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

[ARM] Use AEABI helpers for i64 div and rem 

Differential Revision: http://reviews.llvm.org/D12232

llvm-svn: 245830
This commit is contained in:
Scott Douglass 2015-08-24 09:17:18 +00:00
parent d2974a6afa
commit bdef60462d
3 changed files with 117 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

63
llvm/lib/Target/ARM/ARMISelLowering.cpp
View File

@ -738,11 +738,13 @@ ARMTargetLowering::ARMTargetLowering(const TargetMachine &TM,
setOperationAction(ISD::UDIV, MVT::i32, Expand);
}
// FIXME: Also set divmod for SREM on EABI/androideabi
setOperationAction(ISD::SREM, MVT::i32, Expand);
setOperationAction(ISD::UREM, MVT::i32, Expand);
// Register based DivRem for AEABI (RTABI 4.2)
if (Subtarget->isTargetAEABI() || Subtarget->isTargetAndroid()) {
setOperationAction(ISD::SREM, MVT::i64, Custom);
setOperationAction(ISD::UREM, MVT::i64, Custom);
setLibcallName(RTLIB::SDIVREM_I8, "__aeabi_idivmod");
setLibcallName(RTLIB::SDIVREM_I16, "__aeabi_idivmod");
setLibcallName(RTLIB::SDIVREM_I32, "__aeabi_idivmod");
@ -6716,6 +6718,8 @@ SDValue ARMTargetLowering::LowerOperation(SDValue Op, SelectionDAG &DAG) const {
case ISD::SHL:
case ISD::SRL:
case ISD::SRA: return LowerShift(Op.getNode(), DAG, Subtarget);
case ISD::SREM: return LowerREM(Op.getNode(), DAG);
case ISD::UREM: return LowerREM(Op.getNode(), DAG);
case ISD::SHL_PARTS: return LowerShiftLeftParts(Op, DAG);
case ISD::SRL_PARTS:
case ISD::SRA_PARTS: return LowerShiftRightParts(Op, DAG);
@ -6775,6 +6779,10 @@ void ARMTargetLowering::ReplaceNodeResults(SDNode *N,
case ISD::SRA:
Res = Expand64BitShift(N, DAG, Subtarget);
break;
case ISD::SREM:
case ISD::UREM:
Res = LowerREM(N, DAG);
break;
case ISD::READCYCLECOUNTER:
ReplaceREADCYCLECOUNTER(N, Results, DAG, Subtarget);
return;
@ -11103,9 +11111,11 @@ void ARMTargetLowering::LowerAsmOperandForConstraint(SDValue Op,
static RTLIB::Libcall getDivRemLibcall(
const SDNode *N, MVT::SimpleValueType SVT) {
assert((N->getOpcode() == ISD::SDIVREM || N->getOpcode() == ISD::UDIVREM) &&
assert((N->getOpcode() == ISD::SDIVREM || N->getOpcode() == ISD::UDIVREM ||
N->getOpcode() == ISD::SREM || N->getOpcode() == ISD::UREM) &&
"Unhandled Opcode in getDivRemLibcall");
bool isSigned = N->getOpcode() == ISD::SDIVREM;
bool isSigned = N->getOpcode() == ISD::SDIVREM ||
N->getOpcode() == ISD::SREM;
RTLIB::Libcall LC;
switch (SVT) {
default: llvm_unreachable("Unexpected request for libcall!");
@ -11119,9 +11129,11 @@ static RTLIB::Libcall getDivRemLibcall(
