[RISCV] Custom lower SHL_PARTS, SRA_PARTS, SRL_PARTS
When not optimizing for minimum size (-Oz) we custom lower wide shifts
(SHL_PARTS, SRA_PARTS, SRL_PARTS) instead of expanding to a libcall.
Differential Revision: https://reviews.llvm.org/D59477
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@358498 91177308-0d34-0410-b5e6-96231b3b80d8
diff --git a/lib/Target/RISCV/RISCVISelLowering.cpp b/lib/Target/RISCV/RISCVISelLowering.cpp
index cc04c36..377933e 100644
--- a/lib/Target/RISCV/RISCVISelLowering.cpp
+++ b/lib/Target/RISCV/RISCVISelLowering.cpp
@@ -125,9 +125,9 @@
setOperationAction(ISD::SMUL_LOHI, XLenVT, Expand);
setOperationAction(ISD::UMUL_LOHI, XLenVT, Expand);
- setOperationAction(ISD::SHL_PARTS, XLenVT, Expand);
- setOperationAction(ISD::SRL_PARTS, XLenVT, Expand);
- setOperationAction(ISD::SRA_PARTS, XLenVT, Expand);
+ setOperationAction(ISD::SHL_PARTS, XLenVT, Custom);
+ setOperationAction(ISD::SRL_PARTS, XLenVT, Custom);
+ setOperationAction(ISD::SRA_PARTS, XLenVT, Custom);
setOperationAction(ISD::ROTL, XLenVT, Expand);
setOperationAction(ISD::ROTR, XLenVT, Expand);
@@ -360,6 +360,12 @@
return lowerFRAMEADDR(Op, DAG);
case ISD::RETURNADDR:
return lowerRETURNADDR(Op, DAG);
+ case ISD::SHL_PARTS:
+ return lowerShiftLeftParts(Op, DAG);
+ case ISD::SRA_PARTS:
+ return lowerShiftRightParts(Op, DAG, true);
+ case ISD::SRL_PARTS:
+ return lowerShiftRightParts(Op, DAG, false);
case ISD::BITCAST: {
assert(Subtarget.is64Bit() && Subtarget.hasStdExtF() &&
"Unexpected custom legalisation");
@@ -568,6 +574,97 @@
return DAG.getCopyFromReg(DAG.getEntryNode(), DL, Reg, XLenVT);
}
+SDValue RISCVTargetLowering::lowerShiftLeftParts(SDValue Op,
+ SelectionDAG &DAG) const {
+ SDLoc DL(Op);
+ SDValue Lo = Op.getOperand(0);
+ SDValue Hi = Op.getOperand(1);
+ SDValue Shamt = Op.getOperand(2);
+ EVT VT = Lo.getValueType();
+
+ // if Shamt-XLEN < 0: // Shamt < XLEN
+ // Lo = Lo << Shamt
+ // Hi = (Hi << Shamt) | ((Lo >>u 1) >>u (XLEN-1 - Shamt))
+ // else:
+ // Lo = 0
+ // Hi = Lo << (Shamt-XLEN)
+
+ SDValue Zero = DAG.getConstant(0, DL, VT);
+ SDValue One = DAG.getConstant(1, DL, VT);
+ SDValue MinusXLen = DAG.getConstant(-(int)Subtarget.getXLen(), DL, VT);
+ SDValue XLenMinus1 = DAG.getConstant(Subtarget.getXLen() - 1, DL, VT);
+ SDValue ShamtMinusXLen = DAG.getNode(ISD::ADD, DL, VT, Shamt, MinusXLen);
+ SDValue XLenMinus1Shamt = DAG.getNode(ISD::SUB, DL, VT, XLenMinus1, Shamt);
+
+ SDValue LoTrue = DAG.getNode(ISD::SHL, DL, VT, Lo, Shamt);
+ SDValue ShiftRight1Lo = DAG.getNode(ISD::SRL, DL, VT, Lo, One);
+ SDValue ShiftRightLo =
