maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[X86] Add ExpandLargeFpConvert Pass and enable for X86 

As stated in
https://discourse.llvm.org/t/rfc-llc-add-expandlargeintfpconvert-pass-for-fp-int-conversion-of-large-bitint/65528,
this implementation is very similar to ExpandLargeDivRem, which expands
‘fptoui .. to’, ‘fptosi .. to’, ‘uitofp .. to’, ‘sitofp .. to’ instructions
with a bitwidth above a threshold into auto-generated functions. This is
useful for targets like x86_64 that cannot lower fp convertions with more
than 128 bits. The expanded nodes are referring from the IR generated by
`compiler-rt/lib/builtins/floattidf.c`, `compiler-rt/lib/builtins/fixdfti.c`,
and etc.

Corner cases:
1. For fp16: as there is no related builtins added in compliler-rt. So I
mainly utilized the fp32 <-> fp16 lib calls to implement.
2. For fp80: as this pass is soft fp emulation and no fp80 instructions can
help in this problem. I recommend users to deprecate this usage. For now, the
implementation uses fp128 as the temporary conversion type and inserts
fptrunc/ext at top/end of the function.
3. For bf16: as clang FE currently doesn't support bf16 algorithm operations
(convert to int, float, +, -, *, ...), this patch doesn't consider bf16 for
now.
4. For unsigned FPToI: since both default hardware behaviors and libgcc are
ignoring "returns 0 for negative input" spec. This pass follows this old way
to ignore unsigned FPToI. See this example:
https://gcc.godbolt.org/z/bnv3jqW1M

The end-to-end tests are uploaded at https://reviews.llvm.org/D138261

Reviewed By: LuoYuanke, mgehre-amd

Differential Revision: https://reviews.llvm.org/D137241
This commit is contained in:
Freddy Ye 2022-12-01 13:47:25 +08:00
parent 416e8c6ad5
commit 89f36dd8f3
26 changed files with 2045 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
llvm/include/llvm/CodeGen/MachinePassRegistry.def
View File

@ -44,6 +44,7 @@ FUNCTION_PASS("partially-inline-libcalls", PartiallyInlineLibCallsPass, ())
FUNCTION_PASS("ee-instrument", EntryExitInstrumenterPass, (false))
FUNCTION_PASS("post-inline-ee-instrument", EntryExitInstrumenterPass, (true))
FUNCTION_PASS("expand-large-div-rem", ExpandLargeDivRemPass, ())
FUNCTION_PASS("expand-large-fp-convert", ExpandLargeFpConvertPass, ())
FUNCTION_PASS("expand-reductions", ExpandReductionsPass, ())
FUNCTION_PASS("expandvp", ExpandVectorPredicationPass, ())
FUNCTION_PASS("lowerinvoke", LowerInvokePass, ())

3
llvm/include/llvm/CodeGen/Passes.h
View File

@ -494,6 +494,9 @@ namespace llvm {
// Expands large div/rem instructions.
FunctionPass *createExpandLargeDivRemPass();
// Expands large div/rem instructions.
FunctionPass *createExpandLargeFpConvertPass();
// This pass expands memcmp() to load/stores.
FunctionPass *createExpandMemCmpPass();

16
llvm/include/llvm/CodeGen/TargetLowering.h
View File

@ -1961,6 +1961,12 @@ public:
return MaxDivRemBitWidthSupported;
}
/// Returns the size in bits of the maximum larget fp convert the backend
/// supports. Larger operations will be expanded by ExpandLargeFPConvert.
unsigned getMaxLargeFPConvertBitWidthSupported() const {
return MaxLargeFPConvertBitWidthSupported;
}
/// Returns the size of the smallest cmpxchg or ll/sc instruction
/// the backend supports. Any smaller operations are widened in
/// AtomicExpandPass.
@ -2540,6 +2546,12 @@ protected:
MaxDivRemBitWidthSupported = SizeInBits;
}
/// Set the size in bits of the maximum fp convert the backend supports.
/// Larger operations will be expanded by ExpandLargeFPConvert.
void setMaxLargeFPConvertBitWidthSupported(unsigned SizeInBits) {
MaxLargeFPConvertBitWidthSupported = SizeInBits;
}
/// Sets the minimum cmpxchg or ll/sc size supported by the backend.
void setMinCmpXchgSizeInBits(unsigned SizeInBits) {
MinCmpXchgSizeInBits = SizeInBits;
@ -3259,6 +3271,10 @@ private:
/// Larger operations will be expanded by ExpandLargeDivRem.
unsigned MaxDivRemBitWidthSupported;
/// Size in bits of the maximum larget fp convert size the backend
/// supports. Larger operations will be expanded by ExpandLargeFPConvert.
unsigned MaxLargeFPConvertBitWidthSupported;
/// Size in bits of the minimum cmpxchg or ll/sc operation the
/// backend supports.
unsigned MinCmpXchgSizeInBits;

1
llvm/include/llvm/InitializePasses.h
View File

@ -133,6 +133,7 @@ void initializeEarlyTailDuplicatePass(PassRegistry&);
void initializeEdgeBundlesPass(PassRegistry&);
void initializeEHContGuardCatchretPass(PassRegistry &);
void initializeEliminateAvailableExternallyLegacyPassPass(PassRegistry&);
void initializeExpandLargeFpConvertLegacyPassPass(PassRegistry&);
void initializeExpandLargeDivRemLegacyPassPass(PassRegistry&);
void initializeExpandMemCmpPassPass(PassRegistry&);
void initializeExpandPostRAPass(PassRegistry&);

1
llvm/lib/CodeGen/CMakeLists.txt
View File

@ -54,6 +54,7 @@ add_llvm_component_library(LLVMCodeGen
EHContGuardCatchret.cpp
ExecutionDomainFix.cpp
ExpandLargeDivRem.cpp
ExpandLargeFpConvert.cpp
ExpandMemCmp.cpp
ExpandPostRAPseudos.cpp
ExpandReductions.cpp

1
llvm/lib/CodeGen/CodeGen.cpp
View File

@ -37,6 +37,7 @@ void llvm::initializeCodeGen(PassRegistry &Registry) {
initializeEarlyMachineLICMPass(Registry);
initializeEarlyTailDuplicatePass(Registry);
initializeExpandLargeDivRemLegacyPassPass(Registry);
initializeExpandLargeFpConvertLegacyPassPass(Registry);
initializeExpandMemCmpPassPass(Registry);
initializeExpandPostRAPass(Registry);
initializeFEntryInserterPass(Registry);

