Recommit "[Clang] Pragma vectorize_width() implies vectorize(enable)"

This was further discussed at the llvm dev list:

http://lists.llvm.org/pipermail/llvm-dev/2019-October/135602.html

I think the brief summary of that is that this change is an improvement,
this is the behaviour that we expect and promise in ours docs, and also
as a result there are cases where we now emit diagnostics whereas before
pragmas were silently ignored. Two areas where we can improve: 1) the
diagnostic message itself, and 2) and in some cases (e.g. -Os and -Oz)
the vectoriser is (quite understandably) not triggering.

Original commit message:

Specifying the vectorization width was supposed to implicitly enable
vectorization, except that it wasn't really doing this. It was only
setting the vectorize.width metadata, but not vectorize.enable.

This should fix PR27643.

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@374288 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/CodeGen/CGLoopInfo.cpp b/lib/CodeGen/CGLoopInfo.cpp
index 6822c6286fef132b64a6ed97cd70e77c25320519..c21d4feee7a8c117cd797f323274707275ef22a0 100644 (file)
--- a/lib/CodeGen/CGLoopInfo.cpp
+++ b/lib/CodeGen/CGLoopInfo.cpp
@@ -270,6 +270,14 @@ LoopInfo::createLoopVectorizeMetadata(const LoopAttributes &Attrs,
 
   // Setting vectorize.width
   if (Attrs.VectorizeWidth > 0) {
+    // This implies vectorize.enable = true, but only add it when it is not
+    // already enabled.
+    if (Attrs.VectorizeEnable != LoopAttributes::Enable)
+      Args.push_back(
+          MDNode::get(Ctx, {MDString::get(Ctx, "llvm.loop.vectorize.enable"),
+                            ConstantAsMetadata::get(ConstantInt::get(
+                                llvm::Type::getInt1Ty(Ctx), 1))}));
+
     Metadata *Vals[] = {
         MDString::get(Ctx, "llvm.loop.vectorize.width"),
         ConstantAsMetadata::get(ConstantInt::get(llvm::Type::getInt32Ty(Ctx),

diff --git a/test/CodeGenCXX/pragma-loop-predicate.cpp b/test/CodeGenCXX/pragma-loop-predicate.cpp
index ec2161d1772ec750b738a77dc46f3a81c64cec36..33e4cf5df4f477ab258cf4da0551f64c506b9b80 100644 (file)
--- a/test/CodeGenCXX/pragma-loop-predicate.cpp
+++ b/test/CodeGenCXX/pragma-loop-predicate.cpp
@@ -58,7 +58,6 @@ void test5(int *List, int Length) {
     List[i] = i * 2;
 }
 
-
 // CHECK:      ![[LOOP0]] = distinct !{![[LOOP0]], !3}
 // CHECK-NEXT: !3 = !{!"llvm.loop.vectorize.enable", i1 true}
 
@@ -70,7 +69,7 @@ void test5(int *List, int Length) {
 
 // CHECK-NEXT: ![[LOOP3]] = distinct !{![[LOOP3]], !5, !3}
 
-// CHECK-NEXT: ![[LOOP4]] = distinct !{![[LOOP4]], !10}
+// CHECK-NEXT: ![[LOOP4]] = distinct !{![[LOOP4]], !3, !10}
 // CHECK-NEXT: !10 = !{!"llvm.loop.vectorize.width", i32 1}
 
-// CHECK-NEXT: ![[LOOP5]] = distinct !{![[LOOP5]], !10}
+// CHECK-NEXT: ![[LOOP5]] = distinct !{![[LOOP5]], !3, !10}

diff --git a/test/CodeGenCXX/pragma-loop.cpp b/test/CodeGenCXX/pragma-loop.cpp
index 32075f965cd78052c8d5b5525651bff942d7e47a..6b44dff4030e7bf42a683c8394977a22160f2995 100644 (file)
--- a/test/CodeGenCXX/pragma-loop.cpp
+++ b/test/CodeGenCXX/pragma-loop.cpp
@@ -158,23 +158,41 @@ void template_test(double *List, int Length) {
   for_template_constant_expression_test<double, 2, 4, 8>(List, Length);
 }
 
+void vec_width_1(int *List, int Length) {
+// CHECK-LABEL: @{{.*}}vec_width_1{{.*}}(
+// CHECK: br label {{.*}}, !llvm.loop ![[LOOP_15:.*]]
+
+  #pragma clang loop vectorize(enable) vectorize_width(1)
+  for (int i = 0; i < Length; i++)
+    List[i] = i * 2;
+}
+
+void width_1(int *List, int Length) {
+// CHECK-LABEL: @{{.*}}width_1{{.*}}(
+// CHECK: br label {{.*}}, !llvm.loop ![[LOOP_16:.*]]
+
+  #pragma clang loop vectorize_width(1)
+  for (int i = 0; i < Length; i++)
+    List[i] = i * 2;
+}
+
 // CHECK: ![[LOOP_1]] = distinct !{![[LOOP_1]], ![[UNROLL_FULL:.*]]}
 // CHECK: ![[UNROLL_FULL]] = !{!"llvm.loop.unroll.full"}
 
