[mips] Enable arithmetic and binary operations for the i128 data type.

Summary:
This patch adds support for some operations that were missing from
128-bit integer types (add/sub/mul/sdiv/udiv... etc.). With these
changes we can support the __int128_t and __uint128_t data types
from C/C++.

Depends on D7125

Reviewers: dsanders

Subscribers: llvm-commits

Differential Revision: http://reviews.llvm.org/D7143

llvm-svn: 227089
This commit is contained in:
Vasileios Kalintiris 2015-01-26 12:33:22 +00:00
parent dceac987bd
commit ef96a8ecd6
17 changed files with 450 additions and 46 deletions

View File

@ -498,6 +498,16 @@ def : MipsPat<(i64 (sext_inreg GPR64:$src, i32)),
// bswap MipsPattern
def : MipsPat<(bswap GPR64:$rt), (DSHD (DSBH GPR64:$rt))>;
// Carry pattern
def : MipsPat<(subc GPR64:$lhs, GPR64:$rhs),
(DSUBu GPR64:$lhs, GPR64:$rhs)>;
let AdditionalPredicates = [NotDSP] in {
def : MipsPat<(addc GPR64:$lhs, GPR64:$rhs),
(DADDu GPR64:$lhs, GPR64:$rhs)>;
def : MipsPat<(addc GPR64:$lhs, immSExt16:$imm),
(DADDiu GPR64:$lhs, imm:$imm)>;
}
// Octeon bbit0/bbit1 MipsPattern
let Predicates = [HasMips64, HasCnMips] in {
def : MipsPat<(brcond (i32 (seteq (and i64:$lhs, PowerOf2LO:$mask), 0)), bb:$dst),

