[FPEnv][InstSimplify] Fold fadd X, 0 ==> X, when we know X is not -0

[kpn]

Summary

Currently the fadd optimizations in InstSimplify don't know how to do this NoSignedZeros "X + 0.0 ==> X" fold when using the constrained intrinsics. This adds the support.

This review is derived from D106362 with some improvements from D107285 and is a follow-on to D111085.

[spatel]

llvm/test/Transforms/InstSimplify/strictfp-fadd.ll

303

Don't we want a test without nnan where exceptions are ignored but is not the default FP env?

Ie, this should fold?

%add = call nsz float @llvm.experimental.constrained.fadd.f32(float %a, float 0.0, metadata !"round.downward", metadata !"fpexcept.ignore") #0

[kpn]

llvm/test/Transforms/InstSimplify/strictfp-fadd.ll

303

Yes, that's a good idea. And, yes, I believe we do want this to fold. The "nsz" flag means (I think) that if "x" is zero the sign of "0 - 0" is insignificant. I think that's what that means, anyway.

[kpn]

As requested, add tests for rounding to negative infinity, exceptions ignored, no sized zeros fast math flag.

[spatel]

LGTM

llvm/lib/Analysis/InstructionSimplify.cpp

SimplifyFAddInst(Value *Op0, Value *Op1, FastMathFlags FMF,
   // fadd SNaN, -0.0 --> QNaN
   // fadd +0.0, -0.0 --> -0.0 (but only with round toward negative)
   if (canIgnoreSNaN(ExBehavior, FMF) &&
       (!canRoundingModeBe(Rounding, RoundingMode::TowardNegative) ||
        FMF.noSignedZeros()))
     if (match(Op1, m_NegZeroFP()))
       return Op0;
 
-  if (!isDefaultFPEnvironment(ExBehavior, Rounding))
-    return nullptr;
-
   // fadd X, 0 ==> X, when we know X is not -0
+  if (canIgnoreSNaN(ExBehavior, FMF))
     if (match(Op1, m_PosZeroFP()) &&
         (FMF.noSignedZeros() || CannotBeNegativeZero(Op0, Q.TLI)))
       return Op0;
 
+  if (!isDefaultFPEnvironment(ExBehavior, Rounding))
+    return nullptr;
+
   // With nnan: -X + X --> 0.0 (and commuted variant)
   // We don't have to explicitly exclude infinities (ninf): INF + -INF == NaN.
   // Negative zeros are allowed because we always end up with positive zero:
   // X = -0.0: (-0.0 - (-0.0)) + (-0.0) == ( 0.0) + (-0.0) == 0.0
   // X = -0.0: ( 0.0 - (-0.0)) + (-0.0) == ( 0.0) + (-0.0) == 0.0
   // X =  0.0: (-0.0 - ( 0.0)) + ( 0.0) == (-0.0) + ( 0.0) == 0.0
   // X =  0.0: ( 0.0 - ( 0.0)) + ( 0.0) == ( 0.0) + ( 0.0) == 0.0
   if (FMF.noNaNs()) {

llvm/test/Transforms/InstSimplify/strictfp-fadd.ll

 define <2 x float> @fold_fadd_vec_nsz_x_0_defaultenv(<2 x float> %a) #0 {
 ; CHECK-LABEL: @fold_fadd_vec_nsz_x_0_defaultenv(
 ; CHECK-NEXT:    ret <2 x float> [[A:%.*]]
 ;
   %add = call nsz <2 x float> @llvm.experimental.constrained.fadd.v2f32(<2 x float> %a, <2 x float> zeroinitializer, metadata !"round.tonearest", metadata !"fpexcept.ignore") #0
   ret <2 x float> %add
 }
 
+define float @fold_fadd_nsz_x_0_neginf(float %a) #0 {
+; CHECK-LABEL: @fold_fadd_nsz_x_0_neginf(
+; CHECK-NEXT:    ret float [[A:%.*]]
+;
+  %add = call nsz float @llvm.experimental.constrained.fadd.f32(float %a, float 0.0, metadata !"round.downward", metadata !"fpexcept.ignore") #0
+  ret float %add
+}
+
+define <2 x float> @fold_fadd_vec_nsz_x_0_neginf(<2 x float> %a) #0 {
+; CHECK-LABEL: @fold_fadd_vec_nsz_x_0_neginf(
+; CHECK-NEXT:    ret <2 x float> [[A:%.*]]
+;
+  %add = call nsz <2 x float> @llvm.experimental.constrained.fadd.v2f32(<2 x float> %a, <2 x float> zeroinitializer, metadata !"round.downward", metadata !"fpexcept.ignore") #0
+  ret <2 x float> %add
+}
+
 define float @fold_fadd_nsz_x_0_ebmaytrap(float %a) #0 {
 ; CHECK-LABEL: @fold_fadd_nsz_x_0_ebmaytrap(
 ; CHECK-NEXT:    [[ADD:%.*]] = call nsz float @llvm.experimental.constrained.fadd.f32(float [[A:%.*]], float 0.000000e+00, metadata !"round.tonearest", metadata !"fpexcept.maytrap") #[[ATTR0]]
 ; CHECK-NEXT:    ret float [[ADD]]
 ;
   %add = call nsz float @llvm.experimental.constrained.fadd.f32(float %a, float 0.0, metadata !"round.tonearest", metadata !"fpexcept.maytrap") #0
   ret float %add
 }
 
