; CHECK: # BB#0:
; CHECK-NEXT: retq
entry:
%extractVec = shufflevector <3 x float> %x, <3 x float> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 undef>
ret <4 x float> %extractVec
}
; PR11580
define <3 x float> @cvtf4_f3(<4 x float> %x) {
; CHECK-LABEL: cvtf4_f3
; CHECK: # BB#0:
; CHECK-NEXT: retq
entry:
%extractVec = shufflevector <4 x float> %x, <4 x float> undef, <3 x i32> <i32 0, i32 1, i32 2>
ret <3 x float> %extractVec
}
; RUN: llc < %s -mtriple=x86_64-unknown-unknown | FileCheck %s
; PR11580
define <3 x float> @addf3(<3 x float> %x) {
; CHECK-LABEL: addf3
; CHECK: # BB#0:
; CHECK-NEXT: addps .LCPI0_0(%rip), %xmm0
; CHECK-NEXT: retq
entry:
%add = fadd <3 x float> %x, <float 1.000000e+00, float 1.000000e+00, float 1.000000e+00>
ret <3 x float> %add
}
; PR11580
define <4 x float> @cvtf3_f4(<3 x float> %x) {
; CHECK-LABEL: cvtf3_f4
; CHECK: # BB#0:
; CHECK-NEXT: retq
entry:
%extractVec = shufflevector <3 x float> %x, <3 x float> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 undef>
ret <4 x float> %extractVec
}
; PR11580
define <3 x float> @cvtf4_f3(<4 x float> %x) {
; CHECK-LABEL: cvtf4_f3
; CHECK: # BB#0:
; CHECK-NEXT: retq
entry:
%extractVec = shufflevector <4 x float> %x, <4 x float> undef, <3 x i32> <i32 0, i32 1, i32 2>
ret <3 x float> %extractVec
}

238
test/CodeGen/X86/vec_reassociate.ll
View File

@ -1,119 +1,119 @@
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+sse4.1 | FileCheck %s
define <4 x i32> @add_4i32(<4 x i32> %a0, <4 x i32> %a1) {
;CHECK-LABEL: @add_4i32
;CHECK: # BB#0:
;CHECK-NEXT: paddd %xmm1, %xmm0
;CHECK-NEXT: retq
%1 = add <4 x i32> %a0, <i32 1, i32 -2, i32 3, i32 -4>
%2 = add <4 x i32> %a1, <i32 -1, i32 2, i32 -3, i32 4>
%3 = add <4 x i32> %1, %2
ret <4 x i32> %3
}
define <4 x i32> @add_4i32_commute(<4 x i32> %a0, <4 x i32> %a1) {
;CHECK-LABEL: @add_4i32_commute
;CHECK: # BB#0:
;CHECK-NEXT: paddd %xmm1, %xmm0
;CHECK-NEXT: retq
%1 = add <4 x i32> <i32 1, i32 -2, i32 3, i32 -4>, %a0
%2 = add <4 x i32> <i32 -1, i32 2, i32 -3, i32 4>, %a1
%3 = add <4 x i32> %1, %2
ret <4 x i32> %3
}
define <4 x i32> @mul_4i32(<4 x i32> %a0, <4 x i32> %a1) {
;CHECK-LABEL: @mul_4i32
;CHECK: # BB#0:
;CHECK-NEXT: pmulld %xmm1, %xmm0
;CHECK-NEXT: pmulld .LCPI2_0(%rip), %xmm0
;CHECK-NEXT: retq
%1 = mul <4 x i32> %a0, <i32 1, i32 2, i32 3, i32 4>
%2 = mul <4 x i32> %a1, <i32 4, i32 3, i32 2, i32 1>
%3 = mul <4 x i32> %1, %2
ret <4 x i32> %3
}
define <4 x i32> @mul_4i32_commute(<4 x i32> %a0, <4 x i32> %a1) {
;CHECK-LABEL: @mul_4i32_commute
;CHECK: # BB#0:
;CHECK-NEXT: pmulld %xmm1, %xmm0
;CHECK-NEXT: pmulld .LCPI3_0(%rip), %xmm0
;CHECK-NEXT: retq
%1 = mul <4 x i32> <i32 1, i32 2, i32 3, i32 4>, %a0
%2 = mul <4 x i32> <i32 4, i32 3, i32 2, i32 1>, %a1
%3 = mul <4 x i32> %1, %2
ret <4 x i32> %3
}
define <4 x i32> @and_4i32(<4 x i32> %a0, <4 x i32> %a1) {
;CHECK-LABEL: @and_4i32
;CHECK: # BB#0:
;CHECK-NEXT: andps %xmm1, %xmm0
;CHECK-NEXT: andps .LCPI4_0(%rip), %xmm0
;CHECK-NEXT: retq
%1 = and <4 x i32> %a0, <i32 -2, i32 -2, i32 3, i32 3>
%2 = and <4 x i32> %a1, <i32 -1, i32 -1, i32 1, i32 1>
%3 = and <4 x i32> %1, %2
ret <4 x i32> %3
}
define <4 x i32> @and_4i32_commute(<4 x i32> %a0, <4 x i32> %a1) {
;CHECK-LABEL: @and_4i32_commute
;CHECK: # BB#0:
;CHECK-NEXT: andps %xmm1, %xmm0
;CHECK-NEXT: andps .LCPI5_0(%rip), %xmm0
;CHECK-NEXT: retq
%1 = and <4 x i32> <i32 -2, i32 -2, i32 3, i32 3>, %a0
%2 = and <4 x i32> <i32 -1, i32 -1, i32 1, i32 1>, %a1
%3 = and <4 x i32> %1, %2
ret <4 x i32> %3
}
define <4 x i32> @or_4i32(<4 x i32> %a0, <4 x i32> %a1) {
;CHECK-LABEL: @or_4i32
;CHECK: # BB#0:
;CHECK-NEXT: orps %xmm1, %xmm0
;CHECK-NEXT: orps .LCPI6_0(%rip), %xmm0
;CHECK-NEXT: retq
%1 = or <4 x i32> %a0, <i32 -2, i32 -2, i32 3, i32 3>
%2 = or <4 x i32> %a1, <i32 -1, i32 -1, i32 1, i32 1>
%3 = or <4 x i32> %1, %2
ret <4 x i32> %3
}
define <4 x i32> @or_4i32_commute(<4 x i32> %a0, <4 x i32> %a1) {
;CHECK-LABEL: @or_4i32_commute
;CHECK: # BB#0:
;CHECK-NEXT: orps %xmm1, %xmm0
;CHECK-NEXT: orps .LCPI7_0(%rip), %xmm0
;CHECK-NEXT: retq
%1 = or <4 x i32> <i32 -2, i32 -2, i32 3, i32 3>, %a0
%2 = or <4 x i32> <i32 -1, i32 -1, i32 1, i32 1>, %a1
%3 = or <4 x i32> %1, %2
ret <4 x i32> %3
}
define <4 x i32> @xor_4i32(<4 x i32> %a0, <4 x i32> %a1) {
;CHECK-LABEL: @xor_4i32
;CHECK: # BB#0:
;CHECK-NEXT: xorps %xmm1, %xmm0
;CHECK-NEXT: xorps .LCPI8_0(%rip), %xmm0
;CHECK-NEXT: retq
%1 = xor <4 x i32> %a0, <i32 -2, i32 -2, i32 3, i32 3>
%2 = xor <4 x i32> %a1, <i32 -1, i32 -1, i32 1, i32 1>
%3 = xor <4 x i32> %1, %2
ret <4 x i32> %3
}
define <4 x i32> @xor_4i32_commute(<4 x i32> %a0, <4 x i32> %a1) {
;CHECK-LABEL: @xor_4i32_commute
;CHECK: # BB#0:
;CHECK-NEXT: xorps %xmm1, %xmm0
;CHECK-NEXT: xorps .LCPI9_0(%rip), %xmm0
;CHECK-NEXT: retq
%1 = xor <4 x i32> <i32 -2, i32 -2, i32 3, i32 3>, %a0
%2 = xor <4 x i32> <i32 -1, i32 -1, i32 1, i32 1>, %a1
%3 = xor <4 x i32> %1, %2
ret <4 x i32> %3
}
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+sse4.1 | FileCheck %s
define <4 x i32> @add_4i32(<4 x i32> %a0, <4 x i32> %a1) {
;CHECK-LABEL: @add_4i32
;CHECK: # BB#0:
;CHECK-NEXT: paddd %xmm1, %xmm0
;CHECK-NEXT: retq
%1 = add <4 x i32> %a0, <i32 1, i32 -2, i32 3, i32 -4>
%2 = add <4 x i32> %a1, <i32 -1, i32 2, i32 -3, i32 4>
%3 = add <4 x i32> %1, %2
ret <4 x i32> %3
}
define <4 x i32> @add_4i32_commute(<4 x i32> %a0, <4 x i32> %a1) {
;CHECK-LABEL: @add_4i32_commute
;CHECK: # BB#0:
;CHECK-NEXT: paddd %xmm1, %xmm0
;CHECK-NEXT: retq
%1 = add <4 x i32> <i32 1, i32 -2, i32 3, i32 -4>, %a0
%2 = add <4 x i32> <i32 -1, i32 2, i32 -3, i32 4>, %a1
%3 = add <4 x i32> %1, %2
ret <4 x i32> %3
}
define <4 x i32> @mul_4i32(<4 x i32> %a0, <4 x i32> %a1) {
;CHECK-LABEL: @mul_4i32
;CHECK: # BB#0:
;CHECK-NEXT: pmulld %xmm1, %xmm0
;CHECK-NEXT: pmulld .LCPI2_0(%rip), %xmm0
;CHECK-NEXT: retq
%1 = mul <4 x i32> %a0, <i32 1, i32 2, i32 3, i32 4>
%2 = mul <4 x i32> %a1, <i32 4, i32 3, i32 2, i32 1>
%3 = mul <4 x i32> %1, %2
ret <4 x i32> %3
}
define <4 x i32> @mul_4i32_commute(<4 x i32> %a0, <4 x i32> %a1) {
;CHECK-LABEL: @mul_4i32_commute
;CHECK: # BB#0:
;CHECK-NEXT: pmulld %xmm1, %xmm0
;CHECK-NEXT: pmulld .LCPI3_0(%rip), %xmm0
;CHECK-NEXT: retq
%1 = mul <4 x i32> <i32 1, i32 2, i32 3, i32 4>, %a0
%2 = mul <4 x i32> <i32 4, i32 3, i32 2, i32 1>, %a1
%3 = mul <4 x i32> %1, %2
ret <4 x i32> %3
}
define <4 x i32> @and_4i32(<4 x i32> %a0, <4 x i32> %a1) {
;CHECK-LABEL: @and_4i32
;CHECK: # BB#0:
;CHECK-NEXT: andps %xmm1, %xmm0
;CHECK-NEXT: andps .LCPI4_0(%rip), %xmm0
;CHECK-NEXT: retq
%1 = and <4 x i32> %a0, <i32 -2, i32 -2, i32 3, i32 3>
%2 = and <4 x i32> %a1, <i32 -1, i32 -1, i32 1, i32 1>
%3 = and <4 x i32> %1, %2
ret <4 x i32> %3
}
define <4 x i32> @and_4i32_commute(<4 x i32> %a0, <4 x i32> %a1) {
;CHECK-LABEL: @and_4i32_commute
;CHECK: # BB#0:
;CHECK-NEXT: andps %xmm1, %xmm0
;CHECK-NEXT: andps .LCPI5_0(%rip), %xmm0
;CHECK-NEXT: retq
%1 = and <4 x i32> <i32 -2, i32 -2, i32 3, i32 3>, %a0
%2 = and <4 x i32> <i32 -1, i32 -1, i32 1, i32 1>, %a1
%3 = and <4 x i32> %1, %2
ret <4 x i32> %3
}
define <4 x i32> @or_4i32(<4 x i32> %a0, <4 x i32> %a1) {
;CHECK-LABEL: @or_4i32
;CHECK: # BB#0:
;CHECK-NEXT: orps %xmm1, %xmm0
;CHECK-NEXT: orps .LCPI6_0(%rip), %xmm0
;CHECK-NEXT: retq
%1 = or <4 x i32> %a0, <i32 -2, i32 -2, i32 3, i32 3>
%2 = or <4 x i32> %a1, <i32 -1, i32 -1, i32 1, i32 1>
%3 = or <4 x i32> %1, %2
ret <4 x i32> %3
}
define <4 x i32> @or_4i32_commute(<4 x i32> %a0, <4 x i32> %a1) {
;CHECK-LABEL: @or_4i32_commute
;CHECK: # BB#0:
;CHECK-NEXT: orps %xmm1, %xmm0
;CHECK-NEXT: orps .LCPI7_0(%rip), %xmm0
;CHECK-NEXT: retq
%1 = or <4 x i32> <i32 -2, i32 -2, i32 3, i32 3>, %a0
%2 = or <4 x i32> <i32 -1, i32 -1, i32 1, i32 1>, %a1
%3 = or <4 x i32> %1, %2
ret <4 x i32> %3
}
define <4 x i32> @xor_4i32(<4 x i32> %a0, <4 x i32> %a1) {
;CHECK-LABEL: @xor_4i32
;CHECK: # BB#0:
;CHECK-NEXT: xorps %xmm1, %xmm0
;CHECK-NEXT: xorps .LCPI8_0(%rip), %xmm0
;CHECK-NEXT: retq
%1 = xor <4 x i32> %a0, <i32 -2, i32 -2, i32 3, i32 3>
%2 = xor <4 x i32> %a1, <i32 -1, i32 -1, i32 1, i32 1>
%3 = xor <4 x i32> %1, %2
ret <4 x i32> %3
}
define <4 x i32> @xor_4i32_commute(<4 x i32> %a0, <4 x i32> %a1) {
;CHECK-LABEL: @xor_4i32_commute
;CHECK: # BB#0:
;CHECK-NEXT: xorps %xmm1, %xmm0
;CHECK-NEXT: xorps .LCPI9_0(%rip), %xmm0
;CHECK-NEXT: retq
%1 = xor <4 x i32> <i32 -2, i32 -2, i32 3, i32 3>, %a0
%2 = xor <4 x i32> <i32 -1, i32 -1, i32 1, i32 1>, %a1
%3 = xor <4 x i32> %1, %2
ret <4 x i32> %3
}

