AdjustJumpTableBlocks("arm-adjust-jump-tables", cl::Hidden, cl::init(true),
cl::desc("Adjust basic block layout to better use TB[BH]"));
-// FIXME: This option should be removed once it has received sufficient testing.
-static cl::opt<bool>
-AlignConstantIslands("arm-align-constant-islands", cl::Hidden, cl::init(true),
- cl::desc("Align constant islands in code"));
-
/// UnknownPadding - Return the worst case padding that could result from
/// unknown offset bits. This does not include alignment padding caused by
/// known offset bits.
<< MCP->getConstants().size() << " CP entries, aligned to "
<< MCP->getConstantPoolAlignment() << " bytes *****\n");
- TII = (const ARMBaseInstrInfo *)MF->getTarget()
- .getSubtargetImpl()
- ->getInstrInfo();
+ STI = &static_cast<const ARMSubtarget &>(MF->getSubtarget());
+ TII = STI->getInstrInfo();
AFI = MF->getInfo<ARMFunctionInfo>();
- STI = &MF->getTarget().getSubtarget<ARMSubtarget>();
isThumb = AFI->isThumbFunction();
isThumb1 = AFI->isThumb1OnlyFunction();
MF->RenumberBlocks();
}
- // Thumb1 functions containing constant pools get 4-byte alignment.
- // This is so we can keep exact track of where the alignment padding goes.
-
- // ARM and Thumb2 functions need to be 4-byte aligned.
- if (!isThumb1)
- MF->ensureAlignment(2); // 2 = log2(4)
-
// Perform the initial placement of the constant pool entries. To start with,
// we put them all at the end of the function.
std::vector<MachineInstr*> CPEMIs;
CPEMIs.clear();
DEBUG(dumpBBs());
+ // Functions with jump tables need an alignment of 4 because they use the ADR
+ // instruction, which aligns the PC to 4 bytes before adding an offset.
+ if (!T2JumpTables.empty())
+ MF->ensureAlignment(2);
/// Remove dead constant pool entries.
MadeChange |= removeUnusedCPEntries();
unsigned MaxAlign = Log2_32(MCP->getConstantPoolAlignment());
// Mark the basic block as required by the const-pool.
- // If AlignConstantIslands isn't set, use 4-byte alignment for everything.
- BB->setAlignment(AlignConstantIslands ? MaxAlign : 2);
+ BB->setAlignment(MaxAlign);
// The function needs to be as aligned as the basic blocks. The linker may
// move functions around based on their alignment.
// identity mapping of CPI's to CPE's.
const std::vector<MachineConstantPoolEntry> &CPs = MCP->getConstants();
- const DataLayout &TD = *MF->getSubtarget().getDataLayout();
+ const DataLayout &TD = *MF->getTarget().getDataLayout();
for (unsigned i = 0, e = CPs.size(); i != e; ++i) {
unsigned Size = TD.getTypeAllocSize(CPs[i].getType());
assert(Size >= 4 && "Too small constant pool entry");
unsigned ARMConstantIslands::getCPELogAlign(const MachineInstr *CPEMI) {
assert(CPEMI && CPEMI->getOpcode() == ARM::CONSTPOOL_ENTRY);
- // Everything is 4-byte aligned unless AlignConstantIslands is set.
- if (!AlignConstantIslands)
- return 2;
-
unsigned CPI = CPEMI->getOperand(1).getIndex();
assert(CPI < MCP->getConstants().size() && "Invalid constant pool index.");
unsigned Align = MCP->getConstants()[CPI].getAlignment();
bool ARMConstantIslands::optimizeThumb2Branches() {
bool MadeChange = false;
- for (unsigned i = 0, e = ImmBranches.size(); i != e; ++i) {
- ImmBranch &Br = ImmBranches[i];
+ // The order in which branches appear in ImmBranches is approximately their
+ // order within the function body. By visiting later branches first, we reduce
+ // the distance between earlier forward branches and their targets, making it
+ // more likely that the cbn?z optimization, which can only apply to forward
+ // branches, will succeed.
+ for (unsigned i = ImmBranches.size(); i != 0; --i) {
+ ImmBranch &Br = ImmBranches[i-1];
unsigned Opcode = Br.MI->getOpcode();
unsigned NewOpc = 0;
unsigned Scale = 1;