-// CHECK: ![[LOOP_2]] = distinct !{![[LOOP_2]], ![[UNROLL_DISABLE:.*]], ![[DISTRIBUTE_DISABLE:.*]], ![[WIDTH_8:.*]], ![[INTERLEAVE_4:.*]]}
+// CHECK: ![[LOOP_2]] = distinct !{![[LOOP_2]], ![[UNROLL_DISABLE:.*]], ![[DISTRIBUTE_DISABLE:.*]], ![[VECTORIZE_ENABLE:.*]], ![[WIDTH_8:.*]], ![[INTERLEAVE_4:.*]]}
 // CHECK: ![[UNROLL_DISABLE]] = !{!"llvm.loop.unroll.disable"}
 // CHECK: ![[DISTRIBUTE_DISABLE]] = !{!"llvm.loop.distribute.enable", i1 false}
+// CHECK: ![[VECTORIZE_ENABLE]] = !{!"llvm.loop.vectorize.enable", i1 true}
 // CHECK: ![[WIDTH_8]] = !{!"llvm.loop.vectorize.width", i32 8}
 // CHECK: ![[INTERLEAVE_4]] = !{!"llvm.loop.interleave.count", i32 4}
 
-// CHECK: ![[LOOP_3]] = distinct !{![[LOOP_3]], ![[INTERLEAVE_4:.*]], ![[INTENABLE_1:.*]], ![[FOLLOWUP_VECTOR_3:.*]]}
-// CHECK: ![[INTENABLE_1]] = !{!"llvm.loop.vectorize.enable", i1 true}
+// CHECK: ![[LOOP_3]] = distinct !{![[LOOP_3]], ![[INTERLEAVE_4:.*]], ![[VECTORIZE_ENABLE]], ![[FOLLOWUP_VECTOR_3:.*]]}
 // CHECK: ![[FOLLOWUP_VECTOR_3]] = !{!"llvm.loop.vectorize.followup_all", ![[AFTER_VECTOR_3:.*]]}
 // CHECK: ![[AFTER_VECTOR_3]] = distinct !{![[AFTER_VECTOR_3]], ![[ISVECTORIZED:.*]], ![[UNROLL_8:.*]]}
 // CHECK: ![[ISVECTORIZED]] = !{!"llvm.loop.isvectorized"}
 // CHECK: ![[UNROLL_8]] = !{!"llvm.loop.unroll.count", i32 8}
 
-// CHECK: ![[LOOP_4]] = distinct !{![[LOOP_4]], ![[WIDTH_2:.*]], ![[INTERLEAVE_2:.*]]}
+// CHECK: ![[LOOP_4]] = distinct !{![[LOOP_4]], ![[VECTORIZE_ENABLE]], ![[WIDTH_2:.*]], ![[INTERLEAVE_2:.*]]}
 // CHECK: ![[WIDTH_2]] = !{!"llvm.loop.vectorize.width", i32 2}
 // CHECK: ![[INTERLEAVE_2]] = !{!"llvm.loop.interleave.count", i32 2}
 
@@ -185,7 +203,7 @@ void template_test(double *List, int Length) {
 // CHECK: ![[FOLLOWUP_VECTOR_6]] = !{!"llvm.loop.vectorize.followup_all", ![[AFTER_VECTOR_6:.*]]}
 // CHECK: ![[AFTER_VECTOR_6]] = distinct !{![[AFTER_VECTOR_6]], ![[ISVECTORIZED:.*]], ![[UNROLL_8:.*]]}
 
-// CHECK: ![[LOOP_7]] = distinct !{![[LOOP_7]], ![[WIDTH_5:.*]]}
+// CHECK: ![[LOOP_7]] = distinct !{![[LOOP_7]], ![[VECTORIZE_ENABLE]], ![[WIDTH_5:.*]]}
 // CHECK: ![[WIDTH_5]] = !{!"llvm.loop.vectorize.width", i32 5}
 
 // CHECK: ![[LOOP_8]] = distinct !{![[LOOP_8]], ![[WIDTH_5:.*]]}
@@ -213,5 +231,9 @@ void template_test(double *List, int Length) {
 // CHECK: ![[AFTER_VECTOR_13]] = distinct !{![[AFTER_VECTOR_13]], ![[ISVECTORIZED:.*]], ![[UNROLL_32:.*]]}
 // CHECK: ![[UNROLL_32]] = !{!"llvm.loop.unroll.count", i32 32}
 
-// CHECK: ![[LOOP_14]] = distinct !{![[LOOP_14]], ![[WIDTH_10:.*]]}
+// CHECK: ![[LOOP_14]] = distinct !{![[LOOP_14]], ![[VECTORIZE_ENABLE]], ![[WIDTH_10:.*]]}
 // CHECK: ![[WIDTH_10]] = !{!"llvm.loop.vectorize.width", i32 10}
+
+// CHECK:      ![[LOOP_15]] = distinct !{![[LOOP_15]], ![[WIDTH_1]], ![[VECTORIZE_ENABLE]]}
+
+// CHECK-NEXT: ![[LOOP_16]] = distinct !{![[LOOP_16]], ![[VECTORIZE_ENABLE]], ![[WIDTH_1]]}