static TargetLowering::ArgListTy getDivRemArgList(
const SDNode *N, LLVMContext *Context) {
assert((N->getOpcode() == ISD::SDIVREM || N->getOpcode() == ISD::UDIVREM) &&
assert((N->getOpcode() == ISD::SDIVREM || N->getOpcode() == ISD::UDIVREM ||
N->getOpcode() == ISD::SREM || N->getOpcode() == ISD::UREM) &&
"Unhandled Opcode in getDivRemArgList");
bool isSigned = N->getOpcode() == ISD::SDIVREM;
bool isSigned = N->getOpcode() == ISD::SDIVREM ||
N->getOpcode() == ISD::SREM;
TargetLowering::ArgListTy Args;
TargetLowering::ArgListEntry Entry;
for (unsigned i = 0, e = N->getNumOperands(); i != e; ++i) {
@ -11168,6 +11180,47 @@ SDValue ARMTargetLowering::LowerDivRem(SDValue Op, SelectionDAG &DAG) const {
return CallInfo.first;
}
// Lowers REM using divmod helpers
// see RTABI section 4.2/4.3
SDValue ARMTargetLowering::LowerREM(SDNode *N, SelectionDAG &DAG) const {
// Build return types (div and rem)
std::vector<Type*> RetTyParams;
Type *RetTyElement;
switch (N->getValueType(0).getSimpleVT().SimpleTy) {
default: llvm_unreachable("Unexpected request for libcall!");
case MVT::i8: RetTyElement = Type::getInt8Ty(*DAG.getContext()); break;
case MVT::i16: RetTyElement = Type::getInt16Ty(*DAG.getContext()); break;
case MVT::i32: RetTyElement = Type::getInt32Ty(*DAG.getContext()); break;
case MVT::i64: RetTyElement = Type::getInt64Ty(*DAG.getContext()); break;
}
RetTyParams.push_back(RetTyElement);
RetTyParams.push_back(RetTyElement);
ArrayRef<Type*> ret = ArrayRef<Type*>(RetTyParams);
Type *RetTy = StructType::get(*DAG.getContext(), ret);
RTLIB::Libcall LC = getDivRemLibcall(N, N->getValueType(0).getSimpleVT().
SimpleTy);
SDValue InChain = DAG.getEntryNode();
TargetLowering::ArgListTy Args = getDivRemArgList(N, DAG.getContext());
bool isSigned = N->getOpcode() == ISD::SREM;
SDValue Callee = DAG.getExternalSymbol(getLibcallName(LC),
getPointerTy(DAG.getDataLayout()));
// Lower call
CallLoweringInfo CLI(DAG);
CLI.setChain(InChain)
.setCallee(CallingConv::ARM_AAPCS, RetTy, Callee, std::move(Args), 0)
.setSExtResult(isSigned).setZExtResult(!isSigned).setDebugLoc(SDLoc(N));
std::pair<SDValue, SDValue> CallResult = LowerCallTo(CLI);
// Return second (rem) result operand (first contains div)
SDNode *ResNode = CallResult.first.getNode();
assert(ResNode->getNumOperands() == 2 && "divmod should return two operands");
return ResNode->getOperand(1);
}
SDValue
ARMTargetLowering::LowerDYNAMIC_STACKALLOC(SDValue Op, SelectionDAG &DAG) const {
assert(Subtarget->isTargetWindows() && "unsupported target platform");