158
test/CodeGen/X86/x86-32-intrcc.ll
View File

@ -1,79 +1,79 @@
; RUN: llc -mtriple=i686-unknown-unknown < %s | FileCheck %s
; RUN: llc -mtriple=i686-unknown-unknown -O0 < %s | FileCheck %s -check-prefix=CHECK0
%struct.interrupt_frame = type { i32, i32, i32, i32, i32 }
@llvm.used = appending global [3 x i8*] [i8* bitcast (void (%struct.interrupt_frame*)* @test_isr_no_ecode to i8*), i8* bitcast (void (%struct.interrupt_frame*, i32)* @test_isr_ecode to i8*), i8* bitcast (void (%struct.interrupt_frame*, i32)* @test_isr_clobbers to i8*)], section "llvm.metadata"
; Spills eax, putting original esp at +4.
; No stack adjustment if declared with no error code
define x86_intrcc void @test_isr_no_ecode(%struct.interrupt_frame* %frame) {
; CHECK-LABEL: test_isr_no_ecode:
; CHECK: pushl %eax
; CHECK: movl 12(%esp), %eax
; CHECK: popl %eax
; CHECK: iretl
; CHECK0-LABEL: test_isr_no_ecode:
; CHECK0: pushl %eax
; CHECK0: leal 4(%esp), %eax
; CHECK0: movl 8(%eax), %eax
; CHECK0: popl %eax
; CHECK0: iretl
%pflags = getelementptr inbounds %struct.interrupt_frame, %struct.interrupt_frame* %frame, i32 0, i32 2
%flags = load i32, i32* %pflags, align 4
call void asm sideeffect "", "r"(i32 %flags)
ret void
}
; Spills eax and ecx, putting original esp at +8. Stack is adjusted up another 4 bytes
; before return, popping the error code.
define x86_intrcc void @test_isr_ecode(%struct.interrupt_frame* %frame, i32 %ecode) {
; CHECK-LABEL: test_isr_ecode
; CHECK: pushl %ecx
; CHECK: pushl %eax
; CHECK: movl 8(%esp), %eax
; CHECK: movl 20(%esp), %ecx
; CHECK: popl %eax
; CHECK: popl %ecx
; CHECK: addl $4, %esp
; CHECK: iretl
; CHECK0-LABEL: test_isr_ecode
; CHECK0: pushl %ecx
; CHECK0: pushl %eax
; CHECK0: movl 8(%esp), %eax
; CHECK0: leal 12(%esp), %ecx
; CHECK0: movl 8(%ecx), %ecx
; CHECK0: popl %eax
; CHECK0: popl %ecx
; CHECK0: addl $4, %esp
; CHECK0: iretl
%pflags = getelementptr inbounds %struct.interrupt_frame, %struct.interrupt_frame* %frame, i32 0, i32 2
%flags = load i32, i32* %pflags, align 4
call x86_fastcallcc void asm sideeffect "", "r,r"(i32 %flags, i32 %ecode)
ret void
}
; All clobbered registers must be saved
define x86_intrcc void @test_isr_clobbers(%struct.interrupt_frame* %frame, i32 %ecode) {
call void asm sideeffect "", "~{eax},~{ebx},~{ebp}"()
; CHECK-LABEL: test_isr_clobbers
; CHECK-SSE-NEXT: pushl %ebp
; CHECK-SSE-NEXT: pushl %ebx
; CHECK-SSE-NEXT; pushl %eax
; CHECK-SSE-NEXT: popl %eax
; CHECK-SSE-NEXT: popl %ebx
; CHECK-SSE-NEXT: popl %ebp
; CHECK-SSE-NEXT: addl $4, %esp
; CHECK-SSE-NEXT: iretl
; CHECK0-LABEL: test_isr_clobbers
; CHECK0-SSE-NEXT: pushl %ebp
; CHECK0-SSE-NEXT: pushl %ebx
; CHECK0-SSE-NEXT; pushl %eax
; CHECK0-SSE-NEXT: popl %eax
; CHECK0-SSE-NEXT: popl %ebx
; CHECK0-SSE-NEXT: popl %ebp
; CHECK0-SSE-NEXT: addl $4, %esp
; CHECK0-SSE-NEXT: iretl
ret void
}
; RUN: llc -mtriple=i686-unknown-unknown < %s | FileCheck %s
; RUN: llc -mtriple=i686-unknown-unknown -O0 < %s | FileCheck %s -check-prefix=CHECK0
%struct.interrupt_frame = type { i32, i32, i32, i32, i32 }
@llvm.used = appending global [3 x i8*] [i8* bitcast (void (%struct.interrupt_frame*)* @test_isr_no_ecode to i8*), i8* bitcast (void (%struct.interrupt_frame*, i32)* @test_isr_ecode to i8*), i8* bitcast (void (%struct.interrupt_frame*, i32)* @test_isr_clobbers to i8*)], section "llvm.metadata"
; Spills eax, putting original esp at +4.
; No stack adjustment if declared with no error code
define x86_intrcc void @test_isr_no_ecode(%struct.interrupt_frame* %frame) {
; CHECK-LABEL: test_isr_no_ecode:
; CHECK: pushl %eax
; CHECK: movl 12(%esp), %eax
; CHECK: popl %eax
; CHECK: iretl
; CHECK0-LABEL: test_isr_no_ecode:
; CHECK0: pushl %eax
; CHECK0: leal 4(%esp), %eax
; CHECK0: movl 8(%eax), %eax
; CHECK0: popl %eax
; CHECK0: iretl
%pflags = getelementptr inbounds %struct.interrupt_frame, %struct.interrupt_frame* %frame, i32 0, i32 2
%flags = load i32, i32* %pflags, align 4
call void asm sideeffect "", "r"(i32 %flags)
ret void
}
; Spills eax and ecx, putting original esp at +8. Stack is adjusted up another 4 bytes
; before return, popping the error code.
define x86_intrcc void @test_isr_ecode(%struct.interrupt_frame* %frame, i32 %ecode) {
; CHECK-LABEL: test_isr_ecode
; CHECK: pushl %ecx
; CHECK: pushl %eax
; CHECK: movl 8(%esp), %eax
; CHECK: movl 20(%esp), %ecx
; CHECK: popl %eax
; CHECK: popl %ecx
; CHECK: addl $4, %esp
; CHECK: iretl
; CHECK0-LABEL: test_isr_ecode
; CHECK0: pushl %ecx
; CHECK0: pushl %eax
; CHECK0: movl 8(%esp), %eax
; CHECK0: leal 12(%esp), %ecx
; CHECK0: movl 8(%ecx), %ecx
; CHECK0: popl %eax
; CHECK0: popl %ecx
; CHECK0: addl $4, %esp
; CHECK0: iretl
%pflags = getelementptr inbounds %struct.interrupt_frame, %struct.interrupt_frame* %frame, i32 0, i32 2
%flags = load i32, i32* %pflags, align 4
call x86_fastcallcc void asm sideeffect "", "r,r"(i32 %flags, i32 %ecode)
ret void
}
; All clobbered registers must be saved
define x86_intrcc void @test_isr_clobbers(%struct.interrupt_frame* %frame, i32 %ecode) {
call void asm sideeffect "", "~{eax},~{ebx},~{ebp}"()
; CHECK-LABEL: test_isr_clobbers
; CHECK-SSE-NEXT: pushl %ebp
; CHECK-SSE-NEXT: pushl %ebx
; CHECK-SSE-NEXT; pushl %eax
; CHECK-SSE-NEXT: popl %eax
; CHECK-SSE-NEXT: popl %ebx
; CHECK-SSE-NEXT: popl %ebp
; CHECK-SSE-NEXT: addl $4, %esp
; CHECK-SSE-NEXT: iretl
; CHECK0-LABEL: test_isr_clobbers
; CHECK0-SSE-NEXT: pushl %ebp
; CHECK0-SSE-NEXT: pushl %ebx
; CHECK0-SSE-NEXT; pushl %eax
; CHECK0-SSE-NEXT: popl %eax
; CHECK0-SSE-NEXT: popl %ebx
; CHECK0-SSE-NEXT: popl %ebp
; CHECK0-SSE-NEXT: addl $4, %esp
; CHECK0-SSE-NEXT: iretl
ret void
}

170
test/CodeGen/X86/x86-64-intrcc.ll
View File

@ -1,86 +1,86 @@
; RUN: llc -mtriple=x86_64-unknown-unknown < %s | FileCheck %s
; RUN: llc -mtriple=x86_64-unknown-unknown -O0 < %s | FileCheck %s -check-prefix=CHECK0
%struct.interrupt_frame = type { i64, i64, i64, i64, i64 }