662
llvm/lib/CodeGen/ExpandLargeFpConvert.cpp Normal file
View File

@ -0,0 +1,662 @@
//===--- ExpandLargeFpConvert.cpp - Expand large fp convert----------------===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
// This pass expands ‘fptoui .. to’, ‘fptosi .. to’, ‘uitofp .. to’,
// ‘sitofp .. to’ instructions with a bitwidth above a threshold into
// auto-generated functions. This is useful for targets like x86_64 that cannot
// lower fp convertions with more than 128 bits.
//
//===----------------------------------------------------------------------===//
#include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/StringExtras.h"
#include "llvm/Analysis/GlobalsModRef.h"
#include "llvm/CodeGen/Passes.h"
#include "llvm/CodeGen/TargetLowering.h"
#include "llvm/CodeGen/TargetPassConfig.h"
#include "llvm/CodeGen/TargetSubtargetInfo.h"
#include "llvm/IR/IRBuilder.h"
#include "llvm/IR/InstIterator.h"
#include "llvm/IR/PassManager.h"
#include "llvm/InitializePasses.h"
#include "llvm/Pass.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Target/TargetMachine.h"
using namespace llvm;
static cl::opt<unsigned>
ExpandFpConvertBits("expand-fp-convert-bits", cl::Hidden,
cl::init(llvm::IntegerType::MAX_INT_BITS),
cl::desc("fp convert instructions on integers with "
"more than <N> bits are expanded."));
/// Generate code to convert a fp number to integer, replacing FPToS(U)I with
/// the generated code. This currently generates code similarly to compiler-rt's
/// implementations.
///
/// An example IR generated from compiler-rt/fixsfdi.c looks like below:
/// define dso_local i64 @foo(float noundef %a) local_unnamed_addr #0 {
/// entry:
/// %0 = bitcast float %a to i32
/// %conv.i = zext i32 %0 to i64
/// %tobool.not = icmp sgt i32 %0, -1
/// %conv = select i1 %tobool.not, i64 1, i64 -1
/// %and = lshr i64 %conv.i, 23
/// %shr = and i64 %and, 255
/// %and2 = and i64 %conv.i, 8388607
/// %or = or i64 %and2, 8388608
/// %cmp = icmp ult i64 %shr, 127
/// br i1 %cmp, label %cleanup, label %if.end
///
/// if.end: ; preds = %entry
/// %sub = add nuw nsw i64 %shr, 4294967169
/// %conv5 = and i64 %sub, 4294967232
/// %cmp6.not = icmp eq i64 %conv5, 0
/// br i1 %cmp6.not, label %if.end12, label %if.then8
///
/// if.then8: ; preds = %if.end
/// %cond11 = select i1 %tobool.not, i64 9223372036854775807, i64 -9223372036854775808
/// br label %cleanup
///
/// if.end12: ; preds = %if.end
/// %cmp13 = icmp ult i64 %shr, 150
/// br i1 %cmp13, label %if.then15, label %if.else
///
/// if.then15: ; preds = %if.end12
/// %sub16 = sub nuw nsw i64 150, %shr
/// %shr17 = lshr i64 %or, %sub16
/// %mul = mul nsw i64 %shr17, %conv
/// br label %cleanup
///
/// if.else: ; preds = %if.end12
/// %sub18 = add nsw i64 %shr, -150
/// %shl = shl i64 %or, %sub18
/// %mul19 = mul nsw i64 %shl, %conv
/// br label %cleanup
///
/// cleanup: ; preds = %entry, %if.else, %if.then15, %if.then8
/// %retval.0 = phi i64 [ %cond11, %if.then8 ], [ %mul, %if.then15 ], [ %mul19, %if.else ], [ 0, %entry ]
/// ret i64 %retval.0
/// }
///
/// Replace fp to integer with generated code.
static void expandFPToI(Instruction *FPToI) {
IRBuilder<> Builder(FPToI);
auto *FloatVal = FPToI->getOperand(0);
IntegerType *IntTy = cast<IntegerType>(FPToI->getType());
unsigned BitWidth = FPToI->getType()->getIntegerBitWidth();
unsigned FPMantissaWidth = FloatVal->getType()->getFPMantissaWidth() - 1;
// FIXME: fp16's range is covered by i32. So `fptoi half` can convert
// to i32 first following a sext/zext to target integer type.
Value *A1 = nullptr;
if (FloatVal->getType()->isHalfTy()) {
if (FPToI->getOpcode() == Instruction::FPToUI) {
Value *A0 = Builder.CreateFPToUI(FloatVal, Builder.getIntNTy(32));
A1 = Builder.CreateZExt(A0, IntTy);
} else { // FPToSI
Value *A0 = Builder.CreateFPToSI(FloatVal, Builder.getIntNTy(32));
A1 = Builder.CreateSExt(A0, IntTy);
}
FPToI->replaceAllUsesWith(A1);
FPToI->dropAllReferences();
FPToI->eraseFromParent();
return;
}
// fp80 conversion is implemented by fpext to fp128 first then do the
// conversion.
FPMantissaWidth = FPMantissaWidth == 63 ? 112 : FPMantissaWidth;
unsigned FloatWidth = PowerOf2Ceil(FPMantissaWidth);
unsigned ExponentWidth = FloatWidth - FPMantissaWidth - 1;
unsigned ExponentBias = (1 << (ExponentWidth - 1)) - 1;
Value *ImplicitBit = Builder.CreateShl(
Builder.getIntN(BitWidth, 1), Builder.getIntN(BitWidth, FPMantissaWidth));
Value *SignificandMask =
Builder.CreateSub(ImplicitBit, Builder.getIntN(BitWidth, 1));
Value *NegOne = Builder.CreateSExt(
ConstantInt::getSigned(Builder.getInt32Ty(), -1), IntTy);
Value *NegInf =
Builder.CreateShl(ConstantInt::getSigned(IntTy, 1),
ConstantInt::getSigned(IntTy, BitWidth - 1));
BasicBlock *Entry = Builder.GetInsertBlock();
Function *F = Entry->getParent();
Entry->setName(Twine(Entry->getName(), "fp-to-i-entry"));
BasicBlock *End =
Entry->splitBasicBlock(Builder.GetInsertPoint(), "fp-to-i-cleanup");
BasicBlock *IfEnd =
BasicBlock::Create(Builder.getContext(), "fp-to-i-if-end", F, End);
BasicBlock *IfThen5 =
BasicBlock::Create(Builder.getContext(), "fp-to-i-if-then5", F, End);
BasicBlock *IfEnd9 =
BasicBlock::Create(Builder.getContext(), "fp-to-i-if-end9", F, End);
BasicBlock *IfThen12 =
BasicBlock::Create(Builder.getContext(), "fp-to-i-if-then12", F, End);
BasicBlock *IfElse =
BasicBlock::Create(Builder.getContext(), "fp-to-i-if-else", F, End);
Entry->getTerminator()->eraseFromParent();
// entry:
Builder.SetInsertPoint(Entry);
Value *FloatVal0 = FloatVal;
// fp80 conversion is implemented by fpext to fp128 first then do the
// conversion.
if (FloatVal->getType()->isX86_FP80Ty())
FloatVal0 =
Builder.CreateFPExt(FloatVal, Type::getFP128Ty(Builder.getContext()));
Value *ARep0 =
Builder.CreateBitCast(FloatVal0, Builder.getIntNTy(FloatWidth));
Value *ARep = Builder.CreateZExt(ARep0, FPToI->getType());
Value *PosOrNeg = Builder.CreateICmpSGT(
ARep0, ConstantInt::getSigned(Builder.getIntNTy(FloatWidth), -1));
Value *Sign = Builder.CreateSelect(PosOrNeg, ConstantInt::getSigned(IntTy, 1),
ConstantInt::getSigned(IntTy, -1));
Value *And =
Builder.CreateLShr(ARep, Builder.getIntN(BitWidth, FPMantissaWidth));
Value *And2 = Builder.CreateAnd(
And, Builder.getIntN(BitWidth, (1 << ExponentWidth) - 1));
Value *Abs = Builder.CreateAnd(ARep, SignificandMask);
Value *Or = Builder.CreateOr(Abs, ImplicitBit);
Value *Cmp =
Builder.CreateICmpULT(And2, Builder.getIntN(BitWidth, ExponentBias));
Builder.CreateCondBr(Cmp, End, IfEnd);
// if.end:
Builder.SetInsertPoint(IfEnd);
Value *Add1 = Builder.CreateAdd(
And2, ConstantInt::getSigned(IntTy, -int64_t(ExponentBias + BitWidth)));
Value *Cmp3 =
Builder.CreateICmpULT(Add1, ConstantInt::getSigned(IntTy, -BitWidth));
Builder.CreateCondBr(Cmp3, IfThen5, IfEnd9);
// if.then5:
Builder.SetInsertPoint(IfThen5);
Value *PosInf = Builder.CreateXor(NegOne, NegInf);
Value *Cond8 = Builder.CreateSelect(PosOrNeg, PosInf, NegInf);
Builder.CreateBr(End);
// if.end9:
Builder.SetInsertPoint(IfEnd9);
Value *Cmp10 = Builder.CreateICmpULT(
And2, Builder.getIntN(BitWidth, ExponentBias + FPMantissaWidth));
Builder.CreateCondBr(Cmp10, IfThen12, IfElse);
// if.then12:
Builder.SetInsertPoint(IfThen12);
Value *Sub13 = Builder.CreateSub(
Builder.getIntN(BitWidth, ExponentBias + FPMantissaWidth), And2);
Value *Shr14 = Builder.CreateLShr(Or, Sub13);
Value *Mul = Builder.CreateMul(Shr14, Sign);
Builder.CreateBr(End);
// if.else:
Builder.SetInsertPoint(IfElse);
Value *Sub15 = Builder.CreateAdd(
And2,
ConstantInt::getSigned(IntTy, -(ExponentBias + FPMantissaWidth)));
Value *Shl = Builder.CreateShl(Or, Sub15);
Value *Mul16 = Builder.CreateMul(Shl, Sign);
Builder.CreateBr(End);
// cleanup:
Builder.SetInsertPoint(End, End->begin());
PHINode *Retval0 = Builder.CreatePHI(FPToI->getType(), 4);
Retval0->addIncoming(Cond8, IfThen5);
Retval0->addIncoming(Mul, IfThen12);
Retval0->addIncoming(Mul16, IfElse);
Retval0->addIncoming(Builder.getIntN(BitWidth, 0), Entry);
FPToI->replaceAllUsesWith(Retval0);
FPToI->dropAllReferences();
FPToI->eraseFromParent();
}
/// Generate code to convert a fp number to integer, replacing S(U)IToFP with
/// the generated code. This currently generates code similarly to compiler-rt's
/// implementations. This implementation has an implicit assumption that integer
/// width is larger than fp.
///
/// An example IR generated from compiler-rt/floatdisf.c looks like below:
/// define dso_local float @__floatdisf(i64 noundef %a) local_unnamed_addr #0 {
/// entry:
/// %cmp = icmp eq i64 %a, 0
/// br i1 %cmp, label %return, label %if.end
///
/// if.end: ; preds = %entry
/// %shr = ashr i64 %a, 63
/// %xor = xor i64 %shr, %a
/// %sub = sub nsw i64 %xor, %shr
/// %0 = tail call i64 @llvm.ctlz.i64(i64 %sub, i1 true), !range !5
/// %cast = trunc i64 %0 to i32
/// %sub1 = sub nuw nsw i32 64, %cast
/// %sub2 = xor i32 %cast, 63
/// %cmp3 = icmp ult i32 %cast, 40
/// br i1 %cmp3, label %if.then4, label %if.else
///
/// if.then4: ; preds = %if.end
/// switch i32 %sub1, label %sw.default [
/// i32 25, label %sw.bb
/// i32 26, label %sw.epilog
/// ]
///
/// sw.bb: ; preds = %if.then4
/// %shl = shl i64 %sub, 1
/// br label %sw.epilog
///
/// sw.default: ; preds = %if.then4
/// %sub5 = sub nsw i64 38, %0
/// %sh_prom = and i64 %sub5, 4294967295
/// %shr6 = lshr i64 %sub, %sh_prom
/// %shr9 = lshr i64 274877906943, %0
/// %and = and i64 %shr9, %sub
/// %cmp10 = icmp ne i64 %and, 0
/// %conv11 = zext i1 %cmp10 to i64
/// %or = or i64 %shr6, %conv11
/// br label %sw.epilog
///
/// sw.epilog: ; preds = %sw.default, %if.then4, %sw.bb
/// %a.addr.0 = phi i64 [ %or, %sw.default ], [ %sub, %if.then4 ], [ %shl, %sw.bb ]
/// %1 = lshr i64 %a.addr.0, 2
/// %2 = and i64 %1, 1
/// %or16 = or i64 %2, %a.addr.0
/// %inc = add nsw i64 %or16, 1
/// %3 = and i64 %inc, 67108864
/// %tobool.not = icmp eq i64 %3, 0
/// %spec.select.v = select i1 %tobool.not, i64 2, i64 3
/// %spec.select = ashr i64 %inc, %spec.select.v
/// %spec.select56 = select i1 %tobool.not, i32 %sub2, i32 %sub1
/// br label %if.end26
///
/// if.else: ; preds = %if.end
/// %sub23 = add nuw nsw i64 %0, 4294967256
/// %sh_prom24 = and i64 %sub23, 4294967295
/// %shl25 = shl i64 %sub, %sh_prom24
/// br label %if.end26
///
/// if.end26: ; preds = %sw.epilog, %if.else
/// %a.addr.1 = phi i64 [ %shl25, %if.else ], [ %spec.select, %sw.epilog ]
/// %e.0 = phi i32 [ %sub2, %if.else ], [ %spec.select56, %sw.epilog ]
/// %conv27 = trunc i64 %shr to i32
/// %and28 = and i32 %conv27, -2147483648
/// %add = shl nuw nsw i32 %e.0, 23
/// %shl29 = add nuw nsw i32 %add, 1065353216
/// %conv31 = trunc i64 %a.addr.1 to i32
/// %and32 = and i32 %conv31, 8388607
/// %or30 = or i32 %and32, %and28
/// %or33 = or i32 %or30, %shl29
/// %4 = bitcast i32 %or33 to float
/// br label %return
///
/// return: ; preds = %entry, %if.end26
/// %retval.0 = phi float [ %4, %if.end26 ], [ 0.000000e+00, %entry ]
/// ret float %retval.0
/// }
///
/// Replace integer to fp with generated code.
static void expandIToFP(Instruction *IToFP) {
IRBuilder<> Builder(IToFP);
auto *IntVal = IToFP->getOperand(0);
IntegerType *IntTy = cast<IntegerType>(IntVal->getType());
unsigned BitWidth = IntVal->getType()->getIntegerBitWidth();
unsigned FPMantissaWidth = IToFP->getType()->getFPMantissaWidth() - 1;
// fp80 conversion is implemented by conversion tp fp128 first following
// a fptrunc to fp80.
FPMantissaWidth = FPMantissaWidth == 63 ? 112 : FPMantissaWidth;
// FIXME: As there is no related builtins added in compliler-rt,
// here currently utilized the fp32 <-> fp16 lib calls to implement.
FPMantissaWidth = FPMantissaWidth == 10 ? 23 : FPMantissaWidth;
unsigned FloatWidth = PowerOf2Ceil(FPMantissaWidth);
bool IsSigned = IToFP->getOpcode() == Instruction::SIToFP;
assert(BitWidth > FloatWidth && "Unexpected conversion. expandIToFP() "
"assumes integer width is larger than fp.");
Value *Temp1 =
Builder.CreateShl(Builder.getIntN(BitWidth, 1),
Builder.getIntN(BitWidth, FPMantissaWidth + 3));
BasicBlock *Entry = Builder.GetInsertBlock();
Function *F = Entry->getParent();
Entry->setName(Twine(Entry->getName(), "itofp-entry"));
BasicBlock *End =
Entry->splitBasicBlock(Builder.GetInsertPoint(), "itofp-return");
BasicBlock *IfEnd =
BasicBlock::Create(Builder.getContext(), "itofp-if-end", F, End);
BasicBlock *IfThen4 =
BasicBlock::Create(Builder.getContext(), "itofp-if-then4", F, End);
BasicBlock *SwBB =
BasicBlock::Create(Builder.getContext(), "itofp-sw-bb", F, End);
BasicBlock *SwDefault =
BasicBlock::Create(Builder.getContext(), "itofp-sw-default", F, End);
BasicBlock *SwEpilog =
BasicBlock::Create(Builder.getContext(), "itofp-sw-epilog", F, End);
BasicBlock *IfThen20 =
BasicBlock::Create(Builder.getContext(), "itofp-if-then20", F, End);
BasicBlock *IfElse =
BasicBlock::Create(Builder.getContext(), "itofp-if-else", F, End);
BasicBlock *IfEnd26 =
BasicBlock::Create(Builder.getContext(), "itofp-if-end26", F, End);
Entry->getTerminator()->eraseFromParent();
Function *CTLZ =
Intrinsic::getDeclaration(F->getParent(), Intrinsic::ctlz, IntTy);
ConstantInt *True = Builder.getTrue();
// entry:
Builder.SetInsertPoint(Entry);
Value *Cmp = Builder.CreateICmpEQ(IntVal, ConstantInt::getSigned(IntTy, 0));
Builder.CreateCondBr(Cmp, End, IfEnd);
// if.end:
Builder.SetInsertPoint(IfEnd);
Value *Shr =
Builder.CreateAShr(IntVal, Builder.getIntN(BitWidth, BitWidth - 1));
Value *Xor = Builder.CreateXor(Shr, IntVal);
Value *Sub = Builder.CreateSub(Xor, Shr);
Value *Call = Builder.CreateCall(CTLZ, {IsSigned ? Sub : IntVal, True});
Value *Cast = Builder.CreateTrunc(Call, Builder.getInt32Ty());
int BitWidthNew = FloatWidth == 128 ? BitWidth : 32;
Value *Sub1 = Builder.CreateSub(Builder.getIntN(BitWidthNew, BitWidth),
FloatWidth == 128 ? Call : Cast);
Value *Sub2 = Builder.CreateSub(Builder.getIntN(BitWidthNew, BitWidth - 1),
FloatWidth == 128 ? Call : Cast);
Value *Cmp3 = Builder.CreateICmpSGT(
Sub2, Builder.getIntN(BitWidthNew, FPMantissaWidth + 1));
Builder.CreateCondBr(Cmp3, IfThen4, IfElse);
// if.then4:
Builder.SetInsertPoint(IfThen4);
llvm::SwitchInst *SI = Builder.CreateSwitch(Sub1, SwDefault);
SI->addCase(Builder.getIntN(BitWidthNew, FPMantissaWidth + 2), SwBB);
SI->addCase(Builder.getIntN(BitWidthNew, FPMantissaWidth + 3), SwEpilog);
// sw.bb:
Builder.SetInsertPoint(SwBB);
Value *Shl =
Builder.CreateShl(IsSigned ? Sub : IntVal, Builder.getIntN(BitWidth, 1));
Builder.CreateBr(SwEpilog);
// sw.default:
Builder.SetInsertPoint(SwDefault);
Value *Sub5 = Builder.CreateSub(
Builder.getIntN(BitWidthNew, BitWidth - FPMantissaWidth - 3),
FloatWidth == 128 ? Call : Cast);
Value *ShProm = Builder.CreateZExt(Sub5, IntTy);
Value *Shr6 = Builder.CreateLShr(IsSigned ? Sub : IntVal,
FloatWidth == 128 ? Sub5 : ShProm);
Value *Sub8 =
Builder.CreateAdd(FloatWidth == 128 ? Call : Cast,
Builder.getIntN(BitWidthNew, FPMantissaWidth + 3));
Value *ShProm9 = Builder.CreateZExt(Sub8, IntTy);
Value *Shr9 = Builder.CreateLShr(ConstantInt::getSigned(IntTy, -1),
FloatWidth == 128 ? Sub8 : ShProm9);
Value *And = Builder.CreateAnd(Shr9, IsSigned ? Sub : IntVal);
Value *Cmp10 = Builder.CreateICmpNE(And, Builder.getIntN(BitWidth, 0));
Value *Conv11 = Builder.CreateZExt(Cmp10, IntTy);
Value *Or = Builder.CreateOr(Shr6, Conv11);
Builder.CreateBr(SwEpilog);
// sw.epilog:
Builder.SetInsertPoint(SwEpilog);
PHINode *AAddr0 = Builder.CreatePHI(IntTy, 3);
AAddr0->addIncoming(Or, SwDefault);
AAddr0->addIncoming(IsSigned ? Sub : IntVal, IfThen4);
AAddr0->addIncoming(Shl, SwBB);
Value *A0 = Builder.CreateTrunc(AAddr0, Builder.getInt32Ty());
Value *A1 = Builder.CreateLShr(A0, Builder.getIntN(32, 2));
Value *A2 = Builder.CreateAnd(A1, Builder.getIntN(32, 1));
Value *Conv16 = Builder.CreateZExt(A2, IntTy);
Value *Or17 = Builder.CreateOr(AAddr0, Conv16);
Value *Inc = Builder.CreateAdd(Or17, Builder.getIntN(BitWidth, 1));
Value *Shr18 = nullptr;
if (IsSigned)
Shr18 = Builder.CreateAShr(Inc, Builder.getIntN(BitWidth, 2));
else
Shr18 = Builder.CreateLShr(Inc, Builder.getIntN(BitWidth, 2));
Value *A3 = Builder.CreateAnd(Inc, Temp1, "a3");
Value *PosOrNeg = Builder.CreateICmpEQ(A3, Builder.getIntN(BitWidth, 0));
Value *ExtractT60 = Builder.CreateTrunc(Shr18, Builder.getIntNTy(FloatWidth));
Value *Extract63 = Builder.CreateLShr(Shr18, Builder.getIntN(BitWidth, 32));
Value *ExtractT64 = nullptr;
if (FloatWidth > 80)
ExtractT64 = Builder.CreateTrunc(Sub2, Builder.getInt64Ty());
else
ExtractT64 = Builder.CreateTrunc(Extract63, Builder.getInt32Ty());
Builder.CreateCondBr(PosOrNeg, IfEnd26, IfThen20);
// if.then20
Builder.SetInsertPoint(IfThen20);
Value *Shr21 = nullptr;
if (IsSigned)
Shr21 = Builder.CreateAShr(Inc, Builder.getIntN(BitWidth, 3));
else
Shr21 = Builder.CreateLShr(Inc, Builder.getIntN(BitWidth, 3));
Value *ExtractT = Builder.CreateTrunc(Shr21, Builder.getIntNTy(FloatWidth));
Value *Extract = Builder.CreateLShr(Shr21, Builder.getIntN(BitWidth, 32));
Value *ExtractT62 = nullptr;
if (FloatWidth > 80)
ExtractT62 = Builder.CreateTrunc(Sub1, Builder.getIntNTy(64));
else
ExtractT62 = Builder.CreateTrunc(Extract, Builder.getIntNTy(32));
Builder.CreateBr(IfEnd26);
// if.else:
Builder.SetInsertPoint(IfElse);
Value *Sub24 = Builder.CreateAdd(
FloatWidth == 128 ? Call : Cast,
ConstantInt::getSigned(Builder.getIntNTy(BitWidthNew),
-(BitWidth - FPMantissaWidth - 1)));
Value *ShProm25 = Builder.CreateZExt(Sub24, IntTy);
Value *Shl26 = Builder.CreateShl(IsSigned ? Sub : IntVal,
FloatWidth == 128 ? Sub24 : ShProm25);
Value *ExtractT61 = Builder.CreateTrunc(Shl26, Builder.getIntNTy(FloatWidth));
Value *Extract65 = Builder.CreateLShr(Shl26, Builder.getIntN(BitWidth, 32));
Value *ExtractT66 = nullptr;
if (FloatWidth > 80)
ExtractT66 = Builder.CreateTrunc(Sub2, Builder.getIntNTy(64));
else
ExtractT66 = Builder.CreateTrunc(Extract65, Builder.getInt32Ty());
Builder.CreateBr(IfEnd26);
// if.end26:
Builder.SetInsertPoint(IfEnd26);
PHINode *AAddr1Off0 = Builder.CreatePHI(Builder.getIntNTy(FloatWidth), 3);
AAddr1Off0->addIncoming(ExtractT, IfThen20);
AAddr1Off0->addIncoming(ExtractT60, SwEpilog);
AAddr1Off0->addIncoming(ExtractT61, IfElse);
PHINode *AAddr1Off32 = nullptr;
if (FloatWidth > 32) {
AAddr1Off32 =
Builder.CreatePHI(Builder.getIntNTy(FloatWidth > 80 ? 64 : 32), 3);
AAddr1Off32->addIncoming(ExtractT62, IfThen20);
AAddr1Off32->addIncoming(ExtractT64, SwEpilog);
AAddr1Off32->addIncoming(ExtractT66, IfElse);
}
PHINode *E0 = nullptr;
if (FloatWidth <= 80) {
E0 = Builder.CreatePHI(Builder.getIntNTy(BitWidthNew), 3);
E0->addIncoming(Sub1, IfThen20);
E0->addIncoming(Sub2, SwEpilog);
E0->addIncoming(Sub2, IfElse);
}
Value *And29 = nullptr;
if (FloatWidth > 80) {
Value *Temp2 = Builder.CreateShl(Builder.getIntN(BitWidth, 1),
Builder.getIntN(BitWidth, 63));
And29 = Builder.CreateAnd(Shr, Temp2, "and29");
} else {
Value *Conv28 = Builder.CreateTrunc(Shr, Builder.getIntNTy(32));
And29 = Builder.CreateAnd(
Conv28, ConstantInt::getSigned(Builder.getIntNTy(32), 0x80000000));
}
unsigned TempMod = FPMantissaWidth % 32;
Value *And34 = nullptr;
Value *Shl30 = nullptr;
if (FloatWidth > 80) {
TempMod += 32;
Value *Add = Builder.CreateShl(AAddr1Off32, Builder.getIntN(64, TempMod));
Shl30 = Builder.CreateAdd(
Add,
Builder.getIntN(64, ((1ull << (62ull - TempMod)) - 1ull) << TempMod));
And34 = Builder.CreateZExt(Shl30, Builder.getIntNTy(128));
} else {
Value *Add = Builder.CreateShl(E0, Builder.getIntN(32, TempMod));
Shl30 = Builder.CreateAdd(
Add, Builder.getIntN(32, ((1 << (30 - TempMod)) - 1) << TempMod));
And34 = Builder.CreateAnd(FloatWidth > 32 ? AAddr1Off32 : AAddr1Off0,
Builder.getIntN(32, (1 << TempMod) - 1));
}
Value *Or35 = nullptr;
if (FloatWidth > 80) {
Value *And29Trunc = Builder.CreateTrunc(And29, Builder.getIntNTy(128));
Value *Or31 = Builder.CreateOr(And29Trunc, And34);
Value *Or34 = Builder.CreateShl(Or31, Builder.getIntN(128, 64));
Value *Temp3 = Builder.CreateShl(Builder.getIntN(128, 1),
Builder.getIntN(128, FPMantissaWidth));
Value *Temp4 = Builder.CreateSub(Temp3, Builder.getIntN(128, 1));
Value *A6 = Builder.CreateAnd(AAddr1Off0, Temp4);
Or35 = Builder.CreateOr(Or34, A6);
} else {
Value *Or31 = Builder.CreateOr(And34, And29);
Or35 = Builder.CreateOr(IsSigned ? Or31 : And34, Shl30);
}
Value *A4 = nullptr;
if (IToFP->getType()->isDoubleTy()) {
Value *ZExt1 = Builder.CreateZExt(Or35, Builder.getIntNTy(FloatWidth));
Value *Shl1 = Builder.CreateShl(ZExt1, Builder.getIntN(FloatWidth, 32));
Value *And1 =
Builder.CreateAnd(AAddr1Off0, Builder.getIntN(FloatWidth, 0xFFFFFFFF));
Value *Or1 = Builder.CreateOr(Shl1, And1);
A4 = Builder.CreateBitCast(Or1, IToFP->getType());
} else if (IToFP->getType()->isX86_FP80Ty()) {
Value *A40 =
Builder.CreateBitCast(Or35, Type::getFP128Ty(Builder.getContext()));
A4 = Builder.CreateFPTrunc(A40, IToFP->getType());
} else if (IToFP->getType()->isHalfTy()) {
// Deal with "half" situation. This is a workaround since we don't have
// floattihf.c currently as referring.
Value *A40 =
Builder.CreateBitCast(Or35, Type::getFloatTy(Builder.getContext()));
A4 = Builder.CreateFPTrunc(A40, IToFP->getType());
} else // float type
A4 = Builder.CreateBitCast(Or35, IToFP->getType());
Builder.CreateBr(End);
// return:
Builder.SetInsertPoint(End, End->begin());
PHINode *Retval0 = Builder.CreatePHI(IToFP->getType(), 2);
Retval0->addIncoming(A4, IfEnd26);
Retval0->addIncoming(ConstantFP::getZero(IToFP->getType(), false), Entry);
IToFP->replaceAllUsesWith(Retval0);
IToFP->dropAllReferences();
IToFP->eraseFromParent();
}
static bool runImpl(Function &F, const TargetLowering &TLI) {
SmallVector<Instruction *, 4> Replace;
bool Modified = false;
unsigned MaxLegalFpConvertBitWidth =
TLI.getMaxLargeFPConvertBitWidthSupported();
if (ExpandFpConvertBits != llvm::IntegerType::MAX_INT_BITS)
MaxLegalFpConvertBitWidth = ExpandFpConvertBits;
if (MaxLegalFpConvertBitWidth >= llvm::IntegerType::MAX_INT_BITS)
return false;
for (auto &I : instructions(F)) {
switch (I.getOpcode()) {
case Instruction::FPToUI:
case Instruction::FPToSI: {
// TODO: This pass doesn't handle vectors.
if (I.getOperand(0)->getType()->isVectorTy())
continue;
auto *IntTy = dyn_cast<IntegerType>(I.getType());
if (IntTy->getIntegerBitWidth() <= MaxLegalFpConvertBitWidth)
continue;
Replace.push_back(&I);
Modified = true;
break;
}
case Instruction::UIToFP:
case Instruction::SIToFP: {
// TODO: This pass doesn't handle vectors.
if (I.getOperand(0)->getType()->isVectorTy())
continue;
auto *IntTy = dyn_cast<IntegerType>(I.getOperand(0)->getType());
if (IntTy->getIntegerBitWidth() <= MaxLegalFpConvertBitWidth)
continue;
Replace.push_back(&I);
Modified = true;
break;
}
default:
break;
}
}
if (Replace.empty())
return false;
while (!Replace.empty()) {
Instruction *I = Replace.pop_back_val();
if (I->getOpcode() == Instruction::FPToUI ||
I->getOpcode() == Instruction::FPToSI) {
expandFPToI(I);
} else {
expandIToFP(I);
}
}
return Modified;
}
class ExpandLargeFpConvertLegacyPass : public FunctionPass {
public:
static char ID;
ExpandLargeFpConvertLegacyPass() : FunctionPass(ID) {
initializeExpandLargeFpConvertLegacyPassPass(
*PassRegistry::getPassRegistry());
}
bool runOnFunction(Function &F) override {
auto *TM = &getAnalysis<TargetPassConfig>().getTM<TargetMachine>();
auto *TLI = TM->getSubtargetImpl(F)->getTargetLowering();
return runImpl(F, *TLI);
}
void getAnalysisUsage(AnalysisUsage &AU) const override {
AU.addRequired<TargetPassConfig>();
AU.addPreserved<AAResultsWrapperPass>();
AU.addPreserved<GlobalsAAWrapperPass>();
}
};
char ExpandLargeFpConvertLegacyPass::ID = 0;
INITIALIZE_PASS_BEGIN(ExpandLargeFpConvertLegacyPass, "expand-large-fp-convert",
"Expand large fp convert", false, false)
INITIALIZE_PASS_END(ExpandLargeFpConvertLegacyPass, "expand-large-fp-convert",
"Expand large fp convert", false, false)
FunctionPass *llvm::createExpandLargeFpConvertPass() {
return new ExpandLargeFpConvertLegacyPass();
}

2
llvm/lib/CodeGen/TargetLoweringBase.cpp
View File

@ -726,6 +726,8 @@ TargetLoweringBase::TargetLoweringBase(const TargetMachine &tm) : TM(tm) {
MaxDivRemBitWidthSupported = llvm::IntegerType::MAX_INT_BITS;
MaxLargeFPConvertBitWidthSupported = llvm::IntegerType::MAX_INT_BITS;
MinCmpXchgSizeInBits = 0;
SupportsUnalignedAtomics = false;

1
llvm/lib/CodeGen/TargetPassConfig.cpp
View File

@ -1115,6 +1115,7 @@ bool TargetPassConfig::addISelPasses() {
addPass(createPreISelIntrinsicLoweringPass());
PM->add(createTargetTransformInfoWrapperPass(TM->getTargetIRAnalysis()));
addPass(createExpandLargeDivRemPass());
addPass(createExpandLargeFpConvertPass());
addIRPasses();
addCodeGenPrepare();
addPassesToHandleExceptions();

2
llvm/lib/Target/X86/X86ISelLowering.cpp
View File

@ -172,6 +172,8 @@ X86TargetLowering::X86TargetLowering(const X86TargetMachine &TM,
setMaxDivRemBitWidthSupported(Subtarget.is64Bit() ? 128 : 64);
setMaxLargeFPConvertBitWidthSupported(128);
// Set up the register classes.
addRegisterClass(MVT::i8, &X86::GR8RegClass);
addRegisterClass(MVT::i16, &X86::GR16RegClass);

1
llvm/test/CodeGen/AArch64/O0-pipeline.ll
View File

@ -16,6 +16,7 @@
; CHECK-NEXT: Pre-ISel Intrinsic Lowering
; CHECK-NEXT: FunctionPass Manager
; CHECK-NEXT: Expand large div/rem
; CHECK-NEXT: Expand large fp convert
; CHECK-NEXT: Expand Atomic instructions
; CHECK-NEXT: Module Verifier
; CHECK-NEXT: Lower Garbage Collection Instructions

1
llvm/test/CodeGen/AArch64/O3-pipeline.ll
View File

@ -20,6 +20,7 @@
; CHECK-NEXT: Pre-ISel Intrinsic Lowering
; CHECK-NEXT: FunctionPass Manager
; CHECK-NEXT: Expand large div/rem
; CHECK-NEXT: Expand large fp convert
; CHECK-NEXT: Expand Atomic instructions
; CHECK-NEXT: SVE intrinsics optimizations
; CHECK-NEXT: FunctionPass Manager