+ DAG.getNode(ISD::SRL, DL, VT, ShiftRight1Lo, XLenMinus1Shamt);
+ SDValue ShiftLeftHi = DAG.getNode(ISD::SHL, DL, VT, Hi, Shamt);
+ SDValue HiTrue = DAG.getNode(ISD::OR, DL, VT, ShiftLeftHi, ShiftRightLo);
+ SDValue HiFalse = DAG.getNode(ISD::SHL, DL, VT, Lo, ShamtMinusXLen);
+
+ SDValue CC = DAG.getSetCC(DL, VT, ShamtMinusXLen, Zero, ISD::SETLT);
+
+ Lo = DAG.getNode(ISD::SELECT, DL, VT, CC, LoTrue, Zero);
+ Hi = DAG.getNode(ISD::SELECT, DL, VT, CC, HiTrue, HiFalse);
+
+ SDValue Parts[2] = {Lo, Hi};
+ return DAG.getMergeValues(Parts, DL);
+}
+
+SDValue RISCVTargetLowering::lowerShiftRightParts(SDValue Op, SelectionDAG &DAG,
+ bool IsSRA) const {
+ SDLoc DL(Op);
+ SDValue Lo = Op.getOperand(0);
+ SDValue Hi = Op.getOperand(1);
+ SDValue Shamt = Op.getOperand(2);
+ EVT VT = Lo.getValueType();
+
+ // SRA expansion:
+ // if Shamt-XLEN < 0: // Shamt < XLEN
+ // Lo = (Lo >>u Shamt) | ((Hi << 1) << (XLEN-1 - Shamt))
+ // Hi = Hi >>s Shamt
+ // else:
+ // Lo = Hi >>s (Shamt-XLEN);
+ // Hi = Hi >>s (XLEN-1)
+ //
+ // SRL expansion:
+ // if Shamt-XLEN < 0: // Shamt < XLEN
+ // Lo = (Lo >>u Shamt) | ((Hi << 1) << (XLEN-1 - Shamt))
+ // Hi = Hi >>u Shamt
+ // else:
+ // Lo = Hi >>u (Shamt-XLEN);
+ // Hi = 0;
+
+ unsigned ShiftRightOp = IsSRA ? ISD::SRA : ISD::SRL;
+
+ SDValue Zero = DAG.getConstant(0, DL, VT);
+ SDValue One = DAG.getConstant(1, DL, VT);
+ SDValue MinusXLen = DAG.getConstant(-(int)Subtarget.getXLen(), DL, VT);
+ SDValue XLenMinus1 = DAG.getConstant(Subtarget.getXLen() - 1, DL, VT);
+ SDValue ShamtMinusXLen = DAG.getNode(ISD::ADD, DL, VT, Shamt, MinusXLen);
+ SDValue XLenMinus1Shamt = DAG.getNode(ISD::SUB, DL, VT, XLenMinus1, Shamt);
+
+ SDValue ShiftRightLo = DAG.getNode(ISD::SRL, DL, VT, Lo, Shamt);
+ SDValue ShiftLeftHi1 = DAG.getNode(ISD::SHL, DL, VT, Hi, One);
+ SDValue ShiftLeftHi =
+ DAG.getNode(ISD::SHL, DL, VT, ShiftLeftHi1, XLenMinus1Shamt);
+ SDValue LoTrue = DAG.getNode(ISD::OR, DL, VT, ShiftRightLo, ShiftLeftHi);
+ SDValue HiTrue = DAG.getNode(ShiftRightOp, DL, VT, Hi, Shamt);
+ SDValue LoFalse = DAG.getNode(ShiftRightOp, DL, VT, Hi, ShamtMinusXLen);
+ SDValue HiFalse =
+ IsSRA ? DAG.getNode(ISD::SRA, DL, VT, Hi, XLenMinus1) : Zero;
+
+ SDValue CC = DAG.getSetCC(DL, VT, ShamtMinusXLen, Zero, ISD::SETLT);
+
+ Lo = DAG.getNode(ISD::SELECT, DL, VT, CC, LoTrue, LoFalse);
+ Hi = DAG.getNode(ISD::SELECT, DL, VT, CC, HiTrue, HiFalse);
+
+ SDValue Parts[2] = {Lo, Hi};
+ return DAG.getMergeValues(Parts, DL);
+}
+
// Returns the opcode of the target-specific SDNode that implements the 32-bit
// form of the given Opcode.