View File

@ -261,6 +261,9 @@ MipsTargetLowering::MipsTargetLowering(const MipsTargetMachine &TM,
setOperationAction(ISD::LOAD, MVT::i64, Custom);
setOperationAction(ISD::STORE, MVT::i64, Custom);
setOperationAction(ISD::FP_TO_SINT, MVT::i64, Custom);
setOperationAction(ISD::SHL_PARTS, MVT::i64, Custom);
setOperationAction(ISD::SRA_PARTS, MVT::i64, Custom);
setOperationAction(ISD::SRL_PARTS, MVT::i64, Custom);
}
if (!Subtarget.isGP64bit()) {
@ -2017,10 +2020,11 @@ SDValue MipsTargetLowering::lowerATOMIC_FENCE(SDValue Op,
SDValue MipsTargetLowering::lowerShiftLeftParts(SDValue Op,
SelectionDAG &DAG) const {
SDLoc DL(Op);
MVT VT = Subtarget.isGP64bit() ? MVT::i64 : MVT::i32;
SDValue Lo = Op.getOperand(0), Hi = Op.getOperand(1);
SDValue Shamt = Op.getOperand(2);
// if shamt < 32:
// if shamt < (VT.bits):
// lo = (shl lo, shamt)
// hi = (or (shl hi, shamt) (srl (srl lo, 1), ~shamt))
// else:
@ -2028,18 +2032,17 @@ SDValue MipsTargetLowering::lowerShiftLeftParts(SDValue Op,
// hi = (shl lo, shamt[4:0])
SDValue Not = DAG.getNode(ISD::XOR, DL, MVT::i32, Shamt,
DAG.getConstant(-1, MVT::i32));
SDValue ShiftRight1Lo = DAG.getNode(ISD::SRL, DL, MVT::i32, Lo,
DAG.getConstant(1, MVT::i32));
SDValue ShiftRightLo = DAG.getNode(ISD::SRL, DL, MVT::i32, ShiftRight1Lo,
Not);
SDValue ShiftLeftHi = DAG.getNode(ISD::SHL, DL, MVT::i32, Hi, Shamt);
SDValue Or = DAG.getNode(ISD::OR, DL, MVT::i32, ShiftLeftHi, ShiftRightLo);
SDValue ShiftLeftLo = DAG.getNode(ISD::SHL, DL, MVT::i32, Lo, Shamt);
SDValue ShiftRight1Lo = DAG.getNode(ISD::SRL, DL, VT, Lo,
DAG.getConstant(1, VT));
SDValue ShiftRightLo = DAG.getNode(ISD::SRL, DL, VT, ShiftRight1Lo, Not);
SDValue ShiftLeftHi = DAG.getNode(ISD::SHL, DL, VT, Hi, Shamt);
SDValue Or = DAG.getNode(ISD::OR, DL, VT, ShiftLeftHi, ShiftRightLo);
SDValue ShiftLeftLo = DAG.getNode(ISD::SHL, DL, VT, Lo, Shamt);
SDValue Cond = DAG.getNode(ISD::AND, DL, MVT::i32, Shamt,
DAG.getConstant(0x20, MVT::i32));
Lo = DAG.getNode(ISD::SELECT, DL, MVT::i32, Cond,
DAG.getConstant(0, MVT::i32), ShiftLeftLo);
Hi = DAG.getNode(ISD::SELECT, DL, MVT::i32, Cond, ShiftLeftLo, Or);
Lo = DAG.getNode(ISD::SELECT, DL, VT, Cond,
DAG.getConstant(0, VT), ShiftLeftLo);
Hi = DAG.getNode(ISD::SELECT, DL, VT, Cond, ShiftLeftLo, Or);
SDValue Ops[2] = {Lo, Hi};
return DAG.getMergeValues(Ops, DL);
@ -2050,8 +2053,9 @@ SDValue MipsTargetLowering::lowerShiftRightParts(SDValue Op, SelectionDAG &DAG,
SDLoc DL(Op);
SDValue Lo = Op.getOperand(0), Hi = Op.getOperand(1);
SDValue Shamt = Op.getOperand(2);
MVT VT = Subtarget.isGP64bit() ? MVT::i64 : MVT::i32;
// if shamt < 32:
// if shamt < (VT.bits):
// lo = (or (shl (shl hi, 1), ~shamt) (srl lo, shamt))
// if isSRA:
// hi = (sra hi, shamt)
@ -2066,21 +2070,19 @@ SDValue MipsTargetLowering::lowerShiftRightParts(SDValue Op, SelectionDAG &DAG,
// hi = 0
SDValue Not = DAG.getNode(ISD::XOR, DL, MVT::i32, Shamt,
DAG.getConstant(-1, MVT::i32));
SDValue ShiftLeft1Hi = DAG.getNode(ISD::SHL, DL, MVT::i32, Hi,
DAG.getConstant(1, MVT::i32));
SDValue ShiftLeftHi = DAG.getNode(ISD::SHL, DL, MVT::i32, ShiftLeft1Hi, Not);
SDValue ShiftRightLo = DAG.getNode(ISD::SRL, DL, MVT::i32, Lo, Shamt);
SDValue Or = DAG.getNode(ISD::OR, DL, MVT::i32, ShiftLeftHi, ShiftRightLo);
SDValue ShiftRightHi = DAG.getNode(IsSRA ? ISD::SRA : ISD::SRL, DL, MVT::i32,
Hi, Shamt);
SDValue ShiftLeft1Hi = DAG.getNode(ISD::SHL, DL, VT, Hi,
DAG.getConstant(1, VT));
SDValue ShiftLeftHi = DAG.getNode(ISD::SHL, DL, VT, ShiftLeft1Hi, Not);
SDValue ShiftRightLo = DAG.getNode(ISD::SRL, DL, VT, Lo, Shamt);
SDValue Or = DAG.getNode(ISD::OR, DL, VT, ShiftLeftHi, ShiftRightLo);
SDValue ShiftRightHi = DAG.getNode(IsSRA ? ISD::SRA : ISD::SRL,
DL, VT, Hi, Shamt);
SDValue Cond = DAG.getNode(ISD::AND, DL, MVT::i32, Shamt,
DAG.getConstant(0x20, MVT::i32));
SDValue Shift31 = DAG.getNode(ISD::SRA, DL, MVT::i32, Hi,
DAG.getConstant(31, MVT::i32));
Lo = DAG.getNode(ISD::SELECT, DL, MVT::i32, Cond, ShiftRightHi, Or);
Hi = DAG.getNode(ISD::SELECT, DL, MVT::i32, Cond,
IsSRA ? Shift31 : DAG.getConstant(0, MVT::i32),
ShiftRightHi);
SDValue Shift31 = DAG.getNode(ISD::SRA, DL, VT, Hi, DAG.getConstant(31, VT));
Lo = DAG.getNode(ISD::SELECT, DL, VT, Cond, ShiftRightHi, Or);
Hi = DAG.getNode(ISD::SELECT, DL, VT, Cond,
IsSRA ? Shift31 : DAG.getConstant(0, VT), ShiftRightHi);
SDValue Ops[2] = {Lo, Hi};
return DAG.getMergeValues(Ops, DL);

