2014-05-24 20:50:23 +08:00
|
|
|
//=- AArch64LoadStoreOptimizer.cpp - AArch64 load/store opt. pass -*- C++ -*-=//
|
2014-03-29 18:18:08 +08:00
|
|
|
//
|
|
|
|
// The LLVM Compiler Infrastructure
|
|
|
|
//
|
|
|
|
// This file is distributed under the University of Illinois Open Source
|
|
|
|
// License. See LICENSE.TXT for details.
|
|
|
|
//
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
//
|
|
|
|
// This file contains a pass that performs load / store related peephole
|
|
|
|
// optimizations. This pass should be run after register allocation.
|
|
|
|
//
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
|
2014-05-24 20:50:23 +08:00
|
|
|
#include "AArch64InstrInfo.h"
|
2014-08-05 05:25:23 +08:00
|
|
|
#include "AArch64Subtarget.h"
|
2014-05-24 20:50:23 +08:00
|
|
|
#include "MCTargetDesc/AArch64AddressingModes.h"
|
2014-03-29 18:18:08 +08:00
|
|
|
#include "llvm/ADT/BitVector.h"
|
2015-05-22 05:36:46 +08:00
|
|
|
#include "llvm/ADT/SmallVector.h"
|
2014-07-25 19:42:14 +08:00
|
|
|
#include "llvm/ADT/Statistic.h"
|
2014-03-29 18:18:08 +08:00
|
|
|
#include "llvm/CodeGen/MachineBasicBlock.h"
|
|
|
|
#include "llvm/CodeGen/MachineFunctionPass.h"
|
|
|
|
#include "llvm/CodeGen/MachineInstr.h"
|
|
|
|
#include "llvm/CodeGen/MachineInstrBuilder.h"
|
|
|
|
#include "llvm/Support/CommandLine.h"
|
|
|
|
#include "llvm/Support/Debug.h"
|
|
|
|
#include "llvm/Support/ErrorHandling.h"
|
|
|
|
#include "llvm/Support/raw_ostream.h"
|
2014-07-25 19:42:14 +08:00
|
|
|
#include "llvm/Target/TargetInstrInfo.h"
|
|
|
|
#include "llvm/Target/TargetMachine.h"
|
|
|
|
#include "llvm/Target/TargetRegisterInfo.h"
|
2014-03-29 18:18:08 +08:00
|
|
|
using namespace llvm;
|
|
|
|
|
2014-05-24 20:50:23 +08:00
|
|
|
#define DEBUG_TYPE "aarch64-ldst-opt"
|
2014-04-22 10:41:26 +08:00
|
|
|
|
2014-05-24 20:50:23 +08:00
|
|
|
/// AArch64AllocLoadStoreOpt - Post-register allocation pass to combine
|
2014-03-29 18:18:08 +08:00
|
|
|
/// load / store instructions to form ldp / stp instructions.
|
|
|
|
|
|
|
|
STATISTIC(NumPairCreated, "Number of load/store pair instructions generated");
|
|
|
|
STATISTIC(NumPostFolded, "Number of post-index updates folded");
|
|
|
|
STATISTIC(NumPreFolded, "Number of pre-index updates folded");
|
|
|
|
STATISTIC(NumUnscaledPairCreated,
|
|
|
|
"Number of load/store from unscaled generated");
|
|
|
|
|
2014-06-04 20:40:35 +08:00
|
|
|
static cl::opt<unsigned> ScanLimit("aarch64-load-store-scan-limit",
|
|
|
|
cl::init(20), cl::Hidden);
|
2014-03-29 18:18:08 +08:00
|
|
|
|
|
|
|
// Place holder while testing unscaled load/store combining
|
2014-06-04 20:40:35 +08:00
|
|
|
static cl::opt<bool> EnableAArch64UnscaledMemOp(
|
|
|
|
"aarch64-unscaled-mem-op", cl::Hidden,
|
|
|
|
cl::desc("Allow AArch64 unscaled load/store combining"), cl::init(true));
|
2014-03-29 18:18:08 +08:00
|
|
|
|
2015-08-05 21:44:51 +08:00
|
|
|
namespace llvm {
|
|
|
|
void initializeAArch64LoadStoreOptPass(PassRegistry &);
|
|
|
|
}
|
|
|
|
|
|
|
|
#define AARCH64_LOAD_STORE_OPT_NAME "AArch64 load / store optimization pass"
|
|
|
|
|
2014-03-29 18:18:08 +08:00
|
|
|
namespace {
|
2015-07-22 01:42:04 +08:00
|
|
|
|
|
|
|
typedef struct LdStPairFlags {
|
|
|
|
// If a matching instruction is found, MergeForward is set to true if the
|
|
|
|
// merge is to remove the first instruction and replace the second with
|
|
|
|
// a pair-wise insn, and false if the reverse is true.
|
|
|
|
bool MergeForward;
|
|
|
|
|
|
|
|
// SExtIdx gives the index of the result of the load pair that must be
|
|
|
|
// extended. The value of SExtIdx assumes that the paired load produces the
|
|
|
|
// value in this order: (I, returned iterator), i.e., -1 means no value has
|
|
|
|
// to be extended, 0 means I, and 1 means the returned iterator.
|
|
|
|
int SExtIdx;
|
|
|
|
|
|
|
|
LdStPairFlags() : MergeForward(false), SExtIdx(-1) {}
|
|
|
|
|
|
|
|
void setMergeForward(bool V = true) { MergeForward = V; }
|
|
|
|
bool getMergeForward() const { return MergeForward; }
|
|
|
|
|
|
|
|
void setSExtIdx(int V) { SExtIdx = V; }
|
|
|
|
int getSExtIdx() const { return SExtIdx; }
|
|
|
|
|
|
|
|
} LdStPairFlags;
|
|
|
|
|
2014-05-24 20:50:23 +08:00
|
|
|
struct AArch64LoadStoreOpt : public MachineFunctionPass {
|
2014-03-29 18:18:08 +08:00
|
|
|
static char ID;
|
2015-08-05 21:44:51 +08:00
|
|
|
AArch64LoadStoreOpt() : MachineFunctionPass(ID) {
|
|
|
|
initializeAArch64LoadStoreOptPass(*PassRegistry::getPassRegistry());
|
|
|
|
}
|
2014-03-29 18:18:08 +08:00
|
|
|
|
2014-05-24 20:50:23 +08:00
|
|
|
const AArch64InstrInfo *TII;
|
2014-03-29 18:18:08 +08:00
|
|
|
const TargetRegisterInfo *TRI;
|
|
|
|
|
|
|
|
// Scan the instructions looking for a load/store that can be combined
|
|
|
|
// with the current instruction into a load/store pair.
|
|
|
|
// Return the matching instruction if one is found, else MBB->end().
|
|
|
|
MachineBasicBlock::iterator findMatchingInsn(MachineBasicBlock::iterator I,
|
2015-07-22 01:42:04 +08:00
|
|
|
LdStPairFlags &Flags,
|
2014-03-29 18:18:08 +08:00
|
|
|
unsigned Limit);
|
|
|
|
// Merge the two instructions indicated into a single pair-wise instruction.
|
2014-06-04 20:36:28 +08:00
|
|
|
// If MergeForward is true, erase the first instruction and fold its
|
2014-03-29 18:18:08 +08:00
|
|
|
// operation into the second. If false, the reverse. Return the instruction
|
2014-04-04 07:43:12 +08:00
|
|
|
// following the first instruction (which may change during processing).
|
2014-03-29 18:18:08 +08:00
|
|
|
MachineBasicBlock::iterator
|
|
|
|
mergePairedInsns(MachineBasicBlock::iterator I,
|
2015-07-22 01:42:04 +08:00
|
|
|
MachineBasicBlock::iterator Paired,
|
2015-07-22 01:47:56 +08:00
|
|
|
const LdStPairFlags &Flags);
|
2014-03-29 18:18:08 +08:00
|
|
|
|
|
|
|
// Scan the instruction list to find a base register update that can
|
|
|
|
// be combined with the current instruction (a load or store) using
|
|
|
|
// pre or post indexed addressing with writeback. Scan forwards.
|
|
|
|
MachineBasicBlock::iterator
|
|
|
|
findMatchingUpdateInsnForward(MachineBasicBlock::iterator I, unsigned Limit,
|
2015-10-01 21:33:31 +08:00
|
|
|
int UnscaledOffset);
|
2014-03-29 18:18:08 +08:00
|
|
|
|
|
|
|
// Scan the instruction list to find a base register update that can
|
|
|
|
// be combined with the current instruction (a load or store) using
|
|
|
|
// pre or post indexed addressing with writeback. Scan backwards.
|
|
|
|
MachineBasicBlock::iterator
|
|
|
|
findMatchingUpdateInsnBackward(MachineBasicBlock::iterator I, unsigned Limit);
|
|
|
|
|
2015-09-26 01:48:17 +08:00
|
|
|
// Find an instruction that updates the base register of the ld/st
|
|
|
|
// instruction.
|
|
|
|
bool isMatchingUpdateInsn(MachineInstr *MemMI, MachineInstr *MI,
|
|
|
|
unsigned BaseReg, int Offset);
|
|
|
|
|
2015-09-23 21:51:44 +08:00
|
|
|
// Merge a pre- or post-index base register update into a ld/st instruction.
