[InlineCost] Don't add the soft float functional call cost for the fneg idiom, fsub -0.0, %x

[craig.topper]

Summary

Fneg can be implemented with an xor rather than a function call so we don't need to add the function call overhead. This was pointed out in D62699

[efriedma]

LGTM

llvm/lib/Analysis/InlineCost.cpp

1099

"it's"

llvm/lib/Analysis/InlineCost.cpp

 #include "llvm/IR/CallingConv.h"
 #include "llvm/IR/DataLayout.h"
 #include "llvm/IR/Dominators.h"
 #include "llvm/IR/GetElementPtrTypeIterator.h"
 #include "llvm/IR/GlobalAlias.h"
 #include "llvm/IR/InstVisitor.h"
 #include "llvm/IR/IntrinsicInst.h"
 #include "llvm/IR/Operator.h"
+#include "llvm/IR/PatternMatch.h"
 #include "llvm/Support/Debug.h"
 #include "llvm/Support/raw_ostream.h"
 
 using namespace llvm;
 
 #define DEBUG_TYPE "inline-cost"
 
 STATISTIC(NumCallsAnalyzed, "Number of call sites analyzed");
if (SimpleV)
     return true;
 
   // Disable any SROA on arguments to arbitrary, unsimplified binary operators.
   disableSROA(LHS);
   disableSROA(RHS);
 
   // If the instruction is floating point, and the target says this operation
   // is expensive, this may eventually become a library call. Treat the cost
-  // as such.
+  // as such. Unless its fneg which can be implemented with an xor.
+  using namespace llvm::PatternMatch;
   if (I.getType()->isFloatingPointTy() &&
-      TTI.getFPOpCost(I.getType()) == TargetTransformInfo::TCC_Expensive)
+      TTI.getFPOpCost(I.getType()) == TargetTransformInfo::TCC_Expensive &&
+      !match(&I, m_FNeg(m_Value())))
     addCost(InlineConstants::CallPenalty);
 
   return false;
 }
 
 bool CallAnalyzer::visitLoad(LoadInst &I) {
   Value *SROAArg;
   DenseMap<Value *, int>::iterator CostIt;

llvm/test/Transforms/Inline/ARM/inline-fp.ll

 ; RUN: opt -S -inline -mtriple=arm-eabi -pass-remarks=.* -pass-remarks-missed=.* < %s 2>&1 | FileCheck %s -check-prefix=NOFP
 ; RUN: opt -S -inline -mtriple=arm-eabi -mattr=+vfp2 -pass-remarks=.* -pass-remarks-missed=.* < %s 2>&1 | FileCheck %s -check-prefix=FULLFP
 ; RUN: opt -S -inline -mtriple=arm-eabi -mattr=+vfp2,-fp64 -pass-remarks=.* -pass-remarks-missed=.* < %s 2>&1 | FileCheck %s -check-prefix=SINGLEFP
 ; Make sure that soft float implementations are calculated as being more expensive
 ; to the inliner.
 
 ; NOFP-DAG: single not inlined into test_single because too costly to inline (cost=125, threshold=75)
 ; NOFP-DAG: single not inlined into test_single because too costly to inline (cost=125, threshold=75)
 ; NOFP-DAG: single_cheap inlined into test_single_cheap with (cost=-15, threshold=75)
 ; NOFP-DAG: single_cheap inlined into test_single_cheap with (cost=-15015, threshold=75)
 ; NOFP-DAG: double not inlined into test_double because too costly to inline (cost=125, threshold=75)
 ; NOFP-DAG: double not inlined into test_double because too costly to inline (cost=125, threshold=75)
 ; NOFP-DAG: single_force_soft not inlined into test_single_force_soft because too costly to inline (cost=125, threshold=75)
 ; NOFP-DAG: single_force_soft not inlined into test_single_force_soft because too costly to inline (cost=125, threshold=75)
+; NOFP-DAG: single_force_soft_fneg not inlined into test_single_force_soft_fneg because too costly to inline (cost=100, threshold=75)
+; NOFP-DAG: single_force_soft_fneg not inlined into test_single_force_soft_fneg because too costly to inline (cost=100, threshold=75)
 
