[TailCall] Allow llvm.memcpy/memset/memmove to be tail calls when parent

function return the intrinsics's first argument.

llvm.memcpy/memset/memmove return void but they will return the first
argument after they are expanded as libcalls. Now if the parent function
has any return value, llvm.memcpy cannot be turned into tail call after
expansion.

The patch is to handle that case in SelectionDAGBuilder so when caller
function return the same value as the first argument of llvm.memcpy,
tail call is allowed.

Differential Revision: https://reviews.llvm.org/D37406

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@312641 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/CodeGen/Analysis.cpp b/lib/CodeGen/Analysis.cpp
index c2aecc651b792a67d86ab415f4472ccd3b3cb50b..f561577e1e2e2a5ccf9d0816b93eb39bd8509445 100644 (file)
--- a/lib/CodeGen/Analysis.cpp
+++ b/lib/CodeGen/Analysis.cpp
@@ -565,6 +565,17 @@ bool llvm::returnTypeIsEligibleForTailCall(const Function *F,
     return false;
 
   const Value *RetVal = Ret->getOperand(0), *CallVal = I;
+  // Intrinsic like llvm.memcpy has no return value, but will return the
+  // first argument if it is expanded as libcall.
+  const CallInst *Call = cast<CallInst>(I);
+  if (Function *F = Call->getCalledFunction()) {
+    Intrinsic::ID IID = F->getIntrinsicID();
+    if ((IID == Intrinsic::memcpy || IID == Intrinsic::memmove ||
+         IID == Intrinsic::memset) &&
+        RetVal == Call->getArgOperand(0))
+      return true;
+  }
+
   SmallVector<unsigned, 4> RetPath, CallPath;
   SmallVector<CompositeType *, 4> RetSubTypes, CallSubTypes;
 

diff --git a/test/CodeGen/X86/tailcall-mem-intrinsics.ll b/test/CodeGen/X86/tailcall-mem-intrinsics.ll
index 8e1e4f464baa912a567ba5351356b270388d43d7..7491ea659ba2ca182ae148af8a36bf4f1f1b5100 100644 (file)
--- a/test/CodeGen/X86/tailcall-mem-intrinsics.ll
+++ b/test/CodeGen/X86/tailcall-mem-intrinsics.ll
@@ -24,6 +24,30 @@ entry:
   ret void
 }
 
+; CHECK-LABEL: tail_memcpy_ret
+; CHECK: jmp memcpy
+define i8* @tail_memcpy_ret(i8* nocapture %p, i8* nocapture readonly %q, i32 %n) #0 {
+entry:
+  tail call void @llvm.memcpy.p0i8.p0i8.i32(i8* %p, i8* %q, i32 %n, i32 1, i1 false)
+  ret i8* %p
+}
+
+; CHECK-LABEL: tail_memmove_ret
+; CHECK: jmp memmove
+define i8* @tail_memmove_ret(i8* nocapture %p, i8* nocapture readonly %q, i32 %n) #0 {
+entry:
+  tail call void @llvm.memmove.p0i8.p0i8.i32(i8* %p, i8* %q, i32 %n, i32 1, i1 false)
+  ret i8* %p
+}
+
+; CHECK-LABEL: tail_memset_ret
+; CHECK: jmp memset
+define i8* @tail_memset_ret(i8* nocapture %p, i8 %c, i32 %n) #0 {
+entry:
+  tail call void @llvm.memset.p0i8.i32(i8* %p, i8 %c, i32 %n, i32 1, i1 false)
+  ret i8* %p
+}
+
 declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture readonly, i32, i32, i1) #0
 declare void @llvm.memmove.p0i8.p0i8.i32(i8* nocapture, i8* nocapture readonly, i32, i32, i1) #0
 declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i32, i1) #0