|
2014-03-29 18:18:08 +08:00
|
|
|
MachineBasicBlock::iterator
|
2015-09-23 21:51:44 +08:00
|
|
|
mergeUpdateInsn(MachineBasicBlock::iterator I,
|
|
|
|
MachineBasicBlock::iterator Update, bool IsPreIdx);
|
2014-03-29 18:18:08 +08:00
|
|
|
|
|
|
|
bool optimizeBlock(MachineBasicBlock &MBB);
|
|
|
|
|
2014-04-29 15:58:25 +08:00
|
|
|
bool runOnMachineFunction(MachineFunction &Fn) override;
|
2014-03-29 18:18:08 +08:00
|
|
|
|
2014-04-29 15:58:25 +08:00
|
|
|
const char *getPassName() const override {
|
2015-08-05 21:44:51 +08:00
|
|
|
return AARCH64_LOAD_STORE_OPT_NAME;
|
2014-03-29 18:18:08 +08:00
|
|
|
}
|
|
|
|
};
|
2014-05-24 20:50:23 +08:00
|
|
|
char AArch64LoadStoreOpt::ID = 0;
|
2014-08-12 06:42:31 +08:00
|
|
|
} // namespace
|
2014-03-29 18:18:08 +08:00
|
|
|
|
2015-08-05 21:44:51 +08:00
|
|
|
INITIALIZE_PASS(AArch64LoadStoreOpt, "aarch64-ldst-opt",
|
|
|
|
AARCH64_LOAD_STORE_OPT_NAME, false, false)
|
|
|
|
|
2015-08-07 01:37:18 +08:00
|
|
|
static bool isUnscaledLdSt(unsigned Opc) {
|
2014-03-29 18:18:08 +08:00
|
|
|
switch (Opc) {
|
|
|
|
default:
|
|
|
|
return false;
|
2014-05-24 20:50:23 +08:00
|
|
|
case AArch64::STURSi:
|
|
|
|
case AArch64::STURDi:
|
|
|
|
case AArch64::STURQi:
|
|
|
|
case AArch64::STURWi:
|
|
|
|
case AArch64::STURXi:
|
|
|
|
case AArch64::LDURSi:
|
|
|
|
case AArch64::LDURDi:
|
|
|
|
case AArch64::LDURQi:
|
|
|
|
case AArch64::LDURWi:
|
|
|
|
case AArch64::LDURXi:
|
2015-01-24 09:25:54 +08:00
|
|
|
case AArch64::LDURSWi:
|
|
|
|
return true;
|
2014-03-29 18:18:08 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2015-08-07 01:37:18 +08:00
|
|
|
static bool isUnscaledLdSt(MachineInstr *MI) {
|
|
|
|
return isUnscaledLdSt(MI->getOpcode());
|
|
|
|
}
|
|
|
|
|
2015-09-30 00:07:32 +08:00
|
|
|
// Scaling factor for unscaled load or store.
|
|
|
|
static int getMemScale(MachineInstr *MI) {
|
2015-08-07 01:37:18 +08:00
|
|
|
switch (MI->getOpcode()) {
|
2014-03-29 18:18:08 +08:00
|
|
|
default:
|
2015-09-30 02:26:15 +08:00
|
|
|
llvm_unreachable("Opcode has unknown scale!");
|
|
|
|
case AArch64::LDRBBui:
|
|
|
|
case AArch64::STRBBui:
|
|
|
|
return 1;
|
|
|
|
case AArch64::LDRHHui:
|
|
|
|
case AArch64::STRHHui:
|
|
|
|
return 2;
|
2015-09-29 22:57:10 +08:00
|
|
|
case AArch64::LDRSui:
|
|
|
|
case AArch64::LDURSi:
|
|
|
|
case AArch64::LDRSWui:
|
|
|
|
case AArch64::LDURSWi:
|
|
|
|
case AArch64::LDRWui:
|
|
|
|
case AArch64::LDURWi:
|
2014-05-24 20:50:23 +08:00
|
|
|
case AArch64::STRSui:
|
|
|
|
case AArch64::STURSi:
|
|
|
|
case AArch64::STRWui:
|
|
|
|
case AArch64::STURWi:
|
2015-09-30 00:07:32 +08:00
|
|
|
case AArch64::LDPSi:
|
2015-09-30 04:39:55 +08:00
|
|
|
case AArch64::LDPSWi:
|
2015-09-30 00:07:32 +08:00
|
|
|
case AArch64::LDPWi:
|
|
|
|
case AArch64::STPSi:
|
|
|
|
case AArch64::STPWi:
|
2014-03-29 18:18:08 +08:00
|
|
|
return 4;
|
2014-05-24 20:50:23 +08:00
|
|
|
case AArch64::LDRDui:
|
|
|
|
case AArch64::LDURDi:
|
2015-09-29 22:57:10 +08:00
|
|
|
case AArch64::LDRXui:
|
|
|
|
case AArch64::LDURXi:
|
|
|
|
case AArch64::STRDui:
|
|
|
|
case AArch64::STURDi:
|
|
|
|
case AArch64::STRXui:
|
|
|
|
case AArch64::STURXi:
|
2015-09-30 00:07:32 +08:00
|
|
|
case AArch64::LDPDi:
|
|
|
|
case AArch64::LDPXi:
|
|
|
|
case AArch64::STPDi:
|
|
|
|
case AArch64::STPXi:
|
2014-03-29 18:18:08 +08:00
|
|
|
return 8;
|
2014-05-24 20:50:23 +08:00
|
|
|
case AArch64::LDRQui:
|
|
|
|
case AArch64::LDURQi:
|
2015-09-29 22:57:10 +08:00
|
|
|
case AArch64::STRQui:
|
|
|
|
case AArch64::STURQi:
|
2015-09-30 00:07:32 +08:00
|
|
|
case AArch64::LDPQi:
|
|
|
|
case AArch64::STPQi:
|
2014-03-29 18:18:08 +08:00
|
|
|
return 16;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2015-03-07 06:42:10 +08:00
|
|
|
static unsigned getMatchingNonSExtOpcode(unsigned Opc,
|
|
|
|
bool *IsValidLdStrOpc = nullptr) {
|
|
|
|
if (IsValidLdStrOpc)
|
|
|
|
*IsValidLdStrOpc = true;
|
|
|
|
switch (Opc) {
|
|
|
|
default:
|
|
|
|
if (IsValidLdStrOpc)
|
|
|
|
*IsValidLdStrOpc = false;
|
|
|
|
return UINT_MAX;
|
|
|
|
case AArch64::STRDui:
|
|
|
|
case AArch64::STURDi:
|
|
|
|
case AArch64::STRQui:
|
|
|
|
case AArch64::STURQi:
|
|
|
|
case AArch64::STRWui:
|
|
|
|
case AArch64::STURWi:
|
|
|
|
case AArch64::STRXui:
|
|
|
|
case AArch64::STURXi:
|
|
|
|
case AArch64::LDRDui:
|
|
|
|
case AArch64::LDURDi:
|
|
|
|
case AArch64::LDRQui:
|
|
|
|
case AArch64::LDURQi:
|
|
|
|
case AArch64::LDRWui:
|
|
|
|
case AArch64::LDURWi:
|
|
|
|
case AArch64::LDRXui:
|
|
|
|
case AArch64::LDURXi:
|
|
|
|
case AArch64::STRSui:
|
|
|
|
case AArch64::STURSi:
|
|
|
|
case AArch64::LDRSui:
|
|
|
|
case AArch64::LDURSi:
|
|
|
|
return Opc;
|
|
|
|
case AArch64::LDRSWui:
|
|
|
|
return AArch64::LDRWui;
|
|
|
|
case AArch64::LDURSWi:
|
|
|
|
return AArch64::LDURWi;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2014-03-29 18:18:08 +08:00
|
|
|
static unsigned getMatchingPairOpcode(unsigned Opc) {
|
|
|
|
switch (Opc) {
|
|
|
|
default:
|
|
|
|
llvm_unreachable("Opcode has no pairwise equivalent!");
|
2014-05-24 20:50:23 +08:00
|
|
|
case AArch64::STRSui:
|
|
|
|
case AArch64::STURSi:
|
|
|
|
return AArch64::STPSi;
|
|
|
|
case AArch64::STRDui:
|
|
|
|
case AArch64::STURDi:
|
|
|
|
return AArch64::STPDi;
|
|
|
|
case AArch64::STRQui:
|
|
|
|
case AArch64::STURQi:
|
|
|
|
return AArch64::STPQi;
|
|
|
|
case AArch64::STRWui:
|
|
|
|
case AArch64::STURWi:
|
|
|
|
return AArch64::STPWi;
|
|
|
|
case AArch64::STRXui:
|
|
|
|
case AArch64::STURXi:
|
|
|
|
return AArch64::STPXi;
|
|
|
|
case AArch64::LDRSui:
|
|
|
|
case AArch64::LDURSi:
|
|
|
|
return AArch64::LDPSi;
|
|
|
|
case AArch64::LDRDui:
|
|
|
|
case AArch64::LDURDi:
|
|
|
|
return AArch64::LDPDi;
|
|
|
|
case AArch64::LDRQui:
|
|
|
|
case AArch64::LDURQi:
|
|
|
|
return AArch64::LDPQi;
|
|
|
|
case AArch64::LDRWui:
|
|
|
|
case AArch64::LDURWi:
|
|
|
|
return AArch64::LDPWi;
|
|
|
|
case AArch64::LDRXui:
|
|
|
|
case AArch64::LDURXi:
|
|
|
|
return AArch64::LDPXi;
|
2015-01-24 09:25:54 +08:00
|
|
|
case AArch64::LDRSWui:
|
|
|
|
case AArch64::LDURSWi:
|
|
|
|
return AArch64::LDPSWi;
|
2014-03-29 18:18:08 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
static unsigned getPreIndexedOpcode(unsigned Opc) {
|
|
|
|
switch (Opc) {
|
|
|
|
default:
|
|
|
|
llvm_unreachable("Opcode has no pre-indexed equivalent!");
|
2014-06-04 20:40:35 +08:00
|
|
|
case AArch64::STRSui:
|
|
|
|
return AArch64::STRSpre;
|
|
|
|
case AArch64::STRDui:
|
|
|
|
return AArch64::STRDpre;
|
|
|
|
case AArch64::STRQui:
|
|
|
|
return AArch64::STRQpre;
|
2015-09-30 02:26:15 +08:00
|
|
|
case AArch64::STRBBui:
|
|
|
|
return AArch64::STRBBpre;
|
|
|
|
case AArch64::STRHHui:
|
|
|
|
return AArch64::STRHHpre;
|
2014-06-04 20:40:35 +08:00
|
|
|
case AArch64::STRWui:
|
|
|
|
return AArch64::STRWpre;
|
|
|
|
case AArch64::STRXui:
|
|
|
|
return AArch64::STRXpre;
|
|
|
