[X86][APX] Try to replace non-NF with NF instructions when optimizeCompareInstr (#130488)

https://godbolt.org/z/rWYdqnjjx

Author: phoebewang

llvm/lib/Target/X86/X86InstrInfo.cpp

@@ -5352,10 +5352,12 @@ bool X86InstrInfo::optimizeCompareInstr(MachineInstr &CmpInstr, Register SrcReg,
   MachineInstr *MI = nullptr;
   MachineInstr *Sub = nullptr;
   MachineInstr *Movr0Inst = nullptr;
+  SmallVector<std::pair<MachineInstr *, unsigned>, 4> InstsToUpdate;
   bool NoSignFlag = false;
   bool ClearsOverflowFlag = false;
   bool ShouldUpdateCC = false;
   bool IsSwapped = false;
+  bool HasNF = Subtarget.hasNF();
   unsigned OpNo = 0;
   X86::CondCode NewCC = X86::COND_INVALID;
   int64_t ImmDelta = 0;
@@ -5441,6 +5443,16 @@ bool X86InstrInfo::optimizeCompareInstr(MachineInstr &CmpInstr, Register SrcReg,
           continue;
         }
 
+        // Try to replace non-NF with NF instructions.
+        if (HasNF && Inst.registerDefIsDead(X86::EFLAGS, TRI)) {
+          unsigned NewOp = X86::getNFVariant(Inst.getOpcode());
+          if (!NewOp)
+            return false;
+
+          InstsToUpdate.push_back(std::make_pair(&Inst, NewOp));
+          continue;
+        }
+
         // Cannot do anything for any other EFLAG changes.
         return false;
       }
@@ -5637,6 +5649,12 @@ bool X86InstrInfo::optimizeCompareInstr(MachineInstr &CmpInstr, Register SrcReg,
       return false;
   }
 
+  // Replace non-NF with NF instructions.
+  for (auto &Inst : InstsToUpdate) {
+    Inst.first->setDesc(get(Inst.second));
+    Inst.first->removeOperand(Inst.first->getNumOperands() - 1);
+  }
+
   // Make sure Sub instruction defines EFLAGS and mark the def live.
   MachineOperand *FlagDef =
       Sub->findRegisterDefOperand(X86::EFLAGS, /*TRI=*/nullptr);

llvm/test/CodeGen/X86/apx/cf.ll

@@ -1,5 +1,5 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc < %s -mtriple=x86_64 -mattr=+cf,+avx512f -verify-machineinstrs | FileCheck %s
+; RUN: llc < %s -mtriple=x86_64 -mattr=+cf,+nf,+avx512f -verify-machineinstrs | FileCheck %s
 
 define void @basic(i32 %a, ptr %b, ptr %p, ptr %q) {
 ; CHECK-LABEL: basic:
@@ -125,7 +125,7 @@ entry:
   ret void
 }
 
-define void @single_cmp(i32 %a, i32 %b, ptr %c, ptr %d) #2 {
+define void @single_cmp(i32 %a, i32 %b, ptr %c, ptr %d) {
 ; CHECK-LABEL: single_cmp:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    cmpl %esi, %edi
@@ -139,3 +139,22 @@ entry:
   tail call void @llvm.masked.store.v1i16.p0(<1 x i16> %2, ptr %d, i32 2, <1 x i1> %1)
   ret void
 }
+
+define void @load_add_store(i32 %a, i32 %b, ptr %p) {
+; CHECK-LABEL: load_add_store:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    cmpl %esi, %edi
+; CHECK-NEXT:    cfcmovnew (%rdx), %ax
+; CHECK-NEXT:    {nf} incl %eax
+; CHECK-NEXT:    cfcmovnew %ax, (%rdx)
+; CHECK-NEXT:    retq
+entry:
+  %0 = icmp ne i32 %a, %b
+  %1 = insertelement <1 x i1> poison, i1 %0, i64 0
+  %2 = tail call <1 x i16> @llvm.masked.load.v1i16.p0(ptr %p, i32 2, <1 x i1> %1, <1 x i16> poison)
+  %3 = extractelement <1 x i16> %2, i64 0
+  %4 = add i16 %3, 1
+  %5 = insertelement <1 x i16> poison, i16 %4, i64 0
+  tail call void @llvm.masked.store.v1i16.p0(<1 x i16> %5, ptr %p, i32 2, <1 x i1> %1)
+  ret void
+}