[PATCH] D113680: [AArch64][SVE] Remove i1 type from isElementTypeLegalForScalableVector

[Kerry McLaughlin via Phabricator via llvm-commits]

kmclaughlin created this revision.
kmclaughlin added reviewers: sdesmalen, david-arm, fhahn.
Herald added subscribers: psnobl, hiraditya, kristof.beyls, tschuett.
Herald added a reviewer: efriedma.
kmclaughlin requested review of this revision.
Herald added a project: LLVM.
Herald added a subscriber: llvm-commits.

`collectElementTypesForWidening` collects the types of load, store and
reduction Phis in a loop. These types are later checked using
`isElementTypeLegalForScalableVector` to prevent vectorisation of
loops with instruction types that are unsupported.

This patch removes i1 from the list of types supported for scalable
vectors. This fixes an assert ("Cannot yet scalarize uniform stores") in
`setCostBasedWideningDecision` when we have a loop containing a uniform
i1 store and a scalable VF, which we cannot create a scatter for.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D113680

Files:
  llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h
  llvm/test/Transforms/LoopVectorize/AArch64/sve-illegal-type.ll


Index: llvm/test/Transforms/LoopVectorize/AArch64/sve-illegal-type.ll
===================================================================
--- llvm/test/Transforms/LoopVectorize/AArch64/sve-illegal-type.ll
+++ llvm/test/Transforms/LoopVectorize/AArch64/sve-illegal-type.ll
@@ -79,6 +79,35 @@
   ret void
 }
 
+; CHECK-REMARKS: Scalable vectorization is not supported for all element types found in this loop
+define void @uniform_store_i1(i1* noalias %dst, i64* noalias %start, i64 %N) {
+; CHECK-LABEL: @uniform_store_i1
+; CHECK: vector.body
+; CHECK: %[[GEP:.*]] = getelementptr inbounds i64, <2 x i64*> {{.*}}, i64 1
+; CHECK: %[[ICMP:.*]] = icmp eq <2 x i64*> %[[GEP]], %[[SPLAT:.*]]
+; CHECK: %[[EXTRACT1:.*]] = extractelement <2 x i1> %[[ICMP]], i32 0
+; CHECK: store i1 %[[EXTRACT1]], i1* %dst
+; CHECK: %[[EXTRACT2:.*]] = extractelement <2 x i1> %[[ICMP]], i32 1
+; CHECK: store i1 %[[EXTRACT2]], i1* %dst
+; CHECK-NOT: vscale
+entry:
+  br label %for.body
+
+for.body:
+  %first.sroa = phi i64* [ %incdec.ptr, %for.body ], [ %start, %entry ]
+  %iv = phi i64 [ %iv.next, %for.body ], [ 0, %entry ]
+  %iv.next = add i64 %iv, 1
+  %0 = load i64, i64* %first.sroa
+  %incdec.ptr = getelementptr inbounds i64, i64* %first.sroa, i64 1
+  %cmp.not = icmp eq i64* %incdec.ptr, %start
+  store i1 %cmp.not, i1* %dst
+  %cmp = icmp ult i64 %iv, %N
+  br i1 %cmp, label %for.body, label %end, !llvm.loop !0
+
+end:
+  ret void
+}
+
 define dso_local void @loop_fixed_width_i128(i128* nocapture %ptr, i64 %N) {
 ; CHECK-LABEL: @loop_fixed_width_i128
 ; CHECK: load <4 x i128>, <4 x i128>*
Index: llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h
===================================================================
--- llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h
+++ llvm/lib/Target/AArch64/AArch64TargetTransformInfo.h
@@ -226,7 +226,7 @@
     if (Ty->isHalfTy() || Ty->isFloatTy() || Ty->isDoubleTy())
       return true;
 
-    if (Ty->isIntegerTy(1) || Ty->isIntegerTy(8) || Ty->isIntegerTy(16) ||
+    if (Ty->isIntegerTy(8) || Ty->isIntegerTy(16) ||
         Ty->isIntegerTy(32) || Ty->isIntegerTy(64))
       return true;
 
@@ -241,8 +241,7 @@
     if (isa<FixedVectorType>(DataType) && !ST->useSVEForFixedLengthVectors())
       return false; // Fall back to scalarization of masked operations.
 
-    return !DataType->getScalarType()->isIntegerTy(1) &&
-           isElementTypeLegalForScalableVector(DataType->getScalarType());
+    return isElementTypeLegalForScalableVector(DataType->getScalarType());
   }
 
   bool isLegalMaskedLoad(Type *DataType, Align Alignment) {
@@ -263,8 +262,7 @@
                          DataTypeFVTy->getNumElements() < 2))
       return false;
 
-    return !DataType->getScalarType()->isIntegerTy(1) &&
-           isElementTypeLegalForScalableVector(DataType->getScalarType());
+    return isElementTypeLegalForScalableVector(DataType->getScalarType());
   }
 
   bool isLegalMaskedGather(Type *DataType, Align Alignment) const {


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D113680.386523.patch
Type: text/x-patch
Size: 2985 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20211111/53187daa/attachment.bin>