[PATCH] D70068: [SLP] Enhance SLPVectorizer to vectorize vector aggregate

[Anton Afanasyev via Phabricator via llvm-commits]

anton-afanasyev created this revision.
anton-afanasyev added a reviewer: RKSimon.
Herald added subscribers: llvm-commits, hiraditya.
Herald added a project: LLVM.

Vector aggregate is aggregate of vectors like `{ <2 x float>, <2 x float> }`.
This patch allows `findBuildAggregate()` to consider vector aggregates as
well as scalar ones. For instance, `{ <2 x float>, <2 x float> }` maps to `<4 x float>`.

Fixes vector part of llvm.org/PR42022


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D70068

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


Index: llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
===================================================================
--- llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -611,6 +611,8 @@
   }
 
   /// Check if ArrayType or StructType is isomorphic to some VectorType.
+  /// Accepts homogeneous aggregate of vectors like
+  /// { <2 x float>, <2 x float> }
   ///
   /// \returns number of elements in vector if isomorphism exists, 0 otherwise.
   unsigned canMapToVector(Type *T, const DataLayout &DL) const;
@@ -2872,6 +2874,14 @@
     N = cast<ArrayType>(T)->getNumElements();
     EltTy = cast<ArrayType>(T)->getElementType();
   }
+
+  if (auto *VT = dyn_cast<VectorType>(EltTy)) {
+    if (VT->isScalable())
+      return 0;
+    EltTy = VT->getElementType();
+    N *= VT->getNumElements();
+  }
+
   if (!isValidElementType(EltTy))
     return 0;
   uint64_t VTSize = DL.getTypeStoreSizeInBits(VectorType::get(EltTy, N));
@@ -2880,7 +2890,7 @@
   if (ST) {
     // Check that struct is homogeneous.
     for (const auto *Ty : ST->elements())
-      if (Ty != EltTy)
+      if (Ty != *ST->element_begin())
         return 0;
   }
   return N;
@@ -6745,12 +6755,27 @@
 }
 
 /// Like findBuildVector, but looks for construction of aggregate.
+/// Accepts homegeneous aggregate of vectors like { <2 x float>, <2 x float> }.
 ///
 /// \return true if it matches.
 static bool findBuildAggregate(InsertValueInst *IV,
-                               SmallVectorImpl<Value *> &BuildVectorOpds) {
+                             TargetTransformInfo *TTI,
+                             SmallVectorImpl<Value *> &BuildVectorOpds,
+                             int &UserCost) {
+  UserCost = 0;
   do {
-    BuildVectorOpds.push_back(IV->getInsertedValueOperand());
+    if (auto *IE = dyn_cast<InsertElementInst>(IV->getInsertedValueOperand())) {
+      int TmpUserCost;
+      SmallVector<Value *, 4> TmpBuildVectorOpds;
+      if (!findBuildVector(IE, TTI, TmpBuildVectorOpds, TmpUserCost))
+        return false;
+      for (auto OpdIt = TmpBuildVectorOpds.rbegin();
+           OpdIt != TmpBuildVectorOpds.rend(); OpdIt++)
+        BuildVectorOpds.push_back(*OpdIt);
+      UserCost += TmpUserCost;
+    } else {
+      BuildVectorOpds.push_back(IV->getInsertedValueOperand());
+    }
     Value *V = IV->getAggregateOperand();
     if (isa<UndefValue>(V))
       break;
@@ -6923,18 +6948,19 @@
 
 bool SLPVectorizerPass::vectorizeInsertValueInst(InsertValueInst *IVI,
                                                  BasicBlock *BB, BoUpSLP &R) {
+  int UserCost = 0;
   const DataLayout &DL = BB->getModule()->getDataLayout();
   if (!R.canMapToVector(IVI->getType(), DL))
     return false;
 
   SmallVector<Value *, 16> BuildVectorOpds;
-  if (!findBuildAggregate(IVI, BuildVectorOpds))
+  if (!findBuildAggregate(IVI, TTI, BuildVectorOpds, UserCost))
     return false;
 
   LLVM_DEBUG(dbgs() << "SLP: array mappable to vector: " << *IVI << "\n");
   // Aggregate value is unlikely to be processed in vector register, we need to
   // extract scalars into scalar registers, so NeedExtraction is set true.
-  return tryToVectorizeList(BuildVectorOpds, R);
+  return tryToVectorizeList(BuildVectorOpds, R, UserCost);
 }
 
 bool SLPVectorizerPass::vectorizeInsertElementInst(InsertElementInst *IEI,


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D70068.228642.patch
Type: text/x-patch
Size: 3361 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20191111/f42a9198/attachment-0001.bin>