mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-11-05 13:09:10 +00:00
c7b902e7fe
The current Intel Atom microarchitecture has a feature whereby when a function returns early then it is slightly faster to execute a sequence of NOP instructions to wait until the return address is ready, as opposed to simply stalling on the ret instruction until the return address is ready. When compiling for X86 Atom only, this patch will run a pass, called "X86PadShortFunction" which will add NOP instructions where less than four cycles elapse between function entry and return. It includes tests. This patch has been updated to address Nadav's review comments - Optimize only at >= O1 and don't do optimization if -Os is set - Stores MachineBasicBlock* instead of BBNum - Uses DenseMap instead of std::map - Fixes placement of braces Patch by Andy Zhang. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@171879 91177308-0d34-0410-b5e6-96231b3b80d8
76 lines
2.7 KiB
C++
76 lines
2.7 KiB
C++
//===-- X86.h - Top-level interface for X86 representation ------*- C++ -*-===//
|
|
//
|
|
// The LLVM Compiler Infrastructure
|
|
//
|
|
// This file is distributed under the University of Illinois Open Source
|
|
// License. See LICENSE.TXT for details.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// This file contains the entry points for global functions defined in the x86
|
|
// target library, as used by the LLVM JIT.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#ifndef TARGET_X86_H
|
|
#define TARGET_X86_H
|
|
|
|
#include "MCTargetDesc/X86BaseInfo.h"
|
|
#include "MCTargetDesc/X86MCTargetDesc.h"
|
|
#include "llvm/Support/DataTypes.h"
|
|
#include "llvm/Target/TargetMachine.h"
|
|
|
|
namespace llvm {
|
|
|
|
class FunctionPass;
|
|
class JITCodeEmitter;
|
|
class X86TargetMachine;
|
|
|
|
/// createX86ISelDag - This pass converts a legalized DAG into a
|
|
/// X86-specific DAG, ready for instruction scheduling.
|
|
///
|
|
FunctionPass *createX86ISelDag(X86TargetMachine &TM,
|
|
CodeGenOpt::Level OptLevel);
|
|
|
|
/// createGlobalBaseRegPass - This pass initializes a global base
|
|
/// register for PIC on x86-32.
|
|
FunctionPass* createGlobalBaseRegPass();
|
|
|
|
/// createCleanupLocalDynamicTLSPass() - This pass combines multiple accesses
|
|
/// to local-dynamic TLS variables so that the TLS base address for the module
|
|
/// is only fetched once per execution path through the function.
|
|
FunctionPass *createCleanupLocalDynamicTLSPass();
|
|
|
|
/// createX86FloatingPointStackifierPass - This function returns a pass which
|
|
/// converts floating point register references and pseudo instructions into
|
|
/// floating point stack references and physical instructions.
|
|
///
|
|
FunctionPass *createX86FloatingPointStackifierPass();
|
|
|
|
/// createX86IssueVZeroUpperPass - This pass inserts AVX vzeroupper instructions
|
|
/// before each call to avoid transition penalty between functions encoded with
|
|
/// AVX and SSE.
|
|
FunctionPass *createX86IssueVZeroUpperPass();
|
|
|
|
/// createX86CodeEmitterPass - Return a pass that emits the collected X86 code
|
|
/// to the specified MCE object.
|
|
FunctionPass *createX86JITCodeEmitterPass(X86TargetMachine &TM,
|
|
JITCodeEmitter &JCE);
|
|
|
|
/// createX86EmitCodeToMemory - Returns a pass that converts a register
|
|
/// allocated function into raw machine code in a dynamically
|
|
/// allocated chunk of memory.
|
|
///
|
|
FunctionPass *createEmitX86CodeToMemory();
|
|
|
|
/// \brief Creates an X86-specific Target Transformation Info pass.
|
|
ImmutablePass *createX86TargetTransformInfoPass(const X86TargetMachine *TM);
|
|
|
|
/// createX86PadShortFunctions - Return a pass that pads short functions
|
|
/// with NOOPs. This will prevent a stall when returning on the Atom.
|
|
FunctionPass *createX86PadShortFunctions();
|
|
|
|
} // End llvm namespace
|
|
|
|
#endif
|