|
case AArch64::LDRSui:
|
|
|
|
return AArch64::LDRSpre;
|
|
|
|
case AArch64::LDRDui:
|
|
|
|
return AArch64::LDRDpre;
|
|
|
|
case AArch64::LDRQui:
|
|
|
|
return AArch64::LDRQpre;
|
2015-09-30 02:26:15 +08:00
|
|
|
case AArch64::LDRBBui:
|
|
|
|
return AArch64::LDRBBpre;
|
|
|
|
case AArch64::LDRHHui:
|
|
|
|
return AArch64::LDRHHpre;
|
2014-06-04 20:40:35 +08:00
|
|
|
case AArch64::LDRWui:
|
|
|
|
return AArch64::LDRWpre;
|
|
|
|
case AArch64::LDRXui:
|
|
|
|
return AArch64::LDRXpre;
|
2015-01-24 09:25:54 +08:00
|
|
|
case AArch64::LDRSWui:
|
|
|
|
return AArch64::LDRSWpre;
|
2015-09-26 01:48:17 +08:00
|
|
|
case AArch64::LDPSi:
|
|
|
|
return AArch64::LDPSpre;
|
2015-09-30 04:39:55 +08:00
|
|
|
case AArch64::LDPSWi:
|
|
|
|
return AArch64::LDPSWpre;
|
2015-09-26 01:48:17 +08:00
|
|
|
case AArch64::LDPDi:
|
|
|
|
return AArch64::LDPDpre;
|
|
|
|
case AArch64::LDPQi:
|
|
|
|
return AArch64::LDPQpre;
|
|
|
|
case AArch64::LDPWi:
|
|
|
|
return AArch64::LDPWpre;
|
|
|
|
case AArch64::LDPXi:
|
|
|
|
return AArch64::LDPXpre;
|
|
|
|
case AArch64::STPSi:
|
|
|
|
return AArch64::STPSpre;
|
|
|
|
case AArch64::STPDi:
|
|
|
|
return AArch64::STPDpre;
|
|
|
|
case AArch64::STPQi:
|
|
|
|
return AArch64::STPQpre;
|
|
|
|
case AArch64::STPWi:
|
|
|
|
return AArch64::STPWpre;
|
|
|
|
case AArch64::STPXi:
|
|
|
|
return AArch64::STPXpre;
|
2014-03-29 18:18:08 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
static unsigned getPostIndexedOpcode(unsigned Opc) {
|
|
|
|
switch (Opc) {
|
|
|
|
default:
|
|
|
|
llvm_unreachable("Opcode has no post-indexed wise equivalent!");
|
2014-05-24 20:50:23 +08:00
|
|
|
case AArch64::STRSui:
|
|
|
|
return AArch64::STRSpost;
|
|
|
|
case AArch64::STRDui:
|
|
|
|
return AArch64::STRDpost;
|
|
|
|
case AArch64::STRQui:
|
|
|
|
return AArch64::STRQpost;
|
2015-09-30 02:26:15 +08:00
|
|
|
case AArch64::STRBBui:
|
|
|
|
return AArch64::STRBBpost;
|
|
|
|
case AArch64::STRHHui:
|
|
|
|
return AArch64::STRHHpost;
|
2014-05-24 20:50:23 +08:00
|
|
|
case AArch64::STRWui:
|
|
|
|
return AArch64::STRWpost;
|
|
|
|
case AArch64::STRXui:
|
|
|
|
return AArch64::STRXpost;
|
|
|
|
case AArch64::LDRSui:
|
|
|
|
return AArch64::LDRSpost;
|
|
|
|
case AArch64::LDRDui:
|
|
|
|
return AArch64::LDRDpost;
|
|
|
|
case AArch64::LDRQui:
|
|
|
|
return AArch64::LDRQpost;
|
2015-09-30 02:26:15 +08:00
|
|
|
case AArch64::LDRBBui:
|
|
|
|
return AArch64::LDRBBpost;
|
|
|
|
case AArch64::LDRHHui:
|
|
|
|
return AArch64::LDRHHpost;
|
2014-05-24 20:50:23 +08:00
|
|
|
case AArch64::LDRWui:
|
|
|
|
return AArch64::LDRWpost;
|
|
|
|
case AArch64::LDRXui:
|
|
|
|
return AArch64::LDRXpost;
|
2015-01-24 09:25:54 +08:00
|
|
|
case AArch64::LDRSWui:
|
|
|
|
return AArch64::LDRSWpost;
|
2015-09-26 01:48:17 +08:00
|
|
|
case AArch64::LDPSi:
|
|
|
|
return AArch64::LDPSpost;
|
2015-09-30 04:39:55 +08:00
|
|
|
case AArch64::LDPSWi:
|
|
|
|
return AArch64::LDPSWpost;
|
2015-09-26 01:48:17 +08:00
|
|
|
case AArch64::LDPDi:
|
|
|
|
return AArch64::LDPDpost;
|
|
|
|
case AArch64::LDPQi:
|
|
|
|
return AArch64::LDPQpost;
|
|
|
|
case AArch64::LDPWi:
|
|
|
|
return AArch64::LDPWpost;
|
|
|
|
case AArch64::LDPXi:
|
|
|
|
return AArch64::LDPXpost;
|
|
|
|
case AArch64::STPSi:
|
|
|
|
return AArch64::STPSpost;
|
|
|
|
case AArch64::STPDi:
|
|
|
|
return AArch64::STPDpost;
|
|
|
|
case AArch64::STPQi:
|
|
|
|
return AArch64::STPQpost;
|
|
|
|
case AArch64::STPWi:
|
|
|
|
return AArch64::STPWpost;
|
|
|
|
case AArch64::STPXi:
|
|
|
|
return AArch64::STPXpost;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
static bool isPairedLdSt(const MachineInstr *MI) {
|
|
|
|
switch (MI->getOpcode()) {
|
|
|
|
default:
|
|
|
|
return false;
|
|
|
|
case AArch64::LDPSi:
|
2015-09-30 04:39:55 +08:00
|
|
|
case AArch64::LDPSWi:
|
2015-09-26 01:48:17 +08:00
|
|
|
case AArch64::LDPDi:
|
|
|
|
case AArch64::LDPQi:
|
|
|
|
case AArch64::LDPWi:
|
|
|
|
case AArch64::LDPXi:
|
|
|
|
case AArch64::STPSi:
|
|
|
|
case AArch64::STPDi:
|
|
|
|
case AArch64::STPQi:
|
|
|
|
case AArch64::STPWi:
|
|
|
|
case AArch64::STPXi:
|
|
|
|
return true;
|
2014-03-29 18:18:08 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2015-09-26 01:48:17 +08:00
|
|
|
static const MachineOperand &getLdStRegOp(const MachineInstr *MI,
|
|
|
|
unsigned PairedRegOp = 0) {
|
|
|
|
assert(PairedRegOp < 2 && "Unexpected register operand idx.");
|
|
|
|
unsigned Idx = isPairedLdSt(MI) ? PairedRegOp : 0;
|
|
|
|
return MI->getOperand(Idx);
|
2015-08-06 23:50:12 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static const MachineOperand &getLdStBaseOp(const MachineInstr *MI) {
|
2015-09-26 01:48:17 +08:00
|
|
|
unsigned Idx = isPairedLdSt(MI) ? 2 : 1;
|
|
|
|
return MI->getOperand(Idx);
|
2015-08-06 23:50:12 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static const MachineOperand &getLdStOffsetOp(const MachineInstr *MI) {
|
2015-09-26 01:48:17 +08:00
|
|
|
unsigned Idx = isPairedLdSt(MI) ? 3 : 2;
|
|
|
|
return MI->getOperand(Idx);
|
2015-08-06 23:50:12 +08:00
|
|
|
}
|
|
|
|
|
2014-03-29 18:18:08 +08:00
|
|
|
MachineBasicBlock::iterator
|
2014-05-24 20:50:23 +08:00
|
|
|
AArch64LoadStoreOpt::mergePairedInsns(MachineBasicBlock::iterator I,
|
|
|
|
MachineBasicBlock::iterator Paired,
|
2015-07-22 01:42:04 +08:00
|
|
|
const LdStPairFlags &Flags) {
|
2014-03-29 18:18:08 +08:00
|
|
|
MachineBasicBlock::iterator NextI = I;
|
|
|
|
++NextI;
|
|
|
|
// If NextI is the second of the two instructions to be merged, we need
|
|
|
|
// to skip one further. Either way we merge will invalidate the iterator,
|
|
|
|
// and we don't need to scan the new instruction, as it's a pairwise
|
|
|
|
// instruction, which we're not considering for further action anyway.
|
|
|
|
if (NextI == Paired)
|
|
|
|
++NextI;
|
|
|
|
|
2015-07-22 01:42:04 +08:00
|
|
|
int SExtIdx = Flags.getSExtIdx();
|
2015-03-07 06:42:10 +08:00
|
|
|
unsigned Opc =
|
|
|
|
SExtIdx == -1 ? I->getOpcode() : getMatchingNonSExtOpcode(I->getOpcode());
|
2015-08-07 01:37:18 +08:00
|
|
|
bool IsUnscaled = isUnscaledLdSt(Opc);
|
2014-05-24 20:50:23 +08:00
|
|
|
int OffsetStride =
|
2015-09-30 00:07:32 +08:00
|
|
|
IsUnscaled && EnableAArch64UnscaledMemOp ? getMemScale(I) : 1;
|
2014-03-29 18:18:08 +08:00
|
|
|
|
2015-07-22 01:42:04 +08:00
|
|
|
bool MergeForward = Flags.getMergeForward();
|
2015-03-07 06:42:10 +08:00
|
|
|
unsigned NewOpc = getMatchingPairOpcode(Opc);
|
2014-03-29 18:18:08 +08:00
|
|
|
// Insert our new paired instruction after whichever of the paired
|
2014-06-04 20:36:28 +08:00
|
|
|
// instructions MergeForward indicates.
|
|
|
|
MachineBasicBlock::iterator InsertionPoint = MergeForward ? Paired : I;
|
|
|
|
// Also based on MergeForward is from where we copy the base register operand
|
2014-03-29 18:18:08 +08:00
|
|
|
// so we get the flags compatible with the input code.