View File

@ -236,13 +236,31 @@ SDNode *MipsSEDAGToDAGISel::selectAddESubE(unsigned MOp, SDValue InFlag,
(Opc == ISD::SUBC || Opc == ISD::SUBE)) &&
"(ADD|SUB)E flag operand must come from (ADD|SUB)C/E insn");
unsigned SLTuOp = Mips::SLTu, ADDuOp = Mips::ADDu;
if (Subtarget->isGP64bit()) {
SLTuOp = Mips::SLTu64;
ADDuOp = Mips::DADDu;
}
SDValue Ops[] = { CmpLHS, InFlag.getOperand(1) };
SDValue LHS = Node->getOperand(0), RHS = Node->getOperand(1);
EVT VT = LHS.getValueType();
SDNode *Carry = CurDAG->getMachineNode(Mips::SLTu, DL, VT, Ops);
SDNode *AddCarry = CurDAG->getMachineNode(Mips::ADDu, DL, VT,
SDNode *Carry = CurDAG->getMachineNode(SLTuOp, DL, VT, Ops);
if (Subtarget->isGP64bit()) {
// On 64-bit targets, sltu produces an i64 but our backend currently says
// that SLTu64 produces an i32. We need to fix this in the long run but for
// now, just make the DAG type-correct by asserting the upper bits are zero.
Carry = CurDAG->getMachineNode(Mips::SUBREG_TO_REG, DL, VT,
CurDAG->getTargetConstant(0, VT),
SDValue(Carry, 0),
CurDAG->getTargetConstant(Mips::sub_32, VT));
}
SDNode *AddCarry = CurDAG->getMachineNode(ADDuOp, DL, VT,
SDValue(Carry, 0), RHS);
return CurDAG->SelectNodeTo(Node, MOp, VT, MVT::Glue, LHS,
SDValue(AddCarry, 0));
}
@ -641,7 +659,8 @@ std::pair<bool, SDNode*> MipsSEDAGToDAGISel::selectNode(SDNode *Node) {
case ISD::SUBE: {
SDValue InFlag = Node->getOperand(2);
Result = selectAddESubE(Mips::SUBu, InFlag, InFlag.getOperand(0), DL, Node);
unsigned Opc = Subtarget->isGP64bit() ? Mips::DSUBu : Mips::SUBu;
Result = selectAddESubE(Opc, InFlag, InFlag.getOperand(0), DL, Node);
return std::make_pair(true, Result);
}
@ -649,7 +668,8 @@ std::pair<bool, SDNode*> MipsSEDAGToDAGISel::selectNode(SDNode *Node) {
if (Subtarget->hasDSP()) // Select DSP instructions, ADDSC and ADDWC.
break;
SDValue InFlag = Node->getOperand(2);
Result = selectAddESubE(Mips::ADDu, InFlag, InFlag.getValue(0), DL, Node);
unsigned Opc = Subtarget->isGP64bit() ? Mips::DADDu : Mips::ADDu;
Result = selectAddESubE(Opc, InFlag, InFlag.getValue(0), DL, Node);
return std::make_pair(true, Result);
}

View File

@ -122,6 +122,8 @@ MipsSETargetLowering::MipsSETargetLowering(const MipsTargetMachine &TM,
setOperationAction(ISD::MUL, MVT::i64, Custom);
if (Subtarget.isGP64bit()) {
setOperationAction(ISD::SMUL_LOHI, MVT::i64, Custom);
setOperationAction(ISD::UMUL_LOHI, MVT::i64, Custom);
setOperationAction(ISD::MULHS, MVT::i64, Custom);
setOperationAction(ISD::MULHU, MVT::i64, Custom);
setOperationAction(ISD::SDIVREM, MVT::i64, Custom);
@ -200,6 +202,8 @@ MipsSETargetLowering::MipsSETargetLowering(const MipsTargetMachine &TM,
if (Subtarget.hasMips64r6()) {
// MIPS64r6 replaces the accumulator-based multiplies with a three register
// instruction
setOperationAction(ISD::SMUL_LOHI, MVT::i64, Expand);
setOperationAction(ISD::UMUL_LOHI, MVT::i64, Expand);
setOperationAction(ISD::MUL, MVT::i64, Legal);
setOperationAction(ISD::MULHS, MVT::i64, Legal);
setOperationAction(ISD::MULHU, MVT::i64, Legal);