static RISCVISD::NodeType getRISCVWOpcode(unsigned Opcode) {
diff --git a/lib/Target/RISCV/RISCVISelLowering.h b/lib/Target/RISCV/RISCVISelLowering.h
index 0686a7f..a7f397c 100644
--- a/lib/Target/RISCV/RISCVISelLowering.h
+++ b/lib/Target/RISCV/RISCVISelLowering.h
@@ -114,6 +114,12 @@
return ISD::SIGN_EXTEND;
}
+ bool shouldExpandShift(SelectionDAG &DAG, SDNode *N) const override {
+ if (DAG.getMachineFunction().getFunction().hasMinSize())
+ return false;
+ return true;
+ }
+
private:
void analyzeInputArgs(MachineFunction &MF, CCState &CCInfo,
const SmallVectorImpl<ISD::InputArg> &Ins,
@@ -152,6 +158,8 @@
SDValue lowerVASTART(SDValue Op, SelectionDAG &DAG) const;
SDValue lowerFRAMEADDR(SDValue Op, SelectionDAG &DAG) const;
SDValue lowerRETURNADDR(SDValue Op, SelectionDAG &DAG) const;
+ SDValue lowerShiftLeftParts(SDValue Op, SelectionDAG &DAG) const;
+ SDValue lowerShiftRightParts(SDValue Op, SelectionDAG &DAG, bool IsSRA) const;
bool isEligibleForTailCallOptimization(
CCState &CCInfo, CallLoweringInfo &CLI, MachineFunction &MF,
diff --git a/test/CodeGen/RISCV/alu64.ll b/test/CodeGen/RISCV/alu64.ll
index e66d1d6..fcf695f 100644
--- a/test/CodeGen/RISCV/alu64.ll
+++ b/test/CodeGen/RISCV/alu64.ll
@@ -211,11 +211,20 @@
;
; RV32I-LABEL: sll:
; RV32I: # %bb.0:
-; RV32I-NEXT: addi sp, sp, -16
-; RV32I-NEXT: sw ra, 12(sp)
-; RV32I-NEXT: call __ashldi3
-; RV32I-NEXT: lw ra, 12(sp)
-; RV32I-NEXT: addi sp, sp, 16
+; RV32I-NEXT: addi a3, a2, -32
+; RV32I-NEXT: bltz a3, .LBB11_2
+; RV32I-NEXT: # %bb.1:
+; RV32I-NEXT: sll a1, a0, a3
+; RV32I-NEXT: mv a0, zero
+; RV32I-NEXT: ret
+; RV32I-NEXT: .LBB11_2:
+; RV32I-NEXT: addi a3, zero, 31
+; RV32I-NEXT: sub a3, a3, a2
+; RV32I-NEXT: srli a4, a0, 1
+; RV32I-NEXT: srl a3, a4, a3
+; RV32I-NEXT: sll a1, a1, a2
+; RV32I-NEXT: or a1, a1, a3
+; RV32I-NEXT: sll a0, a0, a2
; RV32I-NEXT: ret
%1 = shl i64 %a, %b
ret i64 %1
@@ -288,11 +297,20 @@
;
; RV32I-LABEL: srl:
; RV32I: # %bb.0:
-; RV32I-NEXT: addi sp, sp, -16
-; RV32I-NEXT: sw ra, 12(sp)
-; RV32I-NEXT: call __lshrdi3
-; RV32I-NEXT: lw ra, 12(sp)
-; RV32I-NEXT: addi sp, sp, 16
+; RV32I-NEXT: addi a3, a2, -32
+; RV32I-NEXT: bltz a3, .LBB15_2
+; RV32I-NEXT: # %bb.1:
+; RV32I-NEXT: srl a0, a1, a3
+; RV32I-NEXT: mv a1, zero