@llvm.used = appending global [3 x i8*] [i8* bitcast (void (%struct.interrupt_frame*)* @test_isr_no_ecode to i8*), i8* bitcast (void (%struct.interrupt_frame*, i64)* @test_isr_ecode to i8*), i8* bitcast (void (%struct.interrupt_frame*, i64)* @test_isr_clobbers to i8*)], section "llvm.metadata"
; Spills rax, putting original esp at +8.
; No stack adjustment if declared with no error code
define x86_intrcc void @test_isr_no_ecode(%struct.interrupt_frame* %frame) {
; CHECK-LABEL: test_isr_no_ecode:
; CHECK: pushq %rax
; CHECK: movq 24(%rsp), %rax
; CHECK: popq %rax
; CHECK: iretq
; CHECK0-LABEL: test_isr_no_ecode:
; CHECK0: pushq %rax
; CHECK0: leaq 8(%rsp), %rax
; CHECK0: movq 16(%rax), %rax
; CHECK0: popq %rax
; CHECK0: iretq
%pflags = getelementptr inbounds %struct.interrupt_frame, %struct.interrupt_frame* %frame, i32 0, i32 2
%flags = load i64, i64* %pflags, align 4
call void asm sideeffect "", "r"(i64 %flags)
ret void
}
; Spills rax and rcx, putting original rsp at +16. Stack is adjusted up another 8 bytes
; before return, popping the error code.
define x86_intrcc void @test_isr_ecode(%struct.interrupt_frame* %frame, i64 %ecode) {
; CHECK-LABEL: test_isr_ecode
; CHECK: pushq %rax
; CHECK: pushq %rcx
; CHECK: movq 16(%rsp), %rax
; CHECK: movq 40(%rsp), %rcx
; CHECK: popq %rcx
; CHECK: popq %rax
; CHECK: addq $8, %rsp
; CHECK: iretq
; CHECK0-LABEL: test_isr_ecode
; CHECK0: pushq %rax
; CHECK0: pushq %rcx
; CHECK0: movq 16(%rsp), %rax
; CHECK0: leaq 24(%rsp), %rcx
; CHECK0: movq 16(%rcx), %rcx
; CHECK0: popq %rcx
; CHECK0: popq %rax
; CHECK0: addq $8, %rsp
; CHECK0: iretq
%pflags = getelementptr inbounds %struct.interrupt_frame, %struct.interrupt_frame* %frame, i32 0, i32 2
%flags = load i64, i64* %pflags, align 4
call void asm sideeffect "", "r,r"(i64 %flags, i64 %ecode)
ret void
}
; All clobbered registers must be saved
define x86_intrcc void @test_isr_clobbers(%struct.interrupt_frame* %frame, i64 %ecode) {
call void asm sideeffect "", "~{rax},~{rbx},~{rbp},~{r11},~{xmm0}"()
; CHECK-LABEL: test_isr_clobbers
; CHECK-SSE-NEXT: pushq %rax
; CHECK-SSE-NEXT; pushq %r11
; CHECK-SSE-NEXT: pushq %rbp
; CHECK-SSE-NEXT: pushq %rbx
; CHECK-SSE-NEXT: movaps %xmm0
; CHECK-SSE-NEXT: movaps %xmm0
; CHECK-SSE-NEXT: popq %rbx
; CHECK-SSE-NEXT: popq %rbp
; CHECK-SSE-NEXT: popq %r11
; CHECK-SSE-NEXT: popq %rax
; CHECK-SSE-NEXT: addq $8, %rsp
; CHECK-SSE-NEXT: iretq
; CHECK0-LABEL: test_isr_clobbers
; CHECK0-SSE-NEXT: pushq %rax
; CHECK0-SSE-NEXT; pushq %r11
; CHECK0-SSE-NEXT: pushq %rbp
; CHECK0-SSE-NEXT: pushq %rbx
; CHECK0-SSE-NEXT: movaps %xmm0
; CHECK0-SSE-NEXT: movaps %xmm0
; CHECK0-SSE-NEXT: popq %rbx
; CHECK0-SSE-NEXT: popq %rbp
; CHECK0-SSE-NEXT: popq %r11
; CHECK0-SSE-NEXT: popq %rax
; CHECK0-SSE-NEXT: addq $8, %rsp
; CHECK0-SSE-NEXT: iretq
ret void
; RUN: llc -mtriple=x86_64-unknown-unknown < %s | FileCheck %s
; RUN: llc -mtriple=x86_64-unknown-unknown -O0 < %s | FileCheck %s -check-prefix=CHECK0
%struct.interrupt_frame = type { i64, i64, i64, i64, i64 }
@llvm.used = appending global [3 x i8*] [i8* bitcast (void (%struct.interrupt_frame*)* @test_isr_no_ecode to i8*), i8* bitcast (void (%struct.interrupt_frame*, i64)* @test_isr_ecode to i8*), i8* bitcast (void (%struct.interrupt_frame*, i64)* @test_isr_clobbers to i8*)], section "llvm.metadata"
; Spills rax, putting original esp at +8.
; No stack adjustment if declared with no error code
define x86_intrcc void @test_isr_no_ecode(%struct.interrupt_frame* %frame) {
; CHECK-LABEL: test_isr_no_ecode:
; CHECK: pushq %rax
; CHECK: movq 24(%rsp), %rax
; CHECK: popq %rax
; CHECK: iretq
; CHECK0-LABEL: test_isr_no_ecode:
; CHECK0: pushq %rax
; CHECK0: leaq 8(%rsp), %rax
; CHECK0: movq 16(%rax), %rax
; CHECK0: popq %rax
; CHECK0: iretq
%pflags = getelementptr inbounds %struct.interrupt_frame, %struct.interrupt_frame* %frame, i32 0, i32 2
%flags = load i64, i64* %pflags, align 4
call void asm sideeffect "", "r"(i64 %flags)
ret void
}
; Spills rax and rcx, putting original rsp at +16. Stack is adjusted up another 8 bytes
; before return, popping the error code.
define x86_intrcc void @test_isr_ecode(%struct.interrupt_frame* %frame, i64 %ecode) {
; CHECK-LABEL: test_isr_ecode
; CHECK: pushq %rax
; CHECK: pushq %rcx
; CHECK: movq 16(%rsp), %rax
; CHECK: movq 40(%rsp), %rcx
; CHECK: popq %rcx
; CHECK: popq %rax
; CHECK: addq $8, %rsp
; CHECK: iretq
; CHECK0-LABEL: test_isr_ecode
; CHECK0: pushq %rax
; CHECK0: pushq %rcx
; CHECK0: movq 16(%rsp), %rax
; CHECK0: leaq 24(%rsp), %rcx
; CHECK0: movq 16(%rcx), %rcx
; CHECK0: popq %rcx
; CHECK0: popq %rax
; CHECK0: addq $8, %rsp
; CHECK0: iretq
%pflags = getelementptr inbounds %struct.interrupt_frame, %struct.interrupt_frame* %frame, i32 0, i32 2
%flags = load i64, i64* %pflags, align 4
call void asm sideeffect "", "r,r"(i64 %flags, i64 %ecode)
ret void
}
; All clobbered registers must be saved
define x86_intrcc void @test_isr_clobbers(%struct.interrupt_frame* %frame, i64 %ecode) {
call void asm sideeffect "", "~{rax},~{rbx},~{rbp},~{r11},~{xmm0}"()
; CHECK-LABEL: test_isr_clobbers
; CHECK-SSE-NEXT: pushq %rax
; CHECK-SSE-NEXT; pushq %r11
; CHECK-SSE-NEXT: pushq %rbp
; CHECK-SSE-NEXT: pushq %rbx
; CHECK-SSE-NEXT: movaps %xmm0
; CHECK-SSE-NEXT: movaps %xmm0
; CHECK-SSE-NEXT: popq %rbx
; CHECK-SSE-NEXT: popq %rbp
; CHECK-SSE-NEXT: popq %r11
; CHECK-SSE-NEXT: popq %rax
; CHECK-SSE-NEXT: addq $8, %rsp
; CHECK-SSE-NEXT: iretq
; CHECK0-LABEL: test_isr_clobbers
; CHECK0-SSE-NEXT: pushq %rax
; CHECK0-SSE-NEXT; pushq %r11
; CHECK0-SSE-NEXT: pushq %rbp
; CHECK0-SSE-NEXT: pushq %rbx
; CHECK0-SSE-NEXT: movaps %xmm0
; CHECK0-SSE-NEXT: movaps %xmm0
; CHECK0-SSE-NEXT: popq %rbx
; CHECK0-SSE-NEXT: popq %rbp
; CHECK0-SSE-NEXT: popq %r11
; CHECK0-SSE-NEXT: popq %rax
; CHECK0-SSE-NEXT: addq $8, %rsp
; CHECK0-SSE-NEXT: iretq
ret void
}