|
2015-08-06 23:50:12 +08:00
|
|
|
const MachineOperand &BaseRegOp =
|
|
|
|
MergeForward ? getLdStBaseOp(Paired) : getLdStBaseOp(I);
|
2014-03-29 18:18:08 +08:00
|
|
|
|
|
|
|
// Which register is Rt and which is Rt2 depends on the offset order.
|
|
|
|
MachineInstr *RtMI, *Rt2MI;
|
2015-09-04 00:41:28 +08:00
|
|
|
if (getLdStOffsetOp(I).getImm() ==
|
|
|
|
getLdStOffsetOp(Paired).getImm() + OffsetStride) {
|
2014-03-29 18:18:08 +08:00
|
|
|
RtMI = Paired;
|
|
|
|
Rt2MI = I;
|
2015-03-07 06:42:10 +08:00
|
|
|
// Here we swapped the assumption made for SExtIdx.
|
|
|
|
// I.e., we turn ldp I, Paired into ldp Paired, I.
|
|
|
|
// Update the index accordingly.
|
|
|
|
if (SExtIdx != -1)
|
|
|
|
SExtIdx = (SExtIdx + 1) % 2;
|
2014-03-29 18:18:08 +08:00
|
|
|
} else {
|
|
|
|
RtMI = I;
|
|
|
|
Rt2MI = Paired;
|
|
|
|
}
|
2015-09-04 00:41:28 +08:00
|
|
|
// Handle Unscaled
|
2015-08-06 23:50:12 +08:00
|
|
|
int OffsetImm = getLdStOffsetOp(RtMI).getImm();
|
2015-09-04 00:41:28 +08:00
|
|
|
if (IsUnscaled && EnableAArch64UnscaledMemOp)
|
|
|
|
OffsetImm /= OffsetStride;
|
2014-03-29 18:18:08 +08:00
|
|
|
|
|
|
|
// Construct the new instruction.
|
|
|
|
MachineInstrBuilder MIB = BuildMI(*I->getParent(), InsertionPoint,
|
|
|
|
I->getDebugLoc(), TII->get(NewOpc))
|
2015-08-06 23:50:12 +08:00
|
|
|
.addOperand(getLdStRegOp(RtMI))
|
|
|
|
.addOperand(getLdStRegOp(Rt2MI))
|
2014-03-29 18:18:08 +08:00
|
|
|
.addOperand(BaseRegOp)
|
|
|
|
.addImm(OffsetImm);
|
|
|
|
(void)MIB;
|
|
|
|
|
|
|
|
// FIXME: Do we need/want to copy the mem operands from the source
|
|
|
|
// instructions? Probably. What uses them after this?
|
|
|
|
|
|
|
|
DEBUG(dbgs() << "Creating pair load/store. Replacing instructions:\n ");
|
|
|
|
DEBUG(I->print(dbgs()));
|
|
|
|
DEBUG(dbgs() << " ");
|
|
|
|
DEBUG(Paired->print(dbgs()));
|
|
|
|
DEBUG(dbgs() << " with instruction:\n ");
|
2015-03-07 06:42:10 +08:00
|
|
|
|
|
|
|
if (SExtIdx != -1) {
|
|
|
|
// Generate the sign extension for the proper result of the ldp.
|
|
|
|
// I.e., with X1, that would be:
|
|
|
|
// %W1<def> = KILL %W1, %X1<imp-def>
|
|
|
|
// %X1<def> = SBFMXri %X1<kill>, 0, 31
|
|
|
|
MachineOperand &DstMO = MIB->getOperand(SExtIdx);
|
|
|
|
// Right now, DstMO has the extended register, since it comes from an
|
|
|
|
// extended opcode.
|
|
|
|
unsigned DstRegX = DstMO.getReg();
|
|
|
|
// Get the W variant of that register.
|
|
|
|
unsigned DstRegW = TRI->getSubReg(DstRegX, AArch64::sub_32);
|
|
|
|
// Update the result of LDP to use the W instead of the X variant.
|
|
|
|
DstMO.setReg(DstRegW);
|
|
|
|
DEBUG(((MachineInstr *)MIB)->print(dbgs()));
|
|
|
|
DEBUG(dbgs() << "\n");
|
|
|
|
// Make the machine verifier happy by providing a definition for
|
|
|
|
// the X register.
|
|
|
|
// Insert this definition right after the generated LDP, i.e., before
|
|
|
|
// InsertionPoint.
|
|
|
|
MachineInstrBuilder MIBKill =
|
|
|
|
BuildMI(*I->getParent(), InsertionPoint, I->getDebugLoc(),
|
|
|
|
TII->get(TargetOpcode::KILL), DstRegW)
|
|
|
|
.addReg(DstRegW)
|
|
|
|
.addReg(DstRegX, RegState::Define);
|
|
|
|
MIBKill->getOperand(2).setImplicit();
|
|
|
|
// Create the sign extension.
|
|
|
|
MachineInstrBuilder MIBSXTW =
|
|
|
|
BuildMI(*I->getParent(), InsertionPoint, I->getDebugLoc(),
|
|
|
|
TII->get(AArch64::SBFMXri), DstRegX)
|
|
|
|
.addReg(DstRegX)
|
|
|
|
.addImm(0)
|
|
|
|
.addImm(31);
|
|
|
|
(void)MIBSXTW;
|
|
|
|
DEBUG(dbgs() << " Extend operand:\n ");
|
|
|
|
DEBUG(((MachineInstr *)MIBSXTW)->print(dbgs()));
|
|
|
|
DEBUG(dbgs() << "\n");
|
|
|
|
} else {
|
|
|
|
DEBUG(((MachineInstr *)MIB)->print(dbgs()));
|
|
|
|
DEBUG(dbgs() << "\n");
|
|
|
|
}
|
2014-03-29 18:18:08 +08:00
|
|
|
|
|
|
|
// Erase the old instructions.
|
|
|
|
I->eraseFromParent();
|
|
|
|
Paired->eraseFromParent();
|
|
|
|
|
|
|
|
return NextI;
|
|
|
|
}
|
|
|
|
|
|
|
|
/// trackRegDefsUses - Remember what registers the specified instruction uses
|
|
|
|
/// and modifies.
|
2015-08-04 03:04:32 +08:00
|
|
|
static void trackRegDefsUses(const MachineInstr *MI, BitVector &ModifiedRegs,
|
2014-03-29 18:18:08 +08:00
|
|
|
BitVector &UsedRegs,
|
|
|
|
const TargetRegisterInfo *TRI) {
|
2015-08-04 03:04:32 +08:00
|
|
|
for (const MachineOperand &MO : MI->operands()) {
|
2014-03-29 18:18:08 +08:00
|
|
|
if (MO.isRegMask())
|
|
|
|
ModifiedRegs.setBitsNotInMask(MO.getRegMask());
|
|
|
|
|
|
|
|
if (!MO.isReg())
|
|
|
|
continue;
|
|
|
|
unsigned Reg = MO.getReg();
|
|
|
|
if (MO.isDef()) {
|
|
|
|
for (MCRegAliasIterator AI(Reg, TRI, true); AI.isValid(); ++AI)
|
|
|
|
ModifiedRegs.set(*AI);
|
|
|
|
} else {
|
|
|
|
assert(MO.isUse() && "Reg operand not a def and not a use?!?");
|
|
|
|
for (MCRegAliasIterator AI(Reg, TRI, true); AI.isValid(); ++AI)
|
|
|
|
UsedRegs.set(*AI);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
static bool inBoundsForPair(bool IsUnscaled, int Offset, int OffsetStride) {
|
2015-08-19 00:20:03 +08:00
|
|
|
// Convert the byte-offset used by unscaled into an "element" offset used
|
|
|
|
// by the scaled pair load/store instructions.
|
2015-09-04 00:41:28 +08:00
|
|
|
if (IsUnscaled)
|
2015-08-19 00:20:03 +08:00
|
|
|
Offset /= OffsetStride;
|
|
|
|
|
|
|
|
return Offset <= 63 && Offset >= -64;
|
2014-03-29 18:18:08 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
// Do alignment, specialized to power of 2 and for signed ints,
|
|
|
|
// avoiding having to do a C-style cast from uint_64t to int when
|
|
|
|
// using RoundUpToAlignment from include/llvm/Support/MathExtras.h.
|
|
|
|
// FIXME: Move this function to include/MathExtras.h?
|
|
|
|
static int alignTo(int Num, int PowOf2) {
|
|
|
|
return (Num + PowOf2 - 1) & ~(PowOf2 - 1);
|
|
|
|
}
|
|
|
|
|
2015-05-22 05:36:46 +08:00
|
|
|
static bool mayAlias(MachineInstr *MIa, MachineInstr *MIb,
|
|
|
|
const AArch64InstrInfo *TII) {
|
|
|
|
// One of the instructions must modify memory.
|
|
|
|
if (!MIa->mayStore() && !MIb->mayStore())
|
|
|
|
return false;
|
|
|
|
|
|
|
|
// Both instructions must be memory operations.
|
|
|
|
if (!MIa->mayLoadOrStore() && !MIb->mayLoadOrStore())
|
|
|
|
return false;
|
|
|
|
|
|
|
|
return !TII->areMemAccessesTriviallyDisjoint(MIa, MIb);
|
|
|
|
}
|
|
|
|
|
|
|
|
static bool mayAlias(MachineInstr *MIa,
|
|
|
|
SmallVectorImpl<MachineInstr *> &MemInsns,
|
|
|
|
const AArch64InstrInfo *TII) {
|
|
|
|
for (auto &MIb : MemInsns)
|
|
|
|
if (mayAlias(MIa, MIb, TII))
|
|
|
|
return true;
|
|
|
|
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
2014-03-29 18:18:08 +08:00
|
|
|
/// findMatchingInsn - Scan the instructions looking for a load/store that can
|
|
|
|
/// be combined with the current instruction into a load/store pair.