1
llvm/lib/Target/ARM/ARMISelLowering.h
View File

@ -522,6 +522,7 @@ namespace llvm {
const ARMSubtarget *ST) const;
SDValue LowerFSINCOS(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerDivRem(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerREM(SDNode *N, SelectionDAG &DAG) const;
SDValue LowerDYNAMIC_STACKALLOC(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerFP_ROUND(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerFP_EXTEND(SDValue Op, SelectionDAG &DAG) const;

71
llvm/test/CodeGen/ARM/div.ll
View File

@ -1,52 +1,97 @@
; RUN: llc < %s -mtriple=arm-apple-ios -mcpu=cortex-a8 | FileCheck %s -check-prefix=CHECK-SWDIV
; RUN: llc < %s -mtriple=arm-apple-ios -mcpu=swift | FileCheck %s -check-prefix=CHECK-HWDIV
; RUN: llc < %s -mtriple=arm-apple-ios -mcpu=cortex-r4 | FileCheck %s -check-prefix=CHECK-SWDIV
; RUN: llc < %s -mtriple=arm-apple-ios -mcpu=cortex-r4f | FileCheck %s -check-prefix=CHECK-SWDIV
; RUN: llc < %s -mtriple=arm-apple-ios -mcpu=cortex-r5 | FileCheck %s -check-prefix=CHECK-HWDIV
; RUN: llc < %s -mtriple=arm-apple-ios -mcpu=cortex-a8 | \
; RUN: FileCheck %s -check-prefix=CHECK -check-prefix=CHECK-SWDIV
; RUN: llc < %s -mtriple=arm-apple-ios -mcpu=swift | \
; RUN: FileCheck %s -check-prefix=CHECK -check-prefix=CHECK-HWDIV
; RUN: llc < %s -mtriple=arm-apple-ios -mcpu=cortex-r4 | \
; RUN: FileCheck %s -check-prefix=CHECK -check-prefix=CHECK-SWDIV
; RUN: llc < %s -mtriple=arm-apple-ios -mcpu=cortex-r4f | \
; RUN: FileCheck %s -check-prefix=CHECK -check-prefix=CHECK-SWDIV
; RUN: llc < %s -mtriple=arm-apple-ios -mcpu=cortex-r5 | \
; RUN: FileCheck %s -check-prefix=CHECK -check-prefix=CHECK-HWDIV
; RUN: llc < %s -mtriple=arm-none-eabi -mcpu=cortex-a8 | \
; RUN: FileCheck %s -check-prefix=CHECK -check-prefix=CHECK-EABI
define i32 @f1(i32 %a, i32 %b) {
entry:
; CHECK-SWDIV: f1
; CHECK-LABEL: f1
; CHECK-SWDIV: __divsi3
; CHECK-HWDIV: f1
; CHECK-HWDIV: sdiv
; CHECK-EABI: __aeabi_idiv
%tmp1 = sdiv i32 %a, %b ; <i32> [#uses=1]
ret i32 %tmp1
}
define i32 @f2(i32 %a, i32 %b) {
entry:
; CHECK-SWDIV: f2
; CHECK-LABEL: f2
; CHECK-SWDIV: __udivsi3
; CHECK-HWDIV: f2
; CHECK-HWDIV: udiv
; CHECK-EABI: __aeabi_uidiv
%tmp1 = udiv i32 %a, %b ; <i32> [#uses=1]
ret i32 %tmp1
}
define i32 @f3(i32 %a, i32 %b) {
entry:
; CHECK-SWDIV: f3
; CHECK-LABEL: f3
; CHECK-SWDIV: __modsi3
; CHECK-HWDIV: f3
; CHECK-HWDIV: sdiv
; CHECK-HWDIV: mls
; EABI MODE = Remainder in R1, quotient in R0
; CHECK-EABI: __aeabi_idivmod
; CHECK-EABI-NEXT: mov r0, r1
%tmp1 = srem i32 %a, %b ; <i32> [#uses=1]
ret i32 %tmp1
}
define i32 @f4(i32 %a, i32 %b) {
entry:
; CHECK-SWDIV: f4
; CHECK-LABEL: f4
; CHECK-SWDIV: __umodsi3
; CHECK-HWDIV: f4
; CHECK-HWDIV: udiv
; CHECK-HWDIV: mls
; EABI MODE = Remainder in R1, quotient in R0
; CHECK-EABI: __aeabi_uidivmod
; CHECK-EABI-NEXT: mov r0, r1
%tmp1 = urem i32 %a, %b ; <i32> [#uses=1]
ret i32 %tmp1
}
define i64 @f5(i64 %a, i64 %b) {
entry:
; CHECK-LABEL: f5
; CHECK-SWDIV: __moddi3
; CHECK-HWDIV: __moddi3
; EABI MODE = Remainder in R2-R3, quotient in R0-R1
; CHECK-EABI: __aeabi_ldivmod
; CHECK-EABI-NEXT: mov r0, r2
; CHECK-EABI-NEXT: mov r1, r3
%tmp1 = srem i64 %a, %b ; <i64> [#uses=1]
ret i64 %tmp1
}
define i64 @f6(i64 %a, i64 %b) {
entry:
; CHECK-LABEL: f6
; CHECK-SWDIV: __umoddi3
; CHECK-HWDIV: __umoddi3
; EABI MODE = Remainder in R2-R3, quotient in R0-R1
; CHECK-EABI: __aeabi_uldivmod
; CHECK-EABI-NEXT: mov r0, r2
; CHECK-EABI-NEXT: mov r1, r3
%tmp1 = urem i64 %a, %b ; <i64> [#uses=1]
ret i64 %tmp1
}