diff options
| -rw-r--r-- | llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp | 22 | ||||
| -rw-r--r-- | llvm/test/Transforms/InstCombine/masked_intrinsics.ll | 18 |
2 files changed, 39 insertions, 1 deletions
diff --git a/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp b/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp index ede5aeb1cd1..753c8fac96a 100644 --- a/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp +++ b/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp @@ -773,6 +773,25 @@ static Value *simplifyMaskedLoad(const IntrinsicInst &II, return nullptr; } +static Instruction *simplifyMaskedStore(IntrinsicInst &II, InstCombiner &IC) { + auto *ConstMask = dyn_cast<Constant>(II.getArgOperand(3)); + if (!ConstMask) + return nullptr; + + // If the mask is all zeros, this instruction does nothing. + if (ConstMask->isNullValue()) + return IC.EraseInstFromFunction(II); + + // If the mask is all ones, this is a plain vector store of the 1st argument. + if (ConstMask->isAllOnesValue()) { + Value *StorePtr = II.getArgOperand(1); + unsigned Alignment = cast<ConstantInt>(II.getArgOperand(2))->getZExtValue(); + return new StoreInst(II.getArgOperand(0), StorePtr, false, Alignment); + } + + return nullptr; +} + /// CallInst simplification. This mostly only handles folding of intrinsic /// instructions. For normal calls, it allows visitCallSite to do the heavy /// lifting. @@ -901,9 +920,10 @@ Instruction *InstCombiner::visitCallInst(CallInst &CI) { if (Value *SimplifiedMaskedOp = simplifyMaskedLoad(*II, *Builder)) return ReplaceInstUsesWith(CI, SimplifiedMaskedOp); break; + case Intrinsic::masked_store: + return simplifyMaskedStore(*II, *this); // TODO: Handle the other masked ops. - // case Intrinsic::masked_store: // case Intrinsic::masked_gather: // case Intrinsic::masked_scatter: diff --git a/llvm/test/Transforms/InstCombine/masked_intrinsics.ll b/llvm/test/Transforms/InstCombine/masked_intrinsics.ll index 3289e3d7744..b40c62784aa 100644 --- a/llvm/test/Transforms/InstCombine/masked_intrinsics.ll +++ b/llvm/test/Transforms/InstCombine/masked_intrinsics.ll @@ -1,6 +1,7 @@ ; RUN: opt -instcombine -S < %s | FileCheck %s declare <2 x double> @llvm.masked.load.v2f64(<2 x double>* %ptrs, i32, <2 x i1> %mask, <2 x double> %src0) +declare void @llvm.masked.store.v2f64(<2 x double> %val, <2 x double>* %ptrs, i32, <2 x i1> %mask) define <2 x double> @load_zeromask(<2 x double>* %ptr, <2 x double> %passthru) { @@ -20,3 +21,20 @@ define <2 x double> @load_onemask(<2 x double>* %ptr, <2 x double> %passthru) { ; CHECK-NEXT: ret <2 x double> %unmaskedload } +define void @store_zeromask(<2 x double>* %ptr, <2 x double> %val) { + call void @llvm.masked.store.v2f64(<2 x double> %val, <2 x double>* %ptr, i32 3, <2 x i1> zeroinitializer) + ret void + +; CHECK-LABEL: @store_zeromask( +; CHECK-NEXT: ret void +} + +define void @store_onemask(<2 x double>* %ptr, <2 x double> %val) { + call void @llvm.masked.store.v2f64(<2 x double> %val, <2 x double>* %ptr, i32 4, <2 x i1> <i1 1, i1 1>) + ret void + +; CHECK-LABEL: @store_onemask( +; CHECK-NEXT: store <2 x double> %val, <2 x double>* %ptr, align 4 +; CHECK-NEXT: ret void +} + |