|
|
|
|
MachineBasicBlock::iterator
|
2014-05-24 20:50:23 +08:00
|
|
|
AArch64LoadStoreOpt::findMatchingInsn(MachineBasicBlock::iterator I,
|
2015-07-22 01:42:04 +08:00
|
|
|
LdStPairFlags &Flags,
|
2015-03-07 06:42:10 +08:00
|
|
|
unsigned Limit) {
|
2014-03-29 18:18:08 +08:00
|
|
|
MachineBasicBlock::iterator E = I->getParent()->end();
|
|
|
|
MachineBasicBlock::iterator MBBI = I;
|
|
|
|
MachineInstr *FirstMI = I;
|
|
|
|
++MBBI;
|
|
|
|
|
2015-05-19 04:27:55 +08:00
|
|
|
unsigned Opc = FirstMI->getOpcode();
|
2014-06-04 20:36:28 +08:00
|
|
|
bool MayLoad = FirstMI->mayLoad();
|
2015-08-07 01:37:18 +08:00
|
|
|
bool IsUnscaled = isUnscaledLdSt(FirstMI);
|
2015-08-06 23:50:12 +08:00
|
|
|
unsigned Reg = getLdStRegOp(FirstMI).getReg();
|
|
|
|
unsigned BaseReg = getLdStBaseOp(FirstMI).getReg();
|
|
|
|
int Offset = getLdStOffsetOp(FirstMI).getImm();
|
2014-03-29 18:18:08 +08:00
|
|
|
|
|
|
|
// Early exit if the first instruction modifies the base register.
|
|
|
|
// e.g., ldr x0, [x0]
|
|
|
|
if (FirstMI->modifiesRegister(BaseReg, TRI))
|
|
|
|
return E;
|
2015-08-11 01:17:19 +08:00
|
|
|
|
|
|
|
// Early exit if the offset if not possible to match. (6 bits of positive
|
|
|
|
// range, plus allow an extra one in case we find a later insn that matches
|
|
|
|
// with Offset-1)
|
2014-03-29 18:18:08 +08:00
|
|
|
int OffsetStride =
|
2015-09-30 00:07:32 +08:00
|
|
|
IsUnscaled && EnableAArch64UnscaledMemOp ? getMemScale(FirstMI) : 1;
|
2014-03-29 18:18:08 +08:00
|
|
|
if (!inBoundsForPair(IsUnscaled, Offset, OffsetStride))
|
|
|
|
return E;
|
|
|
|
|
|
|
|
// Track which registers have been modified and used between the first insn
|
|
|
|
// (inclusive) and the second insn.
|
|
|
|
BitVector ModifiedRegs, UsedRegs;
|
|
|
|
ModifiedRegs.resize(TRI->getNumRegs());
|
|
|
|
UsedRegs.resize(TRI->getNumRegs());
|
2015-05-22 05:36:46 +08:00
|
|
|
|
|
|
|
// Remember any instructions that read/write memory between FirstMI and MI.
|
|
|
|
SmallVector<MachineInstr *, 4> MemInsns;
|
|
|
|
|
2014-03-29 18:18:08 +08:00
|
|
|
for (unsigned Count = 0; MBBI != E && Count < Limit; ++MBBI) {
|
|
|
|
MachineInstr *MI = MBBI;
|
|
|
|
// Skip DBG_VALUE instructions. Otherwise debug info can affect the
|
|
|
|
// optimization by changing how far we scan.
|
|
|
|
if (MI->isDebugValue())
|
|
|
|
continue;
|
|
|
|
|
|
|
|
// Now that we know this is a real instruction, count it.
|
|
|
|
++Count;
|
|
|
|
|
2015-09-04 00:41:28 +08:00
|
|
|
bool CanMergeOpc = Opc == MI->getOpcode();
|
|
|
|
Flags.setSExtIdx(-1);
|
|
|
|
if (!CanMergeOpc) {
|
|
|
|
bool IsValidLdStrOpc;
|
|
|
|
unsigned NonSExtOpc = getMatchingNonSExtOpcode(Opc, &IsValidLdStrOpc);
|
|
|
|
assert(IsValidLdStrOpc &&
|
|
|
|
"Given Opc should be a Load or Store with an immediate");
|
|
|
|
// Opc will be the first instruction in the pair.
|
|
|
|
Flags.setSExtIdx(NonSExtOpc == (unsigned)Opc ? 1 : 0);
|
|
|
|
CanMergeOpc = NonSExtOpc == getMatchingNonSExtOpcode(MI->getOpcode());
|
|
|
|
}
|
|
|
|
|
|
|
|
if (CanMergeOpc && getLdStOffsetOp(MI).isImm()) {
|
2015-08-11 02:42:45 +08:00
|
|
|
assert(MI->mayLoadOrStore() && "Expected memory operation.");
|
2014-03-29 18:18:08 +08:00
|
|
|
// If we've found another instruction with the same opcode, check to see
|
|
|
|
// if the base and offset are compatible with our starting instruction.
|
|
|
|
// These instructions all have scaled immediate operands, so we just
|
|
|
|
// check for +1/-1. Make sure to check the new instruction offset is
|
|
|
|
// actually an immediate and not a symbolic reference destined for
|
|
|
|
// a relocation.
|
|
|
|
//
|
|
|
|
// Pairwise instructions have a 7-bit signed offset field. Single insns
|
|
|
|
// have a 12-bit unsigned offset field. To be a valid combine, the
|
|
|
|
// final offset must be in range.
|
2015-08-06 23:50:12 +08:00
|
|
|
unsigned MIBaseReg = getLdStBaseOp(MI).getReg();
|
|
|
|
int MIOffset = getLdStOffsetOp(MI).getImm();
|
2014-03-29 18:18:08 +08:00
|
|
|
if (BaseReg == MIBaseReg && ((Offset == MIOffset + OffsetStride) ||
|
|
|
|
(Offset + OffsetStride == MIOffset))) {
|
|
|
|
int MinOffset = Offset < MIOffset ? Offset : MIOffset;
|
|
|
|
// If this is a volatile load/store that otherwise matched, stop looking
|
|
|
|
// as something is going on that we don't have enough information to
|
|
|
|
// safely transform. Similarly, stop if we see a hint to avoid pairs.
|
|
|
|
if (MI->hasOrderedMemoryRef() || TII->isLdStPairSuppressed(MI))
|
|
|
|
return E;
|
|
|
|
// If the resultant immediate offset of merging these instructions
|
|
|
|
// is out of range for a pairwise instruction, bail and keep looking.
|
2015-09-04 00:41:28 +08:00
|
|
|
bool MIIsUnscaled = isUnscaledLdSt(MI);
|
|
|
|
if (!inBoundsForPair(MIIsUnscaled, MinOffset, OffsetStride)) {
|
2014-03-29 18:18:08 +08:00
|
|
|
trackRegDefsUses(MI, ModifiedRegs, UsedRegs, TRI);
|
2015-08-11 02:42:45 +08:00
|
|
|
MemInsns.push_back(MI);
|
2014-03-29 18:18:08 +08:00
|
|
|
continue;
|
|
|
|
}
|
|
|
|
// If the alignment requirements of the paired (scaled) instruction
|
|
|
|
// can't express the offset of the unscaled input, bail and keep
|
|
|
|
// looking.
|
2014-05-24 20:50:23 +08:00
|
|
|
if (IsUnscaled && EnableAArch64UnscaledMemOp &&
|
2014-03-29 18:18:08 +08:00
|
|
|
(alignTo(MinOffset, OffsetStride) != MinOffset)) {
|
|
|
|
trackRegDefsUses(MI, ModifiedRegs, UsedRegs, TRI);
|
2015-08-11 02:42:45 +08:00
|
|
|
MemInsns.push_back(MI);
|
2014-03-29 18:18:08 +08:00
|
|
|
continue;
|
|
|
|
}
|
|
|
|
// If the destination register of the loads is the same register, bail
|
|
|
|
// and keep looking. A load-pair instruction with both destination
|
|
|
|
// registers the same is UNPREDICTABLE and will result in an exception.
|
2015-08-06 23:50:12 +08:00
|
|
|
if (MayLoad && Reg == getLdStRegOp(MI).getReg()) {
|
2014-03-29 18:18:08 +08:00
|
|
|
trackRegDefsUses(MI, ModifiedRegs, UsedRegs, TRI);
|
2015-08-11 02:42:45 +08:00
|
|
|
MemInsns.push_back(MI);
|
2014-03-29 18:18:08 +08:00
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
|
|
|
// If the Rt of the second instruction was not modified or used between
|
2015-05-22 05:36:46 +08:00
|
|
|
// the two instructions and none of the instructions between the second
|
|
|
|
// and first alias with the second, we can combine the second into the
|
|
|
|
// first.
|
2015-08-06 23:50:12 +08:00
|
|
|
if (!ModifiedRegs[getLdStRegOp(MI).getReg()] &&
|
|
|
|
!(MI->mayLoad() && UsedRegs[getLdStRegOp(MI).getReg()]) &&
|
2015-05-22 05:36:46 +08:00
|
|
|
!mayAlias(MI, MemInsns, TII)) {
|
2015-07-22 01:42:04 +08:00
|
|
|
Flags.setMergeForward(false);
|
2014-03-29 18:18:08 +08:00
|
|
|
return MBBI;
|
|
|
|
}
|
|
|
|
|
|
|
|
// Likewise, if the Rt of the first instruction is not modified or used
|
2015-05-22 05:36:46 +08:00
|
|
|
// between the two instructions and none of the instructions between the
|
|
|
|
// first and the second alias with the first, we can combine the first
|
|
|
|
// into the second.
|
2015-08-06 23:50:12 +08:00
|
|
|
if (!ModifiedRegs[getLdStRegOp(FirstMI).getReg()] &&
|
2015-09-03 22:19:43 +08:00
|
|
|
!(MayLoad && UsedRegs[getLdStRegOp(FirstMI).getReg()]) &&
|
2015-05-22 05:36:46 +08:00
|
|
|
!mayAlias(FirstMI, MemInsns, TII)) {
|
2015-07-22 01:42:04 +08:00
|
|
|
Flags.setMergeForward(true);
|
2014-03-29 18:18:08 +08:00
|
|
|
return MBBI;
|
|
|
|
}
|
|
|
|
// Unable to combine these instructions due to interference in between.
|
|
|
|
// Keep looking.
