[InstCombine] foldICmpWithLowBitMaskedVal(): handle uncanonical ((-1 << y) >> y)...

Summary:
The last low-bit-mask-pattern-producing-pattern i can think of.

https://rise4fun.com/Alive/UGzE <- non-canonical
But we can not canonicalize it because of extra uses.

https://bugs.llvm.org/show_bug.cgi?id=38123

Reviewers: spatel, craig.topper, RKSimon

Reviewed By: spatel

Subscribers: llvm-commits

Differential Revision: https://reviews.llvm.org/D52148

llvm-svn: 342548

diff --git a/llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp b/llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp
index c6294d1..0cb92e0 100644 (file)
--- a/llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp
@@ -2886,6 +2886,7 @@ Instruction *InstCombiner::foldICmpInstWithConstantNotInt(ICmpInst &I) {
 ///   icmp SrcPred (x & Mask), x    to    icmp DstPred x, Mask
 /// Where Mask is some pattern that produces all-ones in low bits:
 ///    (-1 >> y)
+///    ((-1 << y) >> y)     <- non-canonical, has extra uses
 ///   ~(-1 << y)
 ///    ((1 << y) + (-1))    <- non-canonical, has extra uses
 /// The Mask can be a constant, too.
@@ -2894,11 +2895,12 @@ Instruction *InstCombiner::foldICmpInstWithConstantNotInt(ICmpInst &I) {
 static Value *foldICmpWithLowBitMaskedVal(ICmpInst &I,
                                           InstCombiner::BuilderTy &Builder) {
   ICmpInst::Predicate SrcPred;
-  Value *X, *M;
-  auto m_VariableMask =
-      m_CombineOr(m_CombineOr(m_Not(m_Shl(m_AllOnes(), m_Value())),
-                              m_Add(m_Shl(m_One(), m_Value()), m_AllOnes())),
-                  m_LShr(m_AllOnes(), m_Value()));
+  Value *X, *M, *Y;
+  auto m_VariableMask = m_CombineOr(
+      m_CombineOr(m_Not(m_Shl(m_AllOnes(), m_Value())),
+                  m_Add(m_Shl(m_One(), m_Value()), m_AllOnes())),
+      m_CombineOr(m_LShr(m_AllOnes(), m_Value()),
+                  m_LShr(m_Shl(m_AllOnes(), m_Value(Y)), m_Deferred(Y))));
   auto m_Mask = m_CombineOr(m_VariableMask, m_LowBitMask());
   if (!match(&I, m_c_ICmp(SrcPred,
                           m_c_And(m_CombineAnd(m_Mask, m_Value(M)), m_Value(X)),

