Improve lookThroughCast function.

Summary:
When we have the following case:

  %cond = cmp iN %x, CmpConst
  %tr = trunc iN %x to iK
  %narrowsel = select i1 %cond, iK %t, iK C

We could possibly match only min/max pattern after looking through cast.
So it is more profitable if widened C constant will be equal CmpConst.
That is why just set widened C constant equal to CmpConst, because there
is a further check in this function that trunc CmpConst == C.

Also description for lookTroughCast function was added.

Reviewers: spatel

Subscribers: llvm-commits

Differential Revision: https://reviews.llvm.org/D38536

Patch by: Artur Gainullin <artur.gainullin@intel.com>

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@316070 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Analysis/ValueTracking.cpp b/lib/Analysis/ValueTracking.cpp
index f70f2d19ac6d035dfaf66f4f62956784ed4d9567..55a7a353858fa8cd9d2a7365ccf0322e1e96135f 100644 (file)
--- a/lib/Analysis/ValueTracking.cpp
+++ b/lib/Analysis/ValueTracking.cpp
@@ -4320,6 +4320,20 @@ static SelectPatternResult matchSelectPattern(CmpInst::Predicate Pred,
   return matchFastFloatClamp(Pred, CmpLHS, CmpRHS, TrueVal, FalseVal, LHS, RHS);
 }
 
+/// Helps to match a select pattern in case of a type mismatch.
+///
+/// The function processes the case when type of true and false values of a
+/// select instruction differs from type of the cmp instruction operands because
+/// of a cast instructon. The function checks if it is legal to move the cast
+/// operation after "select". If yes, it returns the new second value of
+/// "select" (with the assumption that cast is moved):
+/// 1. As operand of cast instruction when both values of "select" are same cast
+/// instructions.
+/// 2. As restored constant (by applying reverse cast operation) when the first
+/// value of the "select" is a cast operation and the second value is a
+/// constant.
+/// NOTE: We return only the new second value because the first value could be
+/// accessed as operand of cast instruction.
 static Value *lookThroughCast(CmpInst *CmpI, Value *V1, Value *V2,
                               Instruction::CastOps *CastOp) {
   auto *Cast1 = dyn_cast<CastInst>(V1);
@@ -4350,7 +4364,33 @@ static Value *lookThroughCast(CmpInst *CmpI, Value *V1, Value *V2,
       CastedTo = ConstantExpr::getTrunc(C, SrcTy, true);
     break;
   case Instruction::Trunc:
-    CastedTo = ConstantExpr::getIntegerCast(C, SrcTy, CmpI->isSigned());
+    Constant *CmpConst;
+    if (match(CmpI->getOperand(1), m_Constant(CmpConst))) {
+      // Here we have the following case:
+      //
+      //   %cond = cmp iN %x, CmpConst
+      //   %tr = trunc iN %x to iK
+      //   %narrowsel = select i1 %cond, iK %t, iK C
+      //
+      // We can always move trunc after select operation:
+      //
+      //   %cond = cmp iN %x, CmpConst
+      //   %widesel = select i1 %cond, iN %x, iN CmpConst
+      //   %tr = trunc iN %widesel to iK
+      //
+      // Note that C could be extended in any way because we don't care about
+      // upper bits after truncation. It can't be abs pattern, because it would
+      // look like:
+      //
+      //   select i1 %cond, x, -x.
+      //
+      // So only min/max pattern could be matched. Such match requires widened C
+      // == CmpConst. That is why set widened C = CmpConst, condition trunc
+      // CmpConst == C is checked below.
+      CastedTo = CmpConst;
+    } else {
+      CastedTo = ConstantExpr::getIntegerCast(C, SrcTy, CmpI->isSigned());
+    }
     break;
   case Instruction::FPTrunc:
     CastedTo = ConstantExpr::getFPExtend(C, SrcTy, true);