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2015-05-22 05:36:46 +08:00
|
|
|
// If the instruction wasn't a matching load or store. Stop searching if we
|
|
|
|
// encounter a call instruction that might modify memory.
|
|
|
|
if (MI->isCall())
|
2014-03-29 18:18:08 +08:00
|
|
|
return E;
|
|
|
|
|
|
|
|
// Update modified / uses register lists.
|
|
|
|
trackRegDefsUses(MI, ModifiedRegs, UsedRegs, TRI);
|
|
|
|
|
|
|
|
// Otherwise, if the base register is modified, we have no match, so
|
|
|
|
// return early.
|
|
|
|
if (ModifiedRegs[BaseReg])
|
|
|
|
return E;
|
2015-05-22 05:36:46 +08:00
|
|
|
|
|
|
|
// Update list of instructions that read/write memory.
|
|
|
|
if (MI->mayLoadOrStore())
|
|
|
|
MemInsns.push_back(MI);
|
2014-03-29 18:18:08 +08:00
|
|
|
}
|
|
|
|
return E;
|
|
|
|
}
|
|
|
|
|
|
|
|
MachineBasicBlock::iterator
|
2015-09-23 21:51:44 +08:00
|
|
|
AArch64LoadStoreOpt::mergeUpdateInsn(MachineBasicBlock::iterator I,
|
|
|
|
MachineBasicBlock::iterator Update,
|
|
|
|
bool IsPreIdx) {
|
2014-05-24 20:50:23 +08:00
|
|
|
assert((Update->getOpcode() == AArch64::ADDXri ||
|
|
|
|
Update->getOpcode() == AArch64::SUBXri) &&
|
2014-03-29 18:18:08 +08:00
|
|
|
"Unexpected base register update instruction to merge!");
|
|
|
|
MachineBasicBlock::iterator NextI = I;
|
|
|
|
// Return the instruction following the merged instruction, which is
|
|
|
|
// the instruction following our unmerged load. Unless that's the add/sub
|
|
|
|
// instruction we're merging, in which case it's the one after that.
|
|
|
|
if (++NextI == Update)
|
|
|
|
++NextI;
|
|
|
|
|
|
|
|
int Value = Update->getOperand(2).getImm();
|
2014-05-24 20:50:23 +08:00
|
|
|
assert(AArch64_AM::getShiftValue(Update->getOperand(3).getImm()) == 0 &&
|
2015-09-23 21:51:44 +08:00
|
|
|
"Can't merge 1 << 12 offset into pre-/post-indexed load / store");
|
2014-05-24 20:50:23 +08:00
|
|
|
if (Update->getOpcode() == AArch64::SUBXri)
|
2014-03-29 18:18:08 +08:00
|
|
|
Value = -Value;
|
|
|
|
|
2015-09-23 21:51:44 +08:00
|
|
|
unsigned NewOpc = IsPreIdx ? getPreIndexedOpcode(I->getOpcode())
|
|
|
|
: getPostIndexedOpcode(I->getOpcode());
|
2015-09-26 01:48:17 +08:00
|
|
|
MachineInstrBuilder MIB;
|
|
|
|
if (!isPairedLdSt(I)) {
|
|
|
|
// Non-paired instruction.
|
|
|
|
MIB = BuildMI(*I->getParent(), I, I->getDebugLoc(), TII->get(NewOpc))
|
|
|
|
.addOperand(getLdStRegOp(Update))
|
|
|
|
.addOperand(getLdStRegOp(I))
|
|
|
|
.addOperand(getLdStBaseOp(I))
|
|
|
|
.addImm(Value);
|
|
|
|
} else {
|
|
|
|
// Paired instruction.
|
2015-09-30 00:07:32 +08:00
|
|
|
int Scale = getMemScale(I);
|
2015-09-26 01:48:17 +08:00
|
|
|
MIB = BuildMI(*I->getParent(), I, I->getDebugLoc(), TII->get(NewOpc))
|
|
|
|
.addOperand(getLdStRegOp(Update))
|
|
|
|
.addOperand(getLdStRegOp(I, 0))
|
|
|
|
.addOperand(getLdStRegOp(I, 1))
|
|
|
|
.addOperand(getLdStBaseOp(I))
|
|
|
|
.addImm(Value / Scale);
|
|
|
|
}
|
2014-03-29 18:18:08 +08:00
|
|
|
(void)MIB;
|
|
|
|
|
2015-09-23 21:51:44 +08:00
|
|
|
if (IsPreIdx)
|
|
|
|
DEBUG(dbgs() << "Creating pre-indexed load/store.");
|
|
|
|
else
|
|
|
|
DEBUG(dbgs() << "Creating post-indexed load/store.");
|
2014-03-29 18:18:08 +08:00
|
|
|
DEBUG(dbgs() << " Replacing instructions:\n ");
|
|
|
|
DEBUG(I->print(dbgs()));
|
|
|
|
DEBUG(dbgs() << " ");
|
|
|
|
DEBUG(Update->print(dbgs()));
|
|
|
|
DEBUG(dbgs() << " with instruction:\n ");
|
|
|
|
DEBUG(((MachineInstr *)MIB)->print(dbgs()));
|
|
|
|
DEBUG(dbgs() << "\n");
|
|
|
|
|
|
|
|
// Erase the old instructions for the block.
|
|
|
|
I->eraseFromParent();
|
|
|
|
Update->eraseFromParent();
|
|
|
|
|
|
|
|
return NextI;
|
|
|
|
}
|
|
|
|
|
2015-09-26 01:48:17 +08:00
|
|
|
bool AArch64LoadStoreOpt::isMatchingUpdateInsn(MachineInstr *MemMI,
|
|
|
|
MachineInstr *MI,
|
|
|
|
unsigned BaseReg, int Offset) {
|
2014-03-29 18:18:08 +08:00
|
|
|
switch (MI->getOpcode()) {
|
|
|
|
default:
|
|
|
|
break;
|
2014-05-24 20:50:23 +08:00
|
|
|
case AArch64::SUBXri:
|
2014-03-29 18:18:08 +08:00
|
|
|
// Negate the offset for a SUB instruction.
|
|
|
|
Offset *= -1;
|
|
|
|
// FALLTHROUGH
|
2014-05-24 20:50:23 +08:00
|
|
|
case AArch64::ADDXri:
|
2014-03-29 18:18:08 +08:00
|
|
|
// Make sure it's a vanilla immediate operand, not a relocation or
|
|
|
|
// anything else we can't handle.
|
|
|
|
if (!MI->getOperand(2).isImm())
|
|
|
|
break;
|
|
|
|
// Watch out for 1 << 12 shifted value.
|
2014-05-24 20:50:23 +08:00
|
|
|
if (AArch64_AM::getShiftValue(MI->getOperand(3).getImm()))
|
2014-03-29 18:18:08 +08:00
|
|
|
break;
|
2015-09-26 01:48:17 +08:00
|
|
|
|
|
|
|
// The update instruction source and destination register must be the
|
|
|
|
// same as the load/store base register.
|
|
|
|
if (MI->getOperand(0).getReg() != BaseReg ||
|
|
|
|
MI->getOperand(1).getReg() != BaseReg)
|
|
|
|
break;
|
|
|
|
|
|
|
|
bool IsPairedInsn = isPairedLdSt(MemMI);
|
|
|
|
int UpdateOffset = MI->getOperand(2).getImm();
|
|
|
|
// For non-paired load/store instructions, the immediate must fit in a
|
|
|
|
// signed 9-bit integer.
|
|
|
|
if (!IsPairedInsn && (UpdateOffset > 255 || UpdateOffset < -256))
|
|
|
|
break;
|
|
|
|
|
|
|
|
// For paired load/store instructions, the immediate must be a multiple of
|
|
|
|
// the scaling factor. The scaled offset must also fit into a signed 7-bit
|
|
|
|
// integer.
|
|
|
|
if (IsPairedInsn) {
|
2015-09-30 00:07:32 +08:00
|
|
|
int Scale = getMemScale(MemMI);
|
2015-09-26 01:48:17 +08:00
|
|
|
if (UpdateOffset % Scale != 0)
|
|
|
|
break;
|
|
|
|
|
|
|
|
int ScaledOffset = UpdateOffset / Scale;
|
|
|
|
if (ScaledOffset > 64 || ScaledOffset < -64)
|
|
|
|
break;
|
2014-03-29 18:18:08 +08:00
|
|
|
}
|
2015-09-26 01:48:17 +08:00
|
|
|
|
|
|
|
// If we have a non-zero Offset, we check that it matches the amount
|
|
|
|
// we're adding to the register.
|
|
|
|
if (!Offset || Offset == MI->getOperand(2).getImm())
|
|
|
|
return true;
|
2014-03-29 18:18:08 +08:00
|
|
|
break;
|
|
|
|
}
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
2014-05-24 20:50:23 +08:00
|
|
|
MachineBasicBlock::iterator AArch64LoadStoreOpt::findMatchingUpdateInsnForward(
|
2015-10-01 21:33:31 +08:00
|
|
|
MachineBasicBlock::iterator I, unsigned Limit, int UnscaledOffset) {
|
2014-03-29 18:18:08 +08:00
|
|
|
MachineBasicBlock::iterator E = I->getParent()->end();
|
|
|
|
MachineInstr *MemMI = I;
|
|
|
|
MachineBasicBlock::iterator MBBI = I;
|
|
|
|
|
2015-08-06 23:50:12 +08:00
|
|
|
unsigned BaseReg = getLdStBaseOp(MemMI).getReg();
|
2015-10-01 21:33:31 +08:00
|
|
|
int MIUnscaledOffset = getLdStOffsetOp(MemMI).getImm() * getMemScale(MemMI);
|
2014-03-29 18:18:08 +08:00
|
|
|
|
2015-10-01 21:43:05 +08:00
|
|
|
// Scan forward looking for post-index opportunities. Updating instructions
|
|
|
|
// can't be formed if the memory instruction doesn't have the offset we're
|
|
|
|
// looking for.
