[CodeGen] Emit parallel_loop_access for each loop in the loop stack.

Summary:
Emit !llvm.mem.parallel_loop_access metadata for memory accesses even if the parallel loop is not the top on the loop stack.

Fixes llvm.org/PR37558.

Reviewers: ABataev, hfinkel, amusman, tyler.nowicki

Reviewed By: hfinkel

Subscribers: Meinersbur, hfinkel, cfe-commits

Differential Revision: https://reviews.llvm.org/D48808

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@338810 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/CodeGen/CGLoopInfo.cpp b/lib/CodeGen/CGLoopInfo.cpp
index 09089bf816052ceabe543625a7c731f59dd406df..8f9a9b96077625efa7d17e912424faa2e46cb9d3 100644 (file)
--- a/lib/CodeGen/CGLoopInfo.cpp
+++ b/lib/CodeGen/CGLoopInfo.cpp
@@ -344,6 +344,17 @@ void LoopInfoStack::InsertHelper(Instruction *I) const {
     return;
   }
 
-  if (L.getAttributes().IsParallel && I->mayReadOrWriteMemory())
-    I->setMetadata("llvm.mem.parallel_loop_access", L.getLoopID());
+  if (I->mayReadOrWriteMemory()) {
+    SmallVector<Metadata *, 2> ParallelLoopIDs;
+    for (const LoopInfo &AL : Active)
+      if (AL.getAttributes().IsParallel)
+        ParallelLoopIDs.push_back(AL.getLoopID());
+
+    MDNode *ParallelMD = nullptr;
+    if (ParallelLoopIDs.size() == 1)
+      ParallelMD = cast<MDNode>(ParallelLoopIDs[0]);
+    else if (ParallelLoopIDs.size() >= 2)
+      ParallelMD = MDNode::get(I->getContext(), ParallelLoopIDs);
+    I->setMetadata("llvm.mem.parallel_loop_access", ParallelMD);
+  }
 }

diff --git a/test/CodeGenCXX/pragma-loop-safety-nested.cpp b/test/CodeGenCXX/pragma-loop-safety-nested.cpp
new file mode 100644 (file)
index 0000000..4641c95
--- /dev/null
+++ b/test/CodeGenCXX/pragma-loop-safety-nested.cpp
@@ -0,0 +1,21 @@
+// RUN: %clang_cc1 -triple x86_64-apple-darwin -std=c++11 -emit-llvm -o - %s | FileCheck %s
+
+// Verify that the inner access is tagged with a parallel_loop_access
+// for the inner and outer loop using a list.
+void vectorize_nested_test(int *List, int Length) {
+#pragma clang loop vectorize(assume_safety) interleave(disable) unroll(disable)
+  for (int i = 0; i < Length; ++i) {
+#pragma clang loop vectorize(assume_safety) interleave(disable) unroll(disable)
+    for (int j = 0; j < Length; ++j)
+      List[i * Length + j] = (i + j) * 2;
+  }
+}
+
+// CHECK: %[[MUL:.+]] = mul
+// CHECK: store i32 %[[MUL]], i32* %{{.+}}, !llvm.mem.parallel_loop_access ![[PARALLEL_LIST:[0-9]+]]
+// CHECK: br label %{{.+}}, !llvm.loop ![[INNER_LOOPID:[0-9]+]]
+// CHECK: br label %{{.+}}, !llvm.loop ![[OUTER_LOOPID:[0-9]+]]
+
+// CHECK: ![[OUTER_LOOPID]] = distinct !{![[OUTER_LOOPID]],
+// CHECK: ![[PARALLEL_LIST]] = !{![[OUTER_LOOPID]], ![[INNER_LOOPID]]}
+// CHECK: ![[INNER_LOOPID]] = distinct !{![[INNER_LOOPID]],

diff --git a/test/CodeGenCXX/pragma-loop-safety-outer.cpp b/test/CodeGenCXX/pragma-loop-safety-outer.cpp
new file mode 100644 (file)
index 0000000..83f534e
--- /dev/null
+++ b/test/CodeGenCXX/pragma-loop-safety-outer.cpp
@@ -0,0 +1,20 @@
+// RUN: %clang_cc1 -triple x86_64-apple-darwin -std=c++11 -emit-llvm -o - %s | FileCheck %s
+
+// Verify that the inner access is tagged with a parallel_loop_access
+// for the outer loop.
+void vectorize_outer_test(int *List, int Length) {
+#pragma clang loop vectorize(assume_safety) interleave(disable) unroll(disable)
+  for (int i = 0; i < Length; i += 2) {
+#pragma clang loop unroll(full)
+    for (int j = 0; j < 2; j += 1)
+      List[i + j] = (i + j) * 2;
+  }
+}
+
+// CHECK: %[[MUL:.+]] = mul
+// CHECK: store i32 %[[MUL]], i32* %{{.+}}, !llvm.mem.parallel_loop_access ![[OUTER_LOOPID:[0-9]+]]
+// CHECK: br label %{{.+}}, !llvm.loop ![[INNER_LOOPID:[0-9]+]]
+// CHECK: br label %{{.+}}, !llvm.loop ![[OUTER_LOOPID]]
+
+// CHECK: ![[OUTER_LOOPID]] = distinct !{![[OUTER_LOOPID]],
+// CHECK: ![[INNER_LOOPID]] = distinct !{![[INNER_LOOPID]],