[PATCH] D129473: [LV] Make scalable-vectorization not work if there is a specified scalable pragma hint.

[Yeting Kuo via Phabricator via llvm-commits]

fakepaper56 updated this revision to Diff 443827.
fakepaper56 added a comment.

Add test case and remove some dead code.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D129473/new/

https://reviews.llvm.org/D129473

Files:
  llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp
  llvm/test/Transforms/LoopVectorize/metadata-scalable.ll


Index: llvm/test/Transforms/LoopVectorize/metadata-scalable.ll
===================================================================
--- /dev/null
+++ llvm/test/Transforms/LoopVectorize/metadata-scalable.ll
@@ -0,0 +1,57 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -S -loop-vectorize -scalable-vectorization=on < %s | FileCheck %s
+
+; Test metadata has bigger priority than option -scalable-vectorization=
+
+define void @foo(i32 %N, ptr noalias %a, ptr noalias %b) {
+; CHECK-LABEL: @foo(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[CMP6:%.*]] = icmp sgt i32 [[N:%.*]], 0
+; CHECK-NEXT:    br i1 [[CMP6]], label [[FOR_BODY_PREHEADER:%.*]], label [[FOR_COND_CLEANUP:%.*]]
+; CHECK:       for.body.preheader:
+; CHECK-NEXT:    [[WIDE_TRIP_COUNT:%.*]] = zext i32 [[N]] to i64
+; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
+; CHECK:       for.cond.cleanup.loopexit:
+; CHECK-NEXT:    br label [[FOR_COND_CLEANUP]]
+; CHECK:       for.cond.cleanup:
+; CHECK-NEXT:    ret void
+; CHECK:       for.body:
+; CHECK-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ 0, [[FOR_BODY_PREHEADER]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
+; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds float, ptr [[A:%.*]], i64 [[INDVARS_IV]]
+; CHECK-NEXT:    [[TMP0:%.*]] = load float, ptr [[ARRAYIDX]], align 4
+; CHECK-NEXT:    [[ADD:%.*]] = fadd fast float [[TMP0]], 1.000000e+00
+; CHECK-NEXT:    [[ARRAYIDX2:%.*]] = getelementptr inbounds float, ptr [[B:%.*]], i64 [[INDVARS_IV]]
+; CHECK-NEXT:    store float [[ADD]], ptr [[ARRAYIDX2]], align 4
+; CHECK-NEXT:    [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
+; CHECK-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], [[WIDE_TRIP_COUNT]]
+; CHECK-NEXT:    br i1 [[EXITCOND_NOT]], label [[FOR_COND_CLEANUP_LOOPEXIT:%.*]], label [[FOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
+;
+entry:
+  %cmp6 = icmp sgt i32 %N, 0
+  br i1 %cmp6, label %for.body.preheader, label %for.cond.cleanup
+
+for.body.preheader:                               ; preds = %entry
+  %wide.trip.count = zext i32 %N to i64
+  br label %for.body
+
+for.cond.cleanup.loopexit:                        ; preds = %for.body
+  br label %for.cond.cleanup
+
+for.cond.cleanup:                                 ; preds = %for.cond.cleanup.loopexit, %entry
+  ret void
+
+for.body:                                         ; preds = %for.body.preheader, %for.body
+  %indvars.iv = phi i64 [ 0, %for.body.preheader ], [ %indvars.iv.next, %for.body ]
+  %arrayidx = getelementptr inbounds float, ptr %a, i64 %indvars.iv
+  %0 = load float, ptr %arrayidx, align 4
+  %add = fadd fast float %0, 1.000000e+00
+  %arrayidx2 = getelementptr inbounds float, ptr %b, i64 %indvars.iv
+  store float %add, ptr %arrayidx2, align 4
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond.not = icmp eq i64 %indvars.iv.next, %wide.trip.count
+  br i1 %exitcond.not, label %for.cond.cleanup.loopexit, label %for.body, !llvm.loop !0
+}
+
+!0 = distinct !{!0, !1, !2}
+!1 = !{!"llvm.loop.vectorize.width", i32 1}
+!2 = !{!"llvm.loop.vectorize.scalable.enable", i1 false}
Index: llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp
===================================================================
--- llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp
+++ llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp
@@ -128,17 +128,13 @@
       // property, then assume it concerns only a fixed-width UserVF.
       // If width is not set, the flag takes precedence.
       Scalable.Value = SK_FixedWidthOnly;
-  }
-
-  // If the flag is set to force any use of scalable vectors, override the loop
-  // hints.
-  if (ForceScalableVectorization.getValue() !=
-      LoopVectorizeHints::SK_Unspecified)
-    Scalable.Value = ForceScalableVectorization.getValue();
 
-  // Scalable vectorization is disabled if no preference is specified.
-  if ((LoopVectorizeHints::ScalableForceKind)Scalable.Value == SK_Unspecified)
-    Scalable.Value = SK_FixedWidthOnly;
+    // If the flag is set to force any use of scalable vectors, override the
+    // loop hints.
+    if (ForceScalableVectorization.getValue() !=
+        LoopVectorizeHints::SK_Unspecified)
+      Scalable.Value = ForceScalableVectorization.getValue();
+  }
 
   if (IsVectorized.Value != 1)
     // If the vectorization width and interleaving count are both 1 then


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D129473.443827.patch
Type: text/x-patch
Size: 4393 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20220712/4d7ad622/attachment.bin>