[AArch64] Unfold adds when eliminating frame index with scalable offset

llvm/lib/Target/AArch64/AArch64InstrInfo.cpp

@@ -1920,6 +1920,11 @@ static bool canInstrSubstituteCmpInstr(MachineInstr &MI, MachineInstr &CmpInstr,
           CmpInstr.getOperand(2).getImm() == 0) &&
          "Caller guarantees that CmpInstr compares with constant 0");
 
+  // NZCV is not supported if the stack offset is scalable.
+  auto &ST = MI.getParent()->getParent()->getSubtarget<AArch64Subtarget>();
+  if ((ST.hasSVE() || ST.isStreaming()) && MI.getOperand(1).isFI())
+    return false;
+
   std::optional<UsedNZCV> NZVCUsed = examineCFlagsUse(MI, CmpInstr, TRI);
   if (!NZVCUsed || NZVCUsed->C)
     return false;

llvm/test/CodeGen/AArch64/pr157252.ll

@@ -0,0 +1,96 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
+; RUN: llc -mtriple=aarch64 < %s | FileCheck %s
+
+define void @i(ptr %ad, ptr %0) #0 {
+; CHECK-LABEL: i:
+; CHECK:       // %bb.0: // %entry
+; CHECK-NEXT:    str d11, [sp, #-48]! // 8-byte Folded Spill
+; CHECK-NEXT:    stp x29, x30, [sp, #16] // 16-byte Folded Spill
+; CHECK-NEXT:    add x29, sp, #16
+; CHECK-NEXT:    stp x28, x19, [sp, #32] // 16-byte Folded Spill
+; CHECK-NEXT:    sub sp, sp, #16
+; CHECK-NEXT:    addvl sp, sp, #-1
+; CHECK-NEXT:    .cfi_def_cfa w29, 32
+; CHECK-NEXT:    .cfi_offset w19, -8
+; CHECK-NEXT:    .cfi_offset w28, -16
+; CHECK-NEXT:    .cfi_offset w30, -24
+; CHECK-NEXT:    .cfi_offset w29, -32
+; CHECK-NEXT:    .cfi_offset b11, -48
+; CHECK-NEXT:    //APP
+; CHECK-NEXT:    //NO_APP
+; CHECK-NEXT:  // %bb.1: // %asm.fallthrough
+; CHECK-NEXT:  .LBB0_2: // Inline asm indirect target
+; CHECK-NEXT:    // %ah.preheader.preheader
+; CHECK-NEXT:    // Label of block must be emitted
+; CHECK-NEXT:    mov x8, #-35417 // =0xffffffffffff75a7
+; CHECK-NEXT:    mov x9, #35417 // =0x8a59
+; CHECK-NEXT:    mov w19, #1 // =0x1
+; CHECK-NEXT:    movk x8, #29436, lsl #16
+; CHECK-NEXT:    movk x9, #36099, lsl #16
+; CHECK-NEXT:    stp x1, x0, [sp] // 16-byte Folded Spill
+; CHECK-NEXT:    movk x8, #64591, lsl #32
+; CHECK-NEXT:    movk x9, #944, lsl #32
+; CHECK-NEXT:    index z0.d, x9, x8
+; CHECK-NEXT:    sub x8, x29, #16
+; CHECK-NEXT:    str z0, [x8, #-1, mul vl] // 16-byte Folded Spill
+; CHECK-NEXT:  .LBB0_3: // Inline asm indirect target
+; CHECK-NEXT:    // %ah
+; CHECK-NEXT:    // =>This Inner Loop Header: Depth=1
+; CHECK-NEXT:    // Label of block must be emitted
+; CHECK-NEXT:    sub x9, x29, #16
+; CHECK-NEXT:    ldr x8, [sp, #8] // 8-byte Folded Reload
+; CHECK-NEXT:    ldr z0, [x9, #-1, mul vl] // 16-byte Folded Reload
+; CHECK-NEXT:    str d0, [x8]
+; CHECK-NEXT:    movi v0.2d, #0000000000000000
+; CHECK-NEXT:    sub x8, x29, #16
+; CHECK-NEXT:    str z0, [x8, #-1, mul vl] // 16-byte Folded Spill
+; CHECK-NEXT:    //APP
+; CHECK-NEXT:    //NO_APP
+; CHECK-NEXT:    //APP
+; CHECK-NEXT:    //NO_APP
+; CHECK-NEXT:  // %bb.4: // %asm.fallthrough2
+; CHECK-NEXT:    // in Loop: Header=BB0_3 Depth=1
+; CHECK-NEXT:    bl g
+; CHECK-NEXT:    add x8, sp, #28
+; CHECK-NEXT:    addvl x8, x8, #1
+; CHECK-NEXT:    cmp x8, #0
+; CHECK-NEXT:    ldp x10, x8, [sp] // 16-byte Folded Reload
+; CHECK-NEXT:    cset w9, ne
+; CHECK-NEXT:    strb w19, [x10]
+; CHECK-NEXT:    str w9, [x8]
+; CHECK-NEXT:    //APP
+; CHECK-NEXT:    //NO_APP
+; CHECK-NEXT:    b .LBB0_3
+entry:
+  %aj = alloca i32, align 4
+  callbr void asm sideeffect "", "!i,!i"()
+          to label %asm.fallthrough [label %ah.preheader.preheader, label %ah.preheader.preheader]
+
+ah.preheader.preheader:                           ; preds = %entry, %entry
+  %conv = xor i8 0, 1
+  br label %ah
+
+asm.fallthrough:                                  ; preds = %entry
+  unreachable
+
+ah:                                               ; preds = %asm.fallthrough2, %asm.fallthrough2, %ah, %ah.preheader.preheader
+  %af.2 = phi <8 x i64> [ zeroinitializer, %asm.fallthrough2 ], [ <i64 4056814946905, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0, i64 0>, %ah.preheader.preheader ], [ zeroinitializer, %asm.fallthrough2 ], [ zeroinitializer, %ah ]
+  %vecext = extractelement <8 x i64> %af.2, i64 0
+  store i64 %vecext, ptr %ad, align 8
+  call void asm sideeffect "", "~{v11}"()
+  callbr void asm sideeffect "", "!i"()
+          to label %asm.fallthrough2 [label %ah]
+
+asm.fallthrough2:                                 ; preds = %ah
+  %call = call i32 @g()
+  store i8 %conv, ptr %0, align 1
+  %cmp = icmp ne ptr %aj, null
+  %conv3 = zext i1 %cmp to i32
+  store i32 %conv3, ptr %ad, align 4
+  callbr void asm sideeffect "", "!i"()
+          to label %ah [label %ah]
+}
+
+declare i32 @g(...)
+
+attributes #0 = { "frame-pointer"="non-leaf" "target-features"="+sve" }