[InstCombine] Delay foldICmpUsingKnownBits until simple transforms are done

This patch changes order of transform in InstCombineCompares to avoid
performing transforms based on ranges which produce complex bit arithmetics
before more simple things (like folding with constants) are done. See PR37636
for the motivating example.

Differential Revision: https://reviews.llvm.org/D48584
Reviewed By: spatel, lebedev.ri

llvm-svn: 336172

4 files changed, 21 insertions, 33 deletions

diff --git a/llvm/test/Transforms/InstCombine/icmp-shl-nsw.ll b/llvm/test/Transforms/InstCombine/icmp-shl-nsw.ll
index ba05302897e..942790cc9bb 100644
--- a/llvm/test/Transforms/InstCombine/icmp-shl-nsw.ll
+++ b/llvm/test/Transforms/InstCombine/icmp-shl-nsw.ll
@@ -69,11 +69,9 @@ define <2 x i1> @icmp_shl_nsw_eq_vec(<2 x i32> %x) {
 ; icmp sgt with shl nsw with a constant compare operand and constant
 ; shift amount can always be reduced to icmp sgt alone.
 
-; Known bits analysis turns this into an equality predicate.
-
 define i1 @icmp_sgt1(i8 %x) {
 ; CHECK-LABEL: @icmp_sgt1(
-; CHECK-NEXT:    [[CMP:%.*]] = icmp ne i8 %x, -64
+; CHECK-NEXT:    [[CMP:%.*]] = icmp sgt i8 %x, -64
 ; CHECK-NEXT:    ret i1 [[CMP]]
 ;
   %shl = shl nsw i8 %x, 1
@@ -144,11 +142,10 @@ define i1 @icmp_sgt7(i8 %x) {
   ret i1 %cmp
 }
 
-; Known bits analysis turns this into an equality predicate.
 
 define i1 @icmp_sgt8(i8 %x) {
 ; CHECK-LABEL: @icmp_sgt8(
-; CHECK-NEXT:    [[CMP:%.*]] = icmp eq i8 %x, 63
+; CHECK-NEXT:    [[CMP:%.*]] = icmp sgt i8 %x, 62
 ; CHECK-NEXT:    ret i1 [[CMP]]
 ;
   %shl = shl nsw i8 %x, 1
@@ -158,11 +155,9 @@ define i1 @icmp_sgt8(i8 %x) {
 
 ; Compares with 126 and 127 are recognized as always false.
 
-; Known bits analysis turns this into an equality predicate.
-
 define i1 @icmp_sgt9(i8 %x) {
 ; CHECK-LABEL: @icmp_sgt9(
-; CHECK-NEXT:    [[CMP:%.*]] = icmp ne i8 %x, -1
+; CHECK-NEXT:    [[CMP:%.*]] = icmp sgt i8 %x, -1
 ; CHECK-NEXT:    ret i1 [[CMP]]
 ;
   %shl = shl nsw i8 %x, 7
@@ -210,11 +205,9 @@ define <2 x i1> @icmp_sgt11_vec(<2 x i8> %x) {
 ;
 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 
-; Known bits analysis turns this into an equality predicate.
-
 define i1 @icmp_sle1(i8 %x) {
 ; CHECK-LABEL: @icmp_sle1(
-; CHECK-NEXT:    [[CMP:%.*]] = icmp eq i8 %x, -64
+; CHECK-NEXT:    [[CMP:%.*]] = icmp slt i8 %x, -63
 ; CHECK-NEXT:    ret i1 [[CMP]]
 ;
   %shl = shl nsw i8 %x, 1
@@ -285,11 +278,9 @@ define i1 @icmp_sle7(i8 %x) {
   ret i1 %cmp
 }
 
-; Known bits analysis turns this into an equality predicate.
-
 define i1 @icmp_sle8(i8 %x) {
 ; CHECK-LABEL: @icmp_sle8(
-; CHECK-NEXT:    [[CMP:%.*]] = icmp ne i8 %x, 63
+; CHECK-NEXT:    [[CMP:%.*]] = icmp slt i8 %x, 63
 ; CHECK-NEXT:    ret i1 [[CMP]]
 ;
   %shl = shl nsw i8 %x, 1
@@ -299,11 +290,9 @@ define i1 @icmp_sle8(i8 %x) {
 
 ; Compares with 126 and 127 are recognized as always true.
 