diff --git a/llvm/test/Transforms/InstCombine/canonicalize-low-bit-mask-v4-and-icmp-eq-to-icmp-ule.ll b/llvm/test/Transforms/InstCombine/canonicalize-low-bit-mask-v4-and-icmp-eq-to-icmp-ule.ll
index ab4b114..7a32c5e 100644 (file)
--- a/llvm/test/Transforms/InstCombine/canonicalize-low-bit-mask-v4-and-icmp-eq-to-icmp-ule.ll
+++ b/llvm/test/Transforms/InstCombine/canonicalize-low-bit-mask-v4-and-icmp-eq-to-icmp-ule.ll
@@ -23,9 +23,8 @@ define i1 @p0(i8 %x, i8 %y) {
 ; CHECK-NEXT:    [[T0:%.*]] = shl i8 -1, [[Y:%.*]]
 ; CHECK-NEXT:    call void @use8(i8 [[T0]])
 ; CHECK-NEXT:    [[T1:%.*]] = lshr i8 [[T0]], [[Y]]
-; CHECK-NEXT:    [[T2:%.*]] = and i8 [[T1]], [[X:%.*]]
-; CHECK-NEXT:    [[RET:%.*]] = icmp eq i8 [[T2]], [[X]]
-; CHECK-NEXT:    ret i1 [[RET]]
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp uge i8 [[T1]], [[X:%.*]]
+; CHECK-NEXT:    ret i1 [[TMP1]]
 ;
   %t0 = shl i8 -1, %y
   call void @use8(i8 %t0)
@@ -44,9 +43,8 @@ define <2 x i1> @p1_vec(<2 x i8> %x, <2 x i8> %y) {
 ; CHECK-NEXT:    [[T0:%.*]] = shl <2 x i8> <i8 -1, i8 -1>, [[Y:%.*]]
 ; CHECK-NEXT:    call void @use2i8(<2 x i8> [[T0]])
 ; CHECK-NEXT:    [[T1:%.*]] = lshr <2 x i8> [[T0]], [[Y]]
-; CHECK-NEXT:    [[T2:%.*]] = and <2 x i8> [[T1]], [[X:%.*]]
-; CHECK-NEXT:    [[RET:%.*]] = icmp eq <2 x i8> [[T2]], [[X]]
-; CHECK-NEXT:    ret <2 x i1> [[RET]]
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp uge <2 x i8> [[T1]], [[X:%.*]]
+; CHECK-NEXT:    ret <2 x i1> [[TMP1]]
 ;
   %t0 = shl <2 x i8> <i8 -1, i8 -1>, %y
   call void @use2i8(<2 x i8> %t0)
@@ -61,9 +59,8 @@ define <3 x i1> @p2_vec_undef0(<3 x i8> %x, <3 x i8> %y) {
 ; CHECK-NEXT:    [[T0:%.*]] = shl <3 x i8> <i8 -1, i8 undef, i8 -1>, [[Y:%.*]]
 ; CHECK-NEXT:    call void @use3i8(<3 x i8> [[T0]])
 ; CHECK-NEXT:    [[T1:%.*]] = lshr <3 x i8> [[T0]], [[Y]]
-; CHECK-NEXT:    [[T2:%.*]] = and <3 x i8> [[T1]], [[X:%.*]]
-; CHECK-NEXT:    [[RET:%.*]] = icmp eq <3 x i8> [[T2]], [[X]]
-; CHECK-NEXT:    ret <3 x i1> [[RET]]
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp uge <3 x i8> [[T1]], [[X:%.*]]
+; CHECK-NEXT:    ret <3 x i1> [[TMP1]]
 ;
   %t0 = shl <3 x i8> <i8 -1, i8 undef, i8 -1>, %y
   call void @use3i8(<3 x i8> %t0)
@@ -85,9 +82,8 @@ define i1 @c0(i8 %y) {
 ; CHECK-NEXT:    call void @use8(i8 [[T0]])
 ; CHECK-NEXT:    [[T1:%.*]] = lshr i8 [[T0]], [[Y]]
 ; CHECK-NEXT:    [[X:%.*]] = call i8 @gen8()
-; CHECK-NEXT:    [[T2:%.*]] = and i8 [[X]], [[T1]]
-; CHECK-NEXT:    [[RET:%.*]] = icmp eq i8 [[T2]], [[X]]
-; CHECK-NEXT:    ret i1 [[RET]]
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp ule i8 [[X]], [[T1]]