View File

@ -83,3 +83,33 @@ entry:
%r = add i64 %a, %b
ret i64 %r
}
define signext i128 @add_i128(i128 signext %a, i128 signext %b) {
entry:
; ALL-LABEL: add_i128:
; GP32: lw $[[T0:[0-9]+]], 28($sp)
; GP32: addu $[[T1:[0-9]+]], $7, $[[T0]]
; GP32: sltu $[[T2:[0-9]+]], $[[T1]], $[[T0]]
; GP32: lw $[[T3:[0-9]+]], 24($sp)
; GP32: addu $[[T4:[0-9]+]], $[[T2]], $[[T3]]
; GP32: addu $[[T5:[0-9]+]], $6, $[[T4]]
; GP32: sltu $[[T6:[0-9]+]], $[[T5]], $[[T3]]
; GP32: lw $[[T7:[0-9]+]], 20($sp)
; GP32: addu $[[T8:[0-9]+]], $[[T6]], $[[T7]]
; GP32: lw $[[T9:[0-9]+]], 16($sp)
; GP32: addu $3, $5, $[[T8]]
; GP32: sltu $[[T10:[0-9]+]], $3, $[[T7]]
; GP32: addu $[[T11:[0-9]+]], $[[T10]], $[[T9]]
; GP32: addu $2, $4, $[[T11]]
; GP32: move $4, $[[T5]]
; GP32: move $5, $[[T1]]
; GP64: daddu $3, $5, $7
; GP64: sltu $[[T0:[0-9]+]], $3, $7
; GP64: daddu $[[T1:[0-9]+]], $[[T0]], $6
; GP64: daddu $2, $4, $[[T1]]
%r = add i128 %a, %b
ret i128 %r
}

View File

@ -72,3 +72,23 @@ entry:
%r = and i64 %a, %b
ret i64 %r
}
define signext i128 @and_i128(i128 signext %a, i128 signext %b) {
entry:
; ALL-LABEL: and_i128:
; GP32: lw $[[T0:[0-9]+]], 24($sp)
; GP32: lw $[[T1:[0-9]+]], 20($sp)
; GP32: lw $[[T2:[0-9]+]], 16($sp)
; GP32: and $2, $4, $[[T2]]
; GP32: and $3, $5, $[[T1]]
; GP32: and $4, $6, $[[T0]]
; GP32: lw $[[T3:[0-9]+]], 28($sp)
; GP32: and $5, $7, $[[T3]]
; GP64: and $2, $4, $6
; GP64: and $3, $5, $7
%r = and i128 %a, %b
ret i128 %r
}

View File

@ -126,3 +126,63 @@ entry:
%r = ashr i64 %a, %b
ret i64 %r
}
define signext i128 @ashr_i128(i128 signext %a, i128 signext %b) {
entry:
; ALL-LABEL: ashr_i128:
; GP32: lw $25, %call16(__ashrti3)($gp)
; M3: sll $[[T0:[0-9]+]], $7, 0
; M3: dsrav $[[T1:[0-9]+]], $4, $[[T0]]
; M3: andi $[[T2:[0-9]+]], $[[T0]], 32
; M3: bnez $[[T3:[0-9]+]], $[[BB0:BB[0-9_]+]]
; M3: move $3, $[[T1]]
; M3: dsrlv $[[T4:[0-9]+]], $5, $[[T0]]
; M3: dsll $[[T5:[0-9]+]], $4, 1
; M3: not $[[T6:[0-9]+]], $[[T0]]
; M3: dsllv $[[T7:[0-9]+]], $[[T5]], $[[T6]]
; M3: or $3, $[[T7]], $[[T4]]
; M3: $[[BB0]]:
; M3: beqz $[[T3]], $[[BB1:BB[0-9_]+]]
; M3: nop
; M3: dsra $2, $4, 31
; M3: $[[BB1]]:
; M3: jr $ra
; M3: nop
; GP64-NOT-R6: sll $[[T0:[0-9]+]], $7, 0
; GP64-NOT-R6: dsrlv $[[T1:[0-9]+]], $5, $[[T0]]
; GP64-NOT-R6: dsll $[[T2:[0-9]+]], $4, 1
; GP64-NOT-R6: not $[[T3:[0-9]+]], $[[T0]]
; GP64-NOT-R6: dsllv $[[T4:[0-9]+]], $[[T2]], $[[T3]]
; GP64-NOT-R6: or $3, $[[T4]], $[[T1]]
; GP64-NOT-R6: dsrav $2, $4, $[[T0]]
; GP64-NOT-R6: andi $[[T5:[0-9]+]], $[[T0]], 32
; GP64-NOT-R6: movn $3, $2, $[[T5]]
; GP64-NOT-R6: dsra $[[T6:[0-9]+]], $4, 31
; GP64-NOT-R6: jr $ra
; GP64-NOT-R6: movn $2, $[[T6]], $[[T5]]
; 64R6: sll $[[T0:[0-9]+]], $7, 0
; 64R6: dsrav $[[T1:[0-9]+]], $4, $[[T0]]
; 64R6: andi $[[T2:[0-9]+]], $[[T0]], 32
; 64R6: sll $[[T3:[0-9]+]], $[[T2]], 0
; 64R6: seleqz $[[T4:[0-9]+]], $[[T1]], $[[T3]]
; 64R6: dsra $[[T5:[0-9]+]], $4, 31
; 64R6: selnez $[[T6:[0-9]+]], $[[T5]], $[[T3]]
; 64R6: or $2, $[[T6]], $[[T4]]
; 64R6: dsrlv $[[T7:[0-9]+]], $5, $[[T0]]
; 64R6: dsll $[[T8:[0-9]+]], $4, 1
; 64R6: not $[[T9:[0-9]+]], $[[T0]]
; 64R6: dsllv $[[T10:[0-9]+]], $[[T8]], $[[T9]]
; 64R6: or $[[T11:[0-9]+]], $[[T10]], $[[T7]]
; 64R6: seleqz $[[T12:[0-9]+]], $[[T11]], $[[T3]]
; 64R6: selnez $[[T13:[0-9]+]], $[[T1]], $[[T3]]
; 64R6: jr $ra
; 64R6: or $3, $[[T13]], $[[T12]]
%r = ashr i128 %a, %b
ret i128 %r
}

