[CGP] Fix the rematerialization of gc.relocates

If we want to substitute the relocation of derived pointer with gep of base then
we must ensure that relocation of base dominates the relocation of derived pointer.

Currently only check for basic block is present. However it is possible that both
relocation are in the same basic block but relocation of derived pointer is defined
earlier.

The patch moves the relocation of base pointer right before relocation of derived
pointer in this case.

Reviewers: sanjoy,artagnon,igor-laevsky,reames
Reviewed By: reames
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D36462

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@311067 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/CodeGen/CodeGenPrepare.cpp b/lib/CodeGen/CodeGenPrepare.cpp
index df900d65cf2efcf60bd4eff216fc8b5a1444c45f..6d0043ba9e0add59b72e9b2c259a31ddaa42c01f 100644 (file)
--- a/lib/CodeGen/CodeGenPrepare.cpp
+++ b/lib/CodeGen/CodeGenPrepare.cpp
@@ -948,6 +948,21 @@ static bool
 simplifyRelocatesOffABase(GCRelocateInst *RelocatedBase,
                           const SmallVectorImpl<GCRelocateInst *> &Targets) {
   bool MadeChange = false;
+  // We must ensure the relocation of derived pointer is defined after
+  // relocation of base pointer. If we find a relocation corresponding to base
+  // defined earlier than relocation of base then we move relocation of base
+  // right before found relocation. We consider only relocation in the same
+  // basic block as relocation of base. Relocations from other basic block will
+  // be skipped by optimization and we do not care about them.
+  for (auto R = RelocatedBase->getParent()->getFirstInsertionPt();
+       &*R != RelocatedBase; ++R)
+    if (auto RI = dyn_cast<GCRelocateInst>(R))
+      if (RI->getStatepoint() == RelocatedBase->getStatepoint())
+        if (RI->getBasePtrIndex() == RelocatedBase->getBasePtrIndex()) {
+          RelocatedBase->moveBefore(RI);
+          break;
+        }
+
   for (GCRelocateInst *ToReplace : Targets) {
     assert(ToReplace->getBasePtrIndex() == RelocatedBase->getBasePtrIndex() &&
            "Not relocating a derived object of the original base object");

diff --git a/test/Transforms/CodeGenPrepare/statepoint-relocate.ll b/test/Transforms/CodeGenPrepare/statepoint-relocate.ll
index b31dfe7f3fa63c0d8e3cd70fc22844b731386349..af911c395b65f3dc1f5ce1810a1002673e18b9e5 100644 (file)
--- a/test/Transforms/CodeGenPrepare/statepoint-relocate.ll
+++ b/test/Transforms/CodeGenPrepare/statepoint-relocate.ll
@@ -122,6 +122,28 @@ right:
        ret i32 %ret-base
 }
 
+define i32 @test_sor_noop_same_bb(i1 %external-cond, i32* %base) gc "statepoint-example" {
+; CHECK-LABEL: @test_sor_noop_same_bb
+; Here base relocate doesn't dominate derived relocate. Make sure that we don't
+; produce undefined use of the relocated base pointer.
+entry:
+       %ptr1 = getelementptr i32, i32* %base, i32 15
+       ; CHECK: getelementptr i32, i32* %base, i32 15
+       %ptr2 = getelementptr i32, i32* %base, i32 5
+       ; CHECK: getelementptr i32, i32* %base, i32 5
+       %tok = call token (i64, i32, i1 ()*, i32, i32, ...) @llvm.experimental.gc.statepoint.p0f_i1f(i64 0, i32 0, i1 ()* @return_i1, i32 0, i32 0, i32 0, i32 0, i32* %base, i32* %ptr1, i32* %ptr2)
+       ; CHECK: call i32* @llvm.experimental.gc.relocate.p0i32(token %tok, i32 7, i32 7)
+       %ptr2-new = call i32* @llvm.experimental.gc.relocate.p0i32(token %tok, i32 7, i32 9)
+       %ret2-new = load i32, i32* %ptr2-new
+       ; CHECK: getelementptr i32, i32* %base-new, i32 5
+       %ptr1-new = call i32* @llvm.experimental.gc.relocate.p0i32(token %tok, i32 7, i32 8)
+       %ret1-new = load i32, i32* %ptr1-new
+       ; CHECK: getelementptr i32, i32* %base-new, i32 15
+       %base-new = call i32* @llvm.experimental.gc.relocate.p0i32(token %tok, i32 7, i32 7)
+       %ret-new = add i32 %ret2-new, %ret1-new
+       ret i32 %ret-new
+}
+
 declare token @llvm.experimental.gc.statepoint.p0f_i1f(i64, i32, i1 ()*, i32, i32, ...)
 declare i32* @llvm.experimental.gc.relocate.p0i32(token, i32, i32)
 declare [3 x i32]* @llvm.experimental.gc.relocate.p0a3i32(token, i32, i32)