[PATCH] D48808: [CodeGen] Emit parallel_loop_access for each loop in the loop stack.

Michael Kruse via Phabricator via cfe-commits Thu, 12 Jul 2018 15:38:41 -0700

Meinersbur updated this revision to Diff 155288.
Meinersbur added a comment.


- Hoist I->mayReadOrWriteMemory() condition.


Repository:
  rC Clang

https://reviews.llvm.org/D48808

Files:
  lib/CodeGen/CGLoopInfo.cpp
  test/CodeGenCXX/pragma-loop-safety-nested.cpp
  test/CodeGenCXX/pragma-loop-safety-outer.cpp


Index: test/CodeGenCXX/pragma-loop-safety-outer.cpp
===================================================================
--- /dev/null
+++ 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]],
Index: test/CodeGenCXX/pragma-loop-safety-nested.cpp
===================================================================
--- /dev/null
+++ 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]],
Index: lib/CodeGen/CGLoopInfo.cpp
===================================================================
--- lib/CodeGen/CGLoopInfo.cpp
+++ lib/CodeGen/CGLoopInfo.cpp
@@ -300,6 +300,17 @@
     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);
+  }
 }

Index: test/CodeGenCXX/pragma-loop-safety-outer.cpp
===================================================================
--- /dev/null
+++ 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]],
Index: test/CodeGenCXX/pragma-loop-safety-nested.cpp
===================================================================
--- /dev/null
+++ 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]],
Index: lib/CodeGen/CGLoopInfo.cpp
===================================================================
--- lib/CodeGen/CGLoopInfo.cpp
+++ lib/CodeGen/CGLoopInfo.cpp
@@ -300,6 +300,17 @@
     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);
+  }
 }

_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[PATCH] D48808: [CodeGen] Emit parallel_loop_access for each loop in the loop stack.

Reply via email to