5
llvm/test/CodeGen/AMDGPU/llc-pipeline.ll
View File

@ -28,6 +28,7 @@
; GCN-O0-NEXT: Pre-ISel Intrinsic Lowering
; GCN-O0-NEXT: FunctionPass Manager
; GCN-O0-NEXT: Expand large div/rem
; GCN-O0-NEXT: Expand large fp convert
; GCN-O0-NEXT: AMDGPU Printf lowering
; GCN-O0-NEXT: FunctionPass Manager
; GCN-O0-NEXT: Dominator Tree Construction
@ -169,6 +170,7 @@
; GCN-O1-NEXT: Pre-ISel Intrinsic Lowering
; GCN-O1-NEXT: FunctionPass Manager
; GCN-O1-NEXT: Expand large div/rem
; GCN-O1-NEXT: Expand large fp convert
; GCN-O1-NEXT: AMDGPU Printf lowering
; GCN-O1-NEXT: FunctionPass Manager
; GCN-O1-NEXT: Dominator Tree Construction
@ -432,6 +434,7 @@
; GCN-O1-OPTS-NEXT: Pre-ISel Intrinsic Lowering
; GCN-O1-OPTS-NEXT: FunctionPass Manager
; GCN-O1-OPTS-NEXT: Expand large div/rem
; GCN-O1-OPTS-NEXT: Expand large fp convert
; GCN-O1-OPTS-NEXT: AMDGPU Printf lowering
; GCN-O1-OPTS-NEXT: FunctionPass Manager
; GCN-O1-OPTS-NEXT: Dominator Tree Construction
@ -727,6 +730,7 @@
; GCN-O2-NEXT: Pre-ISel Intrinsic Lowering
; GCN-O2-NEXT: FunctionPass Manager
; GCN-O2-NEXT: Expand large div/rem
; GCN-O2-NEXT: Expand large fp convert
; GCN-O2-NEXT: AMDGPU Printf lowering
; GCN-O2-NEXT: FunctionPass Manager
; GCN-O2-NEXT: Dominator Tree Construction
@ -1025,6 +1029,7 @@
; GCN-O3-NEXT: Pre-ISel Intrinsic Lowering
; GCN-O3-NEXT: FunctionPass Manager
; GCN-O3-NEXT: Expand large div/rem
; GCN-O3-NEXT: Expand large fp convert
; GCN-O3-NEXT: AMDGPU Printf lowering
; GCN-O3-NEXT: FunctionPass Manager
; GCN-O3-NEXT: Dominator Tree Construction

1
llvm/test/CodeGen/ARM/O3-pipeline.ll
View File

@ -6,6 +6,7 @@
; CHECK-NEXT: Pre-ISel Intrinsic Lowering
; CHECK-NEXT: FunctionPass Manager
; CHECK-NEXT: Expand large div/rem
; CHECK-NEXT: Expand large fp convert
; CHECK-NEXT: Expand Atomic instructions
; CHECK-NEXT: Simplify the CFG
; CHECK-NEXT: Dominator Tree Construction

1
llvm/test/CodeGen/M68k/pipeline.ll
View File

@ -3,6 +3,7 @@
; CHECK-NEXT: Pre-ISel Intrinsic Lowering
; CHECK-NEXT: FunctionPass Manager
; CHECK-NEXT: Expand large div/rem
; CHECK-NEXT: Expand large fp convert
; CHECK-NEXT: Expand Atomic instructions
; CHECK-NEXT: Module Verifier
; CHECK-NEXT: Dominator Tree Construction

1
llvm/test/CodeGen/PowerPC/O3-pipeline.ll
View File

@ -20,6 +20,7 @@
; CHECK-NEXT: Pre-ISel Intrinsic Lowering
; CHECK-NEXT: FunctionPass Manager
; CHECK-NEXT: Expand large div/rem
; CHECK-NEXT: Expand large fp convert
; CHECK-NEXT: Convert i1 constants to i32/i64 if they are returned
; CHECK-NEXT: Expand Atomic instructions
; CHECK-NEXT: PPC Lower MASS Entries

1
llvm/test/CodeGen/RISCV/O0-pipeline.ll
View File

@ -20,6 +20,7 @@
; CHECK-NEXT: Pre-ISel Intrinsic Lowering
; CHECK-NEXT: FunctionPass Manager
; CHECK-NEXT: Expand large div/rem
; CHECK-NEXT: Expand large fp convert
; CHECK-NEXT: Expand Atomic instructions
; CHECK-NEXT: Module Verifier
; CHECK-NEXT: Lower Garbage Collection Instructions

1
llvm/test/CodeGen/RISCV/O3-pipeline.ll
View File

@ -24,6 +24,7 @@
; CHECK-NEXT: Pre-ISel Intrinsic Lowering
; CHECK-NEXT: FunctionPass Manager
; CHECK-NEXT: Expand large div/rem
; CHECK-NEXT: Expand large fp convert
; CHECK-NEXT: Expand Atomic instructions
; CHECK-NEXT: Dominator Tree Construction
; CHECK-NEXT: Natural Loop Information

1
llvm/test/CodeGen/X86/O0-pipeline.ll
View File

@ -18,6 +18,7 @@
; CHECK-NEXT: Pre-ISel Intrinsic Lowering
; CHECK-NEXT: FunctionPass Manager
; CHECK-NEXT: Expand large div/rem
; CHECK-NEXT: Expand large fp convert
; CHECK-NEXT: Expand Atomic instructions
; CHECK-NEXT: Lower AMX intrinsics
; CHECK-NEXT: Lower AMX type for load/store

177
llvm/test/CodeGen/X86/expand-large-fp-convert-fptosi129.ll Normal file
View File

@ -0,0 +1,177 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -S -mtriple=x86_64-- -expand-large-fp-convert < %s | FileCheck %s
define i129 @halftosi129(half %a) {
; CHECK-LABEL: @halftosi129(
; CHECK-NEXT: [[TMP1:%.*]] = fptosi half [[A:%.*]] to i32
; CHECK-NEXT: [[TMP2:%.*]] = sext i32 [[TMP1]] to i129
; CHECK-NEXT: ret i129 [[TMP2]]
;
%conv = fptosi half %a to i129
ret i129 %conv
}
define i129 @floattosi129(float %a) {
; CHECK-LABEL: @floattosi129(
; CHECK-NEXT: fp-to-i-entry:
; CHECK-NEXT: [[TMP0:%.*]] = bitcast float [[A:%.*]] to i32
; CHECK-NEXT: [[TMP1:%.*]] = zext i32 [[TMP0]] to i129
; CHECK-NEXT: [[TMP2:%.*]] = icmp sgt i32 [[TMP0]], -1
; CHECK-NEXT: [[TMP3:%.*]] = select i1 [[TMP2]], i129 1, i129 -1
; CHECK-NEXT: [[TMP4:%.*]] = lshr i129 [[TMP1]], 23
; CHECK-NEXT: [[TMP5:%.*]] = and i129 [[TMP4]], 255
; CHECK-NEXT: [[TMP6:%.*]] = and i129 [[TMP1]], 8388607
; CHECK-NEXT: [[TMP7:%.*]] = or i129 [[TMP6]], 8388608
; CHECK-NEXT: [[TMP8:%.*]] = icmp ult i129 [[TMP5]], 127
; CHECK-NEXT: br i1 [[TMP8]], label [[FP_TO_I_CLEANUP:%.*]], label [[FP_TO_I_IF_END:%.*]]
; CHECK: fp-to-i-if-end:
; CHECK-NEXT: [[TMP9:%.*]] = add i129 [[TMP5]], -256
; CHECK-NEXT: [[TMP10:%.*]] = icmp ult i129 [[TMP9]], 4294967167
; CHECK-NEXT: br i1 [[TMP10]], label [[FP_TO_I_IF_THEN5:%.*]], label [[FP_TO_I_IF_END9:%.*]]
; CHECK: fp-to-i-if-then5:
; CHECK-NEXT: [[TMP11:%.*]] = select i1 [[TMP2]], i129 340282366920938463463374607431768211455, i129 -340282366920938463463374607431768211456
; CHECK-NEXT: br label [[FP_TO_I_CLEANUP]]
; CHECK: fp-to-i-if-end9:
; CHECK-NEXT: [[TMP12:%.*]] = icmp ult i129 [[TMP5]], 150
; CHECK-NEXT: br i1 [[TMP12]], label [[FP_TO_I_IF_THEN12:%.*]], label [[FP_TO_I_IF_ELSE:%.*]]
; CHECK: fp-to-i-if-then12:
; CHECK-NEXT: [[TMP13:%.*]] = sub i129 150, [[TMP5]]
; CHECK-NEXT: [[TMP14:%.*]] = lshr i129 [[TMP7]], [[TMP13]]
; CHECK-NEXT: [[TMP15:%.*]] = mul i129 [[TMP14]], [[TMP3]]
; CHECK-NEXT: br label [[FP_TO_I_CLEANUP]]
; CHECK: fp-to-i-if-else:
; CHECK-NEXT: [[TMP16:%.*]] = add i129 [[TMP5]], 4294967146
; CHECK-NEXT: [[TMP17:%.*]] = shl i129 [[TMP7]], [[TMP16]]
; CHECK-NEXT: [[TMP18:%.*]] = mul i129 [[TMP17]], [[TMP3]]
; CHECK-NEXT: br label [[FP_TO_I_CLEANUP]]
; CHECK: fp-to-i-cleanup:
; CHECK-NEXT: [[TMP19:%.*]] = phi i129 [ [[TMP11]], [[FP_TO_I_IF_THEN5]] ], [ [[TMP15]], [[FP_TO_I_IF_THEN12]] ], [ [[TMP18]], [[FP_TO_I_IF_ELSE]] ], [ 0, [[FP_TO_I_ENTRY:%.*]] ]
; CHECK-NEXT: ret i129 [[TMP19]]
;
%conv = fptosi float %a to i129
ret i129 %conv
}
define i129 @doubletosi129(double %a) {
; CHECK-LABEL: @doubletosi129(
; CHECK-NEXT: fp-to-i-entry:
; CHECK-NEXT: [[TMP0:%.*]] = bitcast double [[A:%.*]] to i64
; CHECK-NEXT: [[TMP1:%.*]] = zext i64 [[TMP0]] to i129
; CHECK-NEXT: [[TMP2:%.*]] = icmp sgt i64 [[TMP0]], -1
; CHECK-NEXT: [[TMP3:%.*]] = select i1 [[TMP2]], i129 1, i129 -1
; CHECK-NEXT: [[TMP4:%.*]] = lshr i129 [[TMP1]], 52
; CHECK-NEXT: [[TMP5:%.*]] = and i129 [[TMP4]], 2047
; CHECK-NEXT: [[TMP6:%.*]] = and i129 [[TMP1]], 4503599627370495
; CHECK-NEXT: [[TMP7:%.*]] = or i129 [[TMP6]], 4503599627370496
; CHECK-NEXT: [[TMP8:%.*]] = icmp ult i129 [[TMP5]], 1023
; CHECK-NEXT: br i1 [[TMP8]], label [[FP_TO_I_CLEANUP:%.*]], label [[FP_TO_I_IF_END:%.*]]
; CHECK: fp-to-i-if-end:
; CHECK-NEXT: [[TMP9:%.*]] = add i129 [[TMP5]], -1152
; CHECK-NEXT: [[TMP10:%.*]] = icmp ult i129 [[TMP9]], 4294967167
; CHECK-NEXT: br i1 [[TMP10]], label [[FP_TO_I_IF_THEN5:%.*]], label [[FP_TO_I_IF_END9:%.*]]
; CHECK: fp-to-i-if-then5:
; CHECK-NEXT: [[TMP11:%.*]] = select i1 [[TMP2]], i129 340282366920938463463374607431768211455, i129 -340282366920938463463374607431768211456
; CHECK-NEXT: br label [[FP_TO_I_CLEANUP]]
; CHECK: fp-to-i-if-end9:
; CHECK-NEXT: [[TMP12:%.*]] = icmp ult i129 [[TMP5]], 1075
; CHECK-NEXT: br i1 [[TMP12]], label [[FP_TO_I_IF_THEN12:%.*]], label [[FP_TO_I_IF_ELSE:%.*]]
; CHECK: fp-to-i-if-then12:
; CHECK-NEXT: [[TMP13:%.*]] = sub i129 1075, [[TMP5]]
; CHECK-NEXT: [[TMP14:%.*]] = lshr i129 [[TMP7]], [[TMP13]]
; CHECK-NEXT: [[TMP15:%.*]] = mul i129 [[TMP14]], [[TMP3]]
; CHECK-NEXT: br label [[FP_TO_I_CLEANUP]]
; CHECK: fp-to-i-if-else:
; CHECK-NEXT: [[TMP16:%.*]] = add i129 [[TMP5]], 4294966221
; CHECK-NEXT: [[TMP17:%.*]] = shl i129 [[TMP7]], [[TMP16]]
; CHECK-NEXT: [[TMP18:%.*]] = mul i129 [[TMP17]], [[TMP3]]
; CHECK-NEXT: br label [[FP_TO_I_CLEANUP]]
; CHECK: fp-to-i-cleanup:
; CHECK-NEXT: [[TMP19:%.*]] = phi i129 [ [[TMP11]], [[FP_TO_I_IF_THEN5]] ], [ [[TMP15]], [[FP_TO_I_IF_THEN12]] ], [ [[TMP18]], [[FP_TO_I_IF_ELSE]] ], [ 0, [[FP_TO_I_ENTRY:%.*]] ]
; CHECK-NEXT: ret i129 [[TMP19]]
;
%conv = fptosi double %a to i129
ret i129 %conv
}
define i129 @x86_fp80tosi129(x86_fp80 %a) {
; CHECK-LABEL: @x86_fp80tosi129(
; CHECK-NEXT: fp-to-i-entry:
; CHECK-NEXT: [[TMP0:%.*]] = fpext x86_fp80 [[A:%.*]] to fp128
; CHECK-NEXT: [[TMP1:%.*]] = bitcast fp128 [[TMP0]] to i128
; CHECK-NEXT: [[TMP2:%.*]] = zext i128 [[TMP1]] to i129
; CHECK-NEXT: [[TMP3:%.*]] = icmp sgt i128 [[TMP1]], -1
; CHECK-NEXT: [[TMP4:%.*]] = select i1 [[TMP3]], i129 1, i129 -1
; CHECK-NEXT: [[TMP5:%.*]] = lshr i129 [[TMP2]], 112
; CHECK-NEXT: [[TMP6:%.*]] = and i129 [[TMP5]], 32767
; CHECK-NEXT: [[TMP7:%.*]] = and i129 [[TMP2]], 5192296858534827628530496329220095
; CHECK-NEXT: [[TMP8:%.*]] = or i129 [[TMP7]], 5192296858534827628530496329220096
; CHECK-NEXT: [[TMP9:%.*]] = icmp ult i129 [[TMP6]], 16383
; CHECK-NEXT: br i1 [[TMP9]], label [[FP_TO_I_CLEANUP:%.*]], label [[FP_TO_I_IF_END:%.*]]
; CHECK: fp-to-i-if-end:
; CHECK-NEXT: [[TMP10:%.*]] = add i129 [[TMP6]], -16512
; CHECK-NEXT: [[TMP11:%.*]] = icmp ult i129 [[TMP10]], 4294967167
; CHECK-NEXT: br i1 [[TMP11]], label [[FP_TO_I_IF_THEN5:%.*]], label [[FP_TO_I_IF_END9:%.*]]
; CHECK: fp-to-i-if-then5:
; CHECK-NEXT: [[TMP12:%.*]] = select i1 [[TMP3]], i129 340282366920938463463374607431768211455, i129 -340282366920938463463374607431768211456
; CHECK-NEXT: br label [[FP_TO_I_CLEANUP]]
; CHECK: fp-to-i-if-end9:
; CHECK-NEXT: [[TMP13:%.*]] = icmp ult i129 [[TMP6]], 16495
; CHECK-NEXT: br i1 [[TMP13]], label [[FP_TO_I_IF_THEN12:%.*]], label [[FP_TO_I_IF_ELSE:%.*]]
; CHECK: fp-to-i-if-then12:
; CHECK-NEXT: [[TMP14:%.*]] = sub i129 16495, [[TMP6]]
; CHECK-NEXT: [[TMP15:%.*]] = lshr i129 [[TMP8]], [[TMP14]]
; CHECK-NEXT: [[TMP16:%.*]] = mul i129 [[TMP15]], [[TMP4]]
; CHECK-NEXT: br label [[FP_TO_I_CLEANUP]]
; CHECK: fp-to-i-if-else:
; CHECK-NEXT: [[TMP17:%.*]] = add i129 [[TMP6]], 4294950801
; CHECK-NEXT: [[TMP18:%.*]] = shl i129 [[TMP8]], [[TMP17]]
; CHECK-NEXT: [[TMP19:%.*]] = mul i129 [[TMP18]], [[TMP4]]
; CHECK-NEXT: br label [[FP_TO_I_CLEANUP]]
; CHECK: fp-to-i-cleanup:
; CHECK-NEXT: [[TMP20:%.*]] = phi i129 [ [[TMP12]], [[FP_TO_I_IF_THEN5]] ], [ [[TMP16]], [[FP_TO_I_IF_THEN12]] ], [ [[TMP19]], [[FP_TO_I_IF_ELSE]] ], [ 0, [[FP_TO_I_ENTRY:%.*]] ]
; CHECK-NEXT: ret i129 [[TMP20]]
;
%conv = fptosi x86_fp80 %a to i129
ret i129 %conv
}
define i129 @fp128tosi129(fp128 %a) {
; CHECK-LABEL: @fp128tosi129(
; CHECK-NEXT: fp-to-i-entry:
; CHECK-NEXT: [[TMP0:%.*]] = bitcast fp128 [[A:%.*]] to i128
; CHECK-NEXT: [[TMP1:%.*]] = zext i128 [[TMP0]] to i129
; CHECK-NEXT: [[TMP2:%.*]] = icmp sgt i128 [[TMP0]], -1
; CHECK-NEXT: [[TMP3:%.*]] = select i1 [[TMP2]], i129 1, i129 -1
; CHECK-NEXT: [[TMP4:%.*]] = lshr i129 [[TMP1]], 112
; CHECK-NEXT: [[TMP5:%.*]] = and i129 [[TMP4]], 32767
; CHECK-NEXT: [[TMP6:%.*]] = and i129 [[TMP1]], 5192296858534827628530496329220095
; CHECK-NEXT: [[TMP7:%.*]] = or i129 [[TMP6]], 5192296858534827628530496329220096
; CHECK-NEXT: [[TMP8:%.*]] = icmp ult i129 [[TMP5]], 16383
; CHECK-NEXT: br i1 [[TMP8]], label [[FP_TO_I_CLEANUP:%.*]], label [[FP_TO_I_IF_END:%.*]]
; CHECK: fp-to-i-if-end:
; CHECK-NEXT: [[TMP9:%.*]] = add i129 [[TMP5]], -16512
; CHECK-NEXT: [[TMP10:%.*]] = icmp ult i129 [[TMP9]], 4294967167
; CHECK-NEXT: br i1 [[TMP10]], label [[FP_TO_I_IF_THEN5:%.*]], label [[FP_TO_I_IF_END9:%.*]]
; CHECK: fp-to-i-if-then5:
; CHECK-NEXT: [[TMP11:%.*]] = select i1 [[TMP2]], i129 340282366920938463463374607431768211455, i129 -340282366920938463463374607431768211456
; CHECK-NEXT: br label [[FP_TO_I_CLEANUP]]
; CHECK: fp-to-i-if-end9:
; CHECK-NEXT: [[TMP12:%.*]] = icmp ult i129 [[TMP5]], 16495
; CHECK-NEXT: br i1 [[TMP12]], label [[FP_TO_I_IF_THEN12:%.*]], label [[FP_TO_I_IF_ELSE:%.*]]
; CHECK: fp-to-i-if-then12:
; CHECK-NEXT: [[TMP13:%.*]] = sub i129 16495, [[TMP5]]
; CHECK-NEXT: [[TMP14:%.*]] = lshr i129 [[TMP7]], [[TMP13]]
; CHECK-NEXT: [[TMP15:%.*]] = mul i129 [[TMP14]], [[TMP3]]
; CHECK-NEXT: br label [[FP_TO_I_CLEANUP]]
; CHECK: fp-to-i-if-else:
; CHECK-NEXT: [[TMP16:%.*]] = add i129 [[TMP5]], 4294950801
; CHECK-NEXT: [[TMP17:%.*]] = shl i129 [[TMP7]], [[TMP16]]
; CHECK-NEXT: [[TMP18:%.*]] = mul i129 [[TMP17]], [[TMP3]]
; CHECK-NEXT: br label [[FP_TO_I_CLEANUP]]
; CHECK: fp-to-i-cleanup:
; CHECK-NEXT: [[TMP19:%.*]] = phi i129 [ [[TMP11]], [[FP_TO_I_IF_THEN5]] ], [ [[TMP15]], [[FP_TO_I_IF_THEN12]] ], [ [[TMP18]], [[FP_TO_I_IF_ELSE]] ], [ 0, [[FP_TO_I_ENTRY:%.*]] ]
; CHECK-NEXT: ret i129 [[TMP19]]
;
%conv = fptosi fp128 %a to i129
ret i129 %conv
}

