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

[arm-fast-isel] Add support for -arm-long-calls. 

Patch by Jush Lu <jush.msn@gmail.com>.

llvm-svn: 158368
This commit is contained in:
Chad Rosier 2012-06-12 19:25:13 +00:00
parent 0764e0bb30
commit c6916f88a8
3 changed files with 124 additions and 44 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

104
llvm/lib/Target/ARM/ARMFastISel.cpp
View File

@ -190,7 +190,7 @@ class ARMFastISel : public FastISel {
unsigned ARMMaterializeGV(const GlobalValue *GV, EVT VT);
unsigned ARMMoveToFPReg(EVT VT, unsigned SrcReg);
unsigned ARMMoveToIntReg(EVT VT, unsigned SrcReg);
unsigned ARMSelectCallOp(const GlobalValue *GV);
unsigned ARMSelectCallOp(bool UseReg);
// Call handling routines.
private:
@ -202,6 +202,7 @@ class ARMFastISel : public FastISel {
SmallVectorImpl<unsigned> &RegArgs,
CallingConv::ID CC,
unsigned &NumBytes);
unsigned getLibcallReg(const Twine &Name);
bool FinishCall(MVT RetVT, SmallVectorImpl<unsigned> &UsedRegs,
const Instruction *I, CallingConv::ID CC,
unsigned &NumBytes);
@ -2108,8 +2109,17 @@ bool ARMFastISel::SelectRet(const Instruction *I) {
return true;
}
unsigned ARMFastISel::ARMSelectCallOp(const GlobalValue *GV) {
return isThumb2 ? ARM::tBL : ARM::BL;
unsigned ARMFastISel::ARMSelectCallOp(bool UseReg) {
if (UseReg)
return isThumb2 ? ARM::tBLXr : ARM::BLX;
else
return isThumb2 ? ARM::tBL : ARM::BL;
}
unsigned ARMFastISel::getLibcallReg(const Twine &Name) {
GlobalValue *GV = new GlobalVariable(Type::getInt32Ty(*Context), false,
GlobalValue::ExternalLinkage, 0, Name);
return ARMMaterializeGV(GV, TLI.getValueType(GV->getType()));
}
// A quick function that will emit a call for a named libcall in F with the
@ -2130,9 +2140,6 @@ bool ARMFastISel::ARMEmitLibcall(const Instruction *I, RTLIB::Libcall Call) {
else if (!isTypeLegal(RetTy, RetVT))
return false;
// TODO: For now if we have long calls specified we don't handle the call.
if (EnableARMLongCalls) return false;
// Can't handle non-double multi-reg retvals.
if (RetVT != MVT::isVoid && RetVT != MVT::i32) {
SmallVector<CCValAssign, 16> RVLocs;
@ -2176,20 +2183,32 @@ bool ARMFastISel::ARMEmitLibcall(const Instruction *I, RTLIB::Libcall Call) {
if (!ProcessCallArgs(Args, ArgRegs, ArgVTs, ArgFlags, RegArgs, CC, NumBytes))
return false;
// Issue the call.
MachineInstrBuilder MIB;
unsigned CallOpc = ARMSelectCallOp(NULL);
if (isThumb2)
// Explicitly adding the predicate here.
MIB = AddDefaultPred(BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DL,
TII.get(CallOpc)))
.addExternalSymbol(TLI.getLibcallName(Call));
else
// Explicitly adding the predicate here.
MIB = AddDefaultPred(BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DL,
TII.get(CallOpc))
.addExternalSymbol(TLI.getLibcallName(Call)));
unsigned CalleeReg = 0;
if (EnableARMLongCalls) {
CalleeReg = getLibcallReg(TLI.getLibcallName(Call));
if (CalleeReg == 0) return false;
}