diff --git a/test/Transforms/InstCombine/minmax-fold.ll b/test/Transforms/InstCombine/minmax-fold.ll
index f0873147849d3bc97a4fc112908ceccd241ea7a3..397c6940d2d65ba9da07e367e8fa3e3d7997d455 100644 (file)
--- a/test/Transforms/InstCombine/minmax-fold.ll
+++ b/test/Transforms/InstCombine/minmax-fold.ll
@@ -688,3 +688,57 @@ define <8 x float> @bitcast_vector_umin(<8 x float> %x, <8 x float> %y) {
   %sel = select <8 x i1> %cmp, <8 x float> %x, <8 x float> %y
   ret <8 x float> %sel
 }
+
+; Check that we look through cast and recognize min idiom.
+define zeroext i8 @look_through_cast1(i32 %x) {
+; CHECK-LABEL: @look_through_cast1(
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp slt i32 [[X:%.*]], 511
+; CHECK-NEXT:    [[RES1:%.*]] = select i1 [[TMP1]], i32 [[X]], i32 511
+; CHECK-NEXT:    [[TMP2:%.*]] = trunc i32 [[RES1]] to i8
+; CHECK-NEXT:    ret i8 [[TMP2]]
+;
+  %cmp1 = icmp slt i32 %x, 511
+  %x_trunc = trunc i32 %x to i8
+  %res = select i1 %cmp1, i8 %x_trunc, i8 255
+  ret i8 %res
+}
+
+; Check that we look through cast but min is not recognized.
+define zeroext i8 @look_through_cast2(i32 %x) {
+; CHECK-LABEL: @look_through_cast2(
+; CHECK-NEXT:    [[CMP1:%.*]] = icmp slt i32 [[X:%.*]], 510
+; CHECK-NEXT:    [[X_TRUNC:%.*]] = trunc i32 [[X]] to i8
+; CHECK-NEXT:    [[RES:%.*]] = select i1 [[CMP1]], i8 [[X_TRUNC]], i8 -1
+; CHECK-NEXT:    ret i8 [[RES]]
+;
+  %cmp1 = icmp slt i32 %x, 510
+  %x_trunc = trunc i32 %x to i8
+  %res = select i1 %cmp1, i8 %x_trunc, i8 255
+  ret i8 %res
+}
+
+define <2 x i8> @min_through_cast_vec1(<2 x i32> %x) {
+; CHECK-LABEL: @min_through_cast_vec1(
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp slt <2 x i32> [[X:%.*]], <i32 510, i32 511>
+; CHECK-NEXT:    [[RES1:%.*]] = select <2 x i1> [[TMP1]], <2 x i32> [[X]], <2 x i32> <i32 510, i32 511>
+; CHECK-NEXT:    [[TMP2:%.*]] = trunc <2 x i32> [[RES1]] to <2 x i8>
+; CHECK-NEXT:    ret <2 x i8> [[TMP2]]
+;
+  %cmp = icmp slt <2 x i32> %x, <i32 510, i32 511>
+  %x_trunc = trunc <2 x i32> %x to <2 x i8>
+  %res = select <2 x i1> %cmp, <2 x i8> %x_trunc, <2 x i8> <i8 254, i8 255>
+  ret <2 x i8> %res
+}
+
+define <2 x i8> @min_through_cast_vec2(<2 x i32> %x) {
+; CHECK-LABEL: @min_through_cast_vec2(
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp slt <2 x i32> [[X:%.*]], <i32 511, i32 511>
+; CHECK-NEXT:    [[RES1:%.*]] = select <2 x i1> [[TMP1]], <2 x i32> [[X]], <2 x i32> <i32 511, i32 511>
+; CHECK-NEXT:    [[TMP2:%.*]] = trunc <2 x i32> [[RES1]] to <2 x i8>
+; CHECK-NEXT:    ret <2 x i8> [[TMP2]]
+;
+  %cmp = icmp slt <2 x i32> %x, <i32 511, i32 511>
+  %x_trunc = trunc <2 x i32> %x to <2 x i8>
+  %res = select <2 x i1> %cmp, <2 x i8> %x_trunc, <2 x i8> <i8 255, i8 255>
+  ret <2 x i8> %res
+}