177
llvm/test/CodeGen/X86/expand-large-fp-convert-fptoui129.ll Normal file
View File

@ -0,0 +1,177 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -S -mtriple=x86_64-- -expand-large-fp-convert < %s | FileCheck %s
define i129 @halftoui129(half %a) {
; CHECK-LABEL: @halftoui129(
; CHECK-NEXT: [[TMP1:%.*]] = fptoui half [[A:%.*]] to i32
; CHECK-NEXT: [[TMP2:%.*]] = zext i32 [[TMP1]] to i129
; CHECK-NEXT: ret i129 [[TMP2]]
;
%conv = fptoui half %a to i129
ret i129 %conv
}
define i129 @floattoui129(float %a) {
; CHECK-LABEL: @floattoui129(
; CHECK-NEXT: fp-to-i-entry:
; CHECK-NEXT: [[TMP0:%.*]] = bitcast float [[A:%.*]] to i32
; CHECK-NEXT: [[TMP1:%.*]] = zext i32 [[TMP0]] to i129
; CHECK-NEXT: [[TMP2:%.*]] = icmp sgt i32 [[TMP0]], -1
; CHECK-NEXT: [[TMP3:%.*]] = select i1 [[TMP2]], i129 1, i129 -1
; CHECK-NEXT: [[TMP4:%.*]] = lshr i129 [[TMP1]], 23
; CHECK-NEXT: [[TMP5:%.*]] = and i129 [[TMP4]], 255
; CHECK-NEXT: [[TMP6:%.*]] = and i129 [[TMP1]], 8388607
; CHECK-NEXT: [[TMP7:%.*]] = or i129 [[TMP6]], 8388608
; CHECK-NEXT: [[TMP8:%.*]] = icmp ult i129 [[TMP5]], 127
; CHECK-NEXT: br i1 [[TMP8]], label [[FP_TO_I_CLEANUP:%.*]], label [[FP_TO_I_IF_END:%.*]]
; CHECK: fp-to-i-if-end:
; CHECK-NEXT: [[TMP9:%.*]] = add i129 [[TMP5]], -256
; CHECK-NEXT: [[TMP10:%.*]] = icmp ult i129 [[TMP9]], 4294967167
; CHECK-NEXT: br i1 [[TMP10]], label [[FP_TO_I_IF_THEN5:%.*]], label [[FP_TO_I_IF_END9:%.*]]
; CHECK: fp-to-i-if-then5:
; CHECK-NEXT: [[TMP11:%.*]] = select i1 [[TMP2]], i129 340282366920938463463374607431768211455, i129 -340282366920938463463374607431768211456
; CHECK-NEXT: br label [[FP_TO_I_CLEANUP]]
; CHECK: fp-to-i-if-end9:
; CHECK-NEXT: [[TMP12:%.*]] = icmp ult i129 [[TMP5]], 150
; CHECK-NEXT: br i1 [[TMP12]], label [[FP_TO_I_IF_THEN12:%.*]], label [[FP_TO_I_IF_ELSE:%.*]]
; CHECK: fp-to-i-if-then12:
; CHECK-NEXT: [[TMP13:%.*]] = sub i129 150, [[TMP5]]
; CHECK-NEXT: [[TMP14:%.*]] = lshr i129 [[TMP7]], [[TMP13]]
; CHECK-NEXT: [[TMP15:%.*]] = mul i129 [[TMP14]], [[TMP3]]
; CHECK-NEXT: br label [[FP_TO_I_CLEANUP]]
; CHECK: fp-to-i-if-else:
; CHECK-NEXT: [[TMP16:%.*]] = add i129 [[TMP5]], 4294967146
; CHECK-NEXT: [[TMP17:%.*]] = shl i129 [[TMP7]], [[TMP16]]
; CHECK-NEXT: [[TMP18:%.*]] = mul i129 [[TMP17]], [[TMP3]]
; CHECK-NEXT: br label [[FP_TO_I_CLEANUP]]
; CHECK: fp-to-i-cleanup:
; CHECK-NEXT: [[TMP19:%.*]] = phi i129 [ [[TMP11]], [[FP_TO_I_IF_THEN5]] ], [ [[TMP15]], [[FP_TO_I_IF_THEN12]] ], [ [[TMP18]], [[FP_TO_I_IF_ELSE]] ], [ 0, [[FP_TO_I_ENTRY:%.*]] ]
; CHECK-NEXT: ret i129 [[TMP19]]
;
%conv = fptoui float %a to i129
ret i129 %conv
}
define i129 @doubletoui129(double %a) {
; CHECK-LABEL: @doubletoui129(
; CHECK-NEXT: fp-to-i-entry:
; CHECK-NEXT: [[TMP0:%.*]] = bitcast double [[A:%.*]] to i64
; CHECK-NEXT: [[TMP1:%.*]] = zext i64 [[TMP0]] to i129
; CHECK-NEXT: [[TMP2:%.*]] = icmp sgt i64 [[TMP0]], -1
; CHECK-NEXT: [[TMP3:%.*]] = select i1 [[TMP2]], i129 1, i129 -1
; CHECK-NEXT: [[TMP4:%.*]] = lshr i129 [[TMP1]], 52
; CHECK-NEXT: [[TMP5:%.*]] = and i129 [[TMP4]], 2047
; CHECK-NEXT: [[TMP6:%.*]] = and i129 [[TMP1]], 4503599627370495
; CHECK-NEXT: [[TMP7:%.*]] = or i129 [[TMP6]], 4503599627370496
; CHECK-NEXT: [[TMP8:%.*]] = icmp ult i129 [[TMP5]], 1023
; CHECK-NEXT: br i1 [[TMP8]], label [[FP_TO_I_CLEANUP:%.*]], label [[FP_TO_I_IF_END:%.*]]
; CHECK: fp-to-i-if-end:
; CHECK-NEXT: [[TMP9:%.*]] = add i129 [[TMP5]], -1152
; CHECK-NEXT: [[TMP10:%.*]] = icmp ult i129 [[TMP9]], 4294967167
; CHECK-NEXT: br i1 [[TMP10]], label [[FP_TO_I_IF_THEN5:%.*]], label [[FP_TO_I_IF_END9:%.*]]
; CHECK: fp-to-i-if-then5:
; CHECK-NEXT: [[TMP11:%.*]] = select i1 [[TMP2]], i129 340282366920938463463374607431768211455, i129 -340282366920938463463374607431768211456
; CHECK-NEXT: br label [[FP_TO_I_CLEANUP]]
; CHECK: fp-to-i-if-end9:
; CHECK-NEXT: [[TMP12:%.*]] = icmp ult i129 [[TMP5]], 1075
; CHECK-NEXT: br i1 [[TMP12]], label [[FP_TO_I_IF_THEN12:%.*]], label [[FP_TO_I_IF_ELSE:%.*]]
; CHECK: fp-to-i-if-then12:
; CHECK-NEXT: [[TMP13:%.*]] = sub i129 1075, [[TMP5]]
; CHECK-NEXT: [[TMP14:%.*]] = lshr i129 [[TMP7]], [[TMP13]]
; CHECK-NEXT: [[TMP15:%.*]] = mul i129 [[TMP14]], [[TMP3]]
; CHECK-NEXT: br label [[FP_TO_I_CLEANUP]]
; CHECK: fp-to-i-if-else:
; CHECK-NEXT: [[TMP16:%.*]] = add i129 [[TMP5]], 4294966221
; CHECK-NEXT: [[TMP17:%.*]] = shl i129 [[TMP7]], [[TMP16]]
; CHECK-NEXT: [[TMP18:%.*]] = mul i129 [[TMP17]], [[TMP3]]
; CHECK-NEXT: br label [[FP_TO_I_CLEANUP]]
; CHECK: fp-to-i-cleanup:
; CHECK-NEXT: [[TMP19:%.*]] = phi i129 [ [[TMP11]], [[FP_TO_I_IF_THEN5]] ], [ [[TMP15]], [[FP_TO_I_IF_THEN12]] ], [ [[TMP18]], [[FP_TO_I_IF_ELSE]] ], [ 0, [[FP_TO_I_ENTRY:%.*]] ]
; CHECK-NEXT: ret i129 [[TMP19]]
;
%conv = fptoui double %a to i129
ret i129 %conv
}
define i129 @x86_fp80toui129(x86_fp80 %a) {
; CHECK-LABEL: @x86_fp80toui129(
; CHECK-NEXT: fp-to-i-entry:
; CHECK-NEXT: [[TMP0:%.*]] = fpext x86_fp80 [[A:%.*]] to fp128
; CHECK-NEXT: [[TMP1:%.*]] = bitcast fp128 [[TMP0]] to i128
; CHECK-NEXT: [[TMP2:%.*]] = zext i128 [[TMP1]] to i129
; CHECK-NEXT: [[TMP3:%.*]] = icmp sgt i128 [[TMP1]], -1
; CHECK-NEXT: [[TMP4:%.*]] = select i1 [[TMP3]], i129 1, i129 -1
; CHECK-NEXT: [[TMP5:%.*]] = lshr i129 [[TMP2]], 112
; CHECK-NEXT: [[TMP6:%.*]] = and i129 [[TMP5]], 32767
; CHECK-NEXT: [[TMP7:%.*]] = and i129 [[TMP2]], 5192296858534827628530496329220095
; CHECK-NEXT: [[TMP8:%.*]] = or i129 [[TMP7]], 5192296858534827628530496329220096
; CHECK-NEXT: [[TMP9:%.*]] = icmp ult i129 [[TMP6]], 16383
; CHECK-NEXT: br i1 [[TMP9]], label [[FP_TO_I_CLEANUP:%.*]], label [[FP_TO_I_IF_END:%.*]]
; CHECK: fp-to-i-if-end:
; CHECK-NEXT: [[TMP10:%.*]] = add i129 [[TMP6]], -16512
; CHECK-NEXT: [[TMP11:%.*]] = icmp ult i129 [[TMP10]], 4294967167
; CHECK-NEXT: br i1 [[TMP11]], label [[FP_TO_I_IF_THEN5:%.*]], label [[FP_TO_I_IF_END9:%.*]]
; CHECK: fp-to-i-if-then5:
; CHECK-NEXT: [[TMP12:%.*]] = select i1 [[TMP3]], i129 340282366920938463463374607431768211455, i129 -340282366920938463463374607431768211456
; CHECK-NEXT: br label [[FP_TO_I_CLEANUP]]
; CHECK: fp-to-i-if-end9:
; CHECK-NEXT: [[TMP13:%.*]] = icmp ult i129 [[TMP6]], 16495
; CHECK-NEXT: br i1 [[TMP13]], label [[FP_TO_I_IF_THEN12:%.*]], label [[FP_TO_I_IF_ELSE:%.*]]
; CHECK: fp-to-i-if-then12:
; CHECK-NEXT: [[TMP14:%.*]] = sub i129 16495, [[TMP6]]
; CHECK-NEXT: [[TMP15:%.*]] = lshr i129 [[TMP8]], [[TMP14]]
; CHECK-NEXT: [[TMP16:%.*]] = mul i129 [[TMP15]], [[TMP4]]
; CHECK-NEXT: br label [[FP_TO_I_CLEANUP]]
; CHECK: fp-to-i-if-else:
; CHECK-NEXT: [[TMP17:%.*]] = add i129 [[TMP6]], 4294950801
; CHECK-NEXT: [[TMP18:%.*]] = shl i129 [[TMP8]], [[TMP17]]
; CHECK-NEXT: [[TMP19:%.*]] = mul i129 [[TMP18]], [[TMP4]]
; CHECK-NEXT: br label [[FP_TO_I_CLEANUP]]
; CHECK: fp-to-i-cleanup:
; CHECK-NEXT: [[TMP20:%.*]] = phi i129 [ [[TMP12]], [[FP_TO_I_IF_THEN5]] ], [ [[TMP16]], [[FP_TO_I_IF_THEN12]] ], [ [[TMP19]], [[FP_TO_I_IF_ELSE]] ], [ 0, [[FP_TO_I_ENTRY:%.*]] ]
; CHECK-NEXT: ret i129 [[TMP20]]
;
%conv = fptoui x86_fp80 %a to i129
ret i129 %conv
}
define i129 @fp128toui129(fp128 %a) {
; CHECK-LABEL: @fp128toui129(
; CHECK-NEXT: fp-to-i-entry:
; CHECK-NEXT: [[TMP0:%.*]] = bitcast fp128 [[A:%.*]] to i128
; CHECK-NEXT: [[TMP1:%.*]] = zext i128 [[TMP0]] to i129
; CHECK-NEXT: [[TMP2:%.*]] = icmp sgt i128 [[TMP0]], -1
; CHECK-NEXT: [[TMP3:%.*]] = select i1 [[TMP2]], i129 1, i129 -1
; CHECK-NEXT: [[TMP4:%.*]] = lshr i129 [[TMP1]], 112
; CHECK-NEXT: [[TMP5:%.*]] = and i129 [[TMP4]], 32767
; CHECK-NEXT: [[TMP6:%.*]] = and i129 [[TMP1]], 5192296858534827628530496329220095
; CHECK-NEXT: [[TMP7:%.*]] = or i129 [[TMP6]], 5192296858534827628530496329220096
; CHECK-NEXT: [[TMP8:%.*]] = icmp ult i129 [[TMP5]], 16383
; CHECK-NEXT: br i1 [[TMP8]], label [[FP_TO_I_CLEANUP:%.*]], label [[FP_TO_I_IF_END:%.*]]
; CHECK: fp-to-i-if-end:
; CHECK-NEXT: [[TMP9:%.*]] = add i129 [[TMP5]], -16512
; CHECK-NEXT: [[TMP10:%.*]] = icmp ult i129 [[TMP9]], 4294967167
; CHECK-NEXT: br i1 [[TMP10]], label [[FP_TO_I_IF_THEN5:%.*]], label [[FP_TO_I_IF_END9:%.*]]
; CHECK: fp-to-i-if-then5:
; CHECK-NEXT: [[TMP11:%.*]] = select i1 [[TMP2]], i129 340282366920938463463374607431768211455, i129 -340282366920938463463374607431768211456
; CHECK-NEXT: br label [[FP_TO_I_CLEANUP]]
; CHECK: fp-to-i-if-end9:
; CHECK-NEXT: [[TMP12:%.*]] = icmp ult i129 [[TMP5]], 16495
; CHECK-NEXT: br i1 [[TMP12]], label [[FP_TO_I_IF_THEN12:%.*]], label [[FP_TO_I_IF_ELSE:%.*]]
; CHECK: fp-to-i-if-then12:
; CHECK-NEXT: [[TMP13:%.*]] = sub i129 16495, [[TMP5]]
; CHECK-NEXT: [[TMP14:%.*]] = lshr i129 [[TMP7]], [[TMP13]]
; CHECK-NEXT: [[TMP15:%.*]] = mul i129 [[TMP14]], [[TMP3]]
; CHECK-NEXT: br label [[FP_TO_I_CLEANUP]]
; CHECK: fp-to-i-if-else:
; CHECK-NEXT: [[TMP16:%.*]] = add i129 [[TMP5]], 4294950801
; CHECK-NEXT: [[TMP17:%.*]] = shl i129 [[TMP7]], [[TMP16]]
; CHECK-NEXT: [[TMP18:%.*]] = mul i129 [[TMP17]], [[TMP3]]
; CHECK-NEXT: br label [[FP_TO_I_CLEANUP]]
; CHECK: fp-to-i-cleanup:
; CHECK-NEXT: [[TMP19:%.*]] = phi i129 [ [[TMP11]], [[FP_TO_I_IF_THEN5]] ], [ [[TMP15]], [[FP_TO_I_IF_THEN12]] ], [ [[TMP18]], [[FP_TO_I_IF_ELSE]] ], [ 0, [[FP_TO_I_ENTRY:%.*]] ]
; CHECK-NEXT: ret i129 [[TMP19]]
;
%conv = fptoui fp128 %a to i129
ret i129 %conv
}

427
llvm/test/CodeGen/X86/expand-large-fp-convert-si129tofp.ll Normal file
View File

