Enable generating legacy IT block for AArch32

By default, the behavior of IT block generation will be determinated
dynamically base on the arch (armv8 vs armv7). This patch adds backend
options: -arm-restrict-it and -arm-no-restrict-it.  The former one
restricts the generation of IT blocks (the same behavior as thumbv8) for
both arches. The later one allows the generation of legacy IT block (the
same behavior as ARMv7 Thumb2) for both arches.

Clang will support -mrestrict-it and -mno-restrict-it, which is
compatible with GCC.

llvm-svn: 194592
This commit is contained in:
Weiming Zhao 2013-11-13 18:29:49 +00:00
parent 00229a82cc
commit 0da5cc0765
14 changed files with 57 additions and 8 deletions

View File

@ -525,7 +525,7 @@ bool ARMBaseInstrInfo::isPredicable(MachineInstr *MI) const {
MI->getParent()->getParent()->getInfo<ARMFunctionInfo>();
if (AFI->isThumb2Function()) {
if (getSubtarget().hasV8Ops())
if (getSubtarget().restrictIT())
return isV8EligibleForIT(MI);
} else { // non-Thumb
if ((MI->getDesc().TSFlags & ARMII::DomainMask) == ARMII::DomainNEON)

View File

@ -57,6 +57,23 @@ Align(cl::desc("Load/store alignment support"),
"Allow unaligned memory accesses"),
clEnumValEnd));
enum ITMode {
DefaultIT,
RestrictedIT,
NoRestrictedIT
};
static cl::opt<ITMode>
IT(cl::desc("IT block support"), cl::Hidden, cl::init(DefaultIT),
cl::ZeroOrMore,
cl::values(clEnumValN(DefaultIT, "arm-default-it",
"Generate IT block based on arch"),
clEnumValN(RestrictedIT, "arm-restrict-it",
"Disallow deprecated IT based on ARMv8"),
clEnumValN(NoRestrictedIT, "arm-no-restrict-it",
"Allow IT blocks based on ARMv7"),
clEnumValEnd));
ARMSubtarget::ARMSubtarget(const std::string &TT, const std::string &CPU,
const std::string &FS, const TargetOptions &Options)
: ARMGenSubtargetInfo(TT, CPU, FS)
@ -217,6 +234,18 @@ void ARMSubtarget::resetSubtargetFeatures(StringRef CPU, StringRef FS) {
break;
}
switch (IT) {
case DefaultIT:
RestrictIT = hasV8Ops() ? true : false;
break;
case RestrictedIT:
RestrictIT = true;
break;
case NoRestrictedIT:
RestrictIT = false;
break;
}
// NEON f32 ops are non-IEEE 754 compliant. Darwin is ok with it by default.
uint64_t Bits = getFeatureBits();
if ((Bits & ARM::ProcA5 || Bits & ARM::ProcA8) && // Where this matters

View File

@ -177,6 +177,10 @@ protected:
/// ARMTargetLowering::allowsUnalignedMemoryAccesses().
bool AllowsUnalignedMem;
/// RestrictIT - If true, the subtarget disallows generation of deprecated IT
/// blocks to conform to ARMv8 rule.
bool RestrictIT;
/// Thumb2DSP - If true, the subtarget supports the v7 DSP (saturating arith
/// and such) instructions in Thumb2 code.
bool Thumb2DSP;
@ -327,6 +331,8 @@ public:
bool allowsUnalignedMem() const { return AllowsUnalignedMem; }
bool restrictIT() const { return RestrictIT; }
const std::string & getCPUString() const { return CPUString; }
unsigned getMispredictionPenalty() const;

View File

@ -198,7 +198,7 @@ bool ARMPassConfig::addPreSched2() {
if (getOptLevel() != CodeGenOpt::None) {
if (!getARMSubtarget().isThumb1Only()) {
// in v8, IfConversion depends on Thumb instruction widths
if (getARMSubtarget().hasV8Ops() &&
if (getARMSubtarget().restrictIT() &&
!getARMSubtarget().prefers32BitThumb())
addPass(createThumb2SizeReductionPass());
addPass(&IfConverterID);

View File

@ -28,7 +28,7 @@ namespace {
static char ID;
Thumb2ITBlockPass() : MachineFunctionPass(ID) {}
bool hasV8Ops;
bool restrictIT;
const Thumb2InstrInfo *TII;
const TargetRegisterInfo *TRI;
ARMFunctionInfo *AFI;
@ -194,8 +194,9 @@ bool Thumb2ITBlockPass::InsertITInstructions(MachineBasicBlock &MBB) {
ARMCC::CondCodes OCC = ARMCC::getOppositeCondition(CC);
unsigned Mask = 0, Pos = 3;
// v8 IT blocks are limited to one conditional op: skip the loop
if (!hasV8Ops) {
// v8 IT blocks are limited to one conditional op unless -arm-no-restrict-it
// is set: skip the loop
if (!restrictIT) {
// Branches, including tricky ones like LDM_RET, need to end an IT
// block so check the instruction we just put in the block.
for (; MBBI != E && Pos &&
@ -255,7 +256,7 @@ bool Thumb2ITBlockPass::runOnMachineFunction(MachineFunction &Fn) {
AFI = Fn.getInfo<ARMFunctionInfo>();
TII = static_cast<const Thumb2InstrInfo*>(TM.getInstrInfo());
TRI = TM.getRegisterInfo();
hasV8Ops = TM.getSubtarget<ARMSubtarget>().hasV8Ops();
restrictIT = TM.getSubtarget<ARMSubtarget>().restrictIT();
if (!AFI->isThumbFunction())
return false;