|
|
|
|
if (MIUnscaledOffset != UnscaledOffset)
|
|
|
|
return E;
|
|
|
|
|
2015-09-26 01:48:17 +08:00
|
|
|
// If the base register overlaps a destination register, we can't
|
2014-03-29 18:18:08 +08:00
|
|
|
// merge the update.
|
2015-09-26 01:48:17 +08:00
|
|
|
bool IsPairedInsn = isPairedLdSt(MemMI);
|
|
|
|
for (unsigned i = 0, e = IsPairedInsn ? 2 : 1; i != e; ++i) {
|
|
|
|
unsigned DestReg = getLdStRegOp(MemMI, i).getReg();
|
|
|
|
if (DestReg == BaseReg || TRI->isSubRegister(BaseReg, DestReg))
|
|
|
|
return E;
|
|
|
|
}
|
2014-03-29 18:18:08 +08:00
|
|
|
|
|
|
|
// Track which registers have been modified and used between the first insn
|
|
|
|
// (inclusive) and the second insn.
|
|
|
|
BitVector ModifiedRegs, UsedRegs;
|
|
|
|
ModifiedRegs.resize(TRI->getNumRegs());
|
|
|
|
UsedRegs.resize(TRI->getNumRegs());
|
|
|
|
++MBBI;
|
|
|
|
for (unsigned Count = 0; MBBI != E; ++MBBI) {
|
|
|
|
MachineInstr *MI = MBBI;
|
|
|
|
// Skip DBG_VALUE instructions. Otherwise debug info can affect the
|
|
|
|
// optimization by changing how far we scan.
|
|
|
|
if (MI->isDebugValue())
|
|
|
|
continue;
|
|
|
|
|
|
|
|
// Now that we know this is a real instruction, count it.
|
|
|
|
++Count;
|
|
|
|
|
|
|
|
// If we found a match, return it.
|
2015-10-01 21:33:31 +08:00
|
|
|
if (isMatchingUpdateInsn(I, MI, BaseReg, UnscaledOffset))
|
2014-03-29 18:18:08 +08:00
|
|
|
return MBBI;
|
|
|
|
|
|
|
|
// Update the status of what the instruction clobbered and used.
|
|
|
|
trackRegDefsUses(MI, ModifiedRegs, UsedRegs, TRI);
|
|
|
|
|
|
|
|
// Otherwise, if the base register is used or modified, we have no match, so
|
|
|
|
// return early.
|
|
|
|
if (ModifiedRegs[BaseReg] || UsedRegs[BaseReg])
|
|
|
|
return E;
|
|
|
|
}
|
|
|
|
return E;
|
|
|
|
}
|
|
|
|
|
2014-05-24 20:50:23 +08:00
|
|
|
MachineBasicBlock::iterator AArch64LoadStoreOpt::findMatchingUpdateInsnBackward(
|
|
|
|
MachineBasicBlock::iterator I, unsigned Limit) {
|
2014-03-29 18:18:08 +08:00
|
|
|
MachineBasicBlock::iterator B = I->getParent()->begin();
|
|
|
|
MachineBasicBlock::iterator E = I->getParent()->end();
|
|
|
|
MachineInstr *MemMI = I;
|
|
|
|
MachineBasicBlock::iterator MBBI = I;
|
|
|
|
|
2015-08-06 23:50:12 +08:00
|
|
|
unsigned BaseReg = getLdStBaseOp(MemMI).getReg();
|
|
|
|
int Offset = getLdStOffsetOp(MemMI).getImm();
|
2014-03-29 18:18:08 +08:00
|
|
|
|
|
|
|
// If the load/store is the first instruction in the block, there's obviously
|
|
|
|
// not any matching update. Ditto if the memory offset isn't zero.
|
|
|
|
if (MBBI == B || Offset != 0)
|
|
|
|
return E;
|
2015-09-26 01:48:17 +08:00
|
|
|
// If the base register overlaps a destination register, we can't
|
2014-03-29 18:18:08 +08:00
|
|
|
// merge the update.
|
2015-09-26 01:48:17 +08:00
|
|
|
bool IsPairedInsn = isPairedLdSt(MemMI);
|
|
|
|
for (unsigned i = 0, e = IsPairedInsn ? 2 : 1; i != e; ++i) {
|
|
|
|
unsigned DestReg = getLdStRegOp(MemMI, i).getReg();
|
|
|
|
if (DestReg == BaseReg || TRI->isSubRegister(BaseReg, DestReg))
|
|
|
|
return E;
|
|
|
|
}
|
2014-03-29 18:18:08 +08:00
|
|
|
|
|
|
|
// Track which registers have been modified and used between the first insn
|
|
|
|
// (inclusive) and the second insn.
|
|
|
|
BitVector ModifiedRegs, UsedRegs;
|
|
|
|
ModifiedRegs.resize(TRI->getNumRegs());
|
|
|
|
UsedRegs.resize(TRI->getNumRegs());
|
|
|
|
--MBBI;
|
|
|
|
for (unsigned Count = 0; MBBI != B; --MBBI) {
|
|
|
|
MachineInstr *MI = MBBI;
|
|
|
|
// Skip DBG_VALUE instructions. Otherwise debug info can affect the
|
|
|
|
// optimization by changing how far we scan.
|
|
|
|
if (MI->isDebugValue())
|
|
|
|
continue;
|
|
|
|
|
|
|
|
// Now that we know this is a real instruction, count it.
|
|
|
|
++Count;
|
|
|
|
|
|
|
|
// If we found a match, return it.
|
2015-10-01 03:44:40 +08:00
|
|
|
if (isMatchingUpdateInsn(I, MI, BaseReg, Offset))
|
2014-03-29 18:18:08 +08:00
|
|
|
return MBBI;
|
|
|
|
|
|
|
|
// Update the status of what the instruction clobbered and used.
|
|
|
|
trackRegDefsUses(MI, ModifiedRegs, UsedRegs, TRI);
|
|
|
|
|
|
|
|
// Otherwise, if the base register is used or modified, we have no match, so
|
|
|
|
// return early.
|
|
|
|
if (ModifiedRegs[BaseReg] || UsedRegs[BaseReg])
|
|
|
|
return E;
|
|
|
|
}
|
|
|
|
return E;
|
|
|
|
}
|
|
|
|
|
2014-05-24 20:50:23 +08:00
|
|
|
bool AArch64LoadStoreOpt::optimizeBlock(MachineBasicBlock &MBB) {
|
2014-03-29 18:18:08 +08:00
|
|
|
bool Modified = false;
|
|
|
|
// Two tranformations to do here:
|
|
|
|
// 1) Find loads and stores that can be merged into a single load or store
|
|
|
|
// pair instruction.
|
|
|
|
// e.g.,
|
|
|
|
// ldr x0, [x2]
|
|
|
|
// ldr x1, [x2, #8]
|
|
|
|
// ; becomes
|
|
|
|
// ldp x0, x1, [x2]
|
|
|
|
// 2) Find base register updates that can be merged into the load or store
|
|
|
|
// as a base-reg writeback.
|
|
|
|
// e.g.,
|
|
|
|
// ldr x0, [x2]
|
|
|
|
// add x2, x2, #4
|
|
|
|
// ; becomes
|
|
|
|
// ldr x0, [x2], #4
|
|
|
|
|
|
|
|
for (MachineBasicBlock::iterator MBBI = MBB.begin(), E = MBB.end();
|
|
|
|
MBBI != E;) {
|
|
|
|
MachineInstr *MI = MBBI;
|
|
|
|
switch (MI->getOpcode()) {
|
|
|
|
default:
|
|
|
|
// Just move on to the next instruction.
|
|
|
|
++MBBI;
|
|
|
|
break;
|
2015-09-26 01:48:17 +08:00
|
|
|
// Scaled instructions.
|
2014-05-24 20:50:23 +08:00
|
|
|
case AArch64::STRSui:
|
|
|
|
case AArch64::STRDui:
|
|
|
|
case AArch64::STRQui:
|
|
|
|
case AArch64::STRXui:
|
|
|
|
case AArch64::STRWui:
|
|
|
|
case AArch64::LDRSui:
|
|
|
|
case AArch64::LDRDui:
|
|
|
|
case AArch64::LDRQui:
|
|
|
|
case AArch64::LDRXui:
|
|
|
|
case AArch64::LDRWui:
|
2015-01-24 09:25:54 +08:00
|
|
|
case AArch64::LDRSWui:
|
2015-09-26 01:48:17 +08:00
|
|
|
// Unscaled instructions.
|
2014-05-24 20:50:23 +08:00
|
|
|
case AArch64::STURSi:
|
|
|
|
case AArch64::STURDi:
|
|
|
|
case AArch64::STURQi:
|
|
|
|
case AArch64::STURWi:
|
|
|
|
case AArch64::STURXi:
|
|
|
|
case AArch64::LDURSi:
|
|
|
|
case AArch64::LDURDi:
|
|
|
|
case AArch64::LDURQi:
|
|
|
|
case AArch64::LDURWi:
|
2015-01-24 09:25:54 +08:00
|
|
|
case AArch64::LDURXi:
|
|
|
|
case AArch64::LDURSWi: {
|
2014-03-29 18:18:08 +08:00
|
|
|
// If this is a volatile load/store, don't mess with it.
|
|
|
|
if (MI->hasOrderedMemoryRef()) {
|
|
|
|
++MBBI;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
// Make sure this is a reg+imm (as opposed to an address reloc).
|
2015-08-06 23:50:12 +08:00
|
|
|
if (!getLdStOffsetOp(MI).isImm()) {
|
2014-03-29 18:18:08 +08:00
|
|
|
++MBBI;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
// Check if this load/store has a hint to avoid pair formation.
|
2014-05-24 20:50:23 +08:00
|
|
|
// MachineMemOperands hints are set by the AArch64StorePairSuppress pass.
|
2014-03-29 18:18:08 +08:00
|
|
|
if (TII->isLdStPairSuppressed(MI)) {
|
|
|
|
++MBBI;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
// Look ahead up to ScanLimit instructions for a pairable instruction.
|
2015-07-22 01:42:04 +08:00
|
|
|
LdStPairFlags Flags;
|
2014-03-29 18:18:08 +08:00
|
|
|
MachineBasicBlock::iterator Paired =
|
2015-07-22 01:42:04 +08:00
|
|
|
findMatchingInsn(MBBI, Flags, ScanLimit);
|
2014-03-29 18:18:08 +08:00
|
|
|
if (Paired != E) {
|
2015-08-26 21:39:48 +08:00
|
|
|
++NumPairCreated;
|
|
|
|
if (isUnscaledLdSt(MI))
|
|
|
|
++NumUnscaledPairCreated;
|
|
|
|
|
2014-03-29 18:18:08 +08:00
|
|
|
// Merge the loads into a pair. Keeping the iterator straight is a
|
|
|
|
// pain, so we let the merge routine tell us what the next instruction
|
|
|
|
// is after it's done mucking about.
|
2015-07-22 01:42:04 +08:00
|
|
|
MBBI = mergePairedInsns(MBBI, Paired, Flags);
|
2014-03-29 18:18:08 +08:00
|
|
|
Modified = true;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
++MBBI;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
// FIXME: Do the other instructions.
