Masked load/store optimization for scalar code

[delena]

Summary

When the target is unable to handle masked load/store intrinsic, we convert the intrinsic to scalar code. I added optimization for constant mask.

[mkuper]

LGTM with a few nits.

../lib/CodeGen/CodeGenPrepare.cpp

1142

"Shorten the way" -> "Short-cut"

1154

You can load the first scalar with the original alignment, right? (Not that I'm sure it matters any)

1166

Why do you need the temp variable? I think it's just as clear with "if (isa<ConstantVector>Mask)) { ..."
As a different option, you could have
ConstantVector *ConstMask = dyn_cast<ConstantVector>(Mask)

And then use ConstMask in both lines 1167 and 1169.

1286

Same as above.

1304

Same as above.

[delena]

Michael, Thanks a lot for review!

../lib/CodeGen/CodeGenPrepare.cpp

 //else2:                                            ; preds = %else, %cond.load1
 //  %res.phi.else3 = phi <16 x i32> [ %11, %cond.load1 ], [ %res.phi.else, %else ]
 //  %12 = extractelement <16 x i1> %mask, i32 2
 //  %13 = icmp eq i1 %12, true
 //  br i1 %13, label %cond.load4, label %else5
 //
 static void ScalarizeMaskedLoad(CallInst *CI) {
   Value *Ptr  = CI->getArgOperand(0);
-  Value *Src0 = CI->getArgOperand(3);
+  Value *Alignment = CI->getArgOperand(1);
   Value *Mask = CI->getArgOperand(2);
-  VectorType *VecType = dyn_cast<VectorType>(CI->getType());
-  Type *EltTy = VecType->getElementType();
+  Value *Src0 = CI->getArgOperand(3);
 
+  unsigned AlignVal = cast<ConstantInt>(Alignment)->getZExtValue();
+  VectorType *VecType = dyn_cast<VectorType>(CI->getType());
   assert(VecType && "Unexpected return type of masked load intrinsic");
 
+  Type *EltTy = CI->getType()->getVectorElementType();
+
   IRBuilder<> Builder(CI->getContext());
   Instruction *InsertPt = CI;
   BasicBlock *IfBlock = CI->getParent();
   BasicBlock *CondBlock = nullptr;
   BasicBlock *PrevIfBlock = CI->getParent();
-  Builder.SetInsertPoint(InsertPt);
 
+  Builder.SetInsertPoint(InsertPt);
   Builder.SetCurrentDebugLocation(CI->getDebugLoc());
 
+  // Shorten the way if the mask is all-true.
+  bool IsAllOnesMask = isa<Constant>(Mask) &&
+    cast<Constant>(Mask)->isAllOnesValue();
+
+  if (IsAllOnesMask) {
+    Value *NewI = Builder.CreateAlignedLoad(Ptr, AlignVal);
+    CI->replaceAllUsesWith(NewI);
+    CI->eraseFromParent();
+    return;
+  }
+
+  // Adjust alignment for the scalar instruction.
+  AlignVal = std::min(AlignVal, VecType->getScalarSizeInBits()/8);
   // Bitcast %addr fron i8* to EltTy*
   Type *NewPtrType =
     EltTy->getPointerTo(cast<PointerType>(Ptr->getType())->getAddressSpace());
   Value *FirstEltPtr = Builder.CreateBitCast(Ptr, NewPtrType);
+  unsigned VectorWidth = VecType->getNumElements();
+
   Value *UndefVal = UndefValue::get(VecType);
 
   // The result vector
   Value *VResult = UndefVal;
 
+  bool IsConstMask = isa<ConstantVector>(Mask);
+  if (IsConstMask) {
+    for (unsigned Idx = 0; Idx < VectorWidth; ++Idx) {
+      if (cast<ConstantVector>(Mask)->getOperand(Idx)->isNullValue())
+          continue;
+      Value *Gep =
+          Builder.CreateInBoundsGEP(EltTy, FirstEltPtr, Builder.getInt32(Idx));
+      LoadInst* Load = Builder.CreateAlignedLoad(Gep, AlignVal);
+      VResult = Builder.CreateInsertElement(VResult, Load,
+                                            Builder.getInt32(Idx));
+    }
+    Value *NewI = Builder.CreateSelect(Mask, VResult, Src0);
+    CI->replaceAllUsesWith(NewI);
+    CI->eraseFromParent();
+    return;
+  }
+
   PHINode *Phi = nullptr;
   Value *PrevPhi = UndefVal;
 
-  unsigned VectorWidth = VecType->getNumElements();
   for (unsigned Idx = 0; Idx < VectorWidth; ++Idx) {
 
     // Fill the "else" block, created in the previous iteration
     //
     //  %res.phi.else3 = phi <16 x i32> [ %11, %cond.load1 ], [ %res.phi.else, %else ]
     //  %mask_1 = extractelement <16 x i1> %mask, i32 Idx
     //  %to_load = icmp eq i1 %mask_1, true
     //  br i1 %to_load, label %cond.load, label %else
for (unsigned Idx = 0; Idx < VectorWidth; ++Idx) {
     //  %Elt = load i32* %EltAddr
     //  VResult = insertelement <16 x i32> VResult, i32 %Elt, i32 Idx
     //
     CondBlock = IfBlock->splitBasicBlock(InsertPt->getIterator(), "cond.load");
     Builder.SetInsertPoint(InsertPt);
 