@ -0,0 +1,427 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -S -mtriple=x86_64-- -expand-large-fp-convert < %s | FileCheck %s
define half @si129tohalf(i129 %a) {
; CHECK-LABEL: @si129tohalf(
; CHECK-NEXT: itofp-entry:
; CHECK-NEXT: [[TMP0:%.*]] = icmp eq i129 [[A:%.*]], 0
; CHECK-NEXT: br i1 [[TMP0]], label [[ITOFP_RETURN:%.*]], label [[ITOFP_IF_END:%.*]]
; CHECK: itofp-if-end:
; CHECK-NEXT: [[TMP1:%.*]] = ashr i129 [[A]], 128
; CHECK-NEXT: [[TMP2:%.*]] = xor i129 [[TMP1]], [[A]]
; CHECK-NEXT: [[TMP3:%.*]] = sub i129 [[TMP2]], [[TMP1]]
; CHECK-NEXT: [[TMP4:%.*]] = call i129 @llvm.ctlz.i129(i129 [[TMP3]], i1 true)
; CHECK-NEXT: [[TMP5:%.*]] = trunc i129 [[TMP4]] to i32
; CHECK-NEXT: [[TMP6:%.*]] = sub i32 129, [[TMP5]]
; CHECK-NEXT: [[TMP7:%.*]] = sub i32 128, [[TMP5]]
; CHECK-NEXT: [[TMP8:%.*]] = icmp sgt i32 [[TMP7]], 24
; CHECK-NEXT: br i1 [[TMP8]], label [[ITOFP_IF_THEN4:%.*]], label [[ITOFP_IF_ELSE:%.*]]
; CHECK: itofp-if-then4:
; CHECK-NEXT: switch i32 [[TMP6]], label [[ITOFP_SW_DEFAULT:%.*]] [
; CHECK-NEXT: i32 25, label [[ITOFP_SW_BB:%.*]]
; CHECK-NEXT: i32 26, label [[ITOFP_SW_EPILOG:%.*]]
; CHECK-NEXT: ]
; CHECK: itofp-sw-bb:
; CHECK-NEXT: [[TMP9:%.*]] = shl i129 [[TMP3]], 1
; CHECK-NEXT: br label [[ITOFP_SW_EPILOG]]
; CHECK: itofp-sw-default:
; CHECK-NEXT: [[TMP10:%.*]] = sub i32 103, [[TMP5]]
; CHECK-NEXT: [[TMP11:%.*]] = zext i32 [[TMP10]] to i129
; CHECK-NEXT: [[TMP12:%.*]] = lshr i129 [[TMP3]], [[TMP11]]
; CHECK-NEXT: [[TMP13:%.*]] = add i32 [[TMP5]], 26
; CHECK-NEXT: [[TMP14:%.*]] = zext i32 [[TMP13]] to i129
; CHECK-NEXT: [[TMP15:%.*]] = lshr i129 -1, [[TMP14]]
; CHECK-NEXT: [[TMP16:%.*]] = and i129 [[TMP15]], [[TMP3]]
; CHECK-NEXT: [[TMP17:%.*]] = icmp ne i129 [[TMP16]], 0
; CHECK-NEXT: [[TMP18:%.*]] = zext i1 [[TMP17]] to i129
; CHECK-NEXT: [[TMP19:%.*]] = or i129 [[TMP12]], [[TMP18]]
; CHECK-NEXT: br label [[ITOFP_SW_EPILOG]]
; CHECK: itofp-sw-epilog:
; CHECK-NEXT: [[TMP20:%.*]] = phi i129 [ [[TMP19]], [[ITOFP_SW_DEFAULT]] ], [ [[TMP3]], [[ITOFP_IF_THEN4]] ], [ [[TMP9]], [[ITOFP_SW_BB]] ]
; CHECK-NEXT: [[TMP21:%.*]] = trunc i129 [[TMP20]] to i32
; CHECK-NEXT: [[TMP22:%.*]] = lshr i32 [[TMP21]], 2
; CHECK-NEXT: [[TMP23:%.*]] = and i32 [[TMP22]], 1
; CHECK-NEXT: [[TMP24:%.*]] = zext i32 [[TMP23]] to i129
; CHECK-NEXT: [[TMP25:%.*]] = or i129 [[TMP20]], [[TMP24]]
; CHECK-NEXT: [[TMP26:%.*]] = add i129 [[TMP25]], 1
; CHECK-NEXT: [[TMP27:%.*]] = ashr i129 [[TMP26]], 2
; CHECK-NEXT: [[A3:%.*]] = and i129 [[TMP26]], 67108864
; CHECK-NEXT: [[TMP28:%.*]] = icmp eq i129 [[A3]], 0
; CHECK-NEXT: [[TMP29:%.*]] = trunc i129 [[TMP27]] to i32
; CHECK-NEXT: [[TMP30:%.*]] = lshr i129 [[TMP27]], 32
; CHECK-NEXT: [[TMP31:%.*]] = trunc i129 [[TMP30]] to i32
; CHECK-NEXT: br i1 [[TMP28]], label [[ITOFP_IF_END26:%.*]], label [[ITOFP_IF_THEN20:%.*]]
; CHECK: itofp-if-then20:
; CHECK-NEXT: [[TMP32:%.*]] = ashr i129 [[TMP26]], 3
; CHECK-NEXT: [[TMP33:%.*]] = trunc i129 [[TMP32]] to i32
; CHECK-NEXT: [[TMP34:%.*]] = lshr i129 [[TMP32]], 32
; CHECK-NEXT: [[TMP35:%.*]] = trunc i129 [[TMP34]] to i32
; CHECK-NEXT: br label [[ITOFP_IF_END26]]
; CHECK: itofp-if-else:
; CHECK-NEXT: [[TMP36:%.*]] = add i32 [[TMP5]], -105
; CHECK-NEXT: [[TMP37:%.*]] = zext i32 [[TMP36]] to i129
; CHECK-NEXT: [[TMP38:%.*]] = shl i129 [[TMP3]], [[TMP37]]
; CHECK-NEXT: [[TMP39:%.*]] = trunc i129 [[TMP38]] to i32
; CHECK-NEXT: [[TMP40:%.*]] = lshr i129 [[TMP38]], 32
; CHECK-NEXT: [[TMP41:%.*]] = trunc i129 [[TMP40]] to i32
; CHECK-NEXT: br label [[ITOFP_IF_END26]]
; CHECK: itofp-if-end26:
; CHECK-NEXT: [[TMP42:%.*]] = phi i32 [ [[TMP33]], [[ITOFP_IF_THEN20]] ], [ [[TMP29]], [[ITOFP_SW_EPILOG]] ], [ [[TMP39]], [[ITOFP_IF_ELSE]] ]
; CHECK-NEXT: [[TMP43:%.*]] = phi i32 [ [[TMP6]], [[ITOFP_IF_THEN20]] ], [ [[TMP7]], [[ITOFP_SW_EPILOG]] ], [ [[TMP7]], [[ITOFP_IF_ELSE]] ]
; CHECK-NEXT: [[TMP44:%.*]] = trunc i129 [[TMP1]] to i32
; CHECK-NEXT: [[TMP45:%.*]] = and i32 [[TMP44]], -2147483648
; CHECK-NEXT: [[TMP46:%.*]] = shl i32 [[TMP43]], 23
; CHECK-NEXT: [[TMP47:%.*]] = add i32 [[TMP46]], 1065353216
; CHECK-NEXT: [[TMP48:%.*]] = and i32 [[TMP42]], 8388607
; CHECK-NEXT: [[TMP49:%.*]] = or i32 [[TMP48]], [[TMP45]]
; CHECK-NEXT: [[TMP50:%.*]] = or i32 [[TMP49]], [[TMP47]]
; CHECK-NEXT: [[TMP51:%.*]] = bitcast i32 [[TMP50]] to float
; CHECK-NEXT: [[TMP52:%.*]] = fptrunc float [[TMP51]] to half
; CHECK-NEXT: br label [[ITOFP_RETURN]]
; CHECK: itofp-return:
; CHECK-NEXT: [[TMP53:%.*]] = phi half [ [[TMP52]], [[ITOFP_IF_END26]] ], [ 0xH0000, [[ITOFP_ENTRY:%.*]] ]
; CHECK-NEXT: ret half [[TMP53]]
;
%conv = sitofp i129 %a to half
ret half %conv
}
define float @si129tofloat(i129 %a) {
; CHECK-LABEL: @si129tofloat(
; CHECK-NEXT: itofp-entry:
; CHECK-NEXT: [[TMP0:%.*]] = icmp eq i129 [[A:%.*]], 0
; CHECK-NEXT: br i1 [[TMP0]], label [[ITOFP_RETURN:%.*]], label [[ITOFP_IF_END:%.*]]
; CHECK: itofp-if-end:
; CHECK-NEXT: [[TMP1:%.*]] = ashr i129 [[A]], 128
; CHECK-NEXT: [[TMP2:%.*]] = xor i129 [[TMP1]], [[A]]
; CHECK-NEXT: [[TMP3:%.*]] = sub i129 [[TMP2]], [[TMP1]]
; CHECK-NEXT: [[TMP4:%.*]] = call i129 @llvm.ctlz.i129(i129 [[TMP3]], i1 true)
; CHECK-NEXT: [[TMP5:%.*]] = trunc i129 [[TMP4]] to i32
; CHECK-NEXT: [[TMP6:%.*]] = sub i32 129, [[TMP5]]
; CHECK-NEXT: [[TMP7:%.*]] = sub i32 128, [[TMP5]]
; CHECK-NEXT: [[TMP8:%.*]] = icmp sgt i32 [[TMP7]], 24
; CHECK-NEXT: br i1 [[TMP8]], label [[ITOFP_IF_THEN4:%.*]], label [[ITOFP_IF_ELSE:%.*]]
; CHECK: itofp-if-then4:
; CHECK-NEXT: switch i32 [[TMP6]], label [[ITOFP_SW_DEFAULT:%.*]] [
; CHECK-NEXT: i32 25, label [[ITOFP_SW_BB:%.*]]
; CHECK-NEXT: i32 26, label [[ITOFP_SW_EPILOG:%.*]]
; CHECK-NEXT: ]
; CHECK: itofp-sw-bb:
; CHECK-NEXT: [[TMP9:%.*]] = shl i129 [[TMP3]], 1
; CHECK-NEXT: br label [[ITOFP_SW_EPILOG]]
; CHECK: itofp-sw-default:
; CHECK-NEXT: [[TMP10:%.*]] = sub i32 103, [[TMP5]]
; CHECK-NEXT: [[TMP11:%.*]] = zext i32 [[TMP10]] to i129
; CHECK-NEXT: [[TMP12:%.*]] = lshr i129 [[TMP3]], [[TMP11]]
; CHECK-NEXT: [[TMP13:%.*]] = add i32 [[TMP5]], 26
; CHECK-NEXT: [[TMP14:%.*]] = zext i32 [[TMP13]] to i129
; CHECK-NEXT: [[TMP15:%.*]] = lshr i129 -1, [[TMP14]]
; CHECK-NEXT: [[TMP16:%.*]] = and i129 [[TMP15]], [[TMP3]]
; CHECK-NEXT: [[TMP17:%.*]] = icmp ne i129 [[TMP16]], 0
; CHECK-NEXT: [[TMP18:%.*]] = zext i1 [[TMP17]] to i129
; CHECK-NEXT: [[TMP19:%.*]] = or i129 [[TMP12]], [[TMP18]]
; CHECK-NEXT: br label [[ITOFP_SW_EPILOG]]
; CHECK: itofp-sw-epilog:
; CHECK-NEXT: [[TMP20:%.*]] = phi i129 [ [[TMP19]], [[ITOFP_SW_DEFAULT]] ], [ [[TMP3]], [[ITOFP_IF_THEN4]] ], [ [[TMP9]], [[ITOFP_SW_BB]] ]
; CHECK-NEXT: [[TMP21:%.*]] = trunc i129 [[TMP20]] to i32
; CHECK-NEXT: [[TMP22:%.*]] = lshr i32 [[TMP21]], 2
; CHECK-NEXT: [[TMP23:%.*]] = and i32 [[TMP22]], 1
; CHECK-NEXT: [[TMP24:%.*]] = zext i32 [[TMP23]] to i129
; CHECK-NEXT: [[TMP25:%.*]] = or i129 [[TMP20]], [[TMP24]]
; CHECK-NEXT: [[TMP26:%.*]] = add i129 [[TMP25]], 1
; CHECK-NEXT: [[TMP27:%.*]] = ashr i129 [[TMP26]], 2
; CHECK-NEXT: [[A3:%.*]] = and i129 [[TMP26]], 67108864
; CHECK-NEXT: [[TMP28:%.*]] = icmp eq i129 [[A3]], 0
; CHECK-NEXT: [[TMP29:%.*]] = trunc i129 [[TMP27]] to i32
; CHECK-NEXT: [[TMP30:%.*]] = lshr i129 [[TMP27]], 32
; CHECK-NEXT: [[TMP31:%.*]] = trunc i129 [[TMP30]] to i32
; CHECK-NEXT: br i1 [[TMP28]], label [[ITOFP_IF_END26:%.*]], label [[ITOFP_IF_THEN20:%.*]]
; CHECK: itofp-if-then20:
; CHECK-NEXT: [[TMP32:%.*]] = ashr i129 [[TMP26]], 3
; CHECK-NEXT: [[TMP33:%.*]] = trunc i129 [[TMP32]] to i32
; CHECK-NEXT: [[TMP34:%.*]] = lshr i129 [[TMP32]], 32
; CHECK-NEXT: [[TMP35:%.*]] = trunc i129 [[TMP34]] to i32
; CHECK-NEXT: br label [[ITOFP_IF_END26]]
; CHECK: itofp-if-else:
; CHECK-NEXT: [[TMP36:%.*]] = add i32 [[TMP5]], -105
; CHECK-NEXT: [[TMP37:%.*]] = zext i32 [[TMP36]] to i129
; CHECK-NEXT: [[TMP38:%.*]] = shl i129 [[TMP3]], [[TMP37]]
; CHECK-NEXT: [[TMP39:%.*]] = trunc i129 [[TMP38]] to i32
; CHECK-NEXT: [[TMP40:%.*]] = lshr i129 [[TMP38]], 32
; CHECK-NEXT: [[TMP41:%.*]] = trunc i129 [[TMP40]] to i32
; CHECK-NEXT: br label [[ITOFP_IF_END26]]
; CHECK: itofp-if-end26:
; CHECK-NEXT: [[TMP42:%.*]] = phi i32 [ [[TMP33]], [[ITOFP_IF_THEN20]] ], [ [[TMP29]], [[ITOFP_SW_EPILOG]] ], [ [[TMP39]], [[ITOFP_IF_ELSE]] ]
; CHECK-NEXT: [[TMP43:%.*]] = phi i32 [ [[TMP6]], [[ITOFP_IF_THEN20]] ], [ [[TMP7]], [[ITOFP_SW_EPILOG]] ], [ [[TMP7]], [[ITOFP_IF_ELSE]] ]
; CHECK-NEXT: [[TMP44:%.*]] = trunc i129 [[TMP1]] to i32
; CHECK-NEXT: [[TMP45:%.*]] = and i32 [[TMP44]], -2147483648
; CHECK-NEXT: [[TMP46:%.*]] = shl i32 [[TMP43]], 23
; CHECK-NEXT: [[TMP47:%.*]] = add i32 [[TMP46]], 1065353216
; CHECK-NEXT: [[TMP48:%.*]] = and i32 [[TMP42]], 8388607
; CHECK-NEXT: [[TMP49:%.*]] = or i32 [[TMP48]], [[TMP45]]
; CHECK-NEXT: [[TMP50:%.*]] = or i32 [[TMP49]], [[TMP47]]
; CHECK-NEXT: [[TMP51:%.*]] = bitcast i32 [[TMP50]] to float
; CHECK-NEXT: br label [[ITOFP_RETURN]]
; CHECK: itofp-return:
; CHECK-NEXT: [[TMP52:%.*]] = phi float [ [[TMP51]], [[ITOFP_IF_END26]] ], [ 0.000000e+00, [[ITOFP_ENTRY:%.*]] ]
; CHECK-NEXT: ret float [[TMP52]]
;
%conv = sitofp i129 %a to float
ret float %conv
}
define double @si129todouble(i129 %a) {
; CHECK-LABEL: @si129todouble(
; CHECK-NEXT: itofp-entry:
; CHECK-NEXT: [[TMP0:%.*]] = icmp eq i129 [[A:%.*]], 0
; CHECK-NEXT: br i1 [[TMP0]], label [[ITOFP_RETURN:%.*]], label [[ITOFP_IF_END:%.*]]
; CHECK: itofp-if-end:
; CHECK-NEXT: [[TMP1:%.*]] = ashr i129 [[A]], 128
; CHECK-NEXT: [[TMP2:%.*]] = xor i129 [[TMP1]], [[A]]
; CHECK-NEXT: [[TMP3:%.*]] = sub i129 [[TMP2]], [[TMP1]]
; CHECK-NEXT: [[TMP4:%.*]] = call i129 @llvm.ctlz.i129(i129 [[TMP3]], i1 true)
; CHECK-NEXT: [[TMP5:%.*]] = trunc i129 [[TMP4]] to i32
; CHECK-NEXT: [[TMP6:%.*]] = sub i32 129, [[TMP5]]
; CHECK-NEXT: [[TMP7:%.*]] = sub i32 128, [[TMP5]]
; CHECK-NEXT: [[TMP8:%.*]] = icmp sgt i32 [[TMP7]], 53
; CHECK-NEXT: br i1 [[TMP8]], label [[ITOFP_IF_THEN4:%.*]], label [[ITOFP_IF_ELSE:%.*]]
; CHECK: itofp-if-then4:
; CHECK-NEXT: switch i32 [[TMP6]], label [[ITOFP_SW_DEFAULT:%.*]] [
; CHECK-NEXT: i32 54, label [[ITOFP_SW_BB:%.*]]
; CHECK-NEXT: i32 55, label [[ITOFP_SW_EPILOG:%.*]]
; CHECK-NEXT: ]
; CHECK: itofp-sw-bb:
; CHECK-NEXT: [[TMP9:%.*]] = shl i129 [[TMP3]], 1
; CHECK-NEXT: br label [[ITOFP_SW_EPILOG]]
; CHECK: itofp-sw-default:
; CHECK-NEXT: [[TMP10:%.*]] = sub i32 74, [[TMP5]]
; CHECK-NEXT: [[TMP11:%.*]] = zext i32 [[TMP10]] to i129
; CHECK-NEXT: [[TMP12:%.*]] = lshr i129 [[TMP3]], [[TMP11]]
; CHECK-NEXT: [[TMP13:%.*]] = add i32 [[TMP5]], 55
; CHECK-NEXT: [[TMP14:%.*]] = zext i32 [[TMP13]] to i129
; CHECK-NEXT: [[TMP15:%.*]] = lshr i129 -1, [[TMP14]]
; CHECK-NEXT: [[TMP16:%.*]] = and i129 [[TMP15]], [[TMP3]]
; CHECK-NEXT: [[TMP17:%.*]] = icmp ne i129 [[TMP16]], 0
; CHECK-NEXT: [[TMP18:%.*]] = zext i1 [[TMP17]] to i129
; CHECK-NEXT: [[TMP19:%.*]] = or i129 [[TMP12]], [[TMP18]]
; CHECK-NEXT: br label [[ITOFP_SW_EPILOG]]
; CHECK: itofp-sw-epilog:
; CHECK-NEXT: [[TMP20:%.*]] = phi i129 [ [[TMP19]], [[ITOFP_SW_DEFAULT]] ], [ [[TMP3]], [[ITOFP_IF_THEN4]] ], [ [[TMP9]], [[ITOFP_SW_BB]] ]
; CHECK-NEXT: [[TMP21:%.*]] = trunc i129 [[TMP20]] to i32
; CHECK-NEXT: [[TMP22:%.*]] = lshr i32 [[TMP21]], 2
; CHECK-NEXT: [[TMP23:%.*]] = and i32 [[TMP22]], 1
; CHECK-NEXT: [[TMP24:%.*]] = zext i32 [[TMP23]] to i129
; CHECK-NEXT: [[TMP25:%.*]] = or i129 [[TMP20]], [[TMP24]]
; CHECK-NEXT: [[TMP26:%.*]] = add i129 [[TMP25]], 1
; CHECK-NEXT: [[TMP27:%.*]] = ashr i129 [[TMP26]], 2
; CHECK-NEXT: [[A3:%.*]] = and i129 [[TMP26]], 36028797018963968
; CHECK-NEXT: [[TMP28:%.*]] = icmp eq i129 [[A3]], 0