View File

@ -119,3 +119,58 @@ entry:
%r = lshr i64 %a, %b
ret i64 %r
}
define signext i128 @lshr_i128(i128 signext %a, i128 signext %b) {
entry:
; ALL-LABEL: lshr_i128:
; GP32: lw $25, %call16(__lshrti3)($gp)
; M3: sll $[[T0:[0-9]+]], $7, 0
; M3: dsrlv $[[T1:[0-9]+]], $4, $[[T0]]
; M3: andi $[[T2:[0-9]+]], $[[T0]], 32
; M3: bnez $[[T3:[0-9]+]], $[[BB0:BB[0-9_]+]]
; M3: move $3, $[[T1]]
; M3: dsrlv $[[T4:[0-9]+]], $5, $[[T0]]
; M3: dsll $[[T5:[0-9]+]], $4, 1
; M3: not $[[T6:[0-9]+]], $[[T0]]
; M3: dsllv $[[T7:[0-9]+]], $[[T5]], $[[T6]]
; M3: or $3, $[[T7]], $[[T4]]
; M3: $[[BB0]]:
; M3: bnez $[[T3]], $[[BB1:BB[0-9_]+]]
; M3: daddiu $2, $zero, 0
; M3: move $2, $[[T1]]
; M3: $[[BB1]]:
; M3: jr $ra
; M3: nop
; GP64-NOT-R6: sll $[[T0:[0-9]+]], $7, 0
; GP64-NOT-R6: dsrlv $[[T1:[0-9]+]], $5, $[[T0]]
; GP64-NOT-R6: dsll $[[T2:[0-9]+]], $4, 1
; GP64-NOT-R6: not $[[T3:[0-9]+]], $[[T0]]
; GP64-NOT-R6: dsllv $[[T4:[0-9]+]], $[[T2]], $[[T3]]
; GP64-NOT-R6: or $3, $[[T4]], $[[T1]]
; GP64-NOT-R6: dsrlv $2, $4, $[[T0]]
; GP64-NOT-R6: andi $[[T5:[0-9]+]], $[[T0]], 32
; GP64-NOT-R6: movn $3, $2, $[[T5]]
; GP64-NOT-R6: jr $ra
; GP64-NOT-R6: movn $2, $zero, $1
; 64R6: sll $[[T0:[0-9]+]], $7, 0
; 64R6: dsrlv $[[T1:[0-9]+]], $5, $[[T0]]
; 64R6: dsll $[[T2:[0-9]+]], $4, 1
; 64R6: not $[[T3:[0-9]+]], $[[T0]]
; 64R6: dsllv $[[T4:[0-9]+]], $[[T2]], $[[T3]]
; 64R6: or $[[T5:[0-9]+]], $[[T4]], $[[T1]]
; 64R6: andi $[[T6:[0-9]+]], $[[T0]], 32
; 64R6: sll $[[T7:[0-9]+]], $[[T6]], 0
; 64R6: seleqz $[[T8:[0-9]+]], $[[T5]], $[[T7]]
; 64R6: dsrlv $[[T9:[0-9]+]], $4, $[[T0]]
; 64R6: selnez $[[T10:[0-9]+]], $[[T9]], $[[T7]]
; 64R6: or $3, $[[T10]], $[[T8]]
; 64R6: jr $ra
; 64R6: seleqz $2, $[[T0]], $[[T7]]
%r = lshr i128 %a, %b
ret i128 %r
}