+; RV32I-NEXT: ret
+; RV32I-NEXT: .LBB15_2:
+; RV32I-NEXT: addi a3, zero, 31
+; RV32I-NEXT: sub a3, a3, a2
+; RV32I-NEXT: slli a4, a1, 1
+; RV32I-NEXT: sll a3, a4, a3
+; RV32I-NEXT: srl a0, a0, a2
+; RV32I-NEXT: or a0, a0, a3
+; RV32I-NEXT: srl a1, a1, a2
; RV32I-NEXT: ret
%1 = lshr i64 %a, %b
ret i64 %1
@@ -306,11 +324,20 @@
;
; RV32I-LABEL: sra:
; RV32I: # %bb.0:
-; RV32I-NEXT: addi sp, sp, -16
-; RV32I-NEXT: sw ra, 12(sp)
-; RV32I-NEXT: call __ashrdi3
-; RV32I-NEXT: lw ra, 12(sp)
-; RV32I-NEXT: addi sp, sp, 16
+; RV32I-NEXT: addi a3, a2, -32
+; RV32I-NEXT: bltz a3, .LBB16_2
+; RV32I-NEXT: # %bb.1:
+; RV32I-NEXT: sra a0, a1, a3
+; RV32I-NEXT: srai a1, a1, 31
+; RV32I-NEXT: ret
+; RV32I-NEXT: .LBB16_2:
+; RV32I-NEXT: addi a3, zero, 31
+; RV32I-NEXT: sub a3, a3, a2
+; RV32I-NEXT: slli a4, a1, 1
+; RV32I-NEXT: sll a3, a4, a3
+; RV32I-NEXT: srl a0, a0, a2
+; RV32I-NEXT: or a0, a0, a3
+; RV32I-NEXT: sra a1, a1, a2
; RV32I-NEXT: ret
%1 = ashr i64 %a, %b
ret i64 %1
diff --git a/test/CodeGen/RISCV/shifts.ll b/test/CodeGen/RISCV/shifts.ll
index 4aa66b0..80cf136 100644
--- a/test/CodeGen/RISCV/shifts.ll
+++ b/test/CodeGen/RISCV/shifts.ll
@@ -1,6 +1,8 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=riscv32 -verify-machineinstrs < %s \
; RUN: | FileCheck %s -check-prefix=RV32I
+; RUN: llc -mtriple=riscv64 -verify-machineinstrs < %s \
+; RUN: | FileCheck %s -check-prefix=RV64I
; Basic shift support is tested as part of ALU.ll. This file ensures that
; shifts which may not be supported natively are lowered properly.
@@ -8,12 +10,44 @@
define i64 @lshr64(i64 %a, i64 %b) nounwind {
; RV32I-LABEL: lshr64:
; RV32I: # %bb.0:
+; RV32I-NEXT: addi a3, a2, -32
+; RV32I-NEXT: bltz a3, .LBB0_2
+; RV32I-NEXT: # %bb.1:
+; RV32I-NEXT: srl a0, a1, a3
+; RV32I-NEXT: mv a1, zero
+; RV32I-NEXT: ret
+; RV32I-NEXT: .LBB0_2:
+; RV32I-NEXT: addi a3, zero, 31
+; RV32I-NEXT: sub a3, a3, a2
+; RV32I-NEXT: slli a4, a1, 1
+; RV32I-NEXT: sll a3, a4, a3
+; RV32I-NEXT: srl a0, a0, a2
+; RV32I-NEXT: or a0, a0, a3
+; RV32I-NEXT: srl a1, a1, a2
+; RV32I-NEXT: ret
+;
+; RV64I-LABEL: lshr64:
+; RV64I: # %bb.0:
+; RV64I-NEXT: srl a0, a0, a1
+; RV64I-NEXT: ret
+ %1 = lshr i64 %a, %b
+ ret i64 %1
+}
+
+define i64 @lshr64_minsize(i64 %a, i64 %b) minsize nounwind {