; CHECK-NEXT: [[TMP29:%.*]] = trunc i129 [[TMP27]] to i64
; CHECK-NEXT: [[TMP30:%.*]] = lshr i129 [[TMP27]], 32
; CHECK-NEXT: [[TMP31:%.*]] = trunc i129 [[TMP30]] to i32
; CHECK-NEXT: br i1 [[TMP28]], label [[ITOFP_IF_END26:%.*]], label [[ITOFP_IF_THEN20:%.*]]
; CHECK: itofp-if-then20:
; CHECK-NEXT: [[TMP32:%.*]] = ashr i129 [[TMP26]], 3
; CHECK-NEXT: [[TMP33:%.*]] = trunc i129 [[TMP32]] to i64
; CHECK-NEXT: [[TMP34:%.*]] = lshr i129 [[TMP32]], 32
; CHECK-NEXT: [[TMP35:%.*]] = trunc i129 [[TMP34]] to i32
; CHECK-NEXT: br label [[ITOFP_IF_END26]]
; CHECK: itofp-if-else:
; CHECK-NEXT: [[TMP36:%.*]] = add i32 [[TMP5]], -76
; CHECK-NEXT: [[TMP37:%.*]] = zext i32 [[TMP36]] to i129
; CHECK-NEXT: [[TMP38:%.*]] = shl i129 [[TMP3]], [[TMP37]]
; CHECK-NEXT: [[TMP39:%.*]] = trunc i129 [[TMP38]] to i64
; CHECK-NEXT: [[TMP40:%.*]] = lshr i129 [[TMP38]], 32
; CHECK-NEXT: [[TMP41:%.*]] = trunc i129 [[TMP40]] to i32
; CHECK-NEXT: br label [[ITOFP_IF_END26]]
; CHECK: itofp-if-end26:
; CHECK-NEXT: [[TMP42:%.*]] = phi i64 [ [[TMP33]], [[ITOFP_IF_THEN20]] ], [ [[TMP29]], [[ITOFP_SW_EPILOG]] ], [ [[TMP39]], [[ITOFP_IF_ELSE]] ]
; CHECK-NEXT: [[TMP43:%.*]] = phi i32 [ [[TMP35]], [[ITOFP_IF_THEN20]] ], [ [[TMP31]], [[ITOFP_SW_EPILOG]] ], [ [[TMP41]], [[ITOFP_IF_ELSE]] ]
; CHECK-NEXT: [[TMP44:%.*]] = phi i32 [ [[TMP6]], [[ITOFP_IF_THEN20]] ], [ [[TMP7]], [[ITOFP_SW_EPILOG]] ], [ [[TMP7]], [[ITOFP_IF_ELSE]] ]
; CHECK-NEXT: [[TMP45:%.*]] = trunc i129 [[TMP1]] to i32
; CHECK-NEXT: [[TMP46:%.*]] = and i32 [[TMP45]], -2147483648
; CHECK-NEXT: [[TMP47:%.*]] = shl i32 [[TMP44]], 20
; CHECK-NEXT: [[TMP48:%.*]] = add i32 [[TMP47]], 1072693248
; CHECK-NEXT: [[TMP49:%.*]] = and i32 [[TMP43]], 1048575
; CHECK-NEXT: [[TMP50:%.*]] = or i32 [[TMP49]], [[TMP46]]
; CHECK-NEXT: [[TMP51:%.*]] = or i32 [[TMP50]], [[TMP48]]
; CHECK-NEXT: [[TMP52:%.*]] = zext i32 [[TMP51]] to i64
; CHECK-NEXT: [[TMP53:%.*]] = shl i64 [[TMP52]], 32
; CHECK-NEXT: [[TMP54:%.*]] = and i64 [[TMP42]], 4294967295
; CHECK-NEXT: [[TMP55:%.*]] = or i64 [[TMP53]], [[TMP54]]
; CHECK-NEXT: [[TMP56:%.*]] = bitcast i64 [[TMP55]] to double
; CHECK-NEXT: br label [[ITOFP_RETURN]]
; CHECK: itofp-return:
; CHECK-NEXT: [[TMP57:%.*]] = phi double [ [[TMP56]], [[ITOFP_IF_END26]] ], [ 0.000000e+00, [[ITOFP_ENTRY:%.*]] ]
; CHECK-NEXT: ret double [[TMP57]]
;
%conv = sitofp i129 %a to double
ret double %conv
}
define x86_fp80 @si129tox86_fp80(i129 %a) {
; CHECK-LABEL: @si129tox86_fp80(
; CHECK-NEXT: itofp-entry:
; CHECK-NEXT: [[TMP0:%.*]] = icmp eq i129 [[A:%.*]], 0
; CHECK-NEXT: br i1 [[TMP0]], label [[ITOFP_RETURN:%.*]], label [[ITOFP_IF_END:%.*]]
; CHECK: itofp-if-end:
; CHECK-NEXT: [[TMP1:%.*]] = ashr i129 [[A]], 128
; CHECK-NEXT: [[TMP2:%.*]] = xor i129 [[TMP1]], [[A]]
; CHECK-NEXT: [[TMP3:%.*]] = sub i129 [[TMP2]], [[TMP1]]
; CHECK-NEXT: [[TMP4:%.*]] = call i129 @llvm.ctlz.i129(i129 [[TMP3]], i1 true)
; CHECK-NEXT: [[TMP5:%.*]] = trunc i129 [[TMP4]] to i32
; CHECK-NEXT: [[TMP6:%.*]] = sub i129 129, [[TMP4]]
; CHECK-NEXT: [[TMP7:%.*]] = sub i129 128, [[TMP4]]
; CHECK-NEXT: [[TMP8:%.*]] = icmp sgt i129 [[TMP7]], 113
; CHECK-NEXT: br i1 [[TMP8]], label [[ITOFP_IF_THEN4:%.*]], label [[ITOFP_IF_ELSE:%.*]]
; CHECK: itofp-if-then4:
; CHECK-NEXT: switch i129 [[TMP6]], label [[ITOFP_SW_DEFAULT:%.*]] [
; CHECK-NEXT: i129 114, label [[ITOFP_SW_BB:%.*]]
; CHECK-NEXT: i129 115, label [[ITOFP_SW_EPILOG:%.*]]
; CHECK-NEXT: ]
; CHECK: itofp-sw-bb:
; CHECK-NEXT: [[TMP9:%.*]] = shl i129 [[TMP3]], 1
; CHECK-NEXT: br label [[ITOFP_SW_EPILOG]]
; CHECK: itofp-sw-default:
; CHECK-NEXT: [[TMP10:%.*]] = sub i129 14, [[TMP4]]
; CHECK-NEXT: [[TMP11:%.*]] = lshr i129 [[TMP3]], [[TMP10]]
; CHECK-NEXT: [[TMP12:%.*]] = add i129 [[TMP4]], 115
; CHECK-NEXT: [[TMP13:%.*]] = lshr i129 -1, [[TMP12]]
; CHECK-NEXT: [[TMP14:%.*]] = and i129 [[TMP13]], [[TMP3]]
; CHECK-NEXT: [[TMP15:%.*]] = icmp ne i129 [[TMP14]], 0
; CHECK-NEXT: [[TMP16:%.*]] = zext i1 [[TMP15]] to i129
; CHECK-NEXT: [[TMP17:%.*]] = or i129 [[TMP11]], [[TMP16]]
; CHECK-NEXT: br label [[ITOFP_SW_EPILOG]]
; CHECK: itofp-sw-epilog:
; CHECK-NEXT: [[TMP18:%.*]] = phi i129 [ [[TMP17]], [[ITOFP_SW_DEFAULT]] ], [ [[TMP3]], [[ITOFP_IF_THEN4]] ], [ [[TMP9]], [[ITOFP_SW_BB]] ]
; CHECK-NEXT: [[TMP19:%.*]] = trunc i129 [[TMP18]] to i32
; CHECK-NEXT: [[TMP20:%.*]] = lshr i32 [[TMP19]], 2
; CHECK-NEXT: [[TMP21:%.*]] = and i32 [[TMP20]], 1
; CHECK-NEXT: [[TMP22:%.*]] = zext i32 [[TMP21]] to i129
; CHECK-NEXT: [[TMP23:%.*]] = or i129 [[TMP18]], [[TMP22]]
; CHECK-NEXT: [[TMP24:%.*]] = add i129 [[TMP23]], 1
; CHECK-NEXT: [[TMP25:%.*]] = ashr i129 [[TMP24]], 2
; CHECK-NEXT: [[A3:%.*]] = and i129 [[TMP24]], 41538374868278621028243970633760768
; CHECK-NEXT: [[TMP26:%.*]] = icmp eq i129 [[A3]], 0
; CHECK-NEXT: [[TMP27:%.*]] = trunc i129 [[TMP25]] to i128
; CHECK-NEXT: [[TMP28:%.*]] = lshr i129 [[TMP25]], 32
; CHECK-NEXT: [[TMP29:%.*]] = trunc i129 [[TMP7]] to i64
; CHECK-NEXT: br i1 [[TMP26]], label [[ITOFP_IF_END26:%.*]], label [[ITOFP_IF_THEN20:%.*]]
; CHECK: itofp-if-then20:
; CHECK-NEXT: [[TMP30:%.*]] = ashr i129 [[TMP24]], 3
; CHECK-NEXT: [[TMP31:%.*]] = trunc i129 [[TMP30]] to i128
; CHECK-NEXT: [[TMP32:%.*]] = lshr i129 [[TMP30]], 32
; CHECK-NEXT: [[TMP33:%.*]] = trunc i129 [[TMP6]] to i64
; CHECK-NEXT: br label [[ITOFP_IF_END26]]
; CHECK: itofp-if-else:
; CHECK-NEXT: [[TMP34:%.*]] = add i129 [[TMP4]], 4294967280
; CHECK-NEXT: [[TMP35:%.*]] = shl i129 [[TMP3]], [[TMP34]]
; CHECK-NEXT: [[TMP36:%.*]] = trunc i129 [[TMP35]] to i128
; CHECK-NEXT: [[TMP37:%.*]] = lshr i129 [[TMP35]], 32
; CHECK-NEXT: [[TMP38:%.*]] = trunc i129 [[TMP7]] to i64
; CHECK-NEXT: br label [[ITOFP_IF_END26]]
; CHECK: itofp-if-end26:
; CHECK-NEXT: [[TMP39:%.*]] = phi i128 [ [[TMP31]], [[ITOFP_IF_THEN20]] ], [ [[TMP27]], [[ITOFP_SW_EPILOG]] ], [ [[TMP36]], [[ITOFP_IF_ELSE]] ]
; CHECK-NEXT: [[TMP40:%.*]] = phi i64 [ [[TMP33]], [[ITOFP_IF_THEN20]] ], [ [[TMP29]], [[ITOFP_SW_EPILOG]] ], [ [[TMP38]], [[ITOFP_IF_ELSE]] ]
; CHECK-NEXT: [[AND29:%.*]] = and i129 [[TMP1]], 9223372036854775808
; CHECK-NEXT: [[TMP41:%.*]] = shl i64 [[TMP40]], 48
; CHECK-NEXT: [[TMP42:%.*]] = add i64 [[TMP41]], 4611404543450677248
; CHECK-NEXT: [[TMP43:%.*]] = zext i64 [[TMP42]] to i128
; CHECK-NEXT: [[TMP44:%.*]] = trunc i129 [[AND29]] to i128
; CHECK-NEXT: [[TMP45:%.*]] = or i128 [[TMP44]], [[TMP43]]
; CHECK-NEXT: [[TMP46:%.*]] = shl i128 [[TMP45]], 64
; CHECK-NEXT: [[TMP47:%.*]] = and i128 [[TMP39]], 5192296858534827628530496329220095
; CHECK-NEXT: [[TMP48:%.*]] = or i128 [[TMP46]], [[TMP47]]
; CHECK-NEXT: [[TMP49:%.*]] = bitcast i128 [[TMP48]] to fp128
; CHECK-NEXT: [[TMP50:%.*]] = fptrunc fp128 [[TMP49]] to x86_fp80
; CHECK-NEXT: br label [[ITOFP_RETURN]]
; CHECK: itofp-return:
; CHECK-NEXT: [[TMP51:%.*]] = phi x86_fp80 [ [[TMP50]], [[ITOFP_IF_END26]] ], [ 0xK00000000000000000000, [[ITOFP_ENTRY:%.*]] ]
; CHECK-NEXT: ret x86_fp80 [[TMP51]]
;
%conv = sitofp i129 %a to x86_fp80
ret x86_fp80 %conv
}
define fp128 @si129tofp128(i129 %a) {
; CHECK-LABEL: @si129tofp128(
; CHECK-NEXT: itofp-entry:
; CHECK-NEXT: [[TMP0:%.*]] = icmp eq i129 [[A:%.*]], 0
; CHECK-NEXT: br i1 [[TMP0]], label [[ITOFP_RETURN:%.*]], label [[ITOFP_IF_END:%.*]]
; CHECK: itofp-if-end:
; CHECK-NEXT: [[TMP1:%.*]] = ashr i129 [[A]], 128
; CHECK-NEXT: [[TMP2:%.*]] = xor i129 [[TMP1]], [[A]]
; CHECK-NEXT: [[TMP3:%.*]] = sub i129 [[TMP2]], [[TMP1]]
; CHECK-NEXT: [[TMP4:%.*]] = call i129 @llvm.ctlz.i129(i129 [[TMP3]], i1 true)
; CHECK-NEXT: [[TMP5:%.*]] = trunc i129 [[TMP4]] to i32
; CHECK-NEXT: [[TMP6:%.*]] = sub i129 129, [[TMP4]]
; CHECK-NEXT: [[TMP7:%.*]] = sub i129 128, [[TMP4]]
; CHECK-NEXT: [[TMP8:%.*]] = icmp sgt i129 [[TMP7]], 113
; CHECK-NEXT: br i1 [[TMP8]], label [[ITOFP_IF_THEN4:%.*]], label [[ITOFP_IF_ELSE:%.*]]
; CHECK: itofp-if-then4:
; CHECK-NEXT: switch i129 [[TMP6]], label [[ITOFP_SW_DEFAULT:%.*]] [
; CHECK-NEXT: i129 114, label [[ITOFP_SW_BB:%.*]]
; CHECK-NEXT: i129 115, label [[ITOFP_SW_EPILOG:%.*]]
; CHECK-NEXT: ]
; CHECK: itofp-sw-bb:
; CHECK-NEXT: [[TMP9:%.*]] = shl i129 [[TMP3]], 1
; CHECK-NEXT: br label [[ITOFP_SW_EPILOG]]
; CHECK: itofp-sw-default:
; CHECK-NEXT: [[TMP10:%.*]] = sub i129 14, [[TMP4]]
; CHECK-NEXT: [[TMP11:%.*]] = lshr i129 [[TMP3]], [[TMP10]]
; CHECK-NEXT: [[TMP12:%.*]] = add i129 [[TMP4]], 115
; CHECK-NEXT: [[TMP13:%.*]] = lshr i129 -1, [[TMP12]]
; CHECK-NEXT: [[TMP14:%.*]] = and i129 [[TMP13]], [[TMP3]]
; CHECK-NEXT: [[TMP15:%.*]] = icmp ne i129 [[TMP14]], 0
; CHECK-NEXT: [[TMP16:%.*]] = zext i1 [[TMP15]] to i129
; CHECK-NEXT: [[TMP17:%.*]] = or i129 [[TMP11]], [[TMP16]]
; CHECK-NEXT: br label [[ITOFP_SW_EPILOG]]
; CHECK: itofp-sw-epilog:
; CHECK-NEXT: [[TMP18:%.*]] = phi i129 [ [[TMP17]], [[ITOFP_SW_DEFAULT]] ], [ [[TMP3]], [[ITOFP_IF_THEN4]] ], [ [[TMP9]], [[ITOFP_SW_BB]] ]
; CHECK-NEXT: [[TMP19:%.*]] = trunc i129 [[TMP18]] to i32
; CHECK-NEXT: [[TMP20:%.*]] = lshr i32 [[TMP19]], 2
; CHECK-NEXT: [[TMP21:%.*]] = and i32 [[TMP20]], 1
; CHECK-NEXT: [[TMP22:%.*]] = zext i32 [[TMP21]] to i129
; CHECK-NEXT: [[TMP23:%.*]] = or i129 [[TMP18]], [[TMP22]]
; CHECK-NEXT: [[TMP24:%.*]] = add i129 [[TMP23]], 1
; CHECK-NEXT: [[TMP25:%.*]] = ashr i129 [[TMP24]], 2
; CHECK-NEXT: [[A3:%.*]] = and i129 [[TMP24]], 41538374868278621028243970633760768
; CHECK-NEXT: [[TMP26:%.*]] = icmp eq i129 [[A3]], 0
; CHECK-NEXT: [[TMP27:%.*]] = trunc i129 [[TMP25]] to i128
; CHECK-NEXT: [[TMP28:%.*]] = lshr i129 [[TMP25]], 32
; CHECK-NEXT: [[TMP29:%.*]] = trunc i129 [[TMP7]] to i64
; CHECK-NEXT: br i1 [[TMP26]], label [[ITOFP_IF_END26:%.*]], label [[ITOFP_IF_THEN20:%.*]]
; CHECK: itofp-if-then20:
; CHECK-NEXT: [[TMP30:%.*]] = ashr i129 [[TMP24]], 3
; CHECK-NEXT: [[TMP31:%.*]] = trunc i129 [[TMP30]] to i128
; CHECK-NEXT: [[TMP32:%.*]] = lshr i129 [[TMP30]], 32
; CHECK-NEXT: [[TMP33:%.*]] = trunc i129 [[TMP6]] to i64
; CHECK-NEXT: br label [[ITOFP_IF_END26]]
; CHECK: itofp-if-else:
; CHECK-NEXT: [[TMP34:%.*]] = add i129 [[TMP4]], 4294967280
; CHECK-NEXT: [[TMP35:%.*]] = shl i129 [[TMP3]], [[TMP34]]
; CHECK-NEXT: [[TMP36:%.*]] = trunc i129 [[TMP35]] to i128
; CHECK-NEXT: [[TMP37:%.*]] = lshr i129 [[TMP35]], 32
; CHECK-NEXT: [[TMP38:%.*]] = trunc i129 [[TMP7]] to i64
; CHECK-NEXT: br label [[ITOFP_IF_END26]]
; CHECK: itofp-if-end26:
; CHECK-NEXT: [[TMP39:%.*]] = phi i128 [ [[TMP31]], [[ITOFP_IF_THEN20]] ], [ [[TMP27]], [[ITOFP_SW_EPILOG]] ], [ [[TMP36]], [[ITOFP_IF_ELSE]] ]
; CHECK-NEXT: [[TMP40:%.*]] = phi i64 [ [[TMP33]], [[ITOFP_IF_THEN20]] ], [ [[TMP29]], [[ITOFP_SW_EPILOG]] ], [ [[TMP38]], [[ITOFP_IF_ELSE]] ]
; CHECK-NEXT: [[AND29:%.*]] = and i129 [[TMP1]], 9223372036854775808
; CHECK-NEXT: [[TMP41:%.*]] = shl i64 [[TMP40]], 48
; CHECK-NEXT: [[TMP42:%.*]] = add i64 [[TMP41]], 4611404543450677248
; CHECK-NEXT: [[TMP43:%.*]] = zext i64 [[TMP42]] to i128
; CHECK-NEXT: [[TMP44:%.*]] = trunc i129 [[AND29]] to i128
; CHECK-NEXT: [[TMP45:%.*]] = or i128 [[TMP44]], [[TMP43]]
; CHECK-NEXT: [[TMP46:%.*]] = shl i128 [[TMP45]], 64
; CHECK-NEXT: [[TMP47:%.*]] = and i128 [[TMP39]], 5192296858534827628530496329220095
; CHECK-NEXT: [[TMP48:%.*]] = or i128 [[TMP46]], [[TMP47]]
; CHECK-NEXT: [[TMP49:%.*]] = bitcast i128 [[TMP48]] to fp128
; CHECK-NEXT: br label [[ITOFP_RETURN]]
; CHECK: itofp-return:
; CHECK-NEXT: [[TMP50:%.*]] = phi fp128 [ [[TMP49]], [[ITOFP_IF_END26]] ], [ 0xL00000000000000000000000000000000, [[ITOFP_ENTRY:%.*]] ]
; CHECK-NEXT: ret fp128 [[TMP50]]
;
%conv = sitofp i129 %a to fp128
ret fp128 %conv
}

