[llvm][RISCV] Don't merge pseudo selects with stack adjustment instr in between

llvm/lib/Target/RISCV/RISCVISelLowering.cpp

@@ -22190,6 +22190,7 @@ static MachineBasicBlock *emitSelectPseudo(MachineInstr &MI,
   // - They are debug instructions. Otherwise,
   // - They do not have side-effects, do not access memory and their inputs do
   //   not depend on the results of the select pseudo-instructions.
+  // - They don't adjust stack.
   // The TrueV/FalseV operands of the selects cannot depend on the result of
   // previous selects in the sequence.
   // These conditions could be further relaxed. See the X86 target for a
@@ -22218,6 +22219,8 @@ static MachineBasicBlock *emitSelectPseudo(MachineInstr &MI,
   SelectDests.insert(MI.getOperand(0).getReg());
 
   MachineInstr *LastSelectPseudo = &MI;
+  const RISCVInstrInfo &TII = *Subtarget.getInstrInfo();
+
   for (auto E = BB->end(), SequenceMBBI = MachineBasicBlock::iterator(MI);
        SequenceMBBI != E; ++SequenceMBBI) {
     if (SequenceMBBI->isDebugInstr())
@@ -22237,15 +22240,16 @@ static MachineBasicBlock *emitSelectPseudo(MachineInstr &MI,
     }
     if (SequenceMBBI->hasUnmodeledSideEffects() ||
         SequenceMBBI->mayLoadOrStore() ||
-        SequenceMBBI->usesCustomInsertionHook())
+        SequenceMBBI->usesCustomInsertionHook() ||
+        TII.isFrameInstr(*SequenceMBBI) ||
+        SequenceMBBI->isStackAligningInlineAsm())
       break;
     if (llvm::any_of(SequenceMBBI->operands(), [&](MachineOperand &MO) {
           return MO.isReg() && MO.isUse() && SelectDests.count(MO.getReg());
         }))
       break;
   }
 
-  const RISCVInstrInfo &TII = *Subtarget.getInstrInfo();
   const BasicBlock *LLVM_BB = BB->getBasicBlock();
   DebugLoc DL = MI.getDebugLoc();
   MachineFunction::iterator I = ++BB->getIterator();

llvm/test/CodeGen/RISCV/select-pseudo-merge-with-stack-adj.ll

@@ -0,0 +1,64 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 6
+; RUN: llc %s -mtriple riscv32 -verify-machineinstrs -o - | FileCheck %s
+
+define i32 @test(i1 %arg_1, i32 %arg_2) {
+; CHECK-LABEL: test:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    addi sp, sp, -16
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    sw ra, 12(sp) # 4-byte Folded Spill
+; CHECK-NEXT:    sw s0, 8(sp) # 4-byte Folded Spill
+; CHECK-NEXT:    sw s1, 4(sp) # 4-byte Folded Spill
+; CHECK-NEXT:    .cfi_offset ra, -4
+; CHECK-NEXT:    .cfi_offset s0, -8
+; CHECK-NEXT:    .cfi_offset s1, -12
+; CHECK-NEXT:    andi s1, a0, 1
+; CHECK-NEXT:    mv a0, a1
+; CHECK-NEXT:    mv s0, a1
+; CHECK-NEXT:    bnez s1, .LBB0_2
+; CHECK-NEXT:  # %bb.1: # %entry
+; CHECK-NEXT:    li s0, 1
+; CHECK-NEXT:  .LBB0_2: # %entry
+; CHECK-NEXT:    li a1, 7
+; CHECK-NEXT:    call __udivsi3
+; CHECK-NEXT:    bnez s1, .LBB0_4
+; CHECK-NEXT:  # %bb.3: # %entry
+; CHECK-NEXT:    li a0, 3
+; CHECK-NEXT:  .LBB0_4: # %entry
+; CHECK-NEXT:    bnez s1, .LBB0_6
+; CHECK-NEXT:  # %bb.5: # %entry
+; CHECK-NEXT:    mv s0, a0
+; CHECK-NEXT:  .LBB0_6: # %entry
+; CHECK-NEXT:    li a0, 3
+; CHECK-NEXT:  .LBB0_7: # %body
+; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
+; CHECK-NEXT:    addi s0, s0, 4
+; CHECK-NEXT:    bltu a0, s0, .LBB0_7
+; CHECK-NEXT:  # %bb.8: # %exit
+; CHECK-NEXT:    mv a0, s0
+; CHECK-NEXT:    lw ra, 12(sp) # 4-byte Folded Reload
+; CHECK-NEXT:    lw s0, 8(sp) # 4-byte Folded Reload
+; CHECK-NEXT:    lw s1, 4(sp) # 4-byte Folded Reload
+; CHECK-NEXT:    .cfi_restore ra
+; CHECK-NEXT:    .cfi_restore s0
+; CHECK-NEXT:    .cfi_restore s1
+; CHECK-NEXT:    addi sp, sp, 16
+; CHECK-NEXT:    .cfi_def_cfa_offset 0
+; CHECK-NEXT:    ret
+entry:
+  %sel_1 = select i1 %arg_1, i32 %arg_2, i32 1
+  %div = udiv i32 %arg_2, 7
+  %cond_1 = icmp ugt i32 %div, %sel_1
+  %sel_2 = select i1 %arg_1, i32 %div, i32 3
+  %sel = select i1 %arg_1, i32 %sel_1, i32 %sel_2
+  br label %body
+
+body:
+  %res = phi i32 [ %sel, %entry ], [ %add_loop, %body ]
+  %add_loop = add i32 4, %res
+  %cond_2 = icmp ugt i32 %add_loop, 3
+  br i1 %cond_2, label %body, label %exit
+
+exit:
+  ret i32 %add_loop
+}