2
test/DebugInfo/Inputs/dwarfdump-macro-cmd.h
View File

@ -1 +1 @@
#define M4 Value4
#define M4 Value4

22
test/DebugInfo/Inputs/dwarfdump-macro.cc
View File

@ -1,11 +1,11 @@
#define M1 Value1
#include "dwarfdump-macro.h"
#define M2(x, y) ((x)+(y)* Value2)
// Built with GCC
// $ mkdir -p /tmp/dbginfo
// $ cp dwarfdump-macro.cc /tmp/dbginfo
// $ cp dwarfdump-macro.h /tmp/dbginfo
// $ cp dwarfdump-macro-cmd.h /tmp/dbginfo
// $ cd /tmp/dbginfo
// $ g++ -c -g3 -O0 -DM3=Value3 -include dwarfdump-macro-cmd.h dwarfdump-macro.cc -o <output>
#define M1 Value1
#include "dwarfdump-macro.h"
#define M2(x, y) ((x)+(y)* Value2)
// Built with GCC
// $ mkdir -p /tmp/dbginfo
// $ cp dwarfdump-macro.cc /tmp/dbginfo
// $ cp dwarfdump-macro.h /tmp/dbginfo
// $ cp dwarfdump-macro-cmd.h /tmp/dbginfo
// $ cd /tmp/dbginfo
// $ g++ -c -g3 -O0 -DM3=Value3 -include dwarfdump-macro-cmd.h dwarfdump-macro.cc -o <output>

10
test/DebugInfo/Inputs/dwarfdump-macro.h
View File

@ -1,5 +1,5 @@
#undef M1
#define M1 NewValue1
#undef M1
#define M1 NewValue1

54
test/DebugInfo/debugmacinfo.test
View File

@ -1,27 +1,27 @@
RUN: llvm-dwarfdump -debug-dump=macro %p/Inputs/dwarfdump-macro.o \
RUN: | FileCheck %s -check-prefix TEST_MACINFO
RUN: llvm-dwarfdump -debug-dump=line %p/Inputs/dwarfdump-macro.o \
RUN: | FileCheck %s -check-prefix TEST_LINE
; This test verifies that llvm-dwarfdump tools know how to read .debug_macinfo
; section. It also checks that the file numbers fits with those in the
; .debug_line section.
TEST_MACINFO: .debug_macinfo contents:
TEST_MACINFO: DW_MACINFO_define - lineno: 0 macro: M3 Value3
TEST_MACINFO: DW_MACINFO_start_file - lineno: 0 filenum: 1
TEST_MACINFO: DW_MACINFO_start_file - lineno: 0 filenum: 2
TEST_MACINFO: DW_MACINFO_define - lineno: 1 macro: M4 Value4
TEST_MACINFO: DW_MACINFO_end_file
TEST_MACINFO: DW_MACINFO_define - lineno: 1 macro: M1 Value1
TEST_MACINFO: DW_MACINFO_start_file - lineno: 2 filenum: 3
TEST_MACINFO: DW_MACINFO_undef - lineno: 4 macro: M1
TEST_MACINFO: DW_MACINFO_define - lineno: 5 macro: M1 NewValue1
TEST_MACINFO: DW_MACINFO_end_file
TEST_MACINFO: DW_MACINFO_define - lineno: 3 macro: M2(x,y) ((x)+(y)* Value2)
TEST_MACINFO: DW_MACINFO_end_file
TEST_LINE: .debug_line contents:
TEST_LINE: file_names[ 1] 0 0x00000000 0x00000000 dwarfdump-macro.cc
TEST_LINE: file_names[ 2] 1 0x00000000 0x00000000 dwarfdump-macro-cmd.h
TEST_LINE: file_names[ 3] 0 0x00000000 0x00000000 dwarfdump-macro.h
RUN: llvm-dwarfdump -debug-dump=macro %p/Inputs/dwarfdump-macro.o \
RUN: | FileCheck %s -check-prefix TEST_MACINFO
RUN: llvm-dwarfdump -debug-dump=line %p/Inputs/dwarfdump-macro.o \
RUN: | FileCheck %s -check-prefix TEST_LINE
; This test verifies that llvm-dwarfdump tools know how to read .debug_macinfo
; section. It also checks that the file numbers fits with those in the
; .debug_line section.
TEST_MACINFO: .debug_macinfo contents:
TEST_MACINFO: DW_MACINFO_define - lineno: 0 macro: M3 Value3
TEST_MACINFO: DW_MACINFO_start_file - lineno: 0 filenum: 1
TEST_MACINFO: DW_MACINFO_start_file - lineno: 0 filenum: 2
TEST_MACINFO: DW_MACINFO_define - lineno: 1 macro: M4 Value4
TEST_MACINFO: DW_MACINFO_end_file
TEST_MACINFO: DW_MACINFO_define - lineno: 1 macro: M1 Value1
TEST_MACINFO: DW_MACINFO_start_file - lineno: 2 filenum: 3
TEST_MACINFO: DW_MACINFO_undef - lineno: 4 macro: M1
TEST_MACINFO: DW_MACINFO_define - lineno: 5 macro: M1 NewValue1
TEST_MACINFO: DW_MACINFO_end_file
TEST_MACINFO: DW_MACINFO_define - lineno: 3 macro: M2(x,y) ((x)+(y)* Value2)
TEST_MACINFO: DW_MACINFO_end_file
TEST_LINE: .debug_line contents:
TEST_LINE: file_names[ 1] 0 0x00000000 0x00000000 dwarfdump-macro.cc
TEST_LINE: file_names[ 2] 1 0x00000000 0x00000000 dwarfdump-macro-cmd.h
TEST_LINE: file_names[ 3] 0 0x00000000 0x00000000 dwarfdump-macro.h

