[AVR] Fix incorrect operands of pseudo instruction 'ROLBRd'

Fixes https://github.com/llvm/llvm-project/issues/63098

Reviewed by: benshi001

Differential Revision: https://reviews.llvm.org/D152063

diff --git a/llvm/lib/Target/AVR/AVRExpandPseudoInsts.cpp b/llvm/lib/Target/AVR/AVRExpandPseudoInsts.cpp
index 5b3bb9e..2f991ae 100644 (file)
--- a/llvm/lib/Target/AVR/AVRExpandPseudoInsts.cpp
+++ b/llvm/lib/Target/AVR/AVRExpandPseudoInsts.cpp
@@ -1468,10 +1468,12 @@ bool AVRExpandPseudo::expand<AVR::ROLBRd>(Block &MBB, BlockIt MBBI) {
   // multiple registers, but when we actually need to rotate stuff, we have
   // to explicitly add the carry bit.
 
+  const AVRSubtarget &STI = MBB.getParent()->getSubtarget<AVRSubtarget>();
+
   MachineInstr &MI = *MBBI;
   unsigned OpShift, OpCarry;
   Register DstReg = MI.getOperand(0).getReg();
-  Register ZeroReg = MI.getOperand(2).getReg();
+  Register ZeroReg = STI.getZeroRegister();
   bool DstIsDead = MI.getOperand(0).isDead();
   bool DstIsKill = MI.getOperand(1).isKill();
   OpShift = AVR::ADDRdRr;

diff --git a/llvm/lib/Target/AVR/AVRISelLowering.cpp b/llvm/lib/Target/AVR/AVRISelLowering.cpp
index f2bbff4..5d7d08a 100644 (file)
--- a/llvm/lib/Target/AVR/AVRISelLowering.cpp
+++ b/llvm/lib/Target/AVR/AVRISelLowering.cpp
@@ -1751,7 +1751,6 @@ MachineBasicBlock *AVRTargetLowering::insertShift(MachineInstr &MI,
   unsigned Opc;
   const TargetRegisterClass *RC;
   bool HasRepeatedOperand = false;
-  bool HasZeroOperand = false;
   MachineFunction *F = BB->getParent();
   MachineRegisterInfo &RI = F->getRegInfo();
   const TargetInstrInfo &TII = *Subtarget.getInstrInfo();
@@ -1788,7 +1787,6 @@ MachineBasicBlock *AVRTargetLowering::insertShift(MachineInstr &MI,
   case AVR::Rol8:
     Opc = AVR::ROLBRd;
     RC = &AVR::GPR8RegClass;
-    HasZeroOperand = true;
     break;
   case AVR::Rol16:
     Opc = AVR::ROLWRd;
@@ -1850,8 +1848,6 @@ MachineBasicBlock *AVRTargetLowering::insertShift(MachineInstr &MI,
   auto ShiftMI = BuildMI(LoopBB, dl, TII.get(Opc), ShiftReg2).addReg(ShiftReg);
   if (HasRepeatedOperand)
     ShiftMI.addReg(ShiftReg);
-  if (HasZeroOperand)
-    ShiftMI.addReg(Subtarget.getZeroRegister());
 
   // CheckBB:
   // ShiftReg = phi [%SrcReg, BB], [%ShiftReg2, LoopBB]

diff --git a/llvm/lib/Target/AVR/AVRInstrInfo.td b/llvm/lib/Target/AVR/AVRInstrInfo.td
index 0b35a95..d0e7573 100644 (file)
--- a/llvm/lib/Target/AVR/AVRInstrInfo.td
+++ b/llvm/lib/Target/AVR/AVRInstrInfo.td
@@ -2029,12 +2029,15 @@ let Constraints = "$src = $rd", Defs = [SREG] in {
   def ASRWLoRd : Pseudo<(outs DREGS:$rd), (ins DREGS:$src), "asrwlo\t$rd",
                         [(set i16:$rd, (AVRasrlo i16:$src)), (implicit SREG)]>;
 