View File

@ -1,19 +1,19 @@
; RUN: llc < %s -march=mips -mcpu=mips2 | FileCheck %s \
; RUN: -check-prefix=ALL -check-prefix=M2
; RUN: llc < %s -march=mips -mcpu=mips32 | FileCheck %s \
; RUN: -check-prefix=ALL -check-prefix=32R1-R2 -check-prefix=32R1
; RUN: llc < %s -march=mips -mcpu=mips32r2 | FileCheck %s \
; RUN: -check-prefix=ALL -check-prefix=32R1-R2 -check-prefix=32R2
; RUN: llc < %s -march=mips -mcpu=mips32r6 | FileCheck %s \
; RUN: -check-prefix=ALL -check-prefix=32R6
; RUN: llc < %s -march=mips64 -mcpu=mips4 | FileCheck %s \
; RUN: -check-prefix=ALL -check-prefix=M4
; RUN: llc < %s -march=mips64 -mcpu=mips64 | FileCheck %s \
; RUN: -check-prefix=ALL -check-prefix=64R1-R2
; RUN: llc < %s -march=mips64 -mcpu=mips64r2 | FileCheck %s \
; RUN: -check-prefix=ALL -check-prefix=64R1-R2
; RUN: llc < %s -march=mips64 -mcpu=mips64r6 | FileCheck %s \
; RUN: -check-prefix=ALL -check-prefix=64R6
; RUN: llc < %s -march=mips -mcpu=mips2 | FileCheck %s -check-prefix=ALL \
; RUN: -check-prefix=M2 -check-prefix=GP32
; RUN: llc < %s -march=mips -mcpu=mips32 | FileCheck %s -check-prefix=ALL \
; RUN: -check-prefix=32R1-R2 -check-prefix=GP32
; RUN: llc < %s -march=mips -mcpu=mips32r2 | FileCheck %s -check-prefix=ALL \
; RUN: -check-prefix=32R1-R2 -check-prefix=32R2 -check-prefix=GP32
; RUN: llc < %s -march=mips -mcpu=mips32r6 | FileCheck %s -check-prefix=ALL \
; RUN: -check-prefix=32R6 -check-prefix=GP32
; RUN: llc < %s -march=mips64 -mcpu=mips4 | FileCheck %s -check-prefix=ALL \
; RUN: -check-prefix=M4 -check-prefix=GP64-NOT-R6
; RUN: llc < %s -march=mips64 -mcpu=mips64 | FileCheck %s -check-prefix=ALL \
; RUN: -check-prefix=64R1-R2 -check-prefix=GP64-NOT-R6
; RUN: llc < %s -march=mips64 -mcpu=mips64r2 | FileCheck %s -check-prefix=ALL \
; RUN: -check-prefix=64R1-R2 -check-prefix=GP64 -check-prefix=GP64-NOT-R6
; RUN: llc < %s -march=mips64 -mcpu=mips64r6 | FileCheck %s -check-prefix=ALL \
; RUN: -check-prefix=64R6
define signext i1 @mul_i1(i1 signext %a, i1 signext %b) {
entry:
@ -179,3 +179,30 @@ entry:
%r = mul i64 %a, %b
ret i64 %r
}
define signext i128 @mul_i128(i128 signext %a, i128 signext %b) {
entry:
; ALL-LABEL: mul_i128:
; GP32: lw $25, %call16(__multi3)($gp)
; GP64-NOT-R6: dmult $4, $7
; GP64-NOT-R6: mflo $[[T0:[0-9]+]]
; GP64-NOT-R6: dmult $5, $6
; GP64-NOT-R6: mflo $[[T1:[0-9]+]]
; GP64-NOT-R6: dmultu $5, $7
; GP64-NOT-R6: mflo $3
; GP64-NOT-R6: mfhi $[[T2:[0-9]+]]
; GP64-NOT-R6: daddu $[[T3:[0-9]+]], $[[T2]], $[[T1]]
; GP64-NOT-R6: daddu $2, $[[T3:[0-9]+]], $[[T0]]
; 64R6: dmul $[[T0:[0-9]+]], $5, $6
; 64R6: dmuhu $[[T1:[0-9]+]], $5, $7
; 64R6: daddu $[[T2:[0-9]+]], $[[T1]], $[[T0]]
; 64R6: dmul $[[T3:[0-9]+]], $4, $7
; 64R6: daddu $2, $[[T2]], $[[T3]]
; 64R6: dmul $3, $5, $7
%r = mul i128 %a, %b
ret i128 %r
}