     Value *Gep =
         Builder.CreateInBoundsGEP(EltTy, FirstEltPtr, Builder.getInt32(Idx));
-    LoadInst* Load = Builder.CreateLoad(Gep, false);
+    LoadInst* Load = Builder.CreateAlignedLoad(Gep, AlignVal);
     VResult = Builder.CreateInsertElement(VResult, Load, Builder.getInt32(Idx));
 
     // Create "else" block, fill it in the next iteration
     BasicBlock *NewIfBlock =
         CondBlock->splitBasicBlock(InsertPt->getIterator(), "else");
     Builder.SetInsertPoint(InsertPt);
     Instruction *OldBr = IfBlock->getTerminator();
     BranchInst::Create(CondBlock, NewIfBlock, Cmp, OldBr);

 // 
 // cond.store1:                                      ; preds = %else
 //   %8 = extractelement <16 x i32> %val, i32 1
 //   %9 = getelementptr i32* %1, i32 1
 //   store i32 %8, i32* %9
 //   br label %else2
 //   . . .
 static void ScalarizeMaskedStore(CallInst *CI) {
-  Value *Ptr  = CI->getArgOperand(1);
   Value *Src = CI->getArgOperand(0);
+  Value *Ptr  = CI->getArgOperand(1);
+  Value *Alignment = CI->getArgOperand(2);
   Value *Mask = CI->getArgOperand(3);
 
+  unsigned AlignVal = cast<ConstantInt>(Alignment)->getZExtValue();
   VectorType *VecType = dyn_cast<VectorType>(Src->getType());
-  Type *EltTy = VecType->getElementType();
-
   assert(VecType && "Unexpected data type in masked store intrinsic");
 
+  Type *EltTy = VecType->getElementType();
+
   IRBuilder<> Builder(CI->getContext());
   Instruction *InsertPt = CI;
   BasicBlock *IfBlock = CI->getParent();
   Builder.SetInsertPoint(InsertPt);
   Builder.SetCurrentDebugLocation(CI->getDebugLoc());
 
+  // Shorten the way if the mask is all-true.
+  bool IsAllOnesMask = isa<Constant>(Mask) &&
+    cast<Constant>(Mask)->isAllOnesValue();
+
+  if (IsAllOnesMask) {
+    Builder.CreateAlignedStore(Src, Ptr, AlignVal);
+    CI->eraseFromParent();
+    return;
+  }
+
+  // Adjust alignment for the scalar instruction.
+  AlignVal = std::max(AlignVal, VecType->getScalarSizeInBits()/8);
   // Bitcast %addr fron i8* to EltTy*
   Type *NewPtrType =
     EltTy->getPointerTo(cast<PointerType>(Ptr->getType())->getAddressSpace());
   Value *FirstEltPtr = Builder.CreateBitCast(Ptr, NewPtrType);
-
   unsigned VectorWidth = VecType->getNumElements();
+
+  bool IsConstMask = isa<ConstantVector>(Mask);
+  if (IsConstMask) {
+    for (unsigned Idx = 0; Idx < VectorWidth; ++Idx) {
+      if (cast<ConstantVector>(Mask)->getOperand(Idx)->isNullValue())
+          continue;
+      Value *OneElt = Builder.CreateExtractElement(Src, Builder.getInt32(Idx));
+      Value *Gep =
+          Builder.CreateInBoundsGEP(EltTy, FirstEltPtr, Builder.getInt32(Idx));
+      Builder.CreateAlignedStore(OneElt, Gep, AlignVal);
+    }
+    CI->eraseFromParent();
+    return;
+  }
+
   for (unsigned Idx = 0; Idx < VectorWidth; ++Idx) {
 
     // Fill the "else" block, created in the previous iteration
     //
     //  %mask_1 = extractelement <16 x i1> %mask, i32 Idx
     //  %to_store = icmp eq i1 %mask_1, true
-    //  br i1 %to_load, label %cond.store, label %else
+    //  br i1 %to_store, label %cond.store, label %else
     //
     Value *Predicate = Builder.CreateExtractElement(Mask, Builder.getInt32(Idx));
     Value *Cmp = Builder.CreateICmp(ICmpInst::ICMP_EQ, Predicate,
                                     ConstantInt::get(Predicate->getType(), 1));
 
     // Create "cond" block
     //
     //  %OneElt = extractelement <16 x i32> %Src, i32 Idx
     //  %EltAddr = getelementptr i32* %1, i32 0
     //  %store i32 %OneElt, i32* %EltAddr
     //
     BasicBlock *CondBlock =
         IfBlock->splitBasicBlock(InsertPt->getIterator(), "cond.store");
     Builder.SetInsertPoint(InsertPt);
 