+; RV32I-LABEL: lshr64_minsize:
+; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp)
; RV32I-NEXT: call __lshrdi3
; RV32I-NEXT: lw ra, 12(sp)
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
+;
+; RV64I-LABEL: lshr64_minsize:
+; RV64I: # %bb.0:
+; RV64I-NEXT: srl a0, a0, a1
+; RV64I-NEXT: ret
%1 = lshr i64 %a, %b
ret i64 %1
}
@@ -21,12 +55,44 @@
define i64 @ashr64(i64 %a, i64 %b) nounwind {
; RV32I-LABEL: ashr64:
; RV32I: # %bb.0:
+; RV32I-NEXT: addi a3, a2, -32
+; RV32I-NEXT: bltz a3, .LBB2_2
+; RV32I-NEXT: # %bb.1:
+; RV32I-NEXT: sra a0, a1, a3
+; RV32I-NEXT: srai a1, a1, 31
+; RV32I-NEXT: ret
+; RV32I-NEXT: .LBB2_2:
+; RV32I-NEXT: addi a3, zero, 31
+; RV32I-NEXT: sub a3, a3, a2
+; RV32I-NEXT: slli a4, a1, 1
+; RV32I-NEXT: sll a3, a4, a3
+; RV32I-NEXT: srl a0, a0, a2
+; RV32I-NEXT: or a0, a0, a3
+; RV32I-NEXT: sra a1, a1, a2
+; RV32I-NEXT: ret
+;
+; RV64I-LABEL: ashr64:
+; RV64I: # %bb.0:
+; RV64I-NEXT: sra a0, a0, a1
+; RV64I-NEXT: ret
+ %1 = ashr i64 %a, %b
+ ret i64 %1
+}
+
+define i64 @ashr64_minsize(i64 %a, i64 %b) minsize nounwind {
+; RV32I-LABEL: ashr64_minsize:
+; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp)
; RV32I-NEXT: call __ashrdi3
; RV32I-NEXT: lw ra, 12(sp)
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
+;
+; RV64I-LABEL: ashr64_minsize:
+; RV64I: # %bb.0:
+; RV64I-NEXT: sra a0, a0, a1
+; RV64I-NEXT: ret
%1 = ashr i64 %a, %b
ret i64 %1
}
@@ -34,12 +100,203 @@
define i64 @shl64(i64 %a, i64 %b) nounwind {
; RV32I-LABEL: shl64:
; RV32I: # %bb.0:
+; RV32I-NEXT: addi a3, a2, -32
+; RV32I-NEXT: bltz a3, .LBB4_2
+; RV32I-NEXT: # %bb.1:
+; RV32I-NEXT: sll a1, a0, a3
+; RV32I-NEXT: mv a0, zero
+; RV32I-NEXT: ret
+; RV32I-NEXT: .LBB4_2:
+; RV32I-NEXT: addi a3, zero, 31
+; RV32I-NEXT: sub a3, a3, a2
+; RV32I-NEXT: srli a4, a0, 1
+; RV32I-NEXT: srl a3, a4, a3
+; RV32I-NEXT: sll a1, a1, a2
+; RV32I-NEXT: or a1, a1, a3
+; RV32I-NEXT: sll a0, a0, a2
+; RV32I-NEXT: ret
+;
+; RV64I-LABEL: shl64:
+; RV64I: # %bb.0:
+; RV64I-NEXT: sll a0, a0, a1
+; RV64I-NEXT: ret
+ %1 = shl i64 %a, %b
+ ret i64 %1
+}
+
+define i64 @shl64_minsize(i64 %a, i64 %b) minsize nounwind {
+; RV32I-LABEL: shl64_minsize:
+; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp)
