[InstCombine] Teach SimplifyDemandedBits that udiv doesn't demand low dividend bits...

This is safe as long as the udiv is not exact. The pattern is not common in
C++ code, but comes up all the time in code generated by XLA's GPU backend.

Differential Revision: https://reviews.llvm.org/D46647

llvm-svn: 331933

diff --git a/llvm/lib/Transforms/InstCombine/InstCombineSimplifyDemanded.cpp b/llvm/lib/Transforms/InstCombine/InstCombineSimplifyDemanded.cpp
index 0c03cc312281f1faf9ec0ad3b8c50fd7b68c2ca6..abd3e39314675ea67c2cd7ad9f54a02758c0204d 100644 (file)
--- a/llvm/lib/Transforms/InstCombine/InstCombineSimplifyDemanded.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineSimplifyDemanded.cpp
@@ -545,6 +545,22 @@ Value *InstCombiner::SimplifyDemandedUseBits(Value *V, APInt DemandedMask,
     }
     break;
   }
+  case Instruction::UDiv: {
+    // UDiv doesn't demand low bits that are zero in the divisor.
+    const APInt *SA;
+    if (match(I->getOperand(1), m_APInt(SA))) {
+      // If the shift is exact, then it does demand the low bits.
+      if (cast<UDivOperator>(I)->isExact())
+        break;
+
+      // FIXME: Take the demanded mask of the result into account.
+      APInt DemandedMaskIn =
+          APInt::getHighBitsSet(BitWidth, BitWidth - SA->countTrailingZeros());
+      if (SimplifyDemandedBits(I, 0, DemandedMaskIn, Known, Depth + 1))
+        return I;
+    }
+    break;
+  }
   case Instruction::SRem:
     if (ConstantInt *Rem = dyn_cast<ConstantInt>(I->getOperand(1))) {
       // X % -1 demands all the bits because we don't want to introduce

diff --git a/llvm/test/Transforms/InstCombine/udiv-simplify.ll b/llvm/test/Transforms/InstCombine/udiv-simplify.ll
index 1794e26d389d627b1cd6083e7408494137361427..8fd604b819e504936b225b672c459dd8dd2a0ab1 100644 (file)
--- a/llvm/test/Transforms/InstCombine/udiv-simplify.ll
+++ b/llvm/test/Transforms/InstCombine/udiv-simplify.ll
@@ -83,3 +83,24 @@ define i177 @ossfuzz_4857(i177 %X, i177 %Y) {
   store i1 %C9, i1* undef
   ret i177 %B1
 }
+
+define i32 @udiv_demanded(i32 %a) {
+; CHECK-LABEL: @udiv_demanded(
+; CHECK-NEXT:    [[U:%.*]] = udiv i32 [[A:%.*]], 12
+; CHECK-NEXT:    ret i32 [[U]]
+;
+  %o = or i32 %a, 3
+  %u = udiv i32 %o, 12
+  ret i32 %u
+}
+
+define i32 @udiv_exact_demanded(i32 %a) {
+; CHECK-LABEL: @udiv_exact_demanded(
+; CHECK-NEXT:    [[O:%.*]] = and i32 [[A:%.*]], -3
+; CHECK-NEXT:    [[U:%.*]] = udiv exact i32 [[O]], 12
+; CHECK-NEXT:    ret i32 [[U]]
+;
+  %o = and i32 %a, -3
+  %u = udiv exact i32 %o, 12
+  ret i32 %u
+}