[llvm] b3c687b - [LV] Check early for supported interleave factors with scalable types [nfc] (#111592)

[via llvm-commits]

Author: Philip Reames
Date: 2024-10-15T07:37:46-07:00
New Revision: b3c687b4e920893f224b28ab8223f1559cb3e209

URL: https://github.com/llvm/llvm-project/commit/b3c687b4e920893f224b28ab8223f1559cb3e209
DIFF: https://github.com/llvm/llvm-project/commit/b3c687b4e920893f224b28ab8223f1559cb3e209.diff

LOG: [LV] Check early for supported interleave factors with scalable types [nfc] (#111592)

Previously, the cost model was returning an invalid cost. This simply
moves the check from one place to another. This is mostly to make the
cost modeling code a bit easier to follow.

---------

Co-authored-by: Mel Chen <mel.chen at sifive.com>

Added: 
    

Modified: 
    llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
    llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
    llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
index 91ab3fcfc4c70e..0227532e94c711 100644
--- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -3743,7 +3743,7 @@ InstructionCost AArch64TTIImpl::getInterleavedMemoryOpCost(
   assert(Factor >= 2 && "Invalid interleave factor");
   auto *VecVTy = cast<VectorType>(VecTy);
 
-  if (VecTy->isScalableTy() && (!ST->hasSVE() || Factor != 2))
+  if (VecTy->isScalableTy() && !ST->hasSVE())
     return InstructionCost::getInvalid();
 
   // Vectorization for masked interleaved accesses is only enabled for scalable

diff  --git a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
index 8d18fd63e4a2e1..cba73abdd15028 100644
--- a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
+++ b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
@@ -675,8 +675,6 @@ InstructionCost RISCVTTIImpl::getInterleavedMemoryOpCost(
     unsigned Opcode, Type *VecTy, unsigned Factor, ArrayRef<unsigned> Indices,
     Align Alignment, unsigned AddressSpace, TTI::TargetCostKind CostKind,
     bool UseMaskForCond, bool UseMaskForGaps) {
-  if (isa<ScalableVectorType>(VecTy) && Factor != 2)
-    return InstructionCost::getInvalid();
 
   // The interleaved memory access pass will lower interleaved memory ops (i.e
   // a load and store followed by a specific shuffle) to vlseg/vsseg

diff  --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index 027ee21527d228..c8cf137816d3a0 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -3413,6 +3413,7 @@ bool LoopVectorizationCostModel::interleavedAccessCanBeWidened(
          "Decision should not be set yet.");
   auto *Group = getInterleavedAccessGroup(I);
   assert(Group && "Must have a group.");
+  unsigned InterleaveFactor = Group->getFactor();
 
   // If the instruction's allocated size doesn't equal it's type size, it
   // requires padding and will be scalarized.
@@ -3421,9 +3422,14 @@ bool LoopVectorizationCostModel::interleavedAccessCanBeWidened(
   if (hasIrregularType(ScalarTy, DL))
     return false;
 
+  // We currently only know how to emit interleave/deinterleave with
+  // Factor=2 for scalable vectors. This is purely an implementation
+  // limit.
+  if (VF.isScalable() && InterleaveFactor != 2)
+    return false;
+
   // If the group involves a non-integral pointer, we may not be able to
   // losslessly cast all values to a common type.
-  unsigned InterleaveFactor = Group->getFactor();
   bool ScalarNI = DL.isNonIntegralPointerType(ScalarTy);
   for (unsigned Idx = 0; Idx < InterleaveFactor; Idx++) {
     Instruction *Member = Group->getMember(Idx);