mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2025-02-26 10:29:36 +00:00
b8a6712c27
PowerPC supports pre-increment load/store instructions (except for Altivec/VSX
vector load/stores). Using these on embedded cores can be very important, but
most loops are not naturally set up to use them. We can often change that,
however, by placing loops into a non-canonical form. Generically, this means
transforming loops like this:
for (int i = 0; i < n; ++i)
array[i] = c;
to look like this:
T *p = array[-1];
for (int i = 0; i < n; ++i)
*++p = c;
the key point is that addresses accessed are pulled into dedicated PHIs and
"pre-decremented" in the loop preheader. This allows the use of pre-increment
load/store instructions without loop peeling.
A target-specific late IR-level pass (running post-LSR), PPCLoopPreIncPrep, is
introduced to perform this transformation. I've used this code out-of-tree for
generating code for the PPC A2 for over a year. Somewhat to my surprise,
running the test suite + externals on a P7 with this transformation enabled
showed no performance regressions, and one speedup:
External/SPEC/CINT2006/483.xalancbmk/483.xalancbmk
-2.32514% +/- 1.03736%
So I'm going to enable it on everything for now. I was surprised by this
because, on the POWER cores, these pre-increment load/store instructions are
cracked (and, thus, harder to schedule effectively). But seeing no regressions,
and feeling that it is generally easier to split instructions apart late than
it is to combine them late, this might be the better approach regardless.
In the future, we might want to integrate this functionality into LSR (but
currently LSR does not create new PHI nodes, so (for that and other reasons)
significant work would need to be done).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@228328 91177308-0d34-0410-b5e6-96231b3b80d8
101 lines
3.2 KiB
C++
101 lines
3.2 KiB
C++
//===-- PPC.h - Top-level interface for PowerPC Target ----------*- 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 LLVM
|
|
// PowerPC back-end.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#ifndef LLVM_LIB_TARGET_POWERPC_PPC_H
|
|
#define LLVM_LIB_TARGET_POWERPC_PPC_H
|
|
|
|
#include "MCTargetDesc/PPCMCTargetDesc.h"
|
|
#include <string>
|
|
|
|
// GCC #defines PPC on Linux but we use it as our namespace name
|
|
#undef PPC
|
|
|
|
namespace llvm {
|
|
class PPCTargetMachine;
|
|
class PassRegistry;
|
|
class FunctionPass;
|
|
class ImmutablePass;
|
|
class MachineInstr;
|
|
class AsmPrinter;
|
|
class MCInst;
|
|
|
|
FunctionPass *createPPCCTRLoops(PPCTargetMachine &TM);
|
|
#ifndef NDEBUG
|
|
FunctionPass *createPPCCTRLoopsVerify();
|
|
#endif
|
|
FunctionPass *createPPCLoopPreIncPrepPass(PPCTargetMachine &TM);
|
|
FunctionPass *createPPCEarlyReturnPass();
|
|
FunctionPass *createPPCVSXCopyPass();
|
|
FunctionPass *createPPCVSXFMAMutatePass();
|
|
FunctionPass *createPPCBranchSelectionPass();
|
|
FunctionPass *createPPCISelDag(PPCTargetMachine &TM);
|
|
FunctionPass *createPPCTLSDynamicCallPass();
|
|
void LowerPPCMachineInstrToMCInst(const MachineInstr *MI, MCInst &OutMI,
|
|
AsmPrinter &AP, bool isDarwin);
|
|
|
|
void initializePPCVSXFMAMutatePass(PassRegistry&);
|
|
extern char &PPCVSXFMAMutateID;
|
|
|
|
namespace PPCII {
|
|
|
|
/// Target Operand Flag enum.
|
|
enum TOF {
|
|
//===------------------------------------------------------------------===//
|
|
// PPC Specific MachineOperand flags.
|
|
MO_NO_FLAG,
|
|
|
|
/// MO_PLT_OR_STUB - On a symbol operand "FOO", this indicates that the
|
|
/// reference is actually to the "FOO$stub" or "FOO@plt" symbol. This is
|
|
/// used for calls and jumps to external functions on Tiger and earlier, and
|
|
/// for PIC calls on Linux and ELF systems.
|
|
MO_PLT_OR_STUB = 1,
|
|
|
|
/// MO_PIC_FLAG - If this bit is set, the symbol reference is relative to
|
|
/// the function's picbase, e.g. lo16(symbol-picbase).
|
|
MO_PIC_FLAG = 2,
|
|
|
|
/// MO_NLP_FLAG - If this bit is set, the symbol reference is actually to
|
|
/// the non_lazy_ptr for the global, e.g. lo16(symbol$non_lazy_ptr-picbase).
|
|
MO_NLP_FLAG = 4,
|
|
|
|
/// MO_NLP_HIDDEN_FLAG - If this bit is set, the symbol reference is to a
|
|
/// symbol with hidden visibility. This causes a different kind of
|
|
/// non-lazy-pointer to be generated.
|
|
MO_NLP_HIDDEN_FLAG = 8,
|
|
|
|
/// The next are not flags but distinct values.
|
|
MO_ACCESS_MASK = 0xf0,
|
|
|
|
/// MO_LO, MO_HA - lo16(symbol) and ha16(symbol)
|
|
MO_LO = 1 << 4,
|
|
MO_HA = 2 << 4,
|
|
|
|
MO_TPREL_LO = 4 << 4,
|
|
MO_TPREL_HA = 3 << 4,
|
|
|
|
/// These values identify relocations on immediates folded
|
|
/// into memory operations.
|
|
MO_DTPREL_LO = 5 << 4,
|
|
MO_TLSLD_LO = 6 << 4,
|
|
MO_TOC_LO = 7 << 4,
|
|
|
|
// Symbol for VK_PPC_TLS fixup attached to an ADD instruction
|
|
MO_TLS = 8 << 4
|
|
};
|
|
} // end namespace PPCII
|
|
|
|
} // end namespace llvm;
|
|
|
|
#endif
|