// Issue the call.
unsigned CallOpc = ARMSelectCallOp(EnableARMLongCalls);
MachineInstrBuilder MIB = BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt,
DL, TII.get(CallOpc));
if (isThumb2) {
// Explicitly adding the predicate here.
AddDefaultPred(MIB);
if (EnableARMLongCalls)
MIB.addReg(CalleeReg);
else
MIB.addExternalSymbol(TLI.getLibcallName(Call));
} else {
if (EnableARMLongCalls)
MIB.addReg(CalleeReg);
else
MIB.addExternalSymbol(TLI.getLibcallName(Call));
// Explicitly adding the predicate here.
AddDefaultPred(MIB);
}
// Add implicit physical register uses to the call.
for (unsigned i = 0, e = RegArgs.size(); i != e; ++i)
MIB.addReg(RegArgs[i]);
@ -2237,9 +2256,6 @@ bool ARMFastISel::SelectCall(const Instruction *I,
RetVT != MVT::i8 && RetVT != MVT::i1)
return false;
// TODO: For now if we have long calls specified we don't handle the call.
if (EnableARMLongCalls) return false;
// Can't handle non-double multi-reg retvals.
if (RetVT != MVT::isVoid && RetVT != MVT::i1 && RetVT != MVT::i8 &&
RetVT != MVT::i16 && RetVT != MVT::i32) {
@ -2306,43 +2322,43 @@ bool ARMFastISel::SelectCall(const Instruction *I,
if (!ProcessCallArgs(Args, ArgRegs, ArgVTs, ArgFlags, RegArgs, CC, NumBytes))
return false;
// Issue the call.
MachineInstrBuilder MIB;
bool UseReg = false;
const GlobalValue *GV = dyn_cast<GlobalValue>(Callee);
unsigned CallOpc = ARMSelectCallOp(GV);
unsigned CalleeReg = 0;
if (!GV || EnableARMLongCalls) UseReg = true;
unsigned CalleeReg = 0;
if (UseReg) {
if (IntrMemName)
CalleeReg = getLibcallReg(IntrMemName);
else
CalleeReg = getRegForValue(Callee);
if (!GV){
CallOpc = isThumb2 ? ARM::tBLXr : ARM::BLX;
CalleeReg = getRegForValue(Callee);
if (CalleeReg == 0) return false;
}
// Explicitly adding the predicate here.
// Issue the call.
unsigned CallOpc = ARMSelectCallOp(UseReg);
MachineInstrBuilder MIB = BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt,
DL, TII.get(CallOpc));
if(isThumb2) {
// Explicitly adding the predicate here.
MIB = AddDefaultPred(BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DL,
TII.get(CallOpc)));
if (!GV)
AddDefaultPred(MIB);
if (UseReg)
MIB.addReg(CalleeReg);
else if (!IntrMemName)
MIB.addGlobalAddress(GV, 0, 0);
else
MIB.addExternalSymbol(IntrMemName, 0);
} else {
if (!GV)
MIB = AddDefaultPred(BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DL,
TII.get(CallOpc))
.addReg(CalleeReg));
if (UseReg)
MIB.addReg(CalleeReg);
else if (!IntrMemName)
// Explicitly adding the predicate here.
MIB = AddDefaultPred(BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DL,
TII.get(CallOpc))
.addGlobalAddress(GV, 0, 0));
MIB.addGlobalAddress(GV, 0, 0);
else
MIB = AddDefaultPred(BuildMI(*FuncInfo.MBB, FuncInfo.InsertPt, DL,
TII.get(CallOpc))
.addExternalSymbol(IntrMemName, 0));
MIB.addExternalSymbol(IntrMemName, 0);
// Explicitly adding the predicate here.
AddDefaultPred(MIB);
}
// Add implicit physical register uses to the call.