     Value *OneElt = Builder.CreateExtractElement(Src, Builder.getInt32(Idx));
     Value *Gep =
         Builder.CreateInBoundsGEP(EltTy, FirstEltPtr, Builder.getInt32(Idx));
-    Builder.CreateStore(OneElt, Gep);
+    Builder.CreateAlignedStore(OneElt, Gep, AlignVal);
 
     // Create "else" block, fill it in the next iteration
     BasicBlock *NewIfBlock =
         CondBlock->splitBasicBlock(InsertPt->getIterator(), "else");
     Builder.SetInsertPoint(InsertPt);
     Instruction *OldBr = IfBlock->getTerminator();
     BranchInst::Create(CondBlock, NewIfBlock, Cmp, OldBr);
     OldBr->eraseFromParent();

../test/CodeGen/X86/masked_memop.ll

define <2 x i32> @test17(<2 x i32> %trigger, <2 x i32>* %addr, <2 x i32> %dst) {
   %mask = icmp eq <2 x i32> %trigger, zeroinitializer
   %res = call <2 x i32> @llvm.masked.load.v2i32(<2 x i32>* %addr, i32 4, <2 x i1>%mask, <2 x i32>%dst)
   ret <2 x i32> %res
 }
 
 ; AVX2-LABEL: test18
 ; AVX2: vmaskmovps
 ; AVX2-NOT: blend
+; AVX2: ret
 define <2 x float> @test18(<2 x i32> %trigger, <2 x float>* %addr) {
   %mask = icmp eq <2 x i32> %trigger, zeroinitializer
   %res = call <2 x float> @llvm.masked.load.v2f32(<2 x float>* %addr, i32 4, <2 x i1>%mask, <2 x float>undef)
   ret <2 x float> %res
 }
 
+; AVX_SCALAR-LABEL: test19
+; AVX_SCALAR: load <4 x float>, <4 x float>* %addr, align 4
+
+define <4 x float> @test19(<4 x i32> %trigger, <4 x float>* %addr) {
+  %mask = icmp eq <4 x i32> %trigger, zeroinitializer
+  %res = call <4 x float> @llvm.masked.load.v4f32(<4 x float>* %addr, i32 4, <4 x i1><i1 true, i1 true, i1 true, i1 true>, <4 x float>undef)
+  ret <4 x float> %res
+}
+
+; AVX_SCALAR-LABEL: test20
+; AVX_SCALAR: load float, {{.*}}, align 4
+; AVX_SCALAR: insertelement <4 x float> undef, float
+; AVX_SCALAR: select <4 x i1> <i1 true, i1 false, i1 true, i1 true>
+
+define <4 x float> @test20(<4 x i32> %trigger, <4 x float>* %addr, <4 x float> %src0) {
+  %mask = icmp eq <4 x i32> %trigger, zeroinitializer
+  %res = call <4 x float> @llvm.masked.load.v4f32(<4 x float>* %addr, i32 16, <4 x i1><i1 true, i1 false, i1 true, i1 true>, <4 x float> %src0)
+  ret <4 x float> %res
+}
+
+; AVX_SCALAR-LABEL: test21
+; AVX_SCALAR: store <4 x i32> %val
+define void @test21(<4 x i32> %trigger, <4 x i32>* %addr, <4 x i32> %val) {
+  %mask = icmp eq <4 x i32> %trigger, zeroinitializer
+  call void @llvm.masked.store.v4i32(<4 x i32>%val, <4 x i32>* %addr, i32 4, <4 x i1><i1 true, i1 true, i1 true, i1 true>)
+  ret void
+}
+
+; AVX_SCALAR-LABEL: test22
+; AVX_SCALAR: extractelement <4 x i32> %val, i32 0
+; AVX_SCALAR:  store i32
+define void @test22(<4 x i32> %trigger, <4 x i32>* %addr, <4 x i32> %val) {
+  %mask = icmp eq <4 x i32> %trigger, zeroinitializer
+  call void @llvm.masked.store.v4i32(<4 x i32>%val, <4 x i32>* %addr, i32 4, <4 x i1><i1 true, i1 false, i1 false, i1 false>)
+  ret void
+}
 
 declare <16 x i32> @llvm.masked.load.v16i32(<16 x i32>*, i32, <16 x i1>, <16 x i32>)
 declare <4 x i32> @llvm.masked.load.v4i32(<4 x i32>*, i32, <4 x i1>, <4 x i32>)
 declare <2 x i32> @llvm.masked.load.v2i32(<2 x i32>*, i32, <2 x i1>, <2 x i32>)
 declare void @llvm.masked.store.v16i32(<16 x i32>, <16 x i32>*, i32, <16 x i1>)
 declare void @llvm.masked.store.v8i32(<8 x i32>, <8 x i32>*, i32, <8 x i1>)
 declare void @llvm.masked.store.v4i32(<4 x i32>, <4 x i32>*, i32, <4 x i1>)
 declare void @llvm.masked.store.v2f32(<2 x float>, <2 x float>*, i32, <2 x i1>)