-  let hasSideEffects=0 in
   def ROLBRd : Pseudo<(outs GPR8
                        : $rd),
-                      (ins GPR8:$src, GPR8:$zero),
+                      (ins GPR8
+                       : $src),
                       "rolb\t$rd",
-                      []>;
+                      [(set i8
+                        : $rd, (AVRrol i8
+                                : $src)),
+                       (implicit SREG)]>;
 
   def RORBRd : Pseudo<(outs GPR8
                        : $rd),

diff --git a/llvm/test/CodeGen/AVR/pseudo/ROLBrd.mir b/llvm/test/CodeGen/AVR/pseudo/ROLBrd.mir
index bd3b5b7..023120b 100644 (file)
--- a/llvm/test/CodeGen/AVR/pseudo/ROLBrd.mir
+++ b/llvm/test/CodeGen/AVR/pseudo/ROLBrd.mir
@@ -20,10 +20,5 @@ body: |
 
     ; CHECK:      $r14 = ADDRdRr killed $r14, killed $r14, implicit-def $sreg
     ; CHECK-NEXT: $r14 = ADCRdRr $r14, $r1, implicit-def dead $sreg, implicit killed $sreg
-    $r14 = ROLBRd $r14, $r1, implicit-def $sreg
-
-    ; avrtiny variant
-    ; CHECK:      $r14 = ADDRdRr killed $r14, killed $r14, implicit-def $sreg
-    ; CHECK-NEXT: $r14 = ADCRdRr $r14, $r17, implicit-def dead $sreg, implicit killed $sreg
-    $r14 = ROLBRd $r14, $r17, implicit-def $sreg
+    $r14 = ROLBRd $r14, implicit-def $sreg
 ...