74
test/JitListener/multiple.ll
View File

@ -3,48 +3,48 @@
; This test was created using the following file:
;
; 1: int foo(int a) {
; 2: return a;
; 1: int foo(int a) {
; 2: return a;
; 3: }
; 4:
; 5: int bar(int a) {
; 6: if (a == 0) {
; 7: return 0;
; 8: }
; 9: return 100/a;
; 10: }
; 11:
; 12: int fubar(int a) {
; 13: switch (a) {
; 14: case 0:
; 15: return 10;
; 16: case 1:
; 17: return 20;
; 18: default:
; 19: return 30;
; 20: }
; 5: int bar(int a) {
; 6: if (a == 0) {
; 7: return 0;
; 8: }
; 9: return 100/a;
; 10: }
; 11:
; 12: int fubar(int a) {
; 13: switch (a) {
; 14: case 0:
; 15: return 10;
; 16: case 1:
; 17: return 20;
; 18: default:
; 19: return 30;
; 20: }
; 21: }
;
; CHECK: Method load [1]: bar, Size = {{[0-9]+}}
; CHECK: Line info @ {{[0-9]+}}: multiple.c, line {{[5,6,7,9]}}
; CHECK: Line info @ {{[0-9]+}}: multiple.c, line {{[5,6,7,9]}}
; CHECK: Line info @ {{[0-9]+}}: multiple.c, line {{[5,6,7,9]}}
; CHECK: Line info @ {{[0-9]+}}: multiple.c, line {{[5,6,7,9]}}
; CHECK: Method load [2]: foo, Size = {{[0-9]+}}
; CHECK: Line info @ {{[0-9]+}}: multiple.c, line {{[1,2]}}
; CHECK: Line info @ {{[0-9]+}}: multiple.c, line {{[1,2]}}
; CHECK: Method load [3]: fubar, Size = {{[0-9]+}}
; CHECK: Line info @ {{[0-9]+}}: multiple.c, line {{[12,13,15,17,19]}}
; CHECK: Line info @ {{[0-9]+}}: multiple.c, line {{[12,13,15,17,19]}}
; CHECK: Line info @ {{[0-9]+}}: multiple.c, line {{[12,13,15,17,19]}}
; CHECK: Line info @ {{[0-9]+}}: multiple.c, line {{[12,13,15,17,19]}}
; CHECK: Line info @ {{[0-9]+}}: multiple.c, line {{[12,13,15,17,19]}}
; CHECK: Method unload [1]
; CHECK: Method unload [2]
; CHECK: Method load [1]: bar, Size = {{[0-9]+}}
; CHECK: Line info @ {{[0-9]+}}: multiple.c, line {{[5,6,7,9]}}
; CHECK: Line info @ {{[0-9]+}}: multiple.c, line {{[5,6,7,9]}}
; CHECK: Line info @ {{[0-9]+}}: multiple.c, line {{[5,6,7,9]}}
; CHECK: Line info @ {{[0-9]+}}: multiple.c, line {{[5,6,7,9]}}
; CHECK: Method load [2]: foo, Size = {{[0-9]+}}
; CHECK: Line info @ {{[0-9]+}}: multiple.c, line {{[1,2]}}
; CHECK: Line info @ {{[0-9]+}}: multiple.c, line {{[1,2]}}
; CHECK: Method load [3]: fubar, Size = {{[0-9]+}}
; CHECK: Line info @ {{[0-9]+}}: multiple.c, line {{[12,13,15,17,19]}}
; CHECK: Line info @ {{[0-9]+}}: multiple.c, line {{[12,13,15,17,19]}}
; CHECK: Line info @ {{[0-9]+}}: multiple.c, line {{[12,13,15,17,19]}}
; CHECK: Line info @ {{[0-9]+}}: multiple.c, line {{[12,13,15,17,19]}}
; CHECK: Line info @ {{[0-9]+}}: multiple.c, line {{[12,13,15,17,19]}}
; CHECK: Method unload [1]
; CHECK: Method unload [2]
; CHECK: Method unload [3]
; ModuleID = 'multiple.c'

10
test/JitListener/simple.ll
View File

@ -3,14 +3,14 @@
; This test was created using the following file:
;
; 1: int foo(int a) {
; 2: return a;
; 1: int foo(int a) {
; 2: return a;
; 3: }
;
; CHECK: Method load [1]: foo, Size = {{[0-9]+}}
; CHECK: Line info @ {{[0-9]+}}: simple.c, line 1
; CHECK: Line info @ {{[0-9]+}}: simple.c, line 2
; CHECK: Method load [1]: foo, Size = {{[0-9]+}}
; CHECK: Line info @ {{[0-9]+}}: simple.c, line 1
; CHECK: Line info @ {{[0-9]+}}: simple.c, line 2
; CHECK: Method unload [1]
; ModuleID = 'simple.c'

14
test/MC/ARM/gas-compl-copr-reg.s
View File

@ -5,10 +5,10 @@
ldc p12, cr4, [r0, #4]
stc p14, cr6, [r2, #-224]
@ RUN: llvm-mc -triple=armv7-linux-gnueabi -show-encoding < %s | FileCheck %s
@ CHECK: ldc p12, c4, [r0, #4] @ encoding: [0x01,0x4c,0x90,0xed]
@ CHECK: stc p14, c6, [r2, #-224] @ encoding: [0x38,0x6e,0x02,0xed]
ldc p12, cr4, [r0, #4]
stc p14, cr6, [r2, #-224]
@ RUN: llvm-mc -triple=armv7-linux-gnueabi -show-encoding < %s | FileCheck %s
@ CHECK: ldc p12, c4, [r0, #4] @ encoding: [0x01,0x4c,0x90,0xed]
@ CHECK: stc p14, c6, [r2, #-224] @ encoding: [0x38,0x6e,0x02,0xed]
ldc p12, cr4, [r0, #4]
stc p14, cr6, [r2, #-224]