427
llvm/test/CodeGen/X86/expand-large-fp-convert-ui129tofp.ll Normal file
View File

@ -0,0 +1,427 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -S -mtriple=x86_64-- -expand-large-fp-convert < %s | FileCheck %s
define half @ui129tohalf(i129 %a) {
; CHECK-LABEL: @ui129tohalf(
; CHECK-NEXT: itofp-entry:
; CHECK-NEXT: [[TMP0:%.*]] = icmp eq i129 [[A:%.*]], 0
; CHECK-NEXT: br i1 [[TMP0]], label [[ITOFP_RETURN:%.*]], label [[ITOFP_IF_END:%.*]]
; CHECK: itofp-if-end:
; CHECK-NEXT: [[TMP1:%.*]] = ashr i129 [[A]], 128
; CHECK-NEXT: [[TMP2:%.*]] = xor i129 [[TMP1]], [[A]]
; CHECK-NEXT: [[TMP3:%.*]] = sub i129 [[TMP2]], [[TMP1]]
; CHECK-NEXT: [[TMP4:%.*]] = call i129 @llvm.ctlz.i129(i129 [[A]], i1 true)
; CHECK-NEXT: [[TMP5:%.*]] = trunc i129 [[TMP4]] to i32
; CHECK-NEXT: [[TMP6:%.*]] = sub i32 129, [[TMP5]]
; CHECK-NEXT: [[TMP7:%.*]] = sub i32 128, [[TMP5]]
; CHECK-NEXT: [[TMP8:%.*]] = icmp sgt i32 [[TMP7]], 24
; CHECK-NEXT: br i1 [[TMP8]], label [[ITOFP_IF_THEN4:%.*]], label [[ITOFP_IF_ELSE:%.*]]
; CHECK: itofp-if-then4:
; CHECK-NEXT: switch i32 [[TMP6]], label [[ITOFP_SW_DEFAULT:%.*]] [
; CHECK-NEXT: i32 25, label [[ITOFP_SW_BB:%.*]]
; CHECK-NEXT: i32 26, label [[ITOFP_SW_EPILOG:%.*]]
; CHECK-NEXT: ]
; CHECK: itofp-sw-bb:
; CHECK-NEXT: [[TMP9:%.*]] = shl i129 [[A]], 1
; CHECK-NEXT: br label [[ITOFP_SW_EPILOG]]
; CHECK: itofp-sw-default:
; CHECK-NEXT: [[TMP10:%.*]] = sub i32 103, [[TMP5]]
; CHECK-NEXT: [[TMP11:%.*]] = zext i32 [[TMP10]] to i129
; CHECK-NEXT: [[TMP12:%.*]] = lshr i129 [[A]], [[TMP11]]
; CHECK-NEXT: [[TMP13:%.*]] = add i32 [[TMP5]], 26
; CHECK-NEXT: [[TMP14:%.*]] = zext i32 [[TMP13]] to i129
; CHECK-NEXT: [[TMP15:%.*]] = lshr i129 -1, [[TMP14]]
; CHECK-NEXT: [[TMP16:%.*]] = and i129 [[TMP15]], [[A]]
; CHECK-NEXT: [[TMP17:%.*]] = icmp ne i129 [[TMP16]], 0
; CHECK-NEXT: [[TMP18:%.*]] = zext i1 [[TMP17]] to i129
; CHECK-NEXT: [[TMP19:%.*]] = or i129 [[TMP12]], [[TMP18]]
; CHECK-NEXT: br label [[ITOFP_SW_EPILOG]]
; CHECK: itofp-sw-epilog:
; CHECK-NEXT: [[TMP20:%.*]] = phi i129 [ [[TMP19]], [[ITOFP_SW_DEFAULT]] ], [ [[A]], [[ITOFP_IF_THEN4]] ], [ [[TMP9]], [[ITOFP_SW_BB]] ]
; CHECK-NEXT: [[TMP21:%.*]] = trunc i129 [[TMP20]] to i32
; CHECK-NEXT: [[TMP22:%.*]] = lshr i32 [[TMP21]], 2
; CHECK-NEXT: [[TMP23:%.*]] = and i32 [[TMP22]], 1
; CHECK-NEXT: [[TMP24:%.*]] = zext i32 [[TMP23]] to i129
; CHECK-NEXT: [[TMP25:%.*]] = or i129 [[TMP20]], [[TMP24]]
; CHECK-NEXT: [[TMP26:%.*]] = add i129 [[TMP25]], 1
; CHECK-NEXT: [[TMP27:%.*]] = lshr i129 [[TMP26]], 2
; CHECK-NEXT: [[A3:%.*]] = and i129 [[TMP26]], 67108864
; CHECK-NEXT: [[TMP28:%.*]] = icmp eq i129 [[A3]], 0
; CHECK-NEXT: [[TMP29:%.*]] = trunc i129 [[TMP27]] to i32
; CHECK-NEXT: [[TMP30:%.*]] = lshr i129 [[TMP27]], 32
; CHECK-NEXT: [[TMP31:%.*]] = trunc i129 [[TMP30]] to i32
; CHECK-NEXT: br i1 [[TMP28]], label [[ITOFP_IF_END26:%.*]], label [[ITOFP_IF_THEN20:%.*]]
; CHECK: itofp-if-then20:
; CHECK-NEXT: [[TMP32:%.*]] = lshr i129 [[TMP26]], 3
; CHECK-NEXT: [[TMP33:%.*]] = trunc i129 [[TMP32]] to i32
; CHECK-NEXT: [[TMP34:%.*]] = lshr i129 [[TMP32]], 32
; CHECK-NEXT: [[TMP35:%.*]] = trunc i129 [[TMP34]] to i32
; CHECK-NEXT: br label [[ITOFP_IF_END26]]
; CHECK: itofp-if-else:
; CHECK-NEXT: [[TMP36:%.*]] = add i32 [[TMP5]], -105
; CHECK-NEXT: [[TMP37:%.*]] = zext i32 [[TMP36]] to i129
; CHECK-NEXT: [[TMP38:%.*]] = shl i129 [[A]], [[TMP37]]
; CHECK-NEXT: [[TMP39:%.*]] = trunc i129 [[TMP38]] to i32
; CHECK-NEXT: [[TMP40:%.*]] = lshr i129 [[TMP38]], 32
; CHECK-NEXT: [[TMP41:%.*]] = trunc i129 [[TMP40]] to i32
; CHECK-NEXT: br label [[ITOFP_IF_END26]]
; CHECK: itofp-if-end26:
; CHECK-NEXT: [[TMP42:%.*]] = phi i32 [ [[TMP33]], [[ITOFP_IF_THEN20]] ], [ [[TMP29]], [[ITOFP_SW_EPILOG]] ], [ [[TMP39]], [[ITOFP_IF_ELSE]] ]
; CHECK-NEXT: [[TMP43:%.*]] = phi i32 [ [[TMP6]], [[ITOFP_IF_THEN20]] ], [ [[TMP7]], [[ITOFP_SW_EPILOG]] ], [ [[TMP7]], [[ITOFP_IF_ELSE]] ]
; CHECK-NEXT: [[TMP44:%.*]] = trunc i129 [[TMP1]] to i32
; CHECK-NEXT: [[TMP45:%.*]] = and i32 [[TMP44]], -2147483648
; CHECK-NEXT: [[TMP46:%.*]] = shl i32 [[TMP43]], 23
; CHECK-NEXT: [[TMP47:%.*]] = add i32 [[TMP46]], 1065353216
; CHECK-NEXT: [[TMP48:%.*]] = and i32 [[TMP42]], 8388607
; CHECK-NEXT: [[TMP49:%.*]] = or i32 [[TMP48]], [[TMP45]]
; CHECK-NEXT: [[TMP50:%.*]] = or i32 [[TMP48]], [[TMP47]]
; CHECK-NEXT: [[TMP51:%.*]] = bitcast i32 [[TMP50]] to float
; CHECK-NEXT: [[TMP52:%.*]] = fptrunc float [[TMP51]] to half
; CHECK-NEXT: br label [[ITOFP_RETURN]]
; CHECK: itofp-return:
; CHECK-NEXT: [[TMP53:%.*]] = phi half [ [[TMP52]], [[ITOFP_IF_END26]] ], [ 0xH0000, [[ITOFP_ENTRY:%.*]] ]
; CHECK-NEXT: ret half [[TMP53]]
;
%conv = uitofp i129 %a to half
ret half %conv
}
define float @ui129tofloat(i129 %a) {
; CHECK-LABEL: @ui129tofloat(
; CHECK-NEXT: itofp-entry:
; CHECK-NEXT: [[TMP0:%.*]] = icmp eq i129 [[A:%.*]], 0
; CHECK-NEXT: br i1 [[TMP0]], label [[ITOFP_RETURN:%.*]], label [[ITOFP_IF_END:%.*]]
; CHECK: itofp-if-end:
; CHECK-NEXT: [[TMP1:%.*]] = ashr i129 [[A]], 128
; CHECK-NEXT: [[TMP2:%.*]] = xor i129 [[TMP1]], [[A]]
; CHECK-NEXT: [[TMP3:%.*]] = sub i129 [[TMP2]], [[TMP1]]
; CHECK-NEXT: [[TMP4:%.*]] = call i129 @llvm.ctlz.i129(i129 [[A]], i1 true)
; CHECK-NEXT: [[TMP5:%.*]] = trunc i129 [[TMP4]] to i32
; CHECK-NEXT: [[TMP6:%.*]] = sub i32 129, [[TMP5]]
; CHECK-NEXT: [[TMP7:%.*]] = sub i32 128, [[TMP5]]
; CHECK-NEXT: [[TMP8:%.*]] = icmp sgt i32 [[TMP7]], 24
; CHECK-NEXT: br i1 [[TMP8]], label [[ITOFP_IF_THEN4:%.*]], label [[ITOFP_IF_ELSE:%.*]]
; CHECK: itofp-if-then4:
; CHECK-NEXT: switch i32 [[TMP6]], label [[ITOFP_SW_DEFAULT:%.*]] [
; CHECK-NEXT: i32 25, label [[ITOFP_SW_BB:%.*]]
; CHECK-NEXT: i32 26, label [[ITOFP_SW_EPILOG:%.*]]
; CHECK-NEXT: ]
; CHECK: itofp-sw-bb:
; CHECK-NEXT: [[TMP9:%.*]] = shl i129 [[A]], 1
; CHECK-NEXT: br label [[ITOFP_SW_EPILOG]]
; CHECK: itofp-sw-default:
; CHECK-NEXT: [[TMP10:%.*]] = sub i32 103, [[TMP5]]
; CHECK-NEXT: [[TMP11:%.*]] = zext i32 [[TMP10]] to i129
; CHECK-NEXT: [[TMP12:%.*]] = lshr i129 [[A]], [[TMP11]]
; CHECK-NEXT: [[TMP13:%.*]] = add i32 [[TMP5]], 26
; CHECK-NEXT: [[TMP14:%.*]] = zext i32 [[TMP13]] to i129
; CHECK-NEXT: [[TMP15:%.*]] = lshr i129 -1, [[TMP14]]
; CHECK-NEXT: [[TMP16:%.*]] = and i129 [[TMP15]], [[A]]
; CHECK-NEXT: [[TMP17:%.*]] = icmp ne i129 [[TMP16]], 0
; CHECK-NEXT: [[TMP18:%.*]] = zext i1 [[TMP17]] to i129
; CHECK-NEXT: [[TMP19:%.*]] = or i129 [[TMP12]], [[TMP18]]
; CHECK-NEXT: br label [[ITOFP_SW_EPILOG]]
; CHECK: itofp-sw-epilog:
; CHECK-NEXT: [[TMP20:%.*]] = phi i129 [ [[TMP19]], [[ITOFP_SW_DEFAULT]] ], [ [[A]], [[ITOFP_IF_THEN4]] ], [ [[TMP9]], [[ITOFP_SW_BB]] ]
; CHECK-NEXT: [[TMP21:%.*]] = trunc i129 [[TMP20]] to i32
; CHECK-NEXT: [[TMP22:%.*]] = lshr i32 [[TMP21]], 2
; CHECK-NEXT: [[TMP23:%.*]] = and i32 [[TMP22]], 1
; CHECK-NEXT: [[TMP24:%.*]] = zext i32 [[TMP23]] to i129
; CHECK-NEXT: [[TMP25:%.*]] = or i129 [[TMP20]], [[TMP24]]
; CHECK-NEXT: [[TMP26:%.*]] = add i129 [[TMP25]], 1
; CHECK-NEXT: [[TMP27:%.*]] = lshr i129 [[TMP26]], 2
; CHECK-NEXT: [[A3:%.*]] = and i129 [[TMP26]], 67108864
; CHECK-NEXT: [[TMP28:%.*]] = icmp eq i129 [[A3]], 0
; CHECK-NEXT: [[TMP29:%.*]] = trunc i129 [[TMP27]] to i32
; CHECK-NEXT: [[TMP30:%.*]] = lshr i129 [[TMP27]], 32
; CHECK-NEXT: [[TMP31:%.*]] = trunc i129 [[TMP30]] to i32
; CHECK-NEXT: br i1 [[TMP28]], label [[ITOFP_IF_END26:%.*]], label [[ITOFP_IF_THEN20:%.*]]
; CHECK: itofp-if-then20:
; CHECK-NEXT: [[TMP32:%.*]] = lshr i129 [[TMP26]], 3
; CHECK-NEXT: [[TMP33:%.*]] = trunc i129 [[TMP32]] to i32
; CHECK-NEXT: [[TMP34:%.*]] = lshr i129 [[TMP32]], 32
; CHECK-NEXT: [[TMP35:%.*]] = trunc i129 [[TMP34]] to i32
; CHECK-NEXT: br label [[ITOFP_IF_END26]]
; CHECK: itofp-if-else:
; CHECK-NEXT: [[TMP36:%.*]] = add i32 [[TMP5]], -105
; CHECK-NEXT: [[TMP37:%.*]] = zext i32 [[TMP36]] to i129
; CHECK-NEXT: [[TMP38:%.*]] = shl i129 [[A]], [[TMP37]]
; CHECK-NEXT: [[TMP39:%.*]] = trunc i129 [[TMP38]] to i32
; CHECK-NEXT: [[TMP40:%.*]] = lshr i129 [[TMP38]], 32
; CHECK-NEXT: [[TMP41:%.*]] = trunc i129 [[TMP40]] to i32
; CHECK-NEXT: br label [[ITOFP_IF_END26]]
; CHECK: itofp-if-end26:
; CHECK-NEXT: [[TMP42:%.*]] = phi i32 [ [[TMP33]], [[ITOFP_IF_THEN20]] ], [ [[TMP29]], [[ITOFP_SW_EPILOG]] ], [ [[TMP39]], [[ITOFP_IF_ELSE]] ]
; CHECK-NEXT: [[TMP43:%.*]] = phi i32 [ [[TMP6]], [[ITOFP_IF_THEN20]] ], [ [[TMP7]], [[ITOFP_SW_EPILOG]] ], [ [[TMP7]], [[ITOFP_IF_ELSE]] ]
; CHECK-NEXT: [[TMP44:%.*]] = trunc i129 [[TMP1]] to i32
; CHECK-NEXT: [[TMP45:%.*]] = and i32 [[TMP44]], -2147483648
; CHECK-NEXT: [[TMP46:%.*]] = shl i32 [[TMP43]], 23
; CHECK-NEXT: [[TMP47:%.*]] = add i32 [[TMP46]], 1065353216
; CHECK-NEXT: [[TMP48:%.*]] = and i32 [[TMP42]], 8388607
; CHECK-NEXT: [[TMP49:%.*]] = or i32 [[TMP48]], [[TMP45]]
; CHECK-NEXT: [[TMP50:%.*]] = or i32 [[TMP48]], [[TMP47]]
; CHECK-NEXT: [[TMP51:%.*]] = bitcast i32 [[TMP50]] to float
; CHECK-NEXT: br label [[ITOFP_RETURN]]
; CHECK: itofp-return:
; CHECK-NEXT: [[TMP52:%.*]] = phi float [ [[TMP51]], [[ITOFP_IF_END26]] ], [ 0.000000e+00, [[ITOFP_ENTRY:%.*]] ]
; CHECK-NEXT: ret float [[TMP52]]
;
%conv = uitofp i129 %a to float
ret float %conv
}
define double @ui129todouble(i129 %a) {
; CHECK-LABEL: @ui129todouble(
; CHECK-NEXT: itofp-entry:
; CHECK-NEXT: [[TMP0:%.*]] = icmp eq i129 [[A:%.*]], 0
; CHECK-NEXT: br i1 [[TMP0]], label [[ITOFP_RETURN:%.*]], label [[ITOFP_IF_END:%.*]]
; CHECK: itofp-if-end:
; CHECK-NEXT: [[TMP1:%.*]] = ashr i129 [[A]], 128
; CHECK-NEXT: [[TMP2:%.*]] = xor i129 [[TMP1]], [[A]]
; CHECK-NEXT: [[TMP3:%.*]] = sub i129 [[TMP2]], [[TMP1]]
; CHECK-NEXT: [[TMP4:%.*]] = call i129 @llvm.ctlz.i129(i129 [[A]], i1 true)
; CHECK-NEXT: [[TMP5:%.*]] = trunc i129 [[TMP4]] to i32
; CHECK-NEXT: [[TMP6:%.*]] = sub i32 129, [[TMP5]]
; CHECK-NEXT: [[TMP7:%.*]] = sub i32 128, [[TMP5]]
; CHECK-NEXT: [[TMP8:%.*]] = icmp sgt i32 [[TMP7]], 53
; CHECK-NEXT: br i1 [[TMP8]], label [[ITOFP_IF_THEN4:%.*]], label [[ITOFP_IF_ELSE:%.*]]
; CHECK: itofp-if-then4:
; CHECK-NEXT: switch i32 [[TMP6]], label [[ITOFP_SW_DEFAULT:%.*]] [
; CHECK-NEXT: i32 54, label [[ITOFP_SW_BB:%.*]]
; CHECK-NEXT: i32 55, label [[ITOFP_SW_EPILOG:%.*]]
; CHECK-NEXT: ]
; CHECK: itofp-sw-bb:
; CHECK-NEXT: [[TMP9:%.*]] = shl i129 [[A]], 1
; CHECK-NEXT: br label [[ITOFP_SW_EPILOG]]
; CHECK: itofp-sw-default:
; CHECK-NEXT: [[TMP10:%.*]] = sub i32 74, [[TMP5]]
; CHECK-NEXT: [[TMP11:%.*]] = zext i32 [[TMP10]] to i129
; CHECK-NEXT: [[TMP12:%.*]] = lshr i129 [[A]], [[TMP11]]
; CHECK-NEXT: [[TMP13:%.*]] = add i32 [[TMP5]], 55
; CHECK-NEXT: [[TMP14:%.*]] = zext i32 [[TMP13]] to i129
; CHECK-NEXT: [[TMP15:%.*]] = lshr i129 -1, [[TMP14]]
; CHECK-NEXT: [[TMP16:%.*]] = and i129 [[TMP15]], [[A]]
; CHECK-NEXT: [[TMP17:%.*]] = icmp ne i129 [[TMP16]], 0
; CHECK-NEXT: [[TMP18:%.*]] = zext i1 [[TMP17]] to i129
; CHECK-NEXT: [[TMP19:%.*]] = or i129 [[TMP12]], [[TMP18]]
; CHECK-NEXT: br label [[ITOFP_SW_EPILOG]]
; CHECK: itofp-sw-epilog:
; CHECK-NEXT: [[TMP20:%.*]] = phi i129 [ [[TMP19]], [[ITOFP_SW_DEFAULT]] ], [ [[A]], [[ITOFP_IF_THEN4]] ], [ [[TMP9]], [[ITOFP_SW_BB]] ]
; CHECK-NEXT: [[TMP21:%.*]] = trunc i129 [[TMP20]] to i32
; CHECK-NEXT: [[TMP22:%.*]] = lshr i32 [[TMP21]], 2
; CHECK-NEXT: [[TMP23:%.*]] = and i32 [[TMP22]], 1
; CHECK-NEXT: [[TMP24:%.*]] = zext i32 [[TMP23]] to i129
; CHECK-NEXT: [[TMP25:%.*]] = or i129 [[TMP20]], [[TMP24]]
; CHECK-NEXT: [[TMP26:%.*]] = add i129 [[TMP25]], 1
; CHECK-NEXT: [[TMP27:%.*]] = lshr i129 [[TMP26]], 2
; CHECK-NEXT: [[A3:%.*]] = and i129 [[TMP26]], 36028797018963968
; CHECK-NEXT: [[TMP28:%.*]] = icmp eq i129 [[A3]], 0
; CHECK-NEXT: [[TMP29:%.*]] = trunc i129 [[TMP27]] to i64
; CHECK-NEXT: [[TMP30:%.*]] = lshr i129 [[TMP27]], 32
; CHECK-NEXT: [[TMP31:%.*]] = trunc i129 [[TMP30]] to i32
; CHECK-NEXT: br i1 [[TMP28]], label [[ITOFP_IF_END26:%.*]], label [[ITOFP_IF_THEN20:%.*]]
; CHECK: itofp-if-then20:
; CHECK-NEXT: [[TMP32:%.*]] = lshr i129 [[TMP26]], 3
; CHECK-NEXT: [[TMP33:%.*]] = trunc i129 [[TMP32]] to i64
; CHECK-NEXT: [[TMP34:%.*]] = lshr i129 [[TMP32]], 32
; CHECK-NEXT: [[TMP35:%.*]] = trunc i129 [[TMP34]] to i32
; CHECK-NEXT: br label [[ITOFP_IF_END26]]
; CHECK: itofp-if-else:
; CHECK-NEXT: [[TMP36:%.*]] = add i32 [[TMP5]], -76
; CHECK-NEXT: [[TMP37:%.*]] = zext i32 [[TMP36]] to i129
; CHECK-NEXT: [[TMP38:%.*]] = shl i129 [[A]], [[TMP37]]
; CHECK-NEXT: [[TMP39:%.*]] = trunc i129 [[TMP38]] to i64
; CHECK-NEXT: [[TMP40:%.*]] = lshr i129 [[TMP38]], 32
; CHECK-NEXT: [[TMP41:%.*]] = trunc i129 [[TMP40]] to i32
; CHECK-NEXT: br label [[ITOFP_IF_END26]]
; CHECK: itofp-if-end26:
; CHECK-NEXT: [[TMP42:%.*]] = phi i64 [ [[TMP33]], [[ITOFP_IF_THEN20]] ], [ [[TMP29]], [[ITOFP_SW_EPILOG]] ], [ [[TMP39]], [[ITOFP_IF_ELSE]] ]
; CHECK-NEXT: [[TMP43:%.*]] = phi i32 [ [[TMP35]], [[ITOFP_IF_THEN20]] ], [ [[TMP31]], [[ITOFP_SW_EPILOG]] ], [ [[TMP41]], [[ITOFP_IF_ELSE]] ]
; CHECK-NEXT: [[TMP44:%.*]] = phi i32 [ [[TMP6]], [[ITOFP_IF_THEN20]] ], [ [[TMP7]], [[ITOFP_SW_EPILOG]] ], [ [[TMP7]], [[ITOFP_IF_ELSE]] ]
; CHECK-NEXT: [[TMP45:%.*]] = trunc i129 [[TMP1]] to i32
; CHECK-NEXT: [[TMP46:%.*]] = and i32 [[TMP45]], -2147483648
; CHECK-NEXT: [[TMP47:%.*]] = shl i32 [[TMP44]], 20
; CHECK-NEXT: [[TMP48:%.*]] = add i32 [[TMP47]], 1072693248
; CHECK-NEXT: [[TMP49:%.*]] = and i32 [[TMP43]], 1048575
; CHECK-NEXT: [[TMP50:%.*]] = or i32 [[TMP49]], [[TMP46]]
; CHECK-NEXT: [[TMP51:%.*]] = or i32 [[TMP49]], [[TMP48]]
; CHECK-NEXT: [[TMP52:%.*]] = zext i32 [[TMP51]] to i64
; CHECK-NEXT: [[TMP53:%.*]] = shl i64 [[TMP52]], 32
; CHECK-NEXT: [[TMP54:%.*]] = and i64 [[TMP42]], 4294967295
; CHECK-NEXT: [[TMP55:%.*]] = or i64 [[TMP53]], [[TMP54]]
; CHECK-NEXT: [[TMP56:%.*]] = bitcast i64 [[TMP55]] to double
; CHECK-NEXT: br label [[ITOFP_RETURN]]
; CHECK: itofp-return:
; CHECK-NEXT: [[TMP57:%.*]] = phi double [ [[TMP56]], [[ITOFP_IF_END26]] ], [ 0.000000e+00, [[ITOFP_ENTRY:%.*]] ]
; CHECK-NEXT: ret double [[TMP57]]
;
%conv = uitofp i129 %a to double
ret double %conv
}
define x86_fp80 @ui129tox86_fp80(i129 %a) {
; CHECK-LABEL: @ui129tox86_fp80(
; CHECK-NEXT: itofp-entry:
; CHECK-NEXT: [[TMP0:%.*]] = icmp eq i129 [[A:%.*]], 0
; CHECK-NEXT: br i1 [[TMP0]], label [[ITOFP_RETURN:%.*]], label [[ITOFP_IF_END:%.*]]
; CHECK: itofp-if-end:
; CHECK-NEXT: [[TMP1:%.*]] = ashr i129 [[A]], 128
; CHECK-NEXT: [[TMP2:%.*]] = xor i129 [[TMP1]], [[A]]
; CHECK-NEXT: [[TMP3:%.*]] = sub i129 [[TMP2]], [[TMP1]]
; CHECK-NEXT: [[TMP4:%.*]] = call i129 @llvm.ctlz.i129(i129 [[A]], i1 true)
; CHECK-NEXT: [[TMP5:%.*]] = trunc i129 [[TMP4]] to i32
; CHECK-NEXT: [[TMP6:%.*]] = sub i129 129, [[TMP4]]
; CHECK-NEXT: [[TMP7:%.*]] = sub i129 128, [[TMP4]]
; CHECK-NEXT: [[TMP8:%.*]] = icmp sgt i129 [[TMP7]], 113
; CHECK-NEXT: br i1 [[TMP8]], label [[ITOFP_IF_THEN4:%.*]], label [[ITOFP_IF_ELSE:%.*]]
; CHECK: itofp-if-then4:
; CHECK-NEXT: switch i129 [[TMP6]], label [[ITOFP_SW_DEFAULT:%.*]] [
; CHECK-NEXT: i129 114, label [[ITOFP_SW_BB:%.*]]
; CHECK-NEXT: i129 115, label [[ITOFP_SW_EPILOG:%.*]]
; CHECK-NEXT: ]
; CHECK: itofp-sw-bb:
; CHECK-NEXT: [[TMP9:%.*]] = shl i129 [[A]], 1
; CHECK-NEXT: br label [[ITOFP_SW_EPILOG]]
; CHECK: itofp-sw-default:
; CHECK-NEXT: [[TMP10:%.*]] = sub i129 14, [[TMP4]]
; CHECK-NEXT: [[TMP11:%.*]] = lshr i129 [[A]], [[TMP10]]
; CHECK-NEXT: [[TMP12:%.*]] = add i129 [[TMP4]], 115
; CHECK-NEXT: [[TMP13:%.*]] = lshr i129 -1, [[TMP12]]
; CHECK-NEXT: [[TMP14:%.*]] = and i129 [[TMP13]], [[A]]
; CHECK-NEXT: [[TMP15:%.*]] = icmp ne i129 [[TMP14]], 0
; CHECK-NEXT: [[TMP16:%.*]] = zext i1 [[TMP15]] to i129
; CHECK-NEXT: [[TMP17:%.*]] = or i129 [[TMP11]], [[TMP16]]
; CHECK-NEXT: br label [[ITOFP_SW_EPILOG]]
; CHECK: itofp-sw-epilog:
; CHECK-NEXT: [[TMP18:%.*]] = phi i129 [ [[TMP17]], [[ITOFP_SW_DEFAULT]] ], [ [[A]], [[ITOFP_IF_THEN4]] ], [ [[TMP9]], [[ITOFP_SW_BB]] ]
; CHECK-NEXT: [[TMP19:%.*]] = trunc i129 [[TMP18]] to i32
; CHECK-NEXT: [[TMP20:%.*]] = lshr i32 [[TMP19]], 2
; CHECK-NEXT: [[TMP21:%.*]] = and i32 [[TMP20]], 1
; CHECK-NEXT: [[TMP22:%.*]] = zext i32 [[TMP21]] to i129
; CHECK-NEXT: [[TMP23:%.*]] = or i129 [[TMP18]], [[TMP22]]
; CHECK-NEXT: [[TMP24:%.*]] = add i129 [[TMP23]], 1
; CHECK-NEXT: [[TMP25:%.*]] = lshr i129 [[TMP24]], 2
; CHECK-NEXT: [[A3:%.*]] = and i129 [[TMP24]], 41538374868278621028243970633760768
; CHECK-NEXT: [[TMP26:%.*]] = icmp eq i129 [[A3]], 0
; CHECK-NEXT: [[TMP27:%.*]] = trunc i129 [[TMP25]] to i128
; CHECK-NEXT: [[TMP28:%.*]] = lshr i129 [[TMP25]], 32
; CHECK-NEXT: [[TMP29:%.*]] = trunc i129 [[TMP7]] to i64
; CHECK-NEXT: br i1 [[TMP26]], label [[ITOFP_IF_END26:%.*]], label [[ITOFP_IF_THEN20:%.*]]
; CHECK: itofp-if-then20:
; CHECK-NEXT: [[TMP30:%.*]] = lshr i129 [[TMP24]], 3
; CHECK-NEXT: [[TMP31:%.*]] = trunc i129 [[TMP30]] to i128
; CHECK-NEXT: [[TMP32:%.*]] = lshr i129 [[TMP30]], 32
; CHECK-NEXT: [[TMP33:%.*]] = trunc i129 [[TMP6]] to i64
; CHECK-NEXT: br label [[ITOFP_IF_END26]]
; CHECK: itofp-if-else:
; CHECK-NEXT: [[TMP34:%.*]] = add i129 [[TMP4]], 4294967280
; CHECK-NEXT: [[TMP35:%.*]] = shl i129 [[A]], [[TMP34]]
; CHECK-NEXT: [[TMP36:%.*]] = trunc i129 [[TMP35]] to i128
; CHECK-NEXT: [[TMP37:%.*]] = lshr i129 [[TMP35]], 32
; CHECK-NEXT: [[TMP38:%.*]] = trunc i129 [[TMP7]] to i64
; CHECK-NEXT: br label [[ITOFP_IF_END26]]
; CHECK: itofp-if-end26:
; CHECK-NEXT: [[TMP39:%.*]] = phi i128 [ [[TMP31]], [[ITOFP_IF_THEN20]] ], [ [[TMP27]], [[ITOFP_SW_EPILOG]] ], [ [[TMP36]], [[ITOFP_IF_ELSE]] ]
; CHECK-NEXT: [[TMP40:%.*]] = phi i64 [ [[TMP33]], [[ITOFP_IF_THEN20]] ], [ [[TMP29]], [[ITOFP_SW_EPILOG]] ], [ [[TMP38]], [[ITOFP_IF_ELSE]] ]
; CHECK-NEXT: [[AND29:%.*]] = and i129 [[TMP1]], 9223372036854775808
; CHECK-NEXT: [[TMP41:%.*]] = shl i64 [[TMP40]], 48
; CHECK-NEXT: [[TMP42:%.*]] = add i64 [[TMP41]], 4611404543450677248
; CHECK-NEXT: [[TMP43:%.*]] = zext i64 [[TMP42]] to i128
; CHECK-NEXT: [[TMP44:%.*]] = trunc i129 [[AND29]] to i128
; CHECK-NEXT: [[TMP45:%.*]] = or i128 [[TMP44]], [[TMP43]]
; CHECK-NEXT: [[TMP46:%.*]] = shl i128 [[TMP45]], 64
; CHECK-NEXT: [[TMP47:%.*]] = and i128 [[TMP39]], 5192296858534827628530496329220095
; CHECK-NEXT: [[TMP48:%.*]] = or i128 [[TMP46]], [[TMP47]]
; CHECK-NEXT: [[TMP49:%.*]] = bitcast i128 [[TMP48]] to fp128
; CHECK-NEXT: [[TMP50:%.*]] = fptrunc fp128 [[TMP49]] to x86_fp80
; CHECK-NEXT: br label [[ITOFP_RETURN]]
; CHECK: itofp-return:
; CHECK-NEXT: [[TMP51:%.*]] = phi x86_fp80 [ [[TMP50]], [[ITOFP_IF_END26]] ], [ 0xK00000000000000000000, [[ITOFP_ENTRY:%.*]] ]
; CHECK-NEXT: ret x86_fp80 [[TMP51]]
;
%conv = uitofp i129 %a to x86_fp80
ret x86_fp80 %conv
}
define fp128 @ui129tofp128(i129 %a) {
; CHECK-LABEL: @ui129tofp128(
; CHECK-NEXT: itofp-entry:
; CHECK-NEXT: [[TMP0:%.*]] = icmp eq i129 [[A:%.*]], 0
; CHECK-NEXT: br i1 [[TMP0]], label [[ITOFP_RETURN:%.*]], label [[ITOFP_IF_END:%.*]]
; CHECK: itofp-if-end:
; CHECK-NEXT: [[TMP1:%.*]] = ashr i129 [[A]], 128
; CHECK-NEXT: [[TMP2:%.*]] = xor i129 [[TMP1]], [[A]]
; CHECK-NEXT: [[TMP3:%.*]] = sub i129 [[TMP2]], [[TMP1]]
; CHECK-NEXT: [[TMP4:%.*]] = call i129 @llvm.ctlz.i129(i129 [[A]], i1 true)
; CHECK-NEXT: [[TMP5:%.*]] = trunc i129 [[TMP4]] to i32
; CHECK-NEXT: [[TMP6:%.*]] = sub i129 129, [[TMP4]]
; CHECK-NEXT: [[TMP7:%.*]] = sub i129 128, [[TMP4]]
; CHECK-NEXT: [[TMP8:%.*]] = icmp sgt i129 [[TMP7]], 113
; CHECK-NEXT: br i1 [[TMP8]], label [[ITOFP_IF_THEN4:%.*]], label [[ITOFP_IF_ELSE:%.*]]
; CHECK: itofp-if-then4:
; CHECK-NEXT: switch i129 [[TMP6]], label [[ITOFP_SW_DEFAULT:%.*]] [
; CHECK-NEXT: i129 114, label [[ITOFP_SW_BB:%.*]]
; CHECK-NEXT: i129 115, label [[ITOFP_SW_EPILOG:%.*]]
; CHECK-NEXT: ]
; CHECK: itofp-sw-bb:
; CHECK-NEXT: [[TMP9:%.*]] = shl i129 [[A]], 1
; CHECK-NEXT: br label [[ITOFP_SW_EPILOG]]
; CHECK: itofp-sw-default:
; CHECK-NEXT: [[TMP10:%.*]] = sub i129 14, [[TMP4]]
; CHECK-NEXT: [[TMP11:%.*]] = lshr i129 [[A]], [[TMP10]]
; CHECK-NEXT: [[TMP12:%.*]] = add i129 [[TMP4]], 115
; CHECK-NEXT: [[TMP13:%.*]] = lshr i129 -1, [[TMP12]]
; CHECK-NEXT: [[TMP14:%.*]] = and i129 [[TMP13]], [[A]]
; CHECK-NEXT: [[TMP15:%.*]] = icmp ne i129 [[TMP14]], 0
; CHECK-NEXT: [[TMP16:%.*]] = zext i1 [[TMP15]] to i129
; CHECK-NEXT: [[TMP17:%.*]] = or i129 [[TMP11]], [[TMP16]]
; CHECK-NEXT: br label [[ITOFP_SW_EPILOG]]
; CHECK: itofp-sw-epilog:
; CHECK-NEXT: [[TMP18:%.*]] = phi i129 [ [[TMP17]], [[ITOFP_SW_DEFAULT]] ], [ [[A]], [[ITOFP_IF_THEN4]] ], [ [[TMP9]], [[ITOFP_SW_BB]] ]
; CHECK-NEXT: [[TMP19:%.*]] = trunc i129 [[TMP18]] to i32
; CHECK-NEXT: [[TMP20:%.*]] = lshr i32 [[TMP19]], 2
; CHECK-NEXT: [[TMP21:%.*]] = and i32 [[TMP20]], 1
; CHECK-NEXT: [[TMP22:%.*]] = zext i32 [[TMP21]] to i129
; CHECK-NEXT: [[TMP23:%.*]] = or i129 [[TMP18]], [[TMP22]]
; CHECK-NEXT: [[TMP24:%.*]] = add i129 [[TMP23]], 1
; CHECK-NEXT: [[TMP25:%.*]] = lshr i129 [[TMP24]], 2
; CHECK-NEXT: [[A3:%.*]] = and i129 [[TMP24]], 41538374868278621028243970633760768
; CHECK-NEXT: [[TMP26:%.*]] = icmp eq i129 [[A3]], 0
; CHECK-NEXT: [[TMP27:%.*]] = trunc i129 [[TMP25]] to i128
; CHECK-NEXT: [[TMP28:%.*]] = lshr i129 [[TMP25]], 32
; CHECK-NEXT: [[TMP29:%.*]] = trunc i129 [[TMP7]] to i64
; CHECK-NEXT: br i1 [[TMP26]], label [[ITOFP_IF_END26:%.*]], label [[ITOFP_IF_THEN20:%.*]]
; CHECK: itofp-if-then20:
; CHECK-NEXT: [[TMP30:%.*]] = lshr i129 [[TMP24]], 3
; CHECK-NEXT: [[TMP31:%.*]] = trunc i129 [[TMP30]] to i128
; CHECK-NEXT: [[TMP32:%.*]] = lshr i129 [[TMP30]], 32
; CHECK-NEXT: [[TMP33:%.*]] = trunc i129 [[TMP6]] to i64
; CHECK-NEXT: br label [[ITOFP_IF_END26]]
; CHECK: itofp-if-else:
; CHECK-NEXT: [[TMP34:%.*]] = add i129 [[TMP4]], 4294967280
; CHECK-NEXT: [[TMP35:%.*]] = shl i129 [[A]], [[TMP34]]
; CHECK-NEXT: [[TMP36:%.*]] = trunc i129 [[TMP35]] to i128
; CHECK-NEXT: [[TMP37:%.*]] = lshr i129 [[TMP35]], 32
; CHECK-NEXT: [[TMP38:%.*]] = trunc i129 [[TMP7]] to i64
; CHECK-NEXT: br label [[ITOFP_IF_END26]]
; CHECK: itofp-if-end26:
; CHECK-NEXT: [[TMP39:%.*]] = phi i128 [ [[TMP31]], [[ITOFP_IF_THEN20]] ], [ [[TMP27]], [[ITOFP_SW_EPILOG]] ], [ [[TMP36]], [[ITOFP_IF_ELSE]] ]
; CHECK-NEXT: [[TMP40:%.*]] = phi i64 [ [[TMP33]], [[ITOFP_IF_THEN20]] ], [ [[TMP29]], [[ITOFP_SW_EPILOG]] ], [ [[TMP38]], [[ITOFP_IF_ELSE]] ]
; CHECK-NEXT: [[AND29:%.*]] = and i129 [[TMP1]], 9223372036854775808
; CHECK-NEXT: [[TMP41:%.*]] = shl i64 [[TMP40]], 48
; CHECK-NEXT: [[TMP42:%.*]] = add i64 [[TMP41]], 4611404543450677248
; CHECK-NEXT: [[TMP43:%.*]] = zext i64 [[TMP42]] to i128
; CHECK-NEXT: [[TMP44:%.*]] = trunc i129 [[AND29]] to i128
; CHECK-NEXT: [[TMP45:%.*]] = or i128 [[TMP44]], [[TMP43]]
; CHECK-NEXT: [[TMP46:%.*]] = shl i128 [[TMP45]], 64
; CHECK-NEXT: [[TMP47:%.*]] = and i128 [[TMP39]], 5192296858534827628530496329220095
; CHECK-NEXT: [[TMP48:%.*]] = or i128 [[TMP46]], [[TMP47]]
; CHECK-NEXT: [[TMP49:%.*]] = bitcast i128 [[TMP48]] to fp128
; CHECK-NEXT: br label [[ITOFP_RETURN]]
; CHECK: itofp-return:
; CHECK-NEXT: [[TMP50:%.*]] = phi fp128 [ [[TMP49]], [[ITOFP_IF_END26]] ], [ 0xL00000000000000000000000000000000, [[ITOFP_ENTRY:%.*]] ]
; CHECK-NEXT: ret fp128 [[TMP50]]
;
%conv = uitofp i129 %a to fp128
ret fp128 %conv
}