diff --git a/llvm/test/CodeGen/AVR/rotate.ll b/llvm/test/CodeGen/AVR/rotate.ll
new file mode 100644 (file)
index 0000000..100f4aa
--- /dev/null
+++ b/llvm/test/CodeGen/AVR/rotate.ll
@@ -0,0 +1,230 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 2
+; RUN: llc < %s -mtriple=avr | FileCheck %s
+
+define i8 @rotl8_1(i8 %x) {
+; CHECK-LABEL: rotl8_1:
+; CHECK:       ; %bb.0: ; %start
+; CHECK-NEXT:    lsl r24
+; CHECK-NEXT:    adc r24, r1
+; CHECK-NEXT:    ret
+start:
+  %0 = call i8 @llvm.fshl.i8(i8 %x, i8 %x, i8 1)
+  ret i8 %0
+}
+
+define i8 @rotl8_3(i8 %x) {
+; CHECK-LABEL: rotl8_3:
+; CHECK:       ; %bb.0: ; %start
+; CHECK-NEXT:    lsl r24
+; CHECK-NEXT:    adc r24, r1
+; CHECK-NEXT:    lsl r24
+; CHECK-NEXT:    adc r24, r1
+; CHECK-NEXT:    lsl r24
+; CHECK-NEXT:    adc r24, r1
+; CHECK-NEXT:    ret
+start:
+  %0 = call i8 @llvm.fshl.i8(i8 %x, i8 %x, i8 3)
+  ret i8 %0
+}
+
+define i8 @rotl8_dyn(i8 %x, i8 %y) {
+; CHECK-LABEL: rotl8_dyn:
+; CHECK:       ; %bb.0: ; %start
+; CHECK-NEXT:    andi r22, 7
+; CHECK-NEXT:    dec r22
+; CHECK-NEXT:    brmi .LBB2_2
+; CHECK-NEXT:  .LBB2_1: ; %start
+; CHECK-NEXT:    ; =>This Inner Loop Header: Depth=1
+; CHECK-NEXT:    lsl r24
+; CHECK-NEXT:    adc r24, r1
+; CHECK-NEXT:    dec r22
+; CHECK-NEXT:    brpl .LBB2_1
+; CHECK-NEXT:  .LBB2_2: ; %start
+; CHECK-NEXT:    ret
+start:
+  %0 = call i8 @llvm.fshl.i8(i8 %x, i8 %x, i8 %y)
+  ret i8 %0
+}
+
+define i8 @rotr8_1(i8 %x) {
+; CHECK-LABEL: rotr8_1:
+; CHECK:       ; %bb.0: ; %start
+; CHECK-NEXT:    bst r24, 0
+; CHECK-NEXT:    ror r24
+; CHECK-NEXT:    bld r24, 7
+; CHECK-NEXT:    ret
+start:
+  %0 = call i8 @llvm.fshr.i8(i8 %x, i8 %x, i8 1)
+  ret i8 %0
+}
+
+define i8 @rotr8_3(i8 %x) {
+; CHECK-LABEL: rotr8_3:
+; CHECK:       ; %bb.0: ; %start
+; CHECK-NEXT:    bst r24, 0
+; CHECK-NEXT:    ror r24
+; CHECK-NEXT:    bld r24, 7
+; CHECK-NEXT:    bst r24, 0
+; CHECK-NEXT:    ror r24
+; CHECK-NEXT:    bld r24, 7
+; CHECK-NEXT:    bst r24, 0
+; CHECK-NEXT:    ror r24
+; CHECK-NEXT:    bld r24, 7
+; CHECK-NEXT:    ret
+start:
+  %0 = call i8 @llvm.fshr.i8(i8 %x, i8 %x, i8 3)
+  ret i8 %0
+}
+
+define i8 @rotr8_dyn(i8 %x, i8 %y) {
+; CHECK-LABEL: rotr8_dyn:
+; CHECK:       ; %bb.0: ; %start
+; CHECK-NEXT:    andi r22, 7
+; CHECK-NEXT:    dec r22
+; CHECK-NEXT:    brmi .LBB5_2
+; CHECK-NEXT:  .LBB5_1: ; %start
+; CHECK-NEXT:    ; =>This Inner Loop Header: Depth=1
+; CHECK-NEXT:    bst r24, 0
+; CHECK-NEXT:    ror r24
+; CHECK-NEXT:    bld r24, 7
+; CHECK-NEXT:    dec r22
+; CHECK-NEXT:    brpl .LBB5_1
+; CHECK-NEXT:  .LBB5_2: ; %start
+; CHECK-NEXT:    ret
+start:
+  %0 = call i8 @llvm.fshr.i8(i8 %x, i8 %x, i8 %y)
+  ret i8 %0
+}
+
+define i16 @rotl16(i16 %x) {
+; CHECK-LABEL: rotl16:
+; CHECK:       ; %bb.0: ; %start
+; CHECK-NEXT:    mov r18, r24
+; CHECK-NEXT:    mov r19, r25
+; CHECK-NEXT:    lsl r18
+; CHECK-NEXT:    rol r19
+; CHECK-NEXT:    lsl r18
+; CHECK-NEXT:    rol r19
+; CHECK-NEXT:    mov r24, r25
+; CHECK-NEXT:    swap r24
+; CHECK-NEXT:    andi r24, 15
+; CHECK-NEXT:    clr r25
+; CHECK-NEXT:    lsr r24
+; CHECK-NEXT:    lsr r24