View File

@ -73,3 +73,23 @@ entry:
%r = or i64 %a, %b
ret i64 %r
}
define signext i128 @or_i128(i128 signext %a, i128 signext %b) {
entry:
; ALL-LABEL: or_i128:
; GP32: lw $[[T0:[0-9]+]], 24($sp)
; GP32: lw $[[T1:[0-9]+]], 20($sp)
; GP32: lw $[[T2:[0-9]+]], 16($sp)
; GP32: or $2, $4, $[[T2]]
; GP32: or $3, $5, $[[T1]]
; GP32: or $4, $6, $[[T0]]
; GP32: lw $[[T3:[0-9]+]], 28($sp)
; GP32: or $5, $7, $[[T3]]
; GP64: or $2, $4, $6
; GP64: or $3, $5, $7
%r = or i128 %a, %b
ret i128 %r
}

View File

@ -121,3 +121,16 @@ entry:
%r = sdiv i64 %a, %b
ret i64 %r
}
define signext i128 @sdiv_i128(i128 signext %a, i128 signext %b) {
entry:
; ALL-LABEL: sdiv_i128:
; GP32: lw $25, %call16(__divti3)($gp)
; GP64-NOT-R6: ld $25, %call16(__divti3)($gp)
; 64R6: ld $25, %call16(__divti3)($gp)
%r = sdiv i128 %a, %b
ret i128 %r
}

View File

@ -131,3 +131,58 @@ entry:
%r = shl i64 %a, %b
ret i64 %r
}
define signext i128 @shl_i128(i128 signext %a, i128 signext %b) {
entry:
; ALL-LABEL: shl_i128:
; GP32: lw $25, %call16(__ashlti3)($gp)
; M3: sll $[[T0:[0-9]+]], $7, 0
; M3: dsllv $[[T1:[0-9]+]], $5, $[[T0]]
; M3: andi $[[T2:[0-9]+]], $[[T0]], 32
; M3: bnez $[[T3:[0-9]+]], $[[BB0:BB[0-9_]+]]
; M3: move $2, $[[T1]]
; M3: dsllv $[[T4:[0-9]+]], $4, $[[T0]]
; M3: dsrl $[[T5:[0-9]+]], $5, 1
; M3: not $[[T6:[0-9]+]], $[[T0]]
; M3: dsrlv $[[T7:[0-9]+]], $[[T5]], $[[T6]]
; M3: or $2, $[[T4]], $[[T7]]
; M3: $[[BB0]]:
; M3: bnez $[[T3]], $[[BB1:BB[0-9_]+]]
; M3: daddiu $3, $zero, 0
; M3: move $3, $[[T1]]
; M3: $[[BB1]]:
; M3: jr $ra
; M3: nop
; GP64-NOT-R6: sll $[[T0:[0-9]+]], $7, 0
; GP64-NOT-R6: dsllv $[[T1:[0-9]+]], $4, $[[T0]]
; GP64-NOT-R6: dsrl $[[T2:[0-9]+]], $5, 1
; GP64-NOT-R6: not $[[T3:[0-9]+]], $[[T0]]
; GP64-NOT-R6: dsrlv $[[T4:[0-9]+]], $[[T2]], $[[T3]]
; GP64-NOT-R6: or $2, $[[T1]], $[[T4]]
; GP64-NOT-R6: dsllv $3, $5, $[[T0]]
; GP64-NOT-R6: andi $[[T5:[0-9]+]], $[[T0]], 32
; GP64-NOT-R6: movn $2, $3, $[[T5]]
; GP64-NOT-R6: jr $ra
; GP64-NOT-R6: movn $3, $zero, $1
; 64R6: sll $[[T0:[0-9]+]], $7, 0
; 64R6: dsllv $[[T1:[0-9]+]], $4, $[[T0]]
; 64R6: dsrl $[[T2:[0-9]+]], $5, 1
; 64R6: not $[[T3:[0-9]+]], $[[T0]]
; 64R6: dsrlv $[[T4:[0-9]+]], $[[T2]], $[[T3]]
; 64R6: or $[[T5:[0-9]+]], $[[T1]], $[[T4]]
; 64R6: andi $[[T6:[0-9]+]], $[[T0]], 32
; 64R6: sll $[[T7:[0-9]+]], $[[T6]], 0
; 64R6: seleqz $[[T8:[0-9]+]], $[[T5]], $[[T7]]
; 64R6: dsllv $[[T9:[0-9]+]], $5, $[[T0]]
; 64R6: selnez $[[T10:[0-9]+]], $[[T9]], $[[T7]]
; 64R6: or $2, $[[T10]], $[[T8]]
; 64R6: jr $ra
; 64R6: seleqz $3, $[[T0]], $[[T7]]
%r = shl i128 %a, %b
ret i128 %r
}

