[llvm] 727a891 - [FPEnv][InstSimplify] Fold fadd X, 0 ==> X, when we know X is not -0

[Kevin P. Neal via llvm-commits]

Author: Kevin P. Neal
Date: 2021-10-14T12:32:45-04:00
New Revision: 727a891ec8c42b134dfd9ac8b830fb6072d34ef3

URL: https://github.com/llvm/llvm-project/commit/727a891ec8c42b134dfd9ac8b830fb6072d34ef3
DIFF: https://github.com/llvm/llvm-project/commit/727a891ec8c42b134dfd9ac8b830fb6072d34ef3.diff

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

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.

Differential Revision: https://reviews.llvm.org/D111450

Added: 
    

Modified: 
    llvm/lib/Analysis/InstructionSimplify.cpp
    llvm/test/Transforms/InstSimplify/strictfp-fadd.ll

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Analysis/InstructionSimplify.cpp b/llvm/lib/Analysis/InstructionSimplify.cpp
index 04948d2ecbf1c..cd59a7e7df470 100644
--- a/llvm/lib/Analysis/InstructionSimplify.cpp
+++ b/llvm/lib/Analysis/InstructionSimplify.cpp
@@ -4977,14 +4977,15 @@ SimplifyFAddInst(Value *Op0, Value *Op1, FastMathFlags FMF,
     if (match(Op1, m_NegZeroFP()))
       return Op0;
 
+  // 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;
 
-  // fadd X, 0 ==> X, when we know X is not -0
-  if (match(Op1, m_PosZeroFP()) &&
-      (FMF.noSignedZeros() || CannotBeNegativeZero(Op0, Q.TLI)))
-    return Op0;
-
   // 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:

diff  --git a/llvm/test/Transforms/InstSimplify/strictfp-fadd.ll b/llvm/test/Transforms/InstSimplify/strictfp-fadd.ll
index 0d836b6e7042f..61b2cafc63adf 100644
--- a/llvm/test/Transforms/InstSimplify/strictfp-fadd.ll
+++ b/llvm/test/Transforms/InstSimplify/strictfp-fadd.ll
@@ -227,6 +227,22 @@ define <2 x float> @fold_fadd_vec_nsz_x_0_defaultenv(<2 x float> %a) #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]]
@@ -247,8 +263,7 @@ define <2 x float> @fold_fadd_vec_nsz_x_0_ebmaytrap(<2 x float> %a) #0 {
 
 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
@@ -256,8 +271,7 @@ define float @fold_fadd_nnan_nsz_x_0_ebmaytrap(float %a) #0 {
 
 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
@@ -284,7 +298,7 @@ define <2 x float> @fold_fadd_vec_nsz_x_0_ebstrict(<2 x float> %a) #0 {
 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
@@ -293,7 +307,7 @@ define float @fold_fadd_nsz_nnan_x_0_ebstrict(float %a) #0 {
 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