[PATCH] D62979: [InstSimplify] enhance/fix fcmp fold with never-nan operand

[Sanjay Patel via Phabricator via llvm-commits]

spatel created this revision.
spatel added reviewers: hfinkel, mcberg2017, efriedma, cameron.mcinally, arsenm.
Herald added subscribers: hiraditya, wdng, mcrosier.
Herald added a project: LLVM.

This is 1 step towards correcting our usage of fast-math-flags when applied on an fcmp. In this case, we were checking for 'nnan' on the fcmp itself rather than the operand of the fcmp.

By using the more general "isKnownNeverNaN()", we gain a simplification shown on the tests with 'uitofp' regardless of the FMF on the fcmp (uitofp never produces a NaN). On the tests with 'fabs', we are now relying on the FMF for the call fabs instruction rather than the FMF on the fcmp.

If this looks ok, I'll update the 'ult' case below here as a follow-up.


https://reviews.llvm.org/D62979

Files:
  llvm/lib/Analysis/InstructionSimplify.cpp
  llvm/test/Transforms/InstSimplify/floating-point-compare.ll


Index: llvm/test/Transforms/InstSimplify/floating-point-compare.ll
===================================================================
--- llvm/test/Transforms/InstSimplify/floating-point-compare.ll
+++ llvm/test/Transforms/InstSimplify/floating-point-compare.ll
@@ -257,9 +257,7 @@
 
 define i1 @UIToFP_is_positive_or_zero(i32 %x) {
 ; CHECK-LABEL: @UIToFP_is_positive_or_zero(
-; CHECK-NEXT:    [[A:%.*]] = uitofp i32 [[X:%.*]] to float
-; CHECK-NEXT:    [[R:%.*]] = fcmp oge float [[A]], 0.000000e+00
-; CHECK-NEXT:    ret i1 [[R]]
+; CHECK-NEXT:    ret i1 true
 ;
   %a = uitofp i32 %x to float
   %r = fcmp oge float %a, 0.000000e+00
@@ -268,9 +266,7 @@
 
 define <2 x i1> @UIToFP_is_positive_or_zero_vec(<2 x i32> %x) {
 ; CHECK-LABEL: @UIToFP_is_positive_or_zero_vec(
-; CHECK-NEXT:    [[A:%.*]] = uitofp <2 x i32> [[X:%.*]] to <2 x float>
-; CHECK-NEXT:    [[R:%.*]] = fcmp oge <2 x float> [[A]], zeroinitializer
-; CHECK-NEXT:    ret <2 x i1> [[R]]
+; CHECK-NEXT:    ret <2 x i1> <i1 true, i1 true>
 ;
   %a = uitofp <2 x i32> %x to <2 x float>
   %r = fcmp oge <2 x float> %a, zeroinitializer
@@ -351,9 +347,7 @@
 
 define i1 @fabs_nnan_is_positive_or_zero(double %x) {
 ; CHECK-LABEL: @fabs_nnan_is_positive_or_zero(
-; CHECK-NEXT:    [[FABS:%.*]] = tail call nnan double @llvm.fabs.f64(double [[X:%.*]])
-; CHECK-NEXT:    [[CMP:%.*]] = fcmp oge double [[FABS]], 0.000000e+00
-; CHECK-NEXT:    ret i1 [[CMP]]
+; CHECK-NEXT:    ret i1 true
 ;
   %fabs = tail call nnan double @llvm.fabs.f64(double %x)
   %cmp = fcmp oge double %fabs, 0.0
@@ -362,9 +356,7 @@
 
 define <2 x i1> @fabs_nnan_is_positive_or_zero_vec(<2 x double> %x) {
 ; CHECK-LABEL: @fabs_nnan_is_positive_or_zero_vec(
-; CHECK-NEXT:    [[FABS:%.*]] = tail call nnan <2 x double> @llvm.fabs.v2f64(<2 x double> [[X:%.*]])
-; CHECK-NEXT:    [[CMP:%.*]] = fcmp oge <2 x double> [[FABS]], zeroinitializer
-; CHECK-NEXT:    ret <2 x i1> [[CMP]]
+; CHECK-NEXT:    ret <2 x i1> <i1 true, i1 true>
 ;
   %fabs = tail call nnan <2 x double> @llvm.fabs.v2f64(<2 x double> %x)
   %cmp = fcmp oge <2 x double> %fabs, zeroinitializer
@@ -373,7 +365,9 @@
 
 define i1 @fabs_fcmp-nnan_is_positive_or_zero(double %x) {
 ; CHECK-LABEL: @fabs_fcmp-nnan_is_positive_or_zero(
-; CHECK-NEXT:    ret i1 true
+; CHECK-NEXT:    [[FABS:%.*]] = tail call double @llvm.fabs.f64(double [[X:%.*]])
+; CHECK-NEXT:    [[CMP:%.*]] = fcmp nnan oge double [[FABS]], 0.000000e+00
+; CHECK-NEXT:    ret i1 [[CMP]]
 ;
   %fabs = tail call double @llvm.fabs.f64(double %x)
   %cmp = fcmp nnan oge double %fabs, 0.0
@@ -382,7 +376,9 @@
 
 define <2 x i1> @fabs_fcmp-nnan_is_positive_or_zero_vec(<2 x double> %x) {
 ; CHECK-LABEL: @fabs_fcmp-nnan_is_positive_or_zero_vec(
-; CHECK-NEXT:    ret <2 x i1> <i1 true, i1 true>
+; CHECK-NEXT:    [[FABS:%.*]] = tail call <2 x double> @llvm.fabs.v2f64(<2 x double> [[X:%.*]])
+; CHECK-NEXT:    [[CMP:%.*]] = fcmp nnan oge <2 x double> [[FABS]], zeroinitializer
+; CHECK-NEXT:    ret <2 x i1> [[CMP]]
 ;
   %fabs = tail call <2 x double> @llvm.fabs.v2f64(<2 x double> %x)
   %cmp = fcmp nnan oge <2 x double> %fabs, zeroinitializer
Index: llvm/lib/Analysis/InstructionSimplify.cpp
===================================================================
--- llvm/lib/Analysis/InstructionSimplify.cpp
+++ llvm/lib/Analysis/InstructionSimplify.cpp
@@ -3477,7 +3477,8 @@
   if (match(RHS, m_AnyZeroFP())) {
     switch (Pred) {
     case FCmpInst::FCMP_OGE:
-      if (FMF.noNaNs() && CannotBeOrderedLessThanZero(LHS, Q.TLI))
+      if (isKnownNeverNaN(LHS, Q.TLI) &&
+          CannotBeOrderedLessThanZero(LHS, Q.TLI))
         return getTrue(RetTy);
       break;
     case FCmpInst::FCMP_UGE:
@@ -3485,6 +3486,7 @@
         return getTrue(RetTy);
       break;
     case FCmpInst::FCMP_ULT:
+      // TODO: This should match 'oge'.
       if (FMF.noNaNs() && CannotBeOrderedLessThanZero(LHS, Q.TLI))
         return getFalse(RetTy);
       break;


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D62979.203435.patch
Type: text/x-patch
Size: 3919 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20190606/5527853c/attachment.bin>