[InstCombine, ARM] Convert vld1 to llvm load
Convert a vector load intrinsic into an llvm load instruction.
This is beneficial when the underlying object being addressed
comes from a constant, since we get constant-folding for free.
Differential Revision: https://reviews.llvm.org/D46273
llvm-svn: 333643
diff --git a/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp b/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
index 7fbf068..b79ac6b 100644
--- a/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
@@ -1427,6 +1427,28 @@
return Builder.CreateShuffleVector(V1, V2, ShuffleMask);
}
+/// Convert a vector load intrinsic into a simple llvm load instruction.
+/// This is beneficial when the underlying object being addressed comes
+/// from a constant, since we get constant-folding for free.
+static Value *simplifyNeonVld1(const IntrinsicInst &II,
+ unsigned MemAlign,
+ InstCombiner::BuilderTy &Builder) {
+ auto *IntrAlign = dyn_cast<ConstantInt>(II.getArgOperand(1));
+
+ if (!IntrAlign)
+ return nullptr;
+
+ unsigned Alignment = IntrAlign->getLimitedValue() < MemAlign ?
+ MemAlign : IntrAlign->getLimitedValue();
+
+ if (!isPowerOf2_32(Alignment))
+ return nullptr;
+
+ auto *BCastInst = Builder.CreateBitCast(II.getArgOperand(0),
+ PointerType::get(II.getType(), 0));
+ return Builder.CreateAlignedLoad(BCastInst, Alignment);
+}
+
// Returns true iff the 2 intrinsics have the same operands, limiting the
// comparison to the first NumOperands.
static bool haveSameOperands(const IntrinsicInst &I, const IntrinsicInst &E,
@@ -2941,7 +2963,14 @@
}
break;
- case Intrinsic::arm_neon_vld1:
+ case Intrinsic::arm_neon_vld1: {
+ unsigned MemAlign = getKnownAlignment(II->getArgOperand(0),
+ DL, II, &AC, &DT);
+ if (Value *V = simplifyNeonVld1(*II, MemAlign, Builder))
+ return replaceInstUsesWith(*II, V);
+ break;
+ }
+
case Intrinsic::arm_neon_vld2:
case Intrinsic::arm_neon_vld3:
case Intrinsic::arm_neon_vld4: