[InstCombine] Propagate FMF from select instead of fcmp (#141010)

Previously,
llvm/llvm-project@3d6b539
propagates FMF from fcmp to avoid performance regressions. With the help
of llvm/llvm-project#139861,
llvm/llvm-project#141015, and
llvm/llvm-project#141914, we can still convert
SPF into fabs/minnum/maxnum intrinsics even if some flags are missing.
This patch propagates FMF from select to address the long-standing
issue.

Closes llvm/llvm-project#140994.

Author: dtcxzyw

llvm/lib/Transforms/InstCombine/InstCombineSelect.cpp

@@ -25,6 +25,7 @@
 #include "llvm/IR/ConstantRange.h"
 #include "llvm/IR/Constants.h"
 #include "llvm/IR/DerivedTypes.h"
+#include "llvm/IR/FMF.h"
 #include "llvm/IR/IRBuilder.h"
 #include "llvm/IR/InstrTypes.h"
 #include "llvm/IR/Instruction.h"
@@ -3879,11 +3880,16 @@ Instruction *InstCombinerImpl::visitSelectInst(SelectInst &SI) {
       // (X ugt Y) ? X : Y -> (X ole Y) ? Y : X
       if (FCmp->hasOneUse() && FCmpInst::isUnordered(Pred)) {
         FCmpInst::Predicate InvPred = FCmp->getInversePredicate();
-        // FIXME: The FMF should propagate from the select, not the fcmp.
         Value *NewCond = Builder.CreateFCmpFMF(InvPred, Cmp0, Cmp1, FCmp,
                                                FCmp->getName() + ".inv");
+        // Propagate ninf/nnan from fcmp to select.
+        FastMathFlags FMF = SI.getFastMathFlags();
+        if (FCmp->hasNoNaNs())
+          FMF.setNoNaNs(true);
+        if (FCmp->hasNoInfs())
+          FMF.setNoInfs(true);
         Value *NewSel =
-            Builder.CreateSelectFMF(NewCond, FalseVal, TrueVal, FCmp);
+            Builder.CreateSelectFMF(NewCond, FalseVal, TrueVal, FMF);
         return replaceInstUsesWith(SI, NewSel);
       }
     }