+; CHECK-NEXT:    ret i1 [[TMP1]]
 ;
   %t0 = shl i8 -1, %y
   call void @use8(i8 %t0)
@@ -104,9 +100,8 @@ define i1 @c1(i8 %y) {
 ; CHECK-NEXT:    call void @use8(i8 [[T0]])
 ; CHECK-NEXT:    [[T1:%.*]] = lshr i8 [[T0]], [[Y]]
 ; CHECK-NEXT:    [[X:%.*]] = call i8 @gen8()
-; CHECK-NEXT:    [[T2:%.*]] = and i8 [[T1]], [[X]]
-; CHECK-NEXT:    [[RET:%.*]] = icmp eq i8 [[X]], [[T2]]
-; CHECK-NEXT:    ret i1 [[RET]]
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp ule i8 [[X]], [[T1]]
+; CHECK-NEXT:    ret i1 [[TMP1]]
 ;
   %t0 = shl i8 -1, %y
   call void @use8(i8 %t0)
@@ -123,9 +118,8 @@ define i1 @c2(i8 %y) {
 ; CHECK-NEXT:    call void @use8(i8 [[T0]])
 ; CHECK-NEXT:    [[T1:%.*]] = lshr i8 [[T0]], [[Y]]
 ; CHECK-NEXT:    [[X:%.*]] = call i8 @gen8()
-; CHECK-NEXT:    [[T2:%.*]] = and i8 [[X]], [[T1]]
-; CHECK-NEXT:    [[RET:%.*]] = icmp eq i8 [[X]], [[T2]]
-; CHECK-NEXT:    ret i1 [[RET]]
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp ule i8 [[X]], [[T1]]
+; CHECK-NEXT:    ret i1 [[TMP1]]
 ;
   %t0 = shl i8 -1, %y
   call void @use8(i8 %t0)
@@ -146,9 +140,8 @@ define i1 @oneuse0(i8 %x, i8 %y) {
 ; CHECK-NEXT:    call void @use8(i8 [[T0]])
 ; CHECK-NEXT:    [[T1:%.*]] = lshr i8 [[T0]], [[Y]]
 ; CHECK-NEXT:    call void @use8(i8 [[T1]])
-; CHECK-NEXT:    [[T2:%.*]] = and i8 [[T1]], [[X:%.*]]
-; CHECK-NEXT:    [[RET:%.*]] = icmp eq i8 [[T2]], [[X]]
-; CHECK-NEXT:    ret i1 [[RET]]
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp uge i8 [[T1]], [[X:%.*]]
+; CHECK-NEXT:    ret i1 [[TMP1]]
 ;
   %t0 = shl i8 -1, %y
   call void @use8(i8 %t0) ; needed anyway
@@ -166,8 +159,8 @@ define i1 @oneuse1(i8 %x, i8 %y) {
 ; CHECK-NEXT:    [[T1:%.*]] = lshr i8 [[T0]], [[Y]]
 ; CHECK-NEXT:    [[T2:%.*]] = and i8 [[T1]], [[X:%.*]]
 ; CHECK-NEXT:    call void @use8(i8 [[T2]])
-; CHECK-NEXT:    [[RET:%.*]] = icmp eq i8 [[T2]], [[X]]
-; CHECK-NEXT:    ret i1 [[RET]]
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp uge i8 [[T1]], [[X]]
+; CHECK-NEXT:    ret i1 [[TMP1]]
 ;
   %t0 = shl i8 -1, %y
   call void @use8(i8 %t0) ; needed anyway
@@ -186,8 +179,8 @@ define i1 @oneuse2(i8 %x, i8 %y) {
 ; CHECK-NEXT:    call void @use8(i8 [[T1]])
 ; CHECK-NEXT:    [[T2:%.*]] = and i8 [[T1]], [[X:%.*]]
 ; CHECK-NEXT:    call void @use8(i8 [[T2]])
-; CHECK-NEXT:    [[RET:%.*]] = icmp eq i8 [[T2]], [[X]]
-; CHECK-NEXT:    ret i1 [[RET]]
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp uge i8 [[T1]], [[X]]
+; CHECK-NEXT:    ret i1 [[TMP1]]
 ;
   %t0 = shl i8 -1, %y
   call void @use8(i8 %t0)