84
test/MC/Disassembler/Mips/mips4/valid-xfail-mips4.txt
View File

@ -1,42 +1,42 @@
# RUN: llvm-mc %s -triple=mips64-unknown-linux -disassemble -mcpu=mips4 | FileCheck %s
# XFAIL: *
0x46 0x2f 0x79 0x32 # CHECK: c.eq.d $fcc1, $f15, $f15
0x46 0x11 0xc5 0x32 # CHECK: c.eq.s $fcc5, $f24, $f17
0x46 0x35 0x5c 0x30 # CHECK: c.f.d $fcc4, $f11, $f21
0x46 0x07 0xf4 0x30 # CHECK: c.f.s $fcc4, $f30, $f7
0x46 0x21 0x94 0x3e # CHECK: c.le.d $fcc4, $f18, $f1
0x46 0x04 0xc6 0x3e # CHECK: c.le.s $fcc6, $f24, $f4
0x46 0x23 0x4b 0x3c # CHECK: c.lt.d $fcc3, $f9, $f3
0x46 0x0e 0x8a 0x3c # CHECK: c.lt.s $fcc2, $f17, $f14
0x46 0x30 0xad 0x3d # CHECK: c.nge.d $fcc5, $f21, $f16
0x46 0x08 0x5b 0x3d # CHECK: c.nge.s $fcc3, $f11, $f8
0x46 0x17 0xfa 0x3b # CHECK: c.ngl.s $fcc2, $f31, $f23
0x46 0x17 0x92 0x39 # CHECK: c.ngle.s $fcc2, $f18, $f23
0x46 0x27 0xc4 0x3f # CHECK: c.ngt.d $fcc4, $f24, $f7
0x46 0x0d 0x45 0x3f # CHECK: c.ngt.s $fcc5, $f8, $f13
0x46 0x3f 0x82 0x36 # CHECK: c.ole.d $fcc2, $f16, $f31
0x46 0x14 0x3b 0x36 # CHECK: c.ole.s $fcc3, $f7, $f20
0x46 0x3c 0x9c 0x34 # CHECK: c.olt.d $fcc4, $f19, $f28
0x46 0x07 0xa6 0x34 # CHECK: c.olt.s $fcc6, $f20, $f7
0x46 0x27 0xfc 0x3a # CHECK: c.seq.d $fcc4, $f31, $f7
0x46 0x19 0x0f 0x3a # CHECK: c.seq.s $fcc7, $f1, $f25
0x46 0x39 0x6c 0x33 # CHECK: c.ueq.d $fcc4, $f13, $f25
0x46 0x1e 0x1e 0x33 # CHECK: c.ueq.s $fcc6, $f3, $f30
0x46 0x32 0xcf 0x37 # CHECK: c.ule.d $fcc7, $f25, $f18
0x46 0x1e 0xaf 0x37 # CHECK: c.ule.s $fcc7, $f21, $f30
0x46 0x31 0x36 0x35 # CHECK: c.ult.d $fcc6, $f6, $f17
0x46 0x0a 0xc7 0x35 # CHECK: c.ult.s $fcc7, $f24, $f10
0x46 0x38 0xbe 0x31 # CHECK: c.un.d $fcc6, $f23, $f24
0x46 0x04 0xf1 0x31 # CHECK: c.un.s $fcc1, $f30, $f4
0x4e 0x74 0xd4 0xa1 # CHECK: madd.d $f18, $f19, $f26, $f20
0x4f 0xf9 0x98 0x60 # CHECK: madd.s $f1, $f31, $f19, $f25
0x4c 0x32 0xfa 0xa9 # CHECK: msub.d $f10, $f1, $f31, $f18
0x4e 0x70 0x53 0x28 # CHECK: msub.s $f12, $f19, $f10, $f16
0x4d 0x33 0x74 0xb1 # CHECK: nmadd.d $f18, $f9, $f14, $f19
0x4c 0xac 0xc8 0x30 # CHECK: nmadd.s $f0, $f5, $f25, $f12
0x4d 0x1e 0x87 0xb9 # CHECK: nmsub.d $f30, $f8, $f16, $f30
0x4f 0x04 0x98 0x78 # CHECK: nmsub.s $f1, $f24, $f19, $f4
0x46 0x20 0x34 0xd5 # CHECK: recip.d $f19, $f6
0x46 0x00 0xf0 0xd5 # CHECK: recip.s $f3, $f30
0x46 0x20 0xe0 0xd6 # CHECK: rsqrt.d $f3, $f28
0x46 0x00 0x41 0x16 # CHECK: rsqrt.s $f4, $f8
# RUN: llvm-mc %s -triple=mips64-unknown-linux -disassemble -mcpu=mips4 | FileCheck %s
# XFAIL: *
0x46 0x2f 0x79 0x32 # CHECK: c.eq.d $fcc1, $f15, $f15
0x46 0x11 0xc5 0x32 # CHECK: c.eq.s $fcc5, $f24, $f17
0x46 0x35 0x5c 0x30 # CHECK: c.f.d $fcc4, $f11, $f21
0x46 0x07 0xf4 0x30 # CHECK: c.f.s $fcc4, $f30, $f7
0x46 0x21 0x94 0x3e # CHECK: c.le.d $fcc4, $f18, $f1
0x46 0x04 0xc6 0x3e # CHECK: c.le.s $fcc6, $f24, $f4
0x46 0x23 0x4b 0x3c # CHECK: c.lt.d $fcc3, $f9, $f3
0x46 0x0e 0x8a 0x3c # CHECK: c.lt.s $fcc2, $f17, $f14
0x46 0x30 0xad 0x3d # CHECK: c.nge.d $fcc5, $f21, $f16
0x46 0x08 0x5b 0x3d # CHECK: c.nge.s $fcc3, $f11, $f8
0x46 0x17 0xfa 0x3b # CHECK: c.ngl.s $fcc2, $f31, $f23
0x46 0x17 0x92 0x39 # CHECK: c.ngle.s $fcc2, $f18, $f23
0x46 0x27 0xc4 0x3f # CHECK: c.ngt.d $fcc4, $f24, $f7
0x46 0x0d 0x45 0x3f # CHECK: c.ngt.s $fcc5, $f8, $f13
0x46 0x3f 0x82 0x36 # CHECK: c.ole.d $fcc2, $f16, $f31
0x46 0x14 0x3b 0x36 # CHECK: c.ole.s $fcc3, $f7, $f20
0x46 0x3c 0x9c 0x34 # CHECK: c.olt.d $fcc4, $f19, $f28
0x46 0x07 0xa6 0x34 # CHECK: c.olt.s $fcc6, $f20, $f7
0x46 0x27 0xfc 0x3a # CHECK: c.seq.d $fcc4, $f31, $f7
0x46 0x19 0x0f 0x3a # CHECK: c.seq.s $fcc7, $f1, $f25
0x46 0x39 0x6c 0x33 # CHECK: c.ueq.d $fcc4, $f13, $f25
0x46 0x1e 0x1e 0x33 # CHECK: c.ueq.s $fcc6, $f3, $f30
0x46 0x32 0xcf 0x37 # CHECK: c.ule.d $fcc7, $f25, $f18
0x46 0x1e 0xaf 0x37 # CHECK: c.ule.s $fcc7, $f21, $f30
0x46 0x31 0x36 0x35 # CHECK: c.ult.d $fcc6, $f6, $f17
0x46 0x0a 0xc7 0x35 # CHECK: c.ult.s $fcc7, $f24, $f10
0x46 0x38 0xbe 0x31 # CHECK: c.un.d $fcc6, $f23, $f24
0x46 0x04 0xf1 0x31 # CHECK: c.un.s $fcc1, $f30, $f4
0x4e 0x74 0xd4 0xa1 # CHECK: madd.d $f18, $f19, $f26, $f20
0x4f 0xf9 0x98 0x60 # CHECK: madd.s $f1, $f31, $f19, $f25
0x4c 0x32 0xfa 0xa9 # CHECK: msub.d $f10, $f1, $f31, $f18
0x4e 0x70 0x53 0x28 # CHECK: msub.s $f12, $f19, $f10, $f16
0x4d 0x33 0x74 0xb1 # CHECK: nmadd.d $f18, $f9, $f14, $f19
0x4c 0xac 0xc8 0x30 # CHECK: nmadd.s $f0, $f5, $f25, $f12
0x4d 0x1e 0x87 0xb9 # CHECK: nmsub.d $f30, $f8, $f16, $f30
0x4f 0x04 0x98 0x78 # CHECK: nmsub.s $f1, $f24, $f19, $f4
0x46 0x20 0x34 0xd5 # CHECK: recip.d $f19, $f6
0x46 0x00 0xf0 0xd5 # CHECK: recip.s $f3, $f30
0x46 0x20 0xe0 0xd6 # CHECK: rsqrt.d $f3, $f28
0x46 0x00 0x41 0x16 # CHECK: rsqrt.s $f4, $f8

6
test/MC/Hexagon/test.s
View File

@ -1,4 +1,4 @@
#RUN: llvm-mc -filetype=obj -triple=hexagon -mcpu=hexagonv60 %s
{ vmem (r0 + #0) = v0
#RUN: llvm-mc -filetype=obj -triple=hexagon -mcpu=hexagonv60 %s
{ vmem (r0 + #0) = v0
r0 = memw(r0) }

14
test/MC/X86/X86_64-pku.s
View File

@ -1,8 +1,8 @@
// RUN: llvm-mc -triple x86_64-unknown-unknown -mattr=+pku --show-encoding < %s | FileCheck %s
// CHECK: rdpkru
// CHECK: encoding: [0x0f,0x01,0xee]
rdpkru
// CHECK: wrpkru
// CHECK: encoding: [0x0f,0x01,0xef]
// RUN: llvm-mc -triple x86_64-unknown-unknown -mattr=+pku --show-encoding < %s | FileCheck %s
// CHECK: rdpkru
// CHECK: encoding: [0x0f,0x01,0xee]
rdpkru
// CHECK: wrpkru
// CHECK: encoding: [0x0f,0x01,0xef]
wrpkru

36
test/Transforms/EarlyCSE/AArch64/ldstN.ll
View File

@ -1,18 +1,18 @@
; RUN: opt -S -early-cse < %s | FileCheck %s
target datalayout = "e-m:e-i64:64-i128:128-n32:64-S128"
target triple = "aarch64--linux-gnu"
declare { <4 x i16>, <4 x i16>, <4 x i16>, <4 x i16> } @llvm.aarch64.neon.ld4.v4i16.p0v4i16(<4 x i16>*)
; Although the store and the ld4 are using the same pointer, the
; data can not be reused because ld4 accesses multiple elements.
define { <4 x i16>, <4 x i16>, <4 x i16>, <4 x i16> } @foo() {
entry:
store <4 x i16> undef, <4 x i16>* undef, align 8
%0 = call { <4 x i16>, <4 x i16>, <4 x i16>, <4 x i16> } @llvm.aarch64.neon.ld4.v4i16.p0v4i16(<4 x i16>* undef)
ret { <4 x i16>, <4 x i16>, <4 x i16>, <4 x i16> } %0
; CHECK-LABEL: @foo(
; CHECK: store
; CHECK-NEXT: call
; CHECK-NEXT: ret
}
; RUN: opt -S -early-cse < %s | FileCheck %s
target datalayout = "e-m:e-i64:64-i128:128-n32:64-S128"
target triple = "aarch64--linux-gnu"
declare { <4 x i16>, <4 x i16>, <4 x i16>, <4 x i16> } @llvm.aarch64.neon.ld4.v4i16.p0v4i16(<4 x i16>*)
; Although the store and the ld4 are using the same pointer, the
; data can not be reused because ld4 accesses multiple elements.
define { <4 x i16>, <4 x i16>, <4 x i16>, <4 x i16> } @foo() {
entry:
store <4 x i16> undef, <4 x i16>* undef, align 8
%0 = call { <4 x i16>, <4 x i16>, <4 x i16>, <4 x i16> } @llvm.aarch64.neon.ld4.v4i16.p0v4i16(<4 x i16>* undef)
ret { <4 x i16>, <4 x i16>, <4 x i16>, <4 x i16> } %0
; CHECK-LABEL: @foo(
; CHECK: store
; CHECK-NEXT: call
; CHECK-NEXT: ret
}