llvm/test/Transforms/InstCombine/clamp-to-minmax.ll

@@ -7,7 +7,8 @@ define float @clamp_float_fast_ordered_strict_maxmin(float %x) {
 ; CHECK-LABEL: @clamp_float_fast_ordered_strict_maxmin(
 ; CHECK-NEXT:    [[CMP2:%.*]] = fcmp fast olt float [[X:%.*]], 2.550000e+02
 ; CHECK-NEXT:    [[MIN:%.*]] = select i1 [[CMP2]], float [[X]], float 2.550000e+02
-; CHECK-NEXT:    [[R1:%.*]] = call fast float @llvm.maxnum.f32(float [[MIN]], float 1.000000e+00)
+; CHECK-NEXT:    [[DOTINV:%.*]] = fcmp fast oge float [[MIN]], 1.000000e+00
+; CHECK-NEXT:    [[R1:%.*]] = select nnan ninf i1 [[DOTINV]], float [[MIN]], float 1.000000e+00
 ; CHECK-NEXT:    ret float [[R1]]
 ;
   %cmp2 = fcmp fast olt float %x, 255.0
@@ -22,7 +23,8 @@ define float @clamp_float_fast_ordered_nonstrict_maxmin(float %x) {
 ; CHECK-LABEL: @clamp_float_fast_ordered_nonstrict_maxmin(
 ; CHECK-NEXT:    [[CMP2:%.*]] = fcmp fast olt float [[X:%.*]], 2.550000e+02
 ; CHECK-NEXT:    [[MIN:%.*]] = select i1 [[CMP2]], float [[X]], float 2.550000e+02
-; CHECK-NEXT:    [[R1:%.*]] = call fast float @llvm.maxnum.f32(float [[MIN]], float 1.000000e+00)
+; CHECK-NEXT:    [[DOTINV:%.*]] = fcmp fast oge float [[MIN]], 1.000000e+00
+; CHECK-NEXT:    [[R1:%.*]] = select nnan ninf i1 [[DOTINV]], float [[MIN]], float 1.000000e+00
 ; CHECK-NEXT:    ret float [[R1]]
 ;
   %cmp2 = fcmp fast olt float %x, 255.0
@@ -37,7 +39,8 @@ define float @clamp_float_fast_ordered_strict_minmax(float %x) {
 ; CHECK-LABEL: @clamp_float_fast_ordered_strict_minmax(
 ; CHECK-NEXT:    [[CMP2:%.*]] = fcmp fast ogt float [[X:%.*]], 1.000000e+00
 ; CHECK-NEXT:    [[MAX:%.*]] = select i1 [[CMP2]], float [[X]], float 1.000000e+00
-; CHECK-NEXT:    [[R1:%.*]] = call fast float @llvm.minnum.f32(float [[MAX]], float 2.550000e+02)
+; CHECK-NEXT:    [[DOTINV:%.*]] = fcmp fast ole float [[MAX]], 2.550000e+02
+; CHECK-NEXT:    [[R1:%.*]] = select nnan ninf i1 [[DOTINV]], float [[MAX]], float 2.550000e+02
 ; CHECK-NEXT:    ret float [[R1]]
 ;
   %cmp2 = fcmp fast ogt float %x, 1.0
@@ -52,7 +55,8 @@ define float @clamp_float_fast_ordered_nonstrict_minmax(float %x) {
 ; CHECK-LABEL: @clamp_float_fast_ordered_nonstrict_minmax(
 ; CHECK-NEXT:    [[CMP2:%.*]] = fcmp fast ogt float [[X:%.*]], 1.000000e+00
 ; CHECK-NEXT:    [[MAX:%.*]] = select i1 [[CMP2]], float [[X]], float 1.000000e+00
-; CHECK-NEXT:    [[R1:%.*]] = call fast float @llvm.minnum.f32(float [[MAX]], float 2.550000e+02)
+; CHECK-NEXT:    [[DOTINV:%.*]] = fcmp fast ole float [[MAX]], 2.550000e+02
+; CHECK-NEXT:    [[R1:%.*]] = select nnan ninf i1 [[DOTINV]], float [[MAX]], float 2.550000e+02
 ; CHECK-NEXT:    ret float [[R1]]
 ;
   %cmp2 = fcmp fast ogt float %x, 1.0
@@ -68,9 +72,10 @@ define float @clamp_float_fast_ordered_nonstrict_minmax(float %x) {
 ; (X < C1) ? C1 : MIN(X, C2)
 define float @clamp_float_fast_unordered_strict_maxmin(float %x) {
 ; CHECK-LABEL: @clamp_float_fast_unordered_strict_maxmin(
