[X86][APX] Try to replace NDD with NF instructions when optimizeCompareInstr

https://godbolt.org/z/rWYdqnjjx

Author: phoebewang

llvm/lib/Target/X86/X86InstrInfo.cpp

@@ -5352,6 +5352,7 @@ bool X86InstrInfo::optimizeCompareInstr(MachineInstr &CmpInstr, Register SrcReg,
   MachineInstr *MI = nullptr;
   MachineInstr *Sub = nullptr;
   MachineInstr *Movr0Inst = nullptr;
+  SmallVector<MachineInstr *, 4> NDDInsts;
   bool NoSignFlag = false;
   bool ClearsOverflowFlag = false;
   bool ShouldUpdateCC = false;
@@ -5441,13 +5442,26 @@ bool X86InstrInfo::optimizeCompareInstr(MachineInstr &CmpInstr, Register SrcReg,
           continue;
         }
 
+        // Try to replace NDD with NF instructions.
+        if (Subtarget.hasNF() &&
+            X86II::hasNewDataDest(Inst.getDesc().TSFlags) &&
+            Inst.registerDefIsDead(X86::EFLAGS, TRI)) {
+          NDDInsts.push_back(&Inst);
+          continue;
+        }
+
         // Cannot do anything for any other EFLAG changes.
         return false;
       }
     }
 
-    if (MI || Sub)
+    if (MI || Sub) {
+      for (MachineInstr *NDD : NDDInsts) {
+        NDD->setDesc(get(X86::getNFVariant(NDD->getOpcode())));
+        NDD->removeOperand(NDD->getNumOperands() - 1);
+      }
       break;
+    }
 
     // Reached begin of basic block. Continue in predecessor if there is
     // exactly one.

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,+ndd,+avx512f -verify-machineinstrs | FileCheck %s
 
 define void @basic(i32 %a, ptr %b, ptr %p, ptr %q) {
 ; CHECK-LABEL: basic:
@@ -57,9 +57,8 @@ entry:
 define i64 @reduced_data_dependency(i64 %a, i64 %b, ptr %c) {
 ; CHECK-LABEL: reduced_data_dependency:
 ; CHECK:       # %bb.0: # %entry
-; CHECK-NEXT:    movq %rdi, %rcx
-; CHECK-NEXT:    subq %rsi, %rcx
-; CHECK-NEXT:    cfcmovnsq (%rdx), %rdi, %rax
+; CHECK-NEXT:    subq %rsi, %rdi, %rax
+; CHECK-NEXT:    cfcmovnsq (%rdx), %rdi, %rcx
 ; CHECK-NEXT:    addq %rcx, %rax
 ; CHECK-NEXT:    retq
 entry:
@@ -125,7 +124,7 @@ 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 +138,22 @@ 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} incw %ax
+; 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
+}