[PATCH] D97861: [LoopVectorize][NFC] Refactor code to use IRBuilder::CreateStepVector

[David Sherwood via Phabricator via llvm-commits]

david-arm created this revision.
david-arm added reviewers: sdesmalen, kmclaughlin, frasercrmck, ctetreau.
Herald added a subscriber: hiraditya.
david-arm requested review of this revision.
Herald added a project: LLVM.
Herald added a subscriber: llvm-commits.

In places where we create a ConstantVector whose elements are a
linear sequence of the form <start, start + 1, start + 2, ...>
I've changed the code to make use of CreateStepVector, which creates
a vector with the sequence <0, 1, 2, ...>, and a vector addition
operation. This patch is a non-functional change, since the output
from the vectoriser remains unchanged for fixed length vectors and
there are existing asserts that still fire when attempting to use
scalable vectors for vectorising induction variables.

In a later patch we will enable support for scalable vectors
in InnerLoopVectorizer::getStepVector(), which relies upon the new
stepvector intrinsic in IRBuilder::CreateStepVector.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D97861

Files:
  llvm/lib/Transforms/Vectorize/LoopVectorize.cpp


Index: llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
===================================================================
--- llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -2241,7 +2241,7 @@
                                           Instruction::BinaryOps BinOp) {
   // Create and check the types.
   auto *ValVTy = cast<FixedVectorType>(Val->getType());
-  int VLen = ValVTy->getNumElements();
+  ElementCount VLen = ValVTy->getElementCount();
 
   Type *STy = Val->getType()->getScalarType();
   assert((STy->isIntegerTy() || STy->isFloatingPointTy()) &&
@@ -2250,31 +2250,34 @@
 
   SmallVector<Constant *, 8> Indices;
 
-  if (STy->isIntegerTy()) {
-    // Create a vector of consecutive numbers from zero to VF.
-    for (int i = 0; i < VLen; ++i)
-      Indices.push_back(ConstantInt::get(STy, StartIdx + i));
+  // Create a vector of consecutive numbers from zero to VF.
+  VectorType *InitVecValVTy = ValVTy;
+  Type *InitVecValSTy = STy;
+  if (STy->isFloatingPointTy()) {
+    InitVecValSTy =
+        IntegerType::get(STy->getContext(), STy->getScalarSizeInBits());
+    InitVecValVTy = VectorType::get(InitVecValSTy, VLen);
+  }
+  Value *InitVec = Builder.CreateStepVector(InitVecValVTy);
+
+  // Add on StartIdx
+  Value *StartIdxSplat = Builder.CreateVectorSplat(
+      VLen, ConstantInt::get(InitVecValSTy, StartIdx));
+  InitVec = Builder.CreateAdd(InitVec, StartIdxSplat);
 
-    // Add the consecutive indices to the vector value.
-    Constant *Cv = ConstantVector::get(Indices);
-    assert(Cv->getType() == Val->getType() && "Invalid consecutive vec");
+  if (STy->isIntegerTy()) {
     Step = Builder.CreateVectorSplat(VLen, Step);
     assert(Step->getType() == Val->getType() && "Invalid step vec");
     // FIXME: The newly created binary instructions should contain nsw/nuw flags,
     // which can be found from the original scalar operations.
-    Step = Builder.CreateMul(Cv, Step);
+    Step = Builder.CreateMul(InitVec, Step);
     return Builder.CreateAdd(Val, Step, "induction");
   }
 
   // Floating point induction.
   assert((BinOp == Instruction::FAdd || BinOp == Instruction::FSub) &&
          "Binary Opcode should be specified for FP induction");
-  // Create a vector of consecutive numbers from zero to VF.
-  for (int i = 0; i < VLen; ++i)
-    Indices.push_back(ConstantFP::get(STy, (double)(StartIdx + i)));
-
-  // Add the consecutive indices to the vector value.
-  Constant *Cv = ConstantVector::get(Indices);
+  InitVec = Builder.CreateUIToFP(InitVec, ValVTy);
 
   Step = Builder.CreateVectorSplat(VLen, Step);
 
@@ -2282,7 +2285,7 @@
   FastMathFlags Flags;
   Flags.setFast();
 
-  Value *MulOp = Builder.CreateFMul(Cv, Step);
+  Value *MulOp = Builder.CreateFMul(InitVec, Step);
   if (isa<Instruction>(MulOp))
     // Have to check, MulOp may be a constant
     cast<Instruction>(MulOp)->setFastMathFlags(Flags);
@@ -4612,12 +4615,12 @@
     // phi as base and a vectorized version of the step value
     // (<step*0, ..., step*N>) as offset.
     for (unsigned Part = 0; Part < State.UF; ++Part) {
-      SmallVector<Constant *, 8> Indices;
+      Type *VecPhiType = VectorType::get(PhiType, State.VF);
+      Value *StartOffset =
+          ConstantInt::get(VecPhiType, Part * State.VF.getKnownMinValue());
       // Create a vector of consecutive numbers from zero to VF.
-      for (unsigned i = 0; i < State.VF.getKnownMinValue(); ++i)
-        Indices.push_back(
-            ConstantInt::get(PhiType, i + Part * State.VF.getKnownMinValue()));
-      Constant *StartOffset = ConstantVector::get(Indices);
+      StartOffset =
+          Builder.CreateAdd(StartOffset, Builder.CreateStepVector(VecPhiType));
 
       Value *GEP = Builder.CreateGEP(
           ScStValueType->getPointerElementType(), NewPointerPhi,


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D97861.327800.patch
Type: text/x-patch
Size: 3838 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20210303/9a8d9376/attachment.bin>