 ; FULLFP-DAG: single inlined into test_single with (cost=0, threshold=75)
 ; FULLFP-DAG: single inlined into test_single with (cost=-15000, threshold=75)
 ; FULLFP-DAG: single_cheap inlined into test_single_cheap with (cost=-15, threshold=75)
 ; FULLFP-DAG: single_cheap inlined into test_single_cheap with (cost=-15015, threshold=75)
 ; FULLFP-DAG: double inlined into test_double with (cost=0, threshold=75)
 ; FULLFP-DAG: double inlined into test_double with (cost=-15000, threshold=75)
 ; FULLFP-DAG: single_force_soft not inlined into test_single_force_soft because too costly to inline (cost=125, threshold=75)
 ; FULLFP-DAG: single_force_soft not inlined into test_single_force_soft because too costly to inline (cost=125, threshold=75)
+; FULLFP-DAG: single_force_soft_fneg not inlined into test_single_force_soft_fneg because too costly to inline (cost=100, threshold=75)
+; FULLFP-DAG: single_force_soft_fneg not inlined into test_single_force_soft_fneg because too costly to inline (cost=100, threshold=75)
 
 ; SINGLEFP-DAG: single inlined into test_single with (cost=0, threshold=75)
 ; SINGLEFP-DAG: single inlined into test_single with (cost=-15000, threshold=75)
 ; SINGLEFP-DAG: single_cheap inlined into test_single_cheap with (cost=-15, threshold=75)
 ; SINGLEFP-DAG: single_cheap inlined into test_single_cheap with (cost=-15015, threshold=75)
 ; SINGLEFP-DAG: double not inlined into test_double because too costly to inline (cost=125, threshold=75)
 ; SINGLEFP-DAG: double not inlined into test_double because too costly to inline (cost=125, threshold=75)
 ; SINGLEFP-DAG: single_force_soft not inlined into test_single_force_soft because too costly to inline (cost=125, threshold=75)
 ; SINGLEFP-DAG: single_force_soft not inlined into test_single_force_soft because too costly to inline (cost=125, threshold=75)
+; SINGLEFP-DAG: single_force_soft_fneg not inlined into test_single_force_soft_fneg because too costly to inline (cost=100, threshold=75)
+; SINGLEFP-DAG: single_force_soft_fneg not inlined into test_single_force_soft_fneg because too costly to inline (cost=100, threshold=75)
 
 define i32 @test_single(i32 %a, i8 %b, i32 %c, i8 %d) #0 {
   %call = call float @single(i32 %a, i8 zeroext %b)
   %call2 = call float @single(i32 %c, i8 zeroext %d)
   ret i32 0
 }
 
 define i32 @test_single_cheap(i32 %a, i8 %b, i32 %c, i8 %d) #0 {

 }
 
 define i32 @test_single_force_soft(i32 %a, i8 %b, i32 %c, i8 %d) #1 {
   %call = call float @single_force_soft(i32 %a, i8 zeroext %b) #1
   %call2 = call float @single_force_soft(i32 %c, i8 zeroext %d) #1
   ret i32 0
 }
 
+define i32 @test_single_force_soft_fneg(i32 %a, i8 %b, i32 %c, i8 %d) #1 {
+  %call = call float @single_force_soft_fneg(i32 %a, i8 zeroext %b) #1
+  %call2 = call float @single_force_soft_fneg(i32 %c, i8 zeroext %d) #1
+  ret i32 0
+}
+
 define internal float @single(i32 %response, i8 zeroext %value1) #0 {
 entry:
   %conv = zext i8 %value1 to i32
   %sub = add nsw i32 %conv, -1
   %conv1 = sitofp i32 %sub to float
   %0 = tail call float @llvm.pow.f32(float 0x3FF028F5C0000000, float %conv1)
   %mul = fmul float %0, 2.620000e+03
   %conv2 = sitofp i32 %response to float
entry:
   %0 = tail call float @llvm.pow.f32(float 0x3FF028F5C0000000, float %conv1)
   %mul = fmul float %0, 2.620000e+03
   %conv2 = sitofp i32 %response to float
   %sub3 = fsub float %conv2, %mul
   %div = fdiv float %sub3, %mul
   ret float %div
 }
 
+define internal float @single_force_soft_fneg(i32 %response, i8 zeroext %value1) #1 {
+entry:
+  %conv = zext i8 %value1 to i32
+  %sub = add nsw i32 %conv, -1
+  %conv1 = sitofp i32 %sub to float
+  %0 = tail call float @llvm.pow.f32(float 0x3FF028F5C0000000, float %conv1)
+  %mul = fsub float -0.0, %0
+  %conv2 = sitofp i32 %response to float
+  %sub3 = fsub float %conv2, %mul
+  %div = fdiv float %sub3, %mul
+  ret float %div
+}
+
 declare float @llvm.pow.f32(float, float) optsize minsize
 declare double @llvm.pow.f64(double, double) optsize minsize
 
 attributes #0 = { optsize }
 attributes #1 = { optsize "use-soft-float"="true" "target-features"="+soft-float" }