-; CHECK-NEXT:    [[MIN:%.*]] = call fast float @llvm.minnum.f32(float [[X:%.*]], float 2.550000e+02)
-; CHECK-NEXT:    [[CMP1:%.*]] = fcmp fast ult float [[X]], 1.000000e+00
-; CHECK-NEXT:    [[R:%.*]] = select i1 [[CMP1]], float 1.000000e+00, float [[MIN]]
+; CHECK-NEXT:    [[CMP2_INV:%.*]] = fcmp fast oge float [[X:%.*]], 2.550000e+02
+; CHECK-NEXT:    [[MIN:%.*]] = select nnan ninf i1 [[CMP2_INV]], float 2.550000e+02, float [[X]]
+; CHECK-NEXT:    [[DOTINV:%.*]] = fcmp fast oge float [[MIN]], 1.000000e+00
+; CHECK-NEXT:    [[R:%.*]] = select nnan ninf i1 [[DOTINV]], float [[MIN]], float 1.000000e+00
 ; CHECK-NEXT:    ret float [[R]]
 ;
   %cmp2 = fcmp fast ult float %x, 255.0
@@ -83,9 +88,10 @@ define float @clamp_float_fast_unordered_strict_maxmin(float %x) {
 ; (X <= C1) ? C1 : MIN(X, C2)
 define float @clamp_float_fast_unordered_nonstrict_maxmin(float %x) {
 ; CHECK-LABEL: @clamp_float_fast_unordered_nonstrict_maxmin(
-; CHECK-NEXT:    [[MIN:%.*]] = call fast float @llvm.minnum.f32(float [[X:%.*]], float 2.550000e+02)
-; CHECK-NEXT:    [[CMP1:%.*]] = fcmp fast ule float [[X]], 1.000000e+00
-; CHECK-NEXT:    [[R:%.*]] = select i1 [[CMP1]], float 1.000000e+00, float [[MIN]]
+; CHECK-NEXT:    [[CMP2_INV:%.*]] = fcmp fast oge float [[X:%.*]], 2.550000e+02
+; CHECK-NEXT:    [[MIN:%.*]] = select nnan ninf i1 [[CMP2_INV]], float 2.550000e+02, float [[X]]
+; CHECK-NEXT:    [[DOTINV:%.*]] = fcmp fast oge float [[MIN]], 1.000000e+00
+; CHECK-NEXT:    [[R:%.*]] = select nnan ninf i1 [[DOTINV]], float [[MIN]], float 1.000000e+00
 ; CHECK-NEXT:    ret float [[R]]
 ;
   %cmp2 = fcmp fast ult float %x, 255.0
@@ -98,9 +104,10 @@ define float @clamp_float_fast_unordered_nonstrict_maxmin(float %x) {
 ; (X > C1) ? C1 : MAX(X, C2)
 define float @clamp_float_fast_unordered_strict_minmax(float %x) {
 ; CHECK-LABEL: @clamp_float_fast_unordered_strict_minmax(
-; CHECK-NEXT:    [[MAX:%.*]] = call fast float @llvm.maxnum.f32(float [[X:%.*]], float 1.000000e+00)
-; CHECK-NEXT:    [[CMP1:%.*]] = fcmp fast ugt float [[X]], 2.550000e+02
-; CHECK-NEXT:    [[R:%.*]] = select i1 [[CMP1]], float 2.550000e+02, float [[MAX]]
+; CHECK-NEXT:    [[CMP2_INV:%.*]] = fcmp fast ole float [[X:%.*]], 1.000000e+00
+; CHECK-NEXT:    [[MAX:%.*]] = select nnan ninf i1 [[CMP2_INV]], float 1.000000e+00, float [[X]]
+; CHECK-NEXT:    [[DOTINV:%.*]] = fcmp fast ole float [[MAX]], 2.550000e+02
+; CHECK-NEXT:    [[R:%.*]] = select nnan ninf i1 [[DOTINV]], float [[MAX]], float 2.550000e+02
 ; CHECK-NEXT:    ret float [[R]]
 ;
   %cmp2 = fcmp fast ugt float %x, 1.0
@@ -113,9 +120,10 @@ define float @clamp_float_fast_unordered_strict_minmax(float %x) {
 ; (X >= C1) ? C1 : MAX(X, C2)
 define float @clamp_float_fast_unordered_nonstrict_minmax(float %x) {
 ; CHECK-LABEL: @clamp_float_fast_unordered_nonstrict_minmax(
-; CHECK-NEXT:    [[MAX:%.*]] = call fast float @llvm.maxnum.f32(float [[X:%.*]], float 1.000000e+00)