62
test/Transforms/PlaceSafepoints/statepoint-coreclr.ll
View File

@ -1,31 +1,31 @@
; RUN: opt %s -S -place-safepoints | FileCheck %s
; Basic test to make sure that safepoints are placed
; for CoreCLR GC
declare void @foo()
define void @test_simple_call() gc "coreclr" {
; CHECK-LABEL: test_simple_call
entry:
br label %other
other:
; CHECK-LABEL: other
; CHECK: statepoint
; CHECK-NOT: gc.result
call void @foo()
ret void
}
; This function is inlined when inserting a poll. To avoid recursive
; issues, make sure we don't place safepoints in it.
declare void @do_safepoint()
define void @gc.safepoint_poll() {
; CHECK-LABEL: gc.safepoint_poll
; CHECK-LABEL: entry
; CHECK-NEXT: do_safepoint
; CHECK-NEXT: ret void
entry:
call void @do_safepoint()
ret void
}
; RUN: opt %s -S -place-safepoints | FileCheck %s
; Basic test to make sure that safepoints are placed
; for CoreCLR GC
declare void @foo()
define void @test_simple_call() gc "coreclr" {
; CHECK-LABEL: test_simple_call
entry:
br label %other
other:
; CHECK-LABEL: other
; CHECK: statepoint
; CHECK-NOT: gc.result
call void @foo()
ret void
}
; This function is inlined when inserting a poll. To avoid recursive
; issues, make sure we don't place safepoints in it.
declare void @do_safepoint()
define void @gc.safepoint_poll() {
; CHECK-LABEL: gc.safepoint_poll
; CHECK-LABEL: entry
; CHECK-NEXT: do_safepoint
; CHECK-NEXT: ret void
entry:
call void @do_safepoint()
ret void
}

128
test/tools/llvm-pdbdump/Inputs/ClassLayoutTest.cpp
View File

@ -1,64 +1,64 @@
// Compile with "cl /c /Zi /GR- ClassLayoutTest.cpp"
// Link with "link ClassLayoutTest.obj /debug /nodefaultlib /entry:main"
namespace MembersTest {
class A {
public:
typedef int NestedTypedef;
enum NestedEnum {
NestedEnumValue1
};
void MemberFunc() {}
private:
int IntMemberVar;
double DoubleMemberVar;
};
}
namespace GlobalsTest {
int IntVar;
double DoubleVar;
typedef int Typedef;
enum Enum {
Val1
} EnumVar;
Typedef TypedefVar;
}
namespace BaseClassTest {
class A {};
class B : public virtual A {};
class C : public virtual A {};
class D : protected B, private C {};
}
namespace UdtKindTest {
struct A {};
class B {};
union C {};
}
namespace BitFieldTest {
struct A {
int Bits1 : 1;
int Bits2 : 2;
int Bits3 : 3;
int Bits4 : 4;
int Bits22 : 22;
int Offset0x04;
};
};
int main(int argc, char **argv) {
MembersTest::A v1;
v1.MemberFunc();
BaseClassTest::D v2;
UdtKindTest::A v3;
UdtKindTest::B v4;
UdtKindTest::C v5;
BitFieldTest::A v7;
return 0;
}
// Compile with "cl /c /Zi /GR- ClassLayoutTest.cpp"
// Link with "link ClassLayoutTest.obj /debug /nodefaultlib /entry:main"
namespace MembersTest {
class A {
public:
typedef int NestedTypedef;
enum NestedEnum {
NestedEnumValue1
};
void MemberFunc() {}
private:
int IntMemberVar;
double DoubleMemberVar;
};
}
namespace GlobalsTest {
int IntVar;
double DoubleVar;
typedef int Typedef;
enum Enum {
Val1
} EnumVar;
Typedef TypedefVar;
}
namespace BaseClassTest {
class A {};
class B : public virtual A {};
class C : public virtual A {};
class D : protected B, private C {};
}
namespace UdtKindTest {
struct A {};
class B {};
union C {};
}
namespace BitFieldTest {
struct A {
int Bits1 : 1;
int Bits2 : 2;
int Bits3 : 3;
int Bits4 : 4;
int Bits22 : 22;
int Offset0x04;
};
};
int main(int argc, char **argv) {
MembersTest::A v1;
v1.MemberFunc();
BaseClassTest::D v2;
UdtKindTest::A v3;
UdtKindTest::B v4;
UdtKindTest::C v5;
BitFieldTest::A v7;
return 0;
}

58
test/tools/llvm-pdbdump/Inputs/FilterTest.cpp
View File

@ -1,29 +1,29 @@
// Compile with "cl /c /Zi /GR- FilterTest.cpp"
// Link with "link FilterTest.obj /debug /nodefaultlib /entry:main"
class FilterTestClass {
public:
typedef int NestedTypedef;
enum NestedEnum {
NestedEnumValue1
};
void MemberFunc() {}
private:
int IntMemberVar;
double DoubleMemberVar;
};
int IntGlobalVar;
double DoubleGlobalVar;
typedef int GlobalTypedef;
enum GlobalEnum {
GlobalEnumVal1
} GlobalEnumVar;
int main(int argc, char **argv) {
FilterTestClass TestClass;
GlobalTypedef v1;
return 0;
}
// Compile with "cl /c /Zi /GR- FilterTest.cpp"
// Link with "link FilterTest.obj /debug /nodefaultlib /entry:main"
class FilterTestClass {
public:
typedef int NestedTypedef;
enum NestedEnum {
NestedEnumValue1
};
void MemberFunc() {}
private:
int IntMemberVar;
double DoubleMemberVar;
};
int IntGlobalVar;
double DoubleGlobalVar;
typedef int GlobalTypedef;
enum GlobalEnum {
GlobalEnumVal1
} GlobalEnumVar;
int main(int argc, char **argv) {
FilterTestClass TestClass;
GlobalTypedef v1;
return 0;
}

12
test/tools/llvm-pdbdump/Inputs/LoadAddressTest.cpp
View File

@ -1,6 +1,6 @@
// Compile with "cl /c /Zi /GR- LoadAddressTest.cpp"
// Link with "link LoadAddressTest.obj /debug /nodefaultlib /entry:main"
int main(int argc, char **argv) {
return 0;
}
// Compile with "cl /c /Zi /GR- LoadAddressTest.cpp"
// Link with "link LoadAddressTest.obj /debug /nodefaultlib /entry:main"
int main(int argc, char **argv) {
return 0;
}