-; Known bits analysis turns this into an equality predicate.
-
 define i1 @icmp_sle9(i8 %x) {
 ; CHECK-LABEL: @icmp_sle9(
-; CHECK-NEXT:    [[CMP:%.*]] = icmp eq i8 %x, -1
+; CHECK-NEXT:    [[CMP:%.*]] = icmp slt i8 %x, 0
 ; CHECK-NEXT:    ret i1 [[CMP]]
 ;
   %shl = shl nsw i8 %x, 7
@@ -353,4 +342,3 @@ define i1 @icmp_ne1(i8 %x) {
   %cmp = icmp ne i8 %shl, -128
   ret i1 %cmp
 }
-
diff --git a/llvm/test/Transforms/InstCombine/icmp-shr-lt-gt.ll b/llvm/test/Transforms/InstCombine/icmp-shr-lt-gt.ll
index bf1a031a412..a43edfab7eb 100644
--- a/llvm/test/Transforms/InstCombine/icmp-shr-lt-gt.ll
+++ b/llvm/test/Transforms/InstCombine/icmp-shr-lt-gt.ll
@@ -1,3 +1,4 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt < %s -instcombine -S | FileCheck %s
 
 define i1 @lshrugt_01_00(i4 %x) {
@@ -1834,7 +1835,7 @@ define i1 @lshrugt_01_05_exact(i4 %x) {
 
 define i1 @lshrugt_01_06_exact(i4 %x) {
 ; CHECK-LABEL: @lshrugt_01_06_exact(
-; CHECK-NEXT:    [[C:%.*]] = icmp eq i4 %x, -2
+; CHECK-NEXT:    [[C:%.*]] = icmp ugt i4 %x, -4
 ; CHECK-NEXT:    ret i1 [[C]]
 ;
   %s = lshr exact i4 %x, 1
@@ -1945,7 +1946,7 @@ define i1 @lshrugt_02_01_exact(i4 %x) {
 
 define i1 @lshrugt_02_02_exact(i4 %x) {
 ; CHECK-LABEL: @lshrugt_02_02_exact(
-; CHECK-NEXT:    [[C:%.*]] = icmp eq i4 %x, -4
+; CHECK-NEXT:    [[C:%.*]] = icmp ugt i4 %x, -8
 ; CHECK-NEXT:    ret i1 [[C]]
 ;
   %s = lshr exact i4 %x, 2
@@ -2226,7 +2227,7 @@ define i1 @lshrult_01_00_exact(i4 %x) {
 
 define i1 @lshrult_01_01_exact(i4 %x) {
 ; CHECK-LABEL: @lshrult_01_01_exact(
-; CHECK-NEXT:    [[C:%.*]] = icmp eq i4 %x, 0
+; CHECK-NEXT:    [[C:%.*]] = icmp ult i4 %x, 2
 ; CHECK-NEXT:    ret i1 [[C]]
 ;
   %s = lshr exact i4 %x, 1
@@ -2286,7 +2287,7 @@ define i1 @lshrult_01_06_exact(i4 %x) {
 
 define i1 @lshrult_01_07_exact(i4 %x) {
 ; CHECK-LABEL: @lshrult_01_07_exact(
-; CHECK-NEXT:    [[C:%.*]] = icmp ne i4 %x, -2
+; CHECK-NEXT:    [[C:%.*]] = icmp ult i4 %x, -2
 ; CHECK-NEXT:    ret i1 [[C]]
 ;
   %s = lshr exact i4 %x, 1
@@ -2377,7 +2378,7 @@ define i1 @lshrult_02_00_exact(i4 %x) {
 
 define i1 @lshrult_02_01_exact(i4 %x) {
 ; CHECK-LABEL: @lshrult_02_01_exact(
-; CHECK-NEXT:    [[C:%.*]] = icmp eq i4 %x, 0
+; CHECK-NEXT:    [[C:%.*]] = icmp ult i4 %x, 4
 ; CHECK-NEXT:    ret i1 [[C]]
 ;
   %s = lshr exact i4 %x, 2
@@ -2397,7 +2398,7 @@ define i1 @lshrult_02_02_exact(i4 %x) {
 
 define i1 @lshrult_02_03_exact(i4 %x) {
 ; CHECK-LABEL: @lshrult_02_03_exact(
-; CHECK-NEXT:    [[C:%.*]] = icmp ne i4 %x, -4
+; CHECK-NEXT:    [[C:%.*]] = icmp ult i4 %x, -4
 ; CHECK-NEXT:    ret i1 [[C]]
 ;
   %s = lshr exact i4 %x, 2
@@ -2524,7 +2525,7 @@ define i1 @lshrult_03_00_exact(i4 %x) {
 
 define i1 @lshrult_03_01_exact(i4 %x) {
 ; CHECK-LABEL: @lshrult_03_01_exact(
-; CHECK-NEXT:    [[C:%.*]] = icmp ne i4 %x, -8
+; CHECK-NEXT:    [[C:%.*]] = icmp sgt i4 %x, -1
 ; CHECK-NEXT:    ret i1 [[C]]
 ;
   %s = lshr exact i4 %x, 3
@@ -2801,7 +2802,7 @@ define i1 @ashrsgt_01_14_exact(i4 %x) {
 