 define <2 x float> @fold_fadd_vec_nsz_x_0_ebmaytrap(<2 x float> %a) #0 {
 ; CHECK-LABEL: @fold_fadd_vec_nsz_x_0_ebmaytrap(
 ; CHECK-NEXT:    [[ADD:%.*]] = call nsz <2 x float> @llvm.experimental.constrained.fadd.v2f32(<2 x float> [[A:%.*]], <2 x float> zeroinitializer, metadata !"round.tonearest", metadata !"fpexcept.maytrap") #[[ATTR0]]
 ; CHECK-NEXT:    ret <2 x float> [[ADD]]
 ;
   %add = call nsz <2 x float> @llvm.experimental.constrained.fadd.v2f32(<2 x float> %a, <2 x float> zeroinitializer, metadata !"round.tonearest", metadata !"fpexcept.maytrap") #0
   ret <2 x float> %add
 }
 
 define float @fold_fadd_nnan_nsz_x_0_ebmaytrap(float %a) #0 {
 ; CHECK-LABEL: @fold_fadd_nnan_nsz_x_0_ebmaytrap(
-; CHECK-NEXT:    [[ADD:%.*]] = call nnan nsz float @llvm.experimental.constrained.fadd.f32(float [[A:%.*]], float 0.000000e+00, metadata !"round.tonearest", metadata !"fpexcept.maytrap") #[[ATTR0]]
-; CHECK-NEXT:    ret float [[ADD]]
+; CHECK-NEXT:    ret float [[A:%.*]]
 ;
   %add = call nnan nsz float @llvm.experimental.constrained.fadd.f32(float %a, float 0.0, metadata !"round.tonearest", metadata !"fpexcept.maytrap") #0
   ret float %add
 }
 
 define <2 x float> @fold_fadd_vec_nnan_nsz_x_0_ebmaytrap(<2 x float> %a) #0 {
 ; CHECK-LABEL: @fold_fadd_vec_nnan_nsz_x_0_ebmaytrap(
-; CHECK-NEXT:    [[ADD:%.*]] = call nnan nsz <2 x float> @llvm.experimental.constrained.fadd.v2f32(<2 x float> [[A:%.*]], <2 x float> zeroinitializer, metadata !"round.tonearest", metadata !"fpexcept.maytrap") #[[ATTR0]]
-; CHECK-NEXT:    ret <2 x float> [[ADD]]
+; CHECK-NEXT:    ret <2 x float> [[A:%.*]]
 ;
   %add = call nnan nsz <2 x float> @llvm.experimental.constrained.fadd.v2f32(<2 x float> %a, <2 x float> zeroinitializer, metadata !"round.tonearest", metadata !"fpexcept.maytrap") #0
   ret <2 x float> %add
 }
 
 define float @fold_fadd_nsz_x_0_ebstrict(float %a) #0 {
 ; CHECK-LABEL: @fold_fadd_nsz_x_0_ebstrict(
 ; CHECK-NEXT:    [[ADD:%.*]] = call nsz float @llvm.experimental.constrained.fadd.f32(float [[A:%.*]], float 0.000000e+00, metadata !"round.tonearest", metadata !"fpexcept.strict") #[[ATTR0]]

 ;
   %add = call nsz <2 x float> @llvm.experimental.constrained.fadd.v2f32(<2 x float> %a, <2 x float> zeroinitializer, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
   ret <2 x float> %add
 }
 
 define float @fold_fadd_nsz_nnan_x_0_ebstrict(float %a) #0 {
 ; CHECK-LABEL: @fold_fadd_nsz_nnan_x_0_ebstrict(
 ; CHECK-NEXT:    [[ADD:%.*]] = call nnan nsz float @llvm.experimental.constrained.fadd.f32(float [[A:%.*]], float 0.000000e+00, metadata !"round.tonearest", metadata !"fpexcept.strict") #[[ATTR0]]
-; CHECK-NEXT:    ret float [[ADD]]
+; CHECK-NEXT:    ret float [[A]]
 ;
   %add = call nsz nnan float @llvm.experimental.constrained.fadd.f32(float %a, float 0.0, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
   ret float %add
 }
 
 define <2 x float> @fold_fadd_vec_nsz_nnan_x_0_ebstrict(<2 x float> %a) #0 {
 ; CHECK-LABEL: @fold_fadd_vec_nsz_nnan_x_0_ebstrict(
 ; CHECK-NEXT:    [[ADD:%.*]] = call nnan nsz <2 x float> @llvm.experimental.constrained.fadd.v2f32(<2 x float> [[A:%.*]], <2 x float> zeroinitializer, metadata !"round.tonearest", metadata !"fpexcept.strict") #[[ATTR0]]
-; CHECK-NEXT:    ret <2 x float> [[ADD]]
+; CHECK-NEXT:    ret <2 x float> [[A]]
 ;
   %add = call nsz nnan <2 x float> @llvm.experimental.constrained.fadd.v2f32(<2 x float> %a, <2 x float> zeroinitializer, metadata !"round.tonearest", metadata !"fpexcept.strict") #0
   ret <2 x float> %add
 }
 
 define float @fold_fadd_nsz_0_x_defaultenv(float %a) #0 {
 ; CHECK-LABEL: @fold_fadd_nsz_0_x_defaultenv(
 ; CHECK-NEXT:    ret float [[A:%.*]]