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
for (MachineBasicBlock::iterator MBBI = MBB.begin(), E = MBB.end();
|
|
|
|
MBBI != E;) {
|
|
|
|
MachineInstr *MI = MBBI;
|
|
|
|
// Do update merging. It's simpler to keep this separate from the above
|
|
|
|
// switch, though not strictly necessary.
|
2015-05-19 04:27:55 +08:00
|
|
|
unsigned Opc = MI->getOpcode();
|
2014-03-29 18:18:08 +08:00
|
|
|
switch (Opc) {
|
|
|
|
default:
|
|
|
|
// Just move on to the next instruction.
|
|
|
|
++MBBI;
|
|
|
|
break;
|
2015-09-26 01:48:17 +08:00
|
|
|
// Scaled instructions.
|
2014-05-24 20:50:23 +08:00
|
|
|
case AArch64::STRSui:
|
|
|
|
case AArch64::STRDui:
|
|
|
|
case AArch64::STRQui:
|
|
|
|
case AArch64::STRXui:
|
|
|
|
case AArch64::STRWui:
|
2015-09-30 02:26:15 +08:00
|
|
|
case AArch64::STRHHui:
|
|
|
|
case AArch64::STRBBui:
|
2014-05-24 20:50:23 +08:00
|
|
|
case AArch64::LDRSui:
|
|
|
|
case AArch64::LDRDui:
|
|
|
|
case AArch64::LDRQui:
|
|
|
|
case AArch64::LDRXui:
|
|
|
|
case AArch64::LDRWui:
|
2015-09-30 02:26:15 +08:00
|
|
|
case AArch64::LDRHHui:
|
|
|
|
case AArch64::LDRBBui:
|
2015-09-26 01:48:17 +08:00
|
|
|
// Unscaled instructions.
|
2014-05-24 20:50:23 +08:00
|
|
|
case AArch64::STURSi:
|
|
|
|
case AArch64::STURDi:
|
|
|
|
case AArch64::STURQi:
|
|
|
|
case AArch64::STURWi:
|
|
|
|
case AArch64::STURXi:
|
|
|
|
case AArch64::LDURSi:
|
|
|
|
case AArch64::LDURDi:
|
|
|
|
case AArch64::LDURQi:
|
|
|
|
case AArch64::LDURWi:
|
2015-09-26 01:48:17 +08:00
|
|
|
case AArch64::LDURXi:
|
|
|
|
// Paired instructions.
|
|
|
|
case AArch64::LDPSi:
|
2015-09-30 04:39:55 +08:00
|
|
|
case AArch64::LDPSWi:
|
2015-09-26 01:48:17 +08:00
|
|
|
case AArch64::LDPDi:
|
|
|
|
case AArch64::LDPQi:
|
|
|
|
case AArch64::LDPWi:
|
|
|
|
case AArch64::LDPXi:
|
|
|
|
case AArch64::STPSi:
|
|
|
|
case AArch64::STPDi:
|
|
|
|
case AArch64::STPQi:
|
|
|
|
case AArch64::STPWi:
|
|
|
|
case AArch64::STPXi: {
|
2014-03-29 18:18:08 +08:00
|
|
|
// Make sure this is a reg+imm (as opposed to an address reloc).
|
2015-08-06 23:50:12 +08:00
|
|
|
if (!getLdStOffsetOp(MI).isImm()) {
|
2014-03-29 18:18:08 +08:00
|
|
|
++MBBI;
|
|
|
|
break;
|
|
|
|
}
|
2015-09-26 01:48:17 +08:00
|
|
|
// Look forward to try to form a post-index instruction. For example,
|
|
|
|
// ldr x0, [x20]
|
|
|
|
// add x20, x20, #32
|
|
|
|
// merged into:
|
|
|
|
// ldr x0, [x20], #32
|
2014-03-29 18:18:08 +08:00
|
|
|
MachineBasicBlock::iterator Update =
|
|
|
|
findMatchingUpdateInsnForward(MBBI, ScanLimit, 0);
|
|
|
|
if (Update != E) {
|
|
|
|
// Merge the update into the ld/st.
|
2015-09-23 21:51:44 +08:00
|
|
|
MBBI = mergeUpdateInsn(MBBI, Update, /*IsPreIdx=*/false);
|
2014-03-29 18:18:08 +08:00
|
|
|
Modified = true;
|
|
|
|
++NumPostFolded;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
// Don't know how to handle pre/post-index versions, so move to the next
|
|
|
|
// instruction.
|
2015-08-07 01:37:18 +08:00
|
|
|
if (isUnscaledLdSt(Opc)) {
|
2014-03-29 18:18:08 +08:00
|
|
|
++MBBI;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
// Look back to try to find a pre-index instruction. For example,
|
|
|
|
// add x0, x0, #8
|
|
|
|
// ldr x1, [x0]
|
|
|
|
// merged into:
|
|
|
|
// ldr x1, [x0, #8]!
|
|
|
|
Update = findMatchingUpdateInsnBackward(MBBI, ScanLimit);
|
|
|
|
if (Update != E) {
|
|
|
|
// Merge the update into the ld/st.
|
2015-09-23 21:51:44 +08:00
|
|
|
MBBI = mergeUpdateInsn(MBBI, Update, /*IsPreIdx=*/true);
|
2014-03-29 18:18:08 +08:00
|
|
|
Modified = true;
|
|
|
|
++NumPreFolded;
|
|
|
|
break;
|
|
|
|
}
|
2015-10-01 21:09:44 +08:00
|
|
|
// The immediate in the load/store is scaled by the size of the memory
|
|
|
|
// operation. The immediate in the add we're looking for,
|
2015-09-26 01:48:17 +08:00
|
|
|
// however, is not, so adjust here.
|
2015-10-01 21:33:31 +08:00
|
|
|
int UnscaledOffset = getLdStOffsetOp(MI).getImm() * getMemScale(MI);
|
2015-09-26 01:48:17 +08:00
|
|
|
|
2014-03-29 18:18:08 +08:00
|
|
|
// Look forward to try to find a post-index instruction. For example,
|
|
|
|
// ldr x1, [x0, #64]
|
|
|
|
// add x0, x0, #64
|
|
|
|
// merged into:
|
[ARM64] Fix wrong comment in load/store optimization pass.
ldr x1, [x0, #64]
add x0, x0, #64
->
ldr x1, [x0], #64
is not a valid transformation, the correct transformation (and what the code actually does) is:
ldr x1, [x0, #64]
add x0, x0, #64
->
ldr x1, [x0, #64]!
llvm-svn: 208998
2014-05-17 00:50:13 +08:00
|
|
|
// ldr x1, [x0, #64]!
|
2015-10-01 21:33:31 +08:00
|
|
|
Update = findMatchingUpdateInsnForward(MBBI, ScanLimit, UnscaledOffset);
|
2014-03-29 18:18:08 +08:00
|
|
|
if (Update != E) {
|
|
|
|
// Merge the update into the ld/st.
|
2015-09-23 21:51:44 +08:00
|
|
|
MBBI = mergeUpdateInsn(MBBI, Update, /*IsPreIdx=*/true);
|
2014-03-29 18:18:08 +08:00
|
|
|
Modified = true;
|
|
|
|
++NumPreFolded;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
// Nothing found. Just move to the next instruction.
|
|
|
|
++MBBI;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
// FIXME: Do the other instructions.
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
return Modified;
|
|
|
|
}
|
|
|
|
|
2014-05-24 20:50:23 +08:00
|
|
|
bool AArch64LoadStoreOpt::runOnMachineFunction(MachineFunction &Fn) {
|
2015-01-28 11:51:33 +08:00
|
|
|
TII = static_cast<const AArch64InstrInfo *>(Fn.getSubtarget().getInstrInfo());
|
|
|
|
TRI = Fn.getSubtarget().getRegisterInfo();
|
2014-03-29 18:18:08 +08:00
|
|
|
|
|
|
|
bool Modified = false;
|
2014-04-03 02:00:53 +08:00
|
|
|
for (auto &MBB : Fn)
|
2014-03-29 18:18:08 +08:00
|
|
|
Modified |= optimizeBlock(MBB);
|
|
|
|
|
|
|
|
return Modified;
|
|
|
|
}
|
|
|
|
|
|
|
|
// FIXME: Do we need/want a pre-alloc pass like ARM has to try to keep
|
|
|
|
// loads and stores near one another?
|
|
|
|
|
2015-08-05 20:40:13 +08:00
|
|
|
/// createAArch64LoadStoreOptimizationPass - returns an instance of the
|
|
|
|
/// load / store optimization pass.
|
2014-05-24 20:50:23 +08:00
|
|
|
FunctionPass *llvm::createAArch64LoadStoreOptimizationPass() {
|
|
|
|
return new AArch64LoadStoreOpt();
|
2014-03-29 18:18:08 +08:00
|
|
|
}
|