+; CHECK-NEXT:    or r24, r18
+; CHECK-NEXT:    or r25, r19
+; CHECK-NEXT:    ret
+start:
+  %0 = call i16 @llvm.fshl.i16(i16 %x, i16 %x, i16 2)
+  ret i16 %0
+}
+
+define i16 @rotr16(i16 %x) {
+; CHECK-LABEL: rotr16:
+; CHECK:       ; %bb.0: ; %start
+; CHECK-NEXT:    mov r18, r24
+; CHECK-NEXT:    mov r19, r25
+; CHECK-NEXT:    lsr r19
+; CHECK-NEXT:    ror r18
+; CHECK-NEXT:    lsr r19
+; CHECK-NEXT:    ror r18
+; CHECK-NEXT:    mov r25, r24
+; CHECK-NEXT:    swap r25
+; CHECK-NEXT:    andi r25, 240
+; CHECK-NEXT:    clr r24
+; CHECK-NEXT:    lsl r25
+; CHECK-NEXT:    lsl r25
+; CHECK-NEXT:    or r24, r18
+; CHECK-NEXT:    or r25, r19
+; CHECK-NEXT:    ret
+start:
+  %0 = call i16 @llvm.fshr.i16(i16 %x, i16 %x, i16 2)
+  ret i16 %0
+}
+
+define i32 @rotl32(i32 %x) {
+; CHECK-LABEL: rotl32:
+; CHECK:       ; %bb.0: ; %start
+; CHECK-NEXT:    mov r20, r22
+; CHECK-NEXT:    mov r21, r23
+; CHECK-NEXT:    lsl r20
+; CHECK-NEXT:    rol r21
+; CHECK-NEXT:    lsl r20
+; CHECK-NEXT:    rol r21
+; CHECK-NEXT:    mov r18, r24
+; CHECK-NEXT:    mov r19, r25
+; CHECK-NEXT:    mov r18, r19
+; CHECK-NEXT:    swap r18
+; CHECK-NEXT:    andi r18, 15
+; CHECK-NEXT:    clr r19
+; CHECK-NEXT:    lsr r18
+; CHECK-NEXT:    lsr r18
+; CHECK-NEXT:    or r18, r20
+; CHECK-NEXT:    or r19, r21
+; CHECK-NEXT:    lsl r24
+; CHECK-NEXT:    rol r25
+; CHECK-NEXT:    lsl r24
+; CHECK-NEXT:    rol r25
+; CHECK-NEXT:    mov r22, r23
+; CHECK-NEXT:    swap r22
+; CHECK-NEXT:    andi r22, 15
+; CHECK-NEXT:    clr r23
+; CHECK-NEXT:    lsr r22
+; CHECK-NEXT:    lsr r22
+; CHECK-NEXT:    or r24, r22
+; CHECK-NEXT:    or r25, r23
+; CHECK-NEXT:    mov r22, r18
+; CHECK-NEXT:    mov r23, r19
+; CHECK-NEXT:    ret
+start:
+  %0 = call i32 @llvm.fshl.i32(i32 %x, i32 %x, i32 2)
+  ret i32 %0
+}
+
+define i32 @rotr32(i32 %x) {
+; CHECK-LABEL: rotr32:
+; CHECK:       ; %bb.0: ; %start
+; CHECK-NEXT:    mov r20, r22
+; CHECK-NEXT:    mov r21, r23
+; CHECK-NEXT:    lsr r21
+; CHECK-NEXT:    ror r20
+; CHECK-NEXT:    lsr r21
+; CHECK-NEXT:    ror r20
+; CHECK-NEXT:    mov r18, r24
+; CHECK-NEXT:    mov r19, r25
+; CHECK-NEXT:    mov r19, r18
+; CHECK-NEXT:    swap r19
+; CHECK-NEXT:    andi r19, 240
+; CHECK-NEXT:    clr r18
+; CHECK-NEXT:    lsl r19
+; CHECK-NEXT:    lsl r19
+; CHECK-NEXT:    or r18, r20
+; CHECK-NEXT:    or r19, r21
+; CHECK-NEXT:    lsr r25
+; CHECK-NEXT:    ror r24
+; CHECK-NEXT:    lsr r25
+; CHECK-NEXT:    ror r24
+; CHECK-NEXT:    mov r23, r22
+; CHECK-NEXT:    swap r23
+; CHECK-NEXT:    andi r23, 240
+; CHECK-NEXT:    clr r22
+; CHECK-NEXT:    lsl r23
+; CHECK-NEXT:    lsl r23
+; CHECK-NEXT:    or r24, r22
+; CHECK-NEXT:    or r25, r23
+; CHECK-NEXT:    mov r22, r18
+; CHECK-NEXT:    mov r23, r19
+; CHECK-NEXT:    ret
+start:
+  %0 = call i32 @llvm.fshr.i32(i32 %x, i32 %x, i32 2)
+  ret i32 %0
+}
+
+declare i8 @llvm.fshl.i8(i8, i8, i8)
+declare i8 @llvm.fshr.i8(i8, i8, i8)
+
+declare i16 @llvm.fshl.i16(i16, i16, i16)
+declare i16 @llvm.fshr.i16(i16, i16, i16)
+
+declare i32 @llvm.fshl.i32(i32, i32, i32)
+declare i32 @llvm.fshr.i32(i32, i32, i32)