diff --git a/llvm/test/Transforms/InstCombine/canonicalize-low-bit-mask-v4-and-icmp-ne-to-icmp-ugt.ll b/llvm/test/Transforms/InstCombine/canonicalize-low-bit-mask-v4-and-icmp-ne-to-icmp-ugt.ll
index f6cb226..86a9167 100644 (file)
--- a/llvm/test/Transforms/InstCombine/canonicalize-low-bit-mask-v4-and-icmp-ne-to-icmp-ugt.ll
+++ b/llvm/test/Transforms/InstCombine/canonicalize-low-bit-mask-v4-and-icmp-ne-to-icmp-ugt.ll
@@ -23,9 +23,8 @@ define i1 @p0(i8 %x, i8 %y) {
 ; CHECK-NEXT:    [[T0:%.*]] = shl i8 -1, [[Y:%.*]]
 ; CHECK-NEXT:    call void @use8(i8 [[T0]])
 ; CHECK-NEXT:    [[T1:%.*]] = lshr i8 [[T0]], [[Y]]
-; CHECK-NEXT:    [[T2:%.*]] = and i8 [[T1]], [[X:%.*]]
-; CHECK-NEXT:    [[RET:%.*]] = icmp ne i8 [[T2]], [[X]]
-; CHECK-NEXT:    ret i1 [[RET]]
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp ult i8 [[T1]], [[X:%.*]]
+; CHECK-NEXT:    ret i1 [[TMP1]]
 ;
   %t0 = shl i8 -1, %y
   call void @use8(i8 %t0)
@@ -44,9 +43,8 @@ define <2 x i1> @p1_vec(<2 x i8> %x, <2 x i8> %y) {
 ; CHECK-NEXT:    [[T0:%.*]] = shl <2 x i8> <i8 -1, i8 -1>, [[Y:%.*]]
 ; CHECK-NEXT:    call void @use2i8(<2 x i8> [[T0]])
 ; CHECK-NEXT:    [[T1:%.*]] = lshr <2 x i8> [[T0]], [[Y]]
-; CHECK-NEXT:    [[T2:%.*]] = and <2 x i8> [[T1]], [[X:%.*]]
-; CHECK-NEXT:    [[RET:%.*]] = icmp ne <2 x i8> [[T2]], [[X]]
-; CHECK-NEXT:    ret <2 x i1> [[RET]]
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp ult <2 x i8> [[T1]], [[X:%.*]]
+; CHECK-NEXT:    ret <2 x i1> [[TMP1]]
 ;
   %t0 = shl <2 x i8> <i8 -1, i8 -1>, %y
   call void @use2i8(<2 x i8> %t0)
@@ -61,9 +59,8 @@ define <3 x i1> @p2_vec_undef0(<3 x i8> %x, <3 x i8> %y) {
 ; CHECK-NEXT:    [[T0:%.*]] = shl <3 x i8> <i8 -1, i8 undef, i8 -1>, [[Y:%.*]]
 ; CHECK-NEXT:    call void @use3i8(<3 x i8> [[T0]])
 ; CHECK-NEXT:    [[T1:%.*]] = lshr <3 x i8> [[T0]], [[Y]]
-; CHECK-NEXT:    [[T2:%.*]] = and <3 x i8> [[T1]], [[X:%.*]]
-; CHECK-NEXT:    [[RET:%.*]] = icmp ne <3 x i8> [[T2]], [[X]]
-; CHECK-NEXT:    ret <3 x i1> [[RET]]
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp ult <3 x i8> [[T1]], [[X:%.*]]
+; CHECK-NEXT:    ret <3 x i1> [[TMP1]]
 ;
   %t0 = shl <3 x i8> <i8 -1, i8 undef, i8 -1>, %y
   call void @use3i8(<3 x i8> %t0)
@@ -85,9 +82,8 @@ define i1 @c0(i8 %y) {
 ; CHECK-NEXT:    call void @use8(i8 [[T0]])
 ; CHECK-NEXT:    [[T1:%.*]] = lshr i8 [[T0]], [[Y]]
 ; CHECK-NEXT:    [[X:%.*]] = call i8 @gen8()
-; CHECK-NEXT:    [[T2:%.*]] = and i8 [[X]], [[T1]]
-; CHECK-NEXT:    [[RET:%.*]] = icmp ne i8 [[T2]], [[X]]
-; CHECK-NEXT:    ret i1 [[RET]]
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp ugt i8 [[X]], [[T1]]