 define i1 @ashrsgt_01_15_exact(i4 %x) {
 ; CHECK-LABEL: @ashrsgt_01_15_exact(
-; CHECK-NEXT:    [[C:%.*]] = icmp sgt i4 %x, -1
+; CHECK-NEXT:    [[C:%.*]] = icmp sgt i4 %x, -2
 ; CHECK-NEXT:    ret i1 [[C]]
 ;
   %s = ashr exact i4 %x, 1
@@ -2948,7 +2949,7 @@ define i1 @ashrsgt_02_14_exact(i4 %x) {
 
 define i1 @ashrsgt_02_15_exact(i4 %x) {
 ; CHECK-LABEL: @ashrsgt_02_15_exact(
-; CHECK-NEXT:    [[C:%.*]] = icmp sgt i4 %x, -1
+; CHECK-NEXT:    [[C:%.*]] = icmp sgt i4 %x, -4
 ; CHECK-NEXT:    ret i1 [[C]]
 ;
   %s = ashr exact i4 %x, 2
@@ -3093,7 +3094,7 @@ define i1 @ashrsgt_03_14_exact(i4 %x) {
 
 define i1 @ashrsgt_03_15_exact(i4 %x) {
 ; CHECK-LABEL: @ashrsgt_03_15_exact(
-; CHECK-NEXT:    [[C:%.*]] = icmp sgt i4 %x, -1
+; CHECK-NEXT:    [[C:%.*]] = icmp ne i4 %x, -8
 ; CHECK-NEXT:    ret i1 [[C]]
 ;
   %s = ashr exact i4 %x, 3
diff --git a/llvm/test/Transforms/InstCombine/icmp_sdiv_with_and_without_range.ll b/llvm/test/Transforms/InstCombine/icmp_sdiv_with_and_without_range.ll
index 174c4b906e3..5b9b0b47f7e 100644
--- a/llvm/test/Transforms/InstCombine/icmp_sdiv_with_and_without_range.ll
+++ b/llvm/test/Transforms/InstCombine/icmp_sdiv_with_and_without_range.ll
@@ -2,7 +2,8 @@
 ; RUN: opt -instcombine -S < %s | FileCheck %s
 
 ; Test that presence of range does not cause unprofitable transforms with bit
-; arithmetics, and instcombine behaves exactly the same as without the range.
+; arithmetics. InstCombine needs to be smart about dealing with range-annotated
+; values.
 
 define i1 @without_range(i32* %A) {
 ; CHECK-LABEL: @without_range(
@@ -19,8 +20,7 @@ define i1 @without_range(i32* %A) {
 define i1 @with_range(i32* %A) {
 ; CHECK-LABEL: @with_range(
 ; CHECK-NEXT:    [[A_VAL:%.*]] = load i32, i32* [[A:%.*]], align 8, !range !0
-; CHECK-NEXT:    [[B_MASK:%.*]] = and i32 [[A_VAL]], 2147483646
-; CHECK-NEXT:    [[C:%.*]] = icmp eq i32 [[B_MASK]], 0
+; CHECK-NEXT:    [[C:%.*]] = icmp ult i32 [[A_VAL]], 2
 ; CHECK-NEXT:    ret i1 [[C]]
 ;
   %A.val = load i32, i32* %A, align 8, !range !0
diff --git a/llvm/test/Transforms/LoopVectorize/X86/masked_load_store.ll b/llvm/test/Transforms/LoopVectorize/X86/masked_load_store.ll
index 8e948639ba1..b4bd5c510d0 100644
--- a/llvm/test/Transforms/LoopVectorize/X86/masked_load_store.ll
+++ b/llvm/test/Transforms/LoopVectorize/X86/masked_load_store.ll
@@ -2052,8 +2052,7 @@ define void @foo4(double* %A, double* %B, i32* %trigger)  {
 ; AVX512-NEXT:    [[PROL_ITER_CMP:%.*]] = icmp eq i64 [[PROL_ITER_SUB]], 0
 ; AVX512-NEXT:    br i1 [[PROL_ITER_CMP]], label [[FOR_BODY_PROL_LOOPEXIT:%.*]], label [[FOR_BODY_PROL]], !llvm.loop !50
 ; AVX512:       for.body.prol.loopexit:
-; AVX512-NEXT:    [[DOTMASK:%.*]] = and i64 [[TMP24]], 9984
-; AVX512-NEXT:    [[TMP28:%.*]] = icmp eq i64 [[DOTMASK]], 0
+; AVX512-NEXT:    [[TMP28:%.*]] = icmp ult i64 [[TMP24]], 48
 ; AVX512-NEXT:    br i1 [[TMP28]], label [[FOR_END:%.*]], label [[FOR_BODY:%.*]]
 ; AVX512:       for.body:
 ; AVX512-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT_3:%.*]], [[FOR_INC_3:%.*]] ], [ [[INDVARS_IV_NEXT_PROL]], [[FOR_BODY_PROL_LOOPEXIT]] ]