View File

@ -1,5 +1,6 @@
; RUN: llc < %s -mtriple=thumbv7-apple-ios -mcpu=cortex-a8 | FileCheck %s
; RUN: llc < %s -mtriple=thumbv8 | FileCheck -check-prefix=CHECK-V8 %s
; RUN: llc < %s -mtriple=thumbv7 -arm-restrict-it | FileCheck -check-prefix=CHECK-V8 %s
; rdar://13782395
define i32 @t1(i32 %a, i32 %b, i8** %retaddr) {

View File

@ -1,5 +1,6 @@
; RUN: llc < %s -mtriple=thumbv7-apple-darwin | FileCheck %s
; RUN: llc < %s -mtriple=thumbv7-apple-darwin -arm-default-it | FileCheck %s
; RUN: llc < %s -mtriple=thumbv8 -arm-no-restrict-it |FileCheck %s
define i32 @t1(i32 %a, i32 %b, i32 %c, i32 %d) nounwind {
; CHECK-LABEL: t1:
; CHECK: ittt ne
@ -74,7 +75,7 @@ entry:
; CHECK-LABEL: t3:
; CHECK: itt ge
; CHECK: movge r0, r1
; CHECK: blge _foo
; CHECK: blge {{_?}}foo
%tmp1 = icmp sgt i32 %a, 10 ; <i1> [#uses=1]
br i1 %tmp1, label %cond_true, label %UnifiedReturnBlock

View File

@ -1,4 +1,6 @@
; RUN: llc < %s -mtriple=thumbv7-apple-ios | FileCheck %s
; RUN: llc < %s -mtriple=thumbv7-apple-ios -arm-default-it | FileCheck %s
; RUN: llc < %s -mtriple=thumbv8-apple-ios -arm-no-restrict-it | FileCheck %s
define void @foo(i32 %X, i32 %Y) {
entry:

View File

@ -1,4 +1,6 @@
; RUN: llc < %s -mtriple=thumbv7-apple-darwin | FileCheck %s
; RUN: llc < %s -mtriple=thumbv7-apple-darwin -arm-default-it | FileCheck %s
; RUN: llc < %s -mtriple=thumbv8-apple-darwin -arm-no-restrict-it | FileCheck %s
; There shouldn't be a unconditional branch at end of bb52.
; rdar://7184787

View File

@ -1,4 +1,5 @@
; RUN: llc < %s -mtriple=thumbv8 -mattr=+neon | FileCheck %s
; RUN: llc < %s -mtriple=thumbv7 -mattr=+neon -arm-restrict-it | FileCheck %s
;CHECK-LABEL: select_s_v_v:
;CHECK-NOT: it

View File

@ -1,4 +1,5 @@
; RUN: llc < %s -mtriple=thumbv8 | FileCheck %s
; RUN: llc < %s -mtriple=thumbv7 -arm-restrict-it | FileCheck %s
%struct.quad_struct = type { i32, i32, %struct.quad_struct*, %struct.quad_struct*, %struct.quad_struct*, %struct.quad_struct*, %struct.quad_struct* }

View File

@ -1,5 +1,7 @@
; RUN: llc < %s -mtriple=thumbv8 | FileCheck %s
; RUN: llc < %s -mtriple=thumbv7 -arm-restrict-it | FileCheck %s
; RUN: llc < %s -mtriple=thumbv8 -relocation-model=pic | FileCheck %s --check-prefix=CHECK-PIC
; RUN: llc < %s -mtriple=thumbv7 -arm-restrict-it -relocation-model=pic | FileCheck %s --check-prefix=CHECK-PIC
%struct.FF = type { i32 (i32*)*, i32 (i32*, i32*, i32, i32, i32, i32)*, i32 (i32, i32, i8*)*, void ()*, i32 (i32, i8*, i32*)*, i32 ()* }
%struct.BD = type { %struct.BD*, i32, i32, i32, i32, i64, i32 (%struct.BD*, i8*, i64, i32)*, i32 (%struct.BD*, i8*, i32, i32)*, i32 (%struct.BD*, i8*, i64, i32)*, i32 (%struct.BD*, i8*, i32, i32)*, i32 (%struct.BD*, i64, i32)*, [16 x i8], i64, i64 }

View File

@ -1,5 +1,7 @@
; RUN: llc < %s -mtriple=thumbv8-eabi -float-abi=hard | FileCheck %s
; RUN: llc < %s -mtriple=thumbv7-eabi -float-abi=hard -arm-restrict-it | FileCheck %s
; RUN: llc < %s -mtriple=thumbv8-eabi -float-abi=hard -regalloc=basic | FileCheck %s
; RUN: llc < %s -mtriple=thumbv7-eabi -float-abi=hard -regalloc=basic -arm-restrict-it | FileCheck %s
%"struct.__gnu_cxx::__normal_iterator<char*,std::basic_string<char, std::char_traits<char>, std::allocator<char> > >" = type { i8* }
%"struct.__gnu_cxx::new_allocator<char>" = type <{ i8 }>

View File

@ -1,4 +1,5 @@
; RUN: llc < %s -mtriple=thumbv8 | FileCheck %s
; RUN: llc < %s -mtriple=thumbv7 -arm-restrict-it | FileCheck %s
; CHECK: it ne
; CHECK-NEXT: cmpne
; CHECK-NEXT: beq