130
llvm/test/CodeGen/X86/fp-i129.ll Normal file
View File

@ -0,0 +1,130 @@
; RUN: llc < %s -mtriple=i686-unknown-unknown | FileCheck %s --check-prefixes=CHECK,X86
; RUN: llc < %s -mtriple=x86_64-unknown-unknown | FileCheck %s --check-prefixes=CHECK,X64
define i129 @fptosi_float(float %a) nounwind {
; CHECK-LABEL: fptosi_float:
; CHECK-NOT: call
%res = fptosi float %a to i129
ret i129 %res
}
define i129 @fptosi_double(double %a) nounwind {
; CHECK-LABEL: fptosi_double:
; CHECK-NOT: call
%res = fptosi double %a to i129
ret i129 %res
}
define i129 @fptosi_fp128(fp128 %a) nounwind {
; CHECK-LABEL: fptosi_fp128:
; CHECK-NOT: call
%res = fptosi fp128 %a to i129
ret i129 %res
}
define i129 @fptoui_float(float %a) nounwind {
; CHECK-LABEL: fptoui_float:
; CHECK-NOT: call
%res = fptoui float %a to i129
ret i129 %res
}
define i129 @fptoui_double(double %a) nounwind {
; CHECK-LABEL: fptoui_double:
; CHECK-NOT: call
%res = fptoui double %a to i129
ret i129 %res
}
define i129 @fptoui_fp128(fp128 %a) nounwind {
; CHECK-LABEL: fptoui_fp128:
; CHECK-NOT: call
%res = fptoui fp128 %a to i129
ret i129 %res
}
define float @sitofp_float(i129 %a) nounwind {
; CHECK-LABEL: sitofp_float:
; CHECK-NOT: call
%res = sitofp i129 %a to float
ret float %res
}
define double @sitofp_double(i129 %a) nounwind {
; CHECK-LABEL: sitofp_double:
; CHECK-NOT: call
%res = sitofp i129 %a to double
ret double %res
}
define fp128 @sitofp_fp128(i129 %a) nounwind {
; CHECK-LABEL: sitofp_fp128:
; CHECK-NOT: call
%res = sitofp i129 %a to fp128
ret fp128 %res
}
define float @uitofp_float(i129 %a) nounwind {
; CHECK-LABEL: uitofp_float:
; CHECK-NOT: call
%res = uitofp i129 %a to float
ret float %res
}
define double @uitofp_double(i129 %a) nounwind {
; CHECK-LABEL: uitofp_double:
; CHECK-NOT: call
%res = uitofp i129 %a to double
ret double %res
}
define fp128 @uitofp_fp128(i129 %a) nounwind {
; CHECK-LABEL: uitofp_fp128:
; CHECK-NOT: call
%res = uitofp i129 %a to fp128
ret fp128 %res
}
; higher sizes
define i257 @fptosi257_double(double %a) nounwind {
; CHECK-LABEL: fptosi257_double:
; CHECK-NOT: call
%res = fptosi double %a to i257
ret i257 %res
}
; half tests
define i257 @fptosi_half(half %a) nounwind {
; X86-LABEL: fptosi_half:
; X86: __gnu_h2f_ieee
;
; X64-LABEL: fptosi_half:
; X64: __extendhfsf2
%res = fptosi half %a to i257
ret i257 %res
}
define half @uitofp_half(i257 %a) nounwind {
; X86-LABEL: uitofp_half:
; X86: __gnu_f2h_ieee
;
; X64-LABEL: uitofp_half:
; X64: __truncsfhf2
%res = uitofp i257 %a to half
ret half %res
}
; x86_fp80 tests
define i257 @fptoui_x86_fp80(x86_fp80 %a) nounwind {
; CHECK-LABEL: fptoui_x86_fp80:
; CHECK: __extendxftf2
%res = fptoui x86_fp80 %a to i257
ret i257 %res
}
define x86_fp80 @sitofp_x86_fp80(i257 %a) nounwind {
; CHECK-LABEL: sitofp_x86_fp80:
; CHECK: __trunctfxf2
%res = sitofp i257 %a to x86_fp80
ret x86_fp80 %res
}

1
llvm/test/CodeGen/X86/opt-pipeline.ll
View File

@ -28,6 +28,7 @@
; CHECK-NEXT: Pre-ISel Intrinsic Lowering
; CHECK-NEXT: FunctionPass Manager
; CHECK-NEXT: Expand large div/rem
; CHECK-NEXT: Expand large fp convert
; CHECK-NEXT: Expand Atomic instructions
; CHECK-NEXT: Lower AMX intrinsics
; CHECK-NEXT: Lower AMX type for load/store

4
llvm/tools/opt/opt.cpp
View File

@ -379,7 +379,8 @@ static bool shouldPinPassToLegacyPM(StringRef Pass) {
"dot-regions", "dot-regions-only",
"view-regions", "view-regions-only",
"select-optimize", "expand-large-div-rem",
"structurizecfg", "fix-irreducible"};
"structurizecfg", "fix-irreducible",
"expand-large-fp-convert"};
for (const auto &P : PassNamePrefix)
if (Pass.startswith(P))
return true;
@ -426,6 +427,7 @@ int main(int argc, char **argv) {
// For codegen passes, only passes that do IR to IR transformation are
// supported.
initializeExpandLargeDivRemLegacyPassPass(Registry);
initializeExpandLargeFpConvertLegacyPassPass(Registry);
initializeExpandMemCmpPassPass(Registry);
initializeScalarizeMaskedMemIntrinLegacyPassPass(Registry);
initializeSelectOptimizePass(Registry);