32
llvm/test/CodeGen/ARM/fast-isel-call.ll
View File

@ -1,5 +1,7 @@
; RUN: llc < %s -O0 -fast-isel-abort -relocation-model=dynamic-no-pic -mtriple=armv7-apple-ios | FileCheck %s --check-prefix=ARM
; RUN: llc < %s -O0 -fast-isel-abort -relocation-model=dynamic-no-pic -mtriple=thumbv7-apple-ios | FileCheck %s --check-prefix=THUMB
; RUN: llc < %s -O0 -fast-isel-abort -relocation-model=dynamic-no-pic -mtriple=armv7-apple-ios -arm-long-calls | FileCheck %s --check-prefix=ARM-LONG
; RUN: llc < %s -O0 -fast-isel-abort -relocation-model=dynamic-no-pic -mtriple=thumbv7-apple-ios -arm-long-calls | FileCheck %s --check-prefix=THUMB-LONG
define i32 @t0(i1 zeroext %a) nounwind {
%1 = zext i1 %a to i32
@ -99,6 +101,11 @@ entry:
; ARM: uxtb r9, r12
; ARM: str r9, [sp, #4]
; ARM: bl _bar
; ARM-LONG: @t10
; ARM-LONG: movw lr, :lower16:L_bar$non_lazy_ptr
; ARM-LONG: movt lr, :upper16:L_bar$non_lazy_ptr
; ARM-LONG: ldr lr, [lr]
; ARM-LONG: blx lr
; THUMB: @t10
; THUMB: movs r0, #0
; THUMB: movt r0, #0
@ -121,6 +128,11 @@ entry:
; THUMB: uxtb.w r9, r12
; THUMB: str.w r9, [sp, #4]
; THUMB: bl _bar
; THUMB-LONG: @t10
; THUMB-LONG: movw lr, :lower16:L_bar$non_lazy_ptr
; THUMB-LONG: movt lr, :upper16:L_bar$non_lazy_ptr
; THUMB-LONG: ldr.w lr, [lr]
; THUMB-LONG: blx lr
%call = call i32 @bar(i8 zeroext 0, i8 zeroext -8, i8 zeroext -69, i8 zeroext 28, i8 zeroext 40, i8 zeroext -70)
ret i32 0
}
@ -146,3 +158,23 @@ define void @foo3() uwtable {
%call = call i32 %1(i32 0)
ret void
}
define i32 @LibCall(i32 %a, i32 %b) {
entry:
; ARM: LibCall
; ARM: bl ___udivsi3
; ARM-LONG: LibCall
; ARM-LONG: movw r2, :lower16:L___udivsi3$non_lazy_ptr
; ARM-LONG: movt r2, :upper16:L___udivsi3$non_lazy_ptr
; ARM-LONG: ldr r2, [r2]
; ARM-LONG: blx r2
; THUMB: LibCall
; THUMB: bl ___udivsi3
; THUMB-LONG: LibCall
; THUMB-LONG: movw r2, :lower16:L___udivsi3$non_lazy_ptr
; THUMB-LONG: movt r2, :upper16:L___udivsi3$non_lazy_ptr
; THUMB-LONG: ldr r2, [r2]
; THUMB-LONG: blx r2
%tmp1 = udiv i32 %a, %b ; <i32> [#uses=1]
ret i32 %tmp1
}

