[llvm] r267515 - [SimplifyCFG] Preserve !llvm.mem.parallel_loop_access when merging

[Hal Finkel via llvm-commits]

Author: hfinkel
Date: Mon Apr 25 21:06:06 2016
New Revision: 267515

URL: http://llvm.org/viewvc/llvm-project?rev=267515&view=rev
Log:
[SimplifyCFG] Preserve !llvm.mem.parallel_loop_access when merging

When SimplifyCFG merges identical instructions from both sides of a diamond, it
can preserve !llvm.mem.parallel_loop_access (as it does with most of the other
metadata). There's no real data or control dependency change in this case.

Added:
    llvm/trunk/test/Transforms/SimplifyCFG/combine-parallel-mem-md.ll
Modified:
    llvm/trunk/lib/Transforms/Utils/Local.cpp
    llvm/trunk/lib/Transforms/Utils/SimplifyCFG.cpp

Modified: llvm/trunk/lib/Transforms/Utils/Local.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Transforms/Utils/Local.cpp?rev=267515&r1=267514&r2=267515&view=diff
==============================================================================
--- llvm/trunk/lib/Transforms/Utils/Local.cpp (original)
+++ llvm/trunk/lib/Transforms/Utils/Local.cpp Mon Apr 25 21:06:06 2016
@@ -1539,6 +1539,7 @@ void llvm::combineMetadata(Instruction *
         K->setMetadata(Kind, MDNode::getMostGenericAliasScope(JMD, KMD));
         break;
       case LLVMContext::MD_noalias:
+      case LLVMContext::MD_mem_parallel_loop_access:
         K->setMetadata(Kind, MDNode::intersect(JMD, KMD));
         break;
       case LLVMContext::MD_range:

Modified: llvm/trunk/lib/Transforms/Utils/SimplifyCFG.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Transforms/Utils/SimplifyCFG.cpp?rev=267515&r1=267514&r2=267515&view=diff
==============================================================================
--- llvm/trunk/lib/Transforms/Utils/SimplifyCFG.cpp (original)
+++ llvm/trunk/lib/Transforms/Utils/SimplifyCFG.cpp Mon Apr 25 21:06:06 2016
@@ -1143,7 +1143,8 @@ static bool HoistThenElseCodeToIf(Branch
         LLVMContext::MD_fpmath,  LLVMContext::MD_invariant_load,
         LLVMContext::MD_nonnull, LLVMContext::MD_invariant_group,
         LLVMContext::MD_align,   LLVMContext::MD_dereferenceable,
-        LLVMContext::MD_dereferenceable_or_null};
+        LLVMContext::MD_dereferenceable_or_null,
+        LLVMContext::MD_mem_parallel_loop_access};
     combineMetadata(I1, I2, KnownIDs);
     I2->eraseFromParent();
     Changed = true;

Added: llvm/trunk/test/Transforms/SimplifyCFG/combine-parallel-mem-md.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/Transforms/SimplifyCFG/combine-parallel-mem-md.ll?rev=267515&view=auto
==============================================================================
--- llvm/trunk/test/Transforms/SimplifyCFG/combine-parallel-mem-md.ll (added)
+++ llvm/trunk/test/Transforms/SimplifyCFG/combine-parallel-mem-md.ll Mon Apr 25 21:06:06 2016
@@ -0,0 +1,55 @@
+; RUN: opt -simplifycfg -S < %s | FileCheck %s
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+; Function Attrs: norecurse nounwind uwtable
+define void @Test(i32* nocapture %res, i32* nocapture readnone %c, i32* nocapture readonly %d, i32* nocapture readonly %p) #0 {
+entry:
+  br label %for.body
+
+; CHECK-LABEL: @Test
+; CHECK: load i32, i32* {{.*}}, align 4, !llvm.mem.parallel_loop_access !0
+; CHECK: load i32, i32* {{.*}}, align 4, !llvm.mem.parallel_loop_access !0
+; CHECK: store i32 {{.*}}, align 4, !llvm.mem.parallel_loop_access !0
+; CHECK-NOT: load
+; CHECK-NOT: store
+
+for.body:                                         ; preds = %cond.end, %entry
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %cond.end ]
+  %arrayidx = getelementptr inbounds i32, i32* %p, i64 %indvars.iv
+  %0 = load i32, i32* %arrayidx, align 4, !llvm.mem.parallel_loop_access !0
+  %cmp1 = icmp eq i32 %0, 0
+  br i1 %cmp1, label %cond.true, label %cond.false
+
+cond.false:                                       ; preds = %for.body
+  %arrayidx3 = getelementptr inbounds i32, i32* %res, i64 %indvars.iv
+  %v = load i32, i32* %arrayidx3, align 4, !llvm.mem.parallel_loop_access !0
+  %arrayidx7 = getelementptr inbounds i32, i32* %d, i64 %indvars.iv
+  %1 = load i32, i32* %arrayidx7, align 4, !llvm.mem.parallel_loop_access !0
+  %add = add nsw i32 %1, %v
+  br label %cond.end
+
+cond.true:                                       ; preds = %for.body
+  %arrayidx4 = getelementptr inbounds i32, i32* %res, i64 %indvars.iv
+  %w = load i32, i32* %arrayidx4, align 4, !llvm.mem.parallel_loop_access !0
+  %arrayidx8 = getelementptr inbounds i32, i32* %d, i64 %indvars.iv
+  %2 = load i32, i32* %arrayidx8, align 4, !llvm.mem.parallel_loop_access !0
+  %add2 = add nsw i32 %2, %w
+  br label %cond.end
+
+cond.end:                                         ; preds = %for.body, %cond.false
+  %cond = phi i32 [ %add, %cond.false ], [ %add2, %cond.true ]
+  %arrayidx9 = getelementptr inbounds i32, i32* %res, i64 %indvars.iv
+  store i32 %cond, i32* %arrayidx9, align 4, !llvm.mem.parallel_loop_access !0
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, 16
+  br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !0
+
+for.end:                                          ; preds = %cond.end
+  ret void
+}
+
+attributes #0 = { norecurse nounwind uwtable }
+
+!0 = distinct !{!0, !1}
+!1 = !{!"llvm.loop.vectorize.enable", i1 true}