[PATCH] D97465: [LoopVectorize] Refine hasIrregularType predicate

[LemonBoy via Phabricator via llvm-commits]

LemonBoy created this revision.
LemonBoy added reviewers: mkuper, fhahn, craig.topper.
Herald added subscribers: hiraditya, kristof.beyls.
LemonBoy requested review of this revision.
Herald added a project: LLVM.
Herald added a subscriber: llvm-commits.

The `hasIrregularType` predicate checks whether an array of N values of type Ty is "bitcast-compatible" with a <N x Ty> vector.
The previous check returned invalid results in some cases where there's some padding between the array elements: eg. a 4-element array of u7 values is considered as compatible with <4 x u7>, even though the vector is only loading/storing 28 bits instead of 32.

The problem causes LLVM to generate incorrect code for some targets: for AArch64 the vector loads/stores are lowered in terms of ubfx/bfi, effectively losing the top (N * padding bits).


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D97465

Files:
  llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
  llvm/test/Transforms/LoopVectorize/irregular_type.ll


Index: llvm/test/Transforms/LoopVectorize/irregular_type.ll
===================================================================
--- /dev/null
+++ llvm/test/Transforms/LoopVectorize/irregular_type.ll
@@ -0,0 +1,24 @@
+; RUN: opt %s -loop-vectorize -force-vector-width=4 -S | FileCheck %s
+
+; CHECK: foo
+; CHECK: vector.body
+; CHECK-NOT: load <4 x i7>
+; CHECK-NOT: store <4 x i7>
+; CHECK: for.body
+define void @foo(i7* %a, i64 %n) {
+entry:
+  br label %for.body
+
+for.body:
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %arrayidx = getelementptr inbounds i7, i7* %a, i64 %indvars.iv
+  %0 = load i7, i7* %arrayidx, align 1
+  %sub = add nuw nsw i7 %0, 0
+  store i7 %sub, i7* %arrayidx, align 1
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %cmp = icmp eq i64 %indvars.iv.next, %n
+  br i1 %cmp, label %for.exit, label %for.body
+
+for.exit:
+  ret void
+}
Index: llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
===================================================================
--- llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -376,15 +376,7 @@
 static bool hasIrregularType(Type *Ty, const DataLayout &DL, ElementCount VF) {
   // Determine if an array of VF elements of type Ty is "bitcast compatible"
   // with a <VF x Ty> vector.
-  if (VF.isVector()) {
-    auto *VectorTy = VectorType::get(Ty, VF);
-    return TypeSize::get(VF.getKnownMinValue() *
-                             DL.getTypeAllocSize(Ty).getFixedValue(),
-                         VF.isScalable()) != DL.getTypeStoreSize(VectorTy);
-  }
-
-  // If the vectorization factor is one, we just check if an array of type Ty
-  // requires padding between elements.
+  // This is only true if there is no padding between the array elements.
   return DL.getTypeAllocSizeInBits(Ty) != DL.getTypeSizeInBits(Ty);
 }
 


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D97465.326369.patch
Type: text/x-patch
Size: 1885 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20210225/e50b3d97/attachment.bin>