+; CHECK-NEXT:    ret i1 [[TMP1]]
 ;
   %t0 = shl i8 -1, %y
   call void @use8(i8 %t0)
@@ -104,9 +100,8 @@ define i1 @c1(i8 %y) {
 ; CHECK-NEXT:    call void @use8(i8 [[T0]])
 ; CHECK-NEXT:    [[T1:%.*]] = lshr i8 [[T0]], [[Y]]
 ; CHECK-NEXT:    [[X:%.*]] = call i8 @gen8()
-; CHECK-NEXT:    [[T2:%.*]] = and i8 [[T1]], [[X]]
-; CHECK-NEXT:    [[RET:%.*]] = icmp ne i8 [[X]], [[T2]]
-; CHECK-NEXT:    ret i1 [[RET]]
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp ugt i8 [[X]], [[T1]]
+; CHECK-NEXT:    ret i1 [[TMP1]]
 ;
   %t0 = shl i8 -1, %y
   call void @use8(i8 %t0)
@@ -123,9 +118,8 @@ define i1 @c2(i8 %y) {
 ; CHECK-NEXT:    call void @use8(i8 [[T0]])
 ; CHECK-NEXT:    [[T1:%.*]] = lshr i8 [[T0]], [[Y]]
 ; CHECK-NEXT:    [[X:%.*]] = call i8 @gen8()
-; CHECK-NEXT:    [[T2:%.*]] = and i8 [[X]], [[T1]]
-; CHECK-NEXT:    [[RET:%.*]] = icmp ne i8 [[X]], [[T2]]
-; CHECK-NEXT:    ret i1 [[RET]]
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp ugt i8 [[X]], [[T1]]
+; CHECK-NEXT:    ret i1 [[TMP1]]
 ;
   %t0 = shl i8 -1, %y
   call void @use8(i8 %t0)
@@ -146,9 +140,8 @@ define i1 @oneuse0(i8 %x, i8 %y) {
 ; CHECK-NEXT:    call void @use8(i8 [[T0]])
 ; CHECK-NEXT:    [[T1:%.*]] = lshr i8 [[T0]], [[Y]]
 ; CHECK-NEXT:    call void @use8(i8 [[T1]])
-; CHECK-NEXT:    [[T2:%.*]] = and i8 [[T1]], [[X:%.*]]
-; CHECK-NEXT:    [[RET:%.*]] = icmp ne i8 [[T2]], [[X]]
-; CHECK-NEXT:    ret i1 [[RET]]
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp ult i8 [[T1]], [[X:%.*]]
+; CHECK-NEXT:    ret i1 [[TMP1]]
 ;
   %t0 = shl i8 -1, %y
   call void @use8(i8 %t0) ; needed anyway
@@ -166,8 +159,8 @@ define i1 @oneuse1(i8 %x, i8 %y) {
 ; CHECK-NEXT:    [[T1:%.*]] = lshr i8 [[T0]], [[Y]]
 ; CHECK-NEXT:    [[T2:%.*]] = and i8 [[T1]], [[X:%.*]]
 ; CHECK-NEXT:    call void @use8(i8 [[T2]])
-; CHECK-NEXT:    [[RET:%.*]] = icmp ne i8 [[T2]], [[X]]
-; CHECK-NEXT:    ret i1 [[RET]]
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp ult i8 [[T1]], [[X]]
+; CHECK-NEXT:    ret i1 [[TMP1]]
 ;
   %t0 = shl i8 -1, %y
   call void @use8(i8 %t0) ; needed anyway
@@ -186,8 +179,8 @@ define i1 @oneuse2(i8 %x, i8 %y) {
 ; CHECK-NEXT:    call void @use8(i8 [[T1]])
 ; CHECK-NEXT:    [[T2:%.*]] = and i8 [[T1]], [[X:%.*]]
 ; CHECK-NEXT:    call void @use8(i8 [[T2]])
-; CHECK-NEXT:    [[RET:%.*]] = icmp ne i8 [[T2]], [[X]]
-; CHECK-NEXT:    ret i1 [[RET]]
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp ult i8 [[T1]], [[X]]
+; CHECK-NEXT:    ret i1 [[TMP1]]
 ;
   %t0 = shl i8 -1, %y
   call void @use8(i8 %t0)