-; CHECK-NEXT:    [[CMP1:%.*]] = fcmp fast uge float [[X]], 2.550000e+02
-; CHECK-NEXT:    [[R:%.*]] = select i1 [[CMP1]], float 2.550000e+02, float [[MAX]]
+; CHECK-NEXT:    [[CMP2_INV:%.*]] = fcmp fast ole float [[X:%.*]], 1.000000e+00
+; CHECK-NEXT:    [[MAX:%.*]] = select nnan ninf i1 [[CMP2_INV]], float 1.000000e+00, float [[X]]
+; CHECK-NEXT:    [[DOTINV:%.*]] = fcmp fast ole float [[MAX]], 2.550000e+02
+; CHECK-NEXT:    [[R:%.*]] = select nnan ninf i1 [[DOTINV]], float [[MAX]], float 2.550000e+02
 ; CHECK-NEXT:    ret float [[R]]
 ;
   %cmp2 = fcmp fast ugt float %x, 1.0
@@ -130,9 +138,10 @@ define float @clamp_float_fast_unordered_nonstrict_minmax(float %x) {
 ; (X > 1.0) ? min(x, 255.0) : 1.0
 define float @clamp_test_1(float %x) {
 ; CHECK-LABEL: @clamp_test_1(
-; CHECK-NEXT:    [[INNER_SEL:%.*]] = call fast float @llvm.minnum.f32(float [[X:%.*]], float 2.550000e+02)
-; CHECK-NEXT:    [[OUTER_CMP:%.*]] = fcmp fast ugt float [[X]], 1.000000e+00
-; CHECK-NEXT:    [[R:%.*]] = select i1 [[OUTER_CMP]], float [[INNER_SEL]], float 1.000000e+00
+; CHECK-NEXT:    [[INNER_CMP_INV:%.*]] = fcmp fast oge float [[X:%.*]], 2.550000e+02
+; CHECK-NEXT:    [[INNER_SEL:%.*]] = select nnan ninf i1 [[INNER_CMP_INV]], float 2.550000e+02, float [[X]]
+; CHECK-NEXT:    [[OUTER_CMP:%.*]] = fcmp fast oge float [[INNER_SEL]], 1.000000e+00
+; CHECK-NEXT:    [[R:%.*]] = select nnan ninf i1 [[OUTER_CMP]], float [[INNER_SEL]], float 1.000000e+00
 ; CHECK-NEXT:    ret float [[R]]
 ;
   %inner_cmp = fcmp fast ult float %x, 255.0
@@ -147,7 +156,8 @@ define float @clamp_test_1(float %x) {
 ; Like @clamp_test_1 but HighConst < LowConst
 define float @clamp_negative_wrong_const(float %x) {
 ; CHECK-LABEL: @clamp_negative_wrong_const(
-; CHECK-NEXT:    [[INNER_SEL:%.*]] = call fast float @llvm.minnum.f32(float [[X:%.*]], float 2.550000e+02)
+; CHECK-NEXT:    [[INNER_CMP_INV:%.*]] = fcmp fast oge float [[X:%.*]], 2.550000e+02
+; CHECK-NEXT:    [[INNER_SEL:%.*]] = select nnan ninf i1 [[INNER_CMP_INV]], float 2.550000e+02, float [[X]]
 ; CHECK-NEXT:    [[OUTER_CMP:%.*]] = fcmp fast ugt float [[X]], 5.120000e+02
 ; CHECK-NEXT:    [[R:%.*]] = select i1 [[OUTER_CMP]], float [[INNER_SEL]], float 5.120000e+02
 ; CHECK-NEXT:    ret float [[R]]
@@ -162,7 +172,8 @@ define float @clamp_negative_wrong_const(float %x) {
 ; Like @clamp_test_1 but both are min
 define float @clamp_negative_same_op(float %x) {
 ; CHECK-LABEL: @clamp_negative_same_op(
-; CHECK-NEXT:    [[INNER_SEL:%.*]] = call fast float @llvm.minnum.f32(float [[X:%.*]], float 2.550000e+02)
+; CHECK-NEXT:    [[INNER_CMP_INV:%.*]] = fcmp fast oge float [[X:%.*]], 2.550000e+02
+; CHECK-NEXT:    [[INNER_SEL:%.*]] = select nnan ninf i1 [[INNER_CMP_INV]], float 2.550000e+02, float [[X]]
 ; CHECK-NEXT:    [[OUTER_CMP:%.*]] = fcmp fast ult float [[X]], 1.000000e+00
 ; CHECK-NEXT:    [[R:%.*]] = select i1 [[OUTER_CMP]], float [[INNER_SEL]], float 1.000000e+00
 ; CHECK-NEXT:    ret float [[R]]