; RV32I-NEXT: call __ashldi3
; RV32I-NEXT: lw ra, 12(sp)
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: ret
+;
+; RV64I-LABEL: shl64_minsize:
+; RV64I: # %bb.0:
+; RV64I-NEXT: sll a0, a0, a1
+; RV64I-NEXT: ret
%1 = shl i64 %a, %b
ret i64 %1
}
+
+define i128 @lshr128(i128 %a, i128 %b) nounwind {
+; RV32I-LABEL: lshr128:
+; RV32I: # %bb.0:
+; RV32I-NEXT: addi sp, sp, -48
+; RV32I-NEXT: sw ra, 44(sp)
+; RV32I-NEXT: sw s0, 40(sp)
+; RV32I-NEXT: mv s0, a0
+; RV32I-NEXT: lw a0, 12(a1)
+; RV32I-NEXT: sw a0, 20(sp)
+; RV32I-NEXT: lw a0, 8(a1)
+; RV32I-NEXT: sw a0, 16(sp)
+; RV32I-NEXT: lw a0, 4(a1)
+; RV32I-NEXT: sw a0, 12(sp)
+; RV32I-NEXT: lw a0, 0(a1)
+; RV32I-NEXT: sw a0, 8(sp)
+; RV32I-NEXT: lw a2, 0(a2)
+; RV32I-NEXT: addi a0, sp, 24
+; RV32I-NEXT: addi a1, sp, 8
+; RV32I-NEXT: call __lshrti3
+; RV32I-NEXT: lw a0, 36(sp)
+; RV32I-NEXT: sw a0, 12(s0)
+; RV32I-NEXT: lw a0, 32(sp)
+; RV32I-NEXT: sw a0, 8(s0)
+; RV32I-NEXT: lw a0, 28(sp)
+; RV32I-NEXT: sw a0, 4(s0)
+; RV32I-NEXT: lw a0, 24(sp)
+; RV32I-NEXT: sw a0, 0(s0)
+; RV32I-NEXT: lw s0, 40(sp)
+; RV32I-NEXT: lw ra, 44(sp)
+; RV32I-NEXT: addi sp, sp, 48
+; RV32I-NEXT: ret
+;
+; RV64I-LABEL: lshr128:
+; RV64I: # %bb.0:
+; RV64I-NEXT: addi a3, a2, -64
+; RV64I-NEXT: bltz a3, .LBB6_2
+; RV64I-NEXT: # %bb.1:
+; RV64I-NEXT: srl a0, a1, a3
+; RV64I-NEXT: mv a1, zero
+; RV64I-NEXT: ret
+; RV64I-NEXT: .LBB6_2:
+; RV64I-NEXT: addi a3, zero, 63
+; RV64I-NEXT: sub a3, a3, a2
+; RV64I-NEXT: slli a4, a1, 1
+; RV64I-NEXT: sll a3, a4, a3
+; RV64I-NEXT: srl a0, a0, a2
+; RV64I-NEXT: or a0, a0, a3
+; RV64I-NEXT: srl a1, a1, a2
+; RV64I-NEXT: ret
+ %1 = lshr i128 %a, %b
+ ret i128 %1
+}
+
+define i128 @ashr128(i128 %a, i128 %b) nounwind {
+; RV32I-LABEL: ashr128:
+; RV32I: # %bb.0:
+; RV32I-NEXT: addi sp, sp, -48
+; RV32I-NEXT: sw ra, 44(sp)
+; RV32I-NEXT: sw s0, 40(sp)
+; RV32I-NEXT: mv s0, a0
+; RV32I-NEXT: lw a0, 12(a1)
+; RV32I-NEXT: sw a0, 20(sp)
+; RV32I-NEXT: lw a0, 8(a1)
+; RV32I-NEXT: sw a0, 16(sp)
+; RV32I-NEXT: lw a0, 4(a1)
+; RV32I-NEXT: sw a0, 12(sp)
+; RV32I-NEXT: lw a0, 0(a1)
+; RV32I-NEXT: sw a0, 8(sp)
+; RV32I-NEXT: lw a2, 0(a2)
+; RV32I-NEXT: addi a0, sp, 24
+; RV32I-NEXT: addi a1, sp, 8
+; RV32I-NEXT: call __ashrti3