114
test/tools/llvm-pdbdump/class-layout.test
View File

@ -1,57 +1,57 @@
; RUN: llvm-pdbdump -all %p/Inputs/ClassLayoutTest.pdb > %t
; RUN: FileCheck -input-file=%t %s -check-prefix=GLOBALS_TEST
; RUN: FileCheck -input-file=%t %s -check-prefix=MEMBERS_TEST
; RUN: FileCheck -input-file=%t %s -check-prefix=BASE_CLASS_A
; RUN: FileCheck -input-file=%t %s -check-prefix=BASE_CLASS_B
; RUN: FileCheck -input-file=%t %s -check-prefix=BASE_CLASS_C
; RUN: FileCheck -input-file=%t %s -check-prefix=BASE_CLASS_D
; RUN: FileCheck -input-file=%t %s -check-prefix=UDT_KIND_TEST
; RUN: FileCheck -input-file=%t %s -check-prefix=BITFIELD_TEST
; GLOBALS_TEST: ---GLOBALS---
; GLOBALS_TEST-DAG: int GlobalsTest::IntVar
; GLOBALS_TEST-DAG: double GlobalsTest::DoubleVar
; GLOBALS_TEST-DAG: GlobalsTest::Enum GlobalsTest::EnumVar
; MEMBERS_TEST: ---TYPES---
; MEMBERS_TEST: class MembersTest::A {
; MEMBERS_TEST-DAG: typedef int NestedTypedef
; MEMBERS_TEST-DAG: enum NestedEnum
; MEMBERS_TEST: public:
; MEMBERS_TEST-NEXT: void MemberFunc()
; MEMBERS_TEST-NEXT: private:
; MEMBERS_TEST-DAG: int IntMemberVar
; MEMBERS_TEST-DAG: double DoubleMemberVar
; MEMBERS_TEST: }
; BASE_CLASS_A: ---TYPES---
; BASE_CLASS_A: class BaseClassTest::A {}
; BASE_CLASS_B: ---TYPES---
; BASE_CLASS_B: class BaseClassTest::B
; BASE_CLASS_B-NEXT: : public virtual BaseClassTest::A {
; BASE_CLASS_C: ---TYPES---
; BASE_CLASS_C: class BaseClassTest::C
; BASE_CLASS_C-NEXT: : public virtual BaseClassTest::A {
; BASE_CLASS_D: ---TYPES---
; BASE_CLASS_D: class BaseClassTest::D
; BASE_CLASS_D-DAG: protected BaseClassTest::B
; BASE_CLASS_D-DAG: private BaseClassTest::C
; BASE_CLASS_D-DAG: protected virtual BaseClassTest::A
; UDT_KIND_TEST: ---TYPES---
; UDT_KIND_TEST-DAG: union UdtKindTest::C {}
; UDT_KIND_TEST-DAG: class UdtKindTest::B {}
; UDT_KIND_TEST-DAG: struct UdtKindTest::A {}
; BITFIELD_TEST: ---TYPES---
; BITFIELD_TEST: struct BitFieldTest::A {
; BITFIELD_TEST-NEXT: public:
; BITFIELD_TEST-NEXT: +0x00 int Bits1 : 1
; BITFIELD_TEST-NEXT: +0x00 int Bits2 : 2
; BITFIELD_TEST-NEXT: +0x00 int Bits3 : 3
; BITFIELD_TEST-NEXT: +0x00 int Bits4 : 4
; BITFIELD_TEST-NEXT: +0x00 int Bits22 : 22
; BITFIELD_TEST-NEXT: +0x04 int Offset0x04
; RUN: llvm-pdbdump -all %p/Inputs/ClassLayoutTest.pdb > %t
; RUN: FileCheck -input-file=%t %s -check-prefix=GLOBALS_TEST
; RUN: FileCheck -input-file=%t %s -check-prefix=MEMBERS_TEST
; RUN: FileCheck -input-file=%t %s -check-prefix=BASE_CLASS_A
; RUN: FileCheck -input-file=%t %s -check-prefix=BASE_CLASS_B
; RUN: FileCheck -input-file=%t %s -check-prefix=BASE_CLASS_C
; RUN: FileCheck -input-file=%t %s -check-prefix=BASE_CLASS_D
; RUN: FileCheck -input-file=%t %s -check-prefix=UDT_KIND_TEST
; RUN: FileCheck -input-file=%t %s -check-prefix=BITFIELD_TEST
; GLOBALS_TEST: ---GLOBALS---
; GLOBALS_TEST-DAG: int GlobalsTest::IntVar
; GLOBALS_TEST-DAG: double GlobalsTest::DoubleVar
; GLOBALS_TEST-DAG: GlobalsTest::Enum GlobalsTest::EnumVar
; MEMBERS_TEST: ---TYPES---
; MEMBERS_TEST: class MembersTest::A {
; MEMBERS_TEST-DAG: typedef int NestedTypedef
; MEMBERS_TEST-DAG: enum NestedEnum
; MEMBERS_TEST: public:
; MEMBERS_TEST-NEXT: void MemberFunc()
; MEMBERS_TEST-NEXT: private:
; MEMBERS_TEST-DAG: int IntMemberVar
; MEMBERS_TEST-DAG: double DoubleMemberVar
; MEMBERS_TEST: }
; BASE_CLASS_A: ---TYPES---
; BASE_CLASS_A: class BaseClassTest::A {}
; BASE_CLASS_B: ---TYPES---
; BASE_CLASS_B: class BaseClassTest::B
; BASE_CLASS_B-NEXT: : public virtual BaseClassTest::A {
; BASE_CLASS_C: ---TYPES---
; BASE_CLASS_C: class BaseClassTest::C
; BASE_CLASS_C-NEXT: : public virtual BaseClassTest::A {
; BASE_CLASS_D: ---TYPES---
; BASE_CLASS_D: class BaseClassTest::D
; BASE_CLASS_D-DAG: protected BaseClassTest::B
; BASE_CLASS_D-DAG: private BaseClassTest::C
; BASE_CLASS_D-DAG: protected virtual BaseClassTest::A
; UDT_KIND_TEST: ---TYPES---
; UDT_KIND_TEST-DAG: union UdtKindTest::C {}
; UDT_KIND_TEST-DAG: class UdtKindTest::B {}
; UDT_KIND_TEST-DAG: struct UdtKindTest::A {}
; BITFIELD_TEST: ---TYPES---
; BITFIELD_TEST: struct BitFieldTest::A {
; BITFIELD_TEST-NEXT: public:
; BITFIELD_TEST-NEXT: +0x00 int Bits1 : 1
; BITFIELD_TEST-NEXT: +0x00 int Bits2 : 2
; BITFIELD_TEST-NEXT: +0x00 int Bits3 : 3
; BITFIELD_TEST-NEXT: +0x00 int Bits4 : 4
; BITFIELD_TEST-NEXT: +0x00 int Bits22 : 22
; BITFIELD_TEST-NEXT: +0x04 int Offset0x04

40
test/tools/llvm-pdbdump/enum-layout.test
View File

@ -1,20 +1,20 @@
; RUN: llvm-pdbdump -types %p/Inputs/ClassLayoutTest.pdb > %t
; RUN: FileCheck -input-file=%t %s -check-prefix=GLOBAL_ENUM
; RUN: FileCheck -input-file=%t %s -check-prefix=MEMBER_ENUM
; GLOBAL_ENUM: ---TYPES---
; GLOBAL_ENUM: Enums:
; GLOBAL_ENUM: enum GlobalsTest::Enum {
; GLOBAL_ENUM-NEXT: Val1 = 0
; GLOBAL_ENUM-NEXT: }
; MEMBER_ENUM: ---TYPES---
; MEMBER_ENUM: Classes:
; MEMBER_ENUM: struct __vc_attributes::threadingAttribute {
; MEMBER_ENUM-NEXT: enum threading_e {
; MEMBER_ENUM-NEXT: apartment = 1
; MEMBER_ENUM-NEXT: single = 2
; MEMBER_ENUM-NEXT: free = 3
; MEMBER_ENUM-NEXT: neutral = 4
; MEMBER_ENUM-NEXT: both = 5
; MEMBER_ENUM-NEXT: }
; RUN: llvm-pdbdump -types %p/Inputs/ClassLayoutTest.pdb > %t
; RUN: FileCheck -input-file=%t %s -check-prefix=GLOBAL_ENUM
; RUN: FileCheck -input-file=%t %s -check-prefix=MEMBER_ENUM
; GLOBAL_ENUM: ---TYPES---
; GLOBAL_ENUM: Enums:
; GLOBAL_ENUM: enum GlobalsTest::Enum {
; GLOBAL_ENUM-NEXT: Val1 = 0
; GLOBAL_ENUM-NEXT: }
; MEMBER_ENUM: ---TYPES---
; MEMBER_ENUM: Classes:
; MEMBER_ENUM: struct __vc_attributes::threadingAttribute {
; MEMBER_ENUM-NEXT: enum threading_e {
; MEMBER_ENUM-NEXT: apartment = 1
; MEMBER_ENUM-NEXT: single = 2
; MEMBER_ENUM-NEXT: free = 3
; MEMBER_ENUM-NEXT: neutral = 4
; MEMBER_ENUM-NEXT: both = 5
; MEMBER_ENUM-NEXT: }

20
test/tools/llvm-pdbdump/load-address.test
View File

@ -1,10 +1,10 @@
; RUN: llvm-pdbdump -externals %p/Inputs/LoadAddressTest.pdb \
; RUN: | FileCheck --check-prefix=RVA %s
; RUN: llvm-pdbdump -externals -load-address=0x40000000 \
; RUN: %p/Inputs/LoadAddressTest.pdb | FileCheck --check-prefix=VA %s
; RVA: ---EXTERNALS---
; RVA: [0x00001010] _main
; VA: ---EXTERNALS---
; VA: [0x40001010] _main
; RUN: llvm-pdbdump -externals %p/Inputs/LoadAddressTest.pdb \
; RUN: | FileCheck --check-prefix=RVA %s
; RUN: llvm-pdbdump -externals -load-address=0x40000000 \
; RUN: %p/Inputs/LoadAddressTest.pdb | FileCheck --check-prefix=VA %s
; RVA: ---EXTERNALS---
; RVA: [0x00001010] _main
; VA: ---EXTERNALS---
; VA: [0x40001010] _main

2
test/tools/llvm-symbolizer/pdb/lit.local.cfg
View File

@ -1 +1 @@
config.unsupported = not config.have_dia_sdk
config.unsupported = not config.have_dia_sdk

14
unittests/IR/TypesTest.cpp
View File

@ -27,12 +27,12 @@ TEST(TypesTest, StructType) {
EXPECT_FALSE(Struct->hasName());
}
TEST(TypesTest, LayoutIdenticalEmptyStructs) {
LLVMContext C;
StructType *Foo = StructType::create(C, "Foo");
StructType *Bar = StructType::create(C, "Bar");
EXPECT_TRUE(Foo->isLayoutIdentical(Bar));
}
TEST(TypesTest, LayoutIdenticalEmptyStructs) {
LLVMContext C;
StructType *Foo = StructType::create(C, "Foo");
StructType *Bar = StructType::create(C, "Bar");
EXPECT_TRUE(Foo->isLayoutIdentical(Bar));
}
} // end anonymous namespace