View File

@ -114,3 +114,16 @@ entry:
%r = srem i64 %a, %b
ret i64 %r
}
define signext i128 @srem_i128(i128 signext %a, i128 signext %b) {
entry:
; ALL-LABEL: srem_i128:
; GP32: lw $25, %call16(__modti3)($gp)
; GP64-NOT-R6: ld $25, %call16(__modti3)($gp)
; 64-R6: ld $25, %call16(__modti3)($gp)
%r = srem i128 %a, %b
ret i128 %r
}

View File

@ -83,3 +83,32 @@ entry:
%r = sub i64 %a, %b
ret i64 %r
}
define signext i128 @sub_i128(i128 signext %a, i128 signext %b) {
entry:
; ALL-LABEL: sub_i128:
; GP32: lw $[[T0:[0-9]+]], 20($sp)
; GP32: sltu $[[T1:[0-9]+]], $5, $[[T0]]
; GP32: lw $[[T2:[0-9]+]], 16($sp)
; GP32: addu $[[T3:[0-9]+]], $[[T1]], $[[T2]]
; GP32: lw $[[T4:[0-9]+]], 24($sp)
; GP32: lw $[[T5:[0-9]+]], 28($sp)
; GP32: subu $[[T6:[0-9]+]], $7, $[[T5]]
; GP32: subu $2, $4, $[[T3]]
; GP32: sltu $[[T8:[0-9]+]], $6, $[[T4]]
; GP32: addu $[[T9:[0-9]+]], $[[T8]], $[[T0]]
; GP32: subu $3, $5, $[[T9]]
; GP32: sltu $[[T10:[0-9]+]], $7, $[[T5]]
; GP32: addu $[[T11:[0-9]+]], $[[T10]], $[[T4]]
; GP32: subu $4, $6, $[[T11]]
; GP32: move $5, $[[T6]]
; GP64: dsubu $3, $5, $7
; GP64: sltu $[[T0:[0-9]+]], $5, $7
; GP64: daddu $[[T1:[0-9]+]], $[[T0]], $6
; GP64: dsubu $2, $4, $[[T1]]
%r = sub i128 %a, %b
ret i128 %r
}

View File

@ -93,3 +93,16 @@ entry:
%r = udiv i64 %a, %b
ret i64 %r
}
define signext i128 @udiv_i128(i128 signext %a, i128 signext %b) {
entry:
; ALL-LABEL: udiv_i128:
; GP32: lw $25, %call16(__udivti3)($gp)
; GP64-NOT-R6: ld $25, %call16(__udivti3)($gp)
; 64-R6: ld $25, %call16(__udivti3)($gp)
%r = udiv i128 %a, %b
ret i128 %r
}

View File

@ -130,3 +130,16 @@ entry:
%r = urem i64 %a, %b
ret i64 %r
}
define signext i128 @urem_i128(i128 signext %a, i128 signext %b) {
entry:
; ALL-LABEL: urem_i128:
; GP32: lw $25, %call16(__umodti3)($gp)
; GP64-NOT-R6: ld $25, %call16(__umodti3)($gp)
; 64-R6: ld $25, %call16(__umodti3)($gp)
%r = urem i128 %a, %b
ret i128 %r
}

View File

@ -72,3 +72,23 @@ entry:
%r = xor i64 %a, %b
ret i64 %r
}
define signext i128 @xor_i128(i128 signext %a, i128 signext %b) {
entry:
; ALL-LABEL: xor_i128:
; GP32: lw $[[T0:[0-9]+]], 24($sp)
; GP32: lw $[[T1:[0-9]+]], 20($sp)
; GP32: lw $[[T2:[0-9]+]], 16($sp)
; GP32: xor $2, $4, $[[T2]]
; GP32: xor $3, $5, $[[T1]]
; GP32: xor $4, $6, $[[T0]]
; GP32: lw $[[T3:[0-9]+]], 28($sp)
; GP32: xor $5, $7, $[[T3]]
; GP64: xor $2, $4, $6
; GP64: xor $3, $5, $7
%r = xor i128 %a, %b
ret i128 %r
}