+; RV32I-NEXT: lw a0, 36(sp)
+; RV32I-NEXT: sw a0, 12(s0)
+; RV32I-NEXT: lw a0, 32(sp)
+; RV32I-NEXT: sw a0, 8(s0)
+; RV32I-NEXT: lw a0, 28(sp)
+; RV32I-NEXT: sw a0, 4(s0)
+; RV32I-NEXT: lw a0, 24(sp)
+; RV32I-NEXT: sw a0, 0(s0)
+; RV32I-NEXT: lw s0, 40(sp)
+; RV32I-NEXT: lw ra, 44(sp)
+; RV32I-NEXT: addi sp, sp, 48
+; RV32I-NEXT: ret
+;
+; RV64I-LABEL: ashr128:
+; RV64I: # %bb.0:
+; RV64I-NEXT: addi a3, a2, -64
+; RV64I-NEXT: bltz a3, .LBB7_2
+; RV64I-NEXT: # %bb.1:
+; RV64I-NEXT: sra a0, a1, a3
+; RV64I-NEXT: srai a1, a1, 63
+; RV64I-NEXT: ret
+; RV64I-NEXT: .LBB7_2:
+; RV64I-NEXT: addi a3, zero, 63
+; RV64I-NEXT: sub a3, a3, a2
+; RV64I-NEXT: slli a4, a1, 1
+; RV64I-NEXT: sll a3, a4, a3
+; RV64I-NEXT: srl a0, a0, a2
+; RV64I-NEXT: or a0, a0, a3
+; RV64I-NEXT: sra a1, a1, a2
+; RV64I-NEXT: ret
+ %1 = ashr i128 %a, %b
+ ret i128 %1
+}
+
+define i128 @shl128(i128 %a, i128 %b) nounwind {
+; RV32I-LABEL: shl128:
+; RV32I: # %bb.0:
+; RV32I-NEXT: addi sp, sp, -48
+; RV32I-NEXT: sw ra, 44(sp)
+; RV32I-NEXT: sw s0, 40(sp)
+; RV32I-NEXT: mv s0, a0
+; RV32I-NEXT: lw a0, 12(a1)
+; RV32I-NEXT: sw a0, 20(sp)
+; RV32I-NEXT: lw a0, 8(a1)
+; RV32I-NEXT: sw a0, 16(sp)
+; RV32I-NEXT: lw a0, 4(a1)
+; RV32I-NEXT: sw a0, 12(sp)
+; RV32I-NEXT: lw a0, 0(a1)
+; RV32I-NEXT: sw a0, 8(sp)
+; RV32I-NEXT: lw a2, 0(a2)
+; RV32I-NEXT: addi a0, sp, 24
+; RV32I-NEXT: addi a1, sp, 8
+; RV32I-NEXT: call __ashlti3
+; RV32I-NEXT: lw a0, 36(sp)
+; RV32I-NEXT: sw a0, 12(s0)
+; RV32I-NEXT: lw a0, 32(sp)
+; RV32I-NEXT: sw a0, 8(s0)
+; RV32I-NEXT: lw a0, 28(sp)
+; RV32I-NEXT: sw a0, 4(s0)
+; RV32I-NEXT: lw a0, 24(sp)
+; RV32I-NEXT: sw a0, 0(s0)
+; RV32I-NEXT: lw s0, 40(sp)
+; RV32I-NEXT: lw ra, 44(sp)
+; RV32I-NEXT: addi sp, sp, 48
+; RV32I-NEXT: ret
+;
+; RV64I-LABEL: shl128:
+; RV64I: # %bb.0:
+; RV64I-NEXT: addi a3, a2, -64
+; RV64I-NEXT: bltz a3, .LBB8_2
+; RV64I-NEXT: # %bb.1:
+; RV64I-NEXT: sll a1, a0, a3
+; RV64I-NEXT: mv a0, zero
+; RV64I-NEXT: ret
+; RV64I-NEXT: .LBB8_2:
+; RV64I-NEXT: addi a3, zero, 63
+; RV64I-NEXT: sub a3, a3, a2
+; RV64I-NEXT: srli a4, a0, 1
+; RV64I-NEXT: srl a3, a4, a3
+; RV64I-NEXT: sll a1, a1, a2
+; RV64I-NEXT: or a1, a1, a3
+; RV64I-NEXT: sll a0, a0, a2
+; RV64I-NEXT: ret
+ %1 = shl i128 %a, %b
+ ret i128 %1
+}