32
llvm/test/CodeGen/ARM/fast-isel-intrinsic.ll
View File

@ -1,5 +1,7 @@
; RUN: llc < %s -O0 -fast-isel-abort -relocation-model=dynamic-no-pic -mtriple=armv7-apple-ios | FileCheck %s --check-prefix=ARM
; RUN: llc < %s -O0 -fast-isel-abort -relocation-model=dynamic-no-pic -mtriple=thumbv7-apple-ios | FileCheck %s --check-prefix=THUMB
; RUN: llc < %s -O0 -fast-isel-abort -relocation-model=dynamic-no-pic -mtriple=armv7-apple-ios -arm-long-calls | FileCheck %s --check-prefix=ARM-LONG
; RUN: llc < %s -O0 -fast-isel-abort -relocation-model=dynamic-no-pic -mtriple=thumbv7-apple-ios -arm-long-calls | FileCheck %s --check-prefix=THUMB-LONG
@message1 = global [60 x i8] c"The LLVM Compiler Infrastructure\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00", align 1
@temp = common global [60 x i8] zeroinitializer, align 1
@ -13,6 +15,11 @@ define void @t1() nounwind ssp {
; ARM: movw r2, #10
; ARM: uxtb r1, r1
; ARM: bl _memset
; ARM-LONG: t1
; ARM-LONG: movw r3, :lower16:L_memset$non_lazy_ptr
; ARM-LONG: movt r3, :upper16:L_memset$non_lazy_ptr
; ARM-LONG: ldr r3, [r3]
; ARM-LONG: blx r3
; THUMB: t1
; THUMB: movw r0, :lower16:_message1
; THUMB: movt r0, :upper16:_message1
@ -23,6 +30,11 @@ define void @t1() nounwind ssp {
; THUMB: movt r2, #0
; THUMB: uxtb r1, r1
; THUMB: bl _memset
; THUMB-LONG: t1
; THUMB-LONG: movw r3, :lower16:L_memset$non_lazy_ptr
; THUMB-LONG: movt r3, :upper16:L_memset$non_lazy_ptr
; THUMB-LONG: ldr r3, [r3]
; THUMB-LONG: blx r3
call void @llvm.memset.p0i8.i32(i8* getelementptr inbounds ([60 x i8]* @message1, i32 0, i32 5), i8 64, i32 10, i32 1, i1 false)
ret void
}
@ -41,6 +53,11 @@ define void @t2() nounwind ssp {
; ARM: mov r0, r1
; ARM: ldr r1, [sp] @ 4-byte Reload
; ARM: bl _memcpy
; ARM-LONG: t2
; ARM-LONG: movw r3, :lower16:L_memcpy$non_lazy_ptr
; ARM-LONG: movt r3, :upper16:L_memcpy$non_lazy_ptr
; ARM-LONG: ldr r3, [r3]
; ARM-LONG: blx r3
; THUMB: t2
; THUMB: movw r0, :lower16:L_temp$non_lazy_ptr
; THUMB: movt r0, :upper16:L_temp$non_lazy_ptr
@ -51,6 +68,11 @@ define void @t2() nounwind ssp {
; THUMB: movt r2, #0
; THUMB: mov r0, r1
; THUMB: bl _memcpy
; THUMB-LONG: t2
; THUMB-LONG: movw r3, :lower16:L_memcpy$non_lazy_ptr
; THUMB-LONG: movt r3, :upper16:L_memcpy$non_lazy_ptr
; THUMB-LONG: ldr r3, [r3]
; THUMB-LONG: blx r3
call void @llvm.memcpy.p0i8.p0i8.i32(i8* getelementptr inbounds ([60 x i8]* @temp, i32 0, i32 4), i8* getelementptr inbounds ([60 x i8]* @temp, i32 0, i32 16), i32 17, i32 1, i1 false)
ret void
}
@ -67,6 +89,11 @@ define void @t3() nounwind ssp {
; ARM: movw r2, #10
; ARM: mov r0, r1
; ARM: bl _memmove
; ARM-LONG: t3
; ARM-LONG: movw r3, :lower16:L_memmove$non_lazy_ptr
; ARM-LONG: movt r3, :upper16:L_memmove$non_lazy_ptr
; ARM-LONG: ldr r3, [r3]
; ARM-LONG: blx r3
; THUMB: t3
; THUMB: movw r0, :lower16:L_temp$non_lazy_ptr
; THUMB: movt r0, :upper16:L_temp$non_lazy_ptr
@ -77,6 +104,11 @@ define void @t3() nounwind ssp {
; THUMB: movt r2, #0
; THUMB: mov r0, r1
; THUMB: bl _memmove
; THUMB-LONG: t3
; THUMB-LONG: movw r3, :lower16:L_memmove$non_lazy_ptr
; THUMB-LONG: movt r3, :upper16:L_memmove$non_lazy_ptr
; THUMB-LONG: ldr r3, [r3]
; THUMB-LONG: blx r3
call void @llvm.memmove.p0i8.p0i8.i32(i8* getelementptr inbounds ([60 x i8]* @temp, i32 0, i32 4), i8* getelementptr inbounds ([60 x i8]* @temp, i32 0, i32 16), i32 10, i32 1, i1 false)
ret void
}