Merge pull request #3544 from aschwaighofer/coro_remove_intrinsics_in_private

Coro: Remove coro_end and coro_suspend_retcon in private unprocessed functions

Author: aschwaighofer

llvm/lib/Transforms/Coroutines/CoroCleanup.cpp

@@ -55,7 +55,8 @@ static void lowerSubFn(IRBuilder<> &Builder, CoroSubFnInst *SubFn) {
 
 bool Lowerer::lowerRemainingCoroIntrinsics(Function &F) {
   bool Changed = false;
-
+  bool IsPrivateAndUnprocessed = F.hasFnAttribute(CORO_PRESPLIT_ATTR) &&
+    F.hasLocalLinkage();
   for (auto IB = inst_begin(F), E = inst_end(F); IB != E;) {
     Instruction &I = *IB++;
     if (auto *II = dyn_cast<IntrinsicInst>(&I)) {
@@ -84,6 +85,12 @@ bool Lowerer::lowerRemainingCoroIntrinsics(Function &F) {
       case Intrinsic::coro_subfn_addr:
         lowerSubFn(Builder, cast<CoroSubFnInst>(II));
         break;
+      case Intrinsic::coro_end:
+      case Intrinsic::coro_suspend_retcon:
+        if (IsPrivateAndUnprocessed) {
+          II->replaceAllUsesWith(UndefValue::get(II->getType()));
+        } else continue;
+        break;
       case Intrinsic::coro_async_size_replace:
         auto *Target = cast<ConstantStruct>(
             cast<GlobalVariable>(II->getArgOperand(0)->stripPointerCasts())

llvm/test/Transforms/Coroutines/coro-retcon-once-private.ll

@@ -0,0 +1,55 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt < %s -enable-coroutines -passes='default<O0>' -S | FileCheck %s
+
+target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-macosx10.12.0"
+
+; CHECK: define internal { i8*, i32 } @f(i8* %buffer, i32* %array)
+; CHECK-NEXT: entry:
+; CHECK-NEXT:  unreachable
+
+define internal {i8*, i32} @f(i8* %buffer, i32* %array) {
+entry:
+  %id = call token @llvm.coro.id.retcon.once(i32 8, i32 8, i8* %buffer, i8* bitcast (void (i8*, i1)* @prototype to i8*), i8* bitcast (i8* (i32)* @allocate to i8*), i8* bitcast (void (i8*)* @deallocate to i8*))
+  %hdl = call i8* @llvm.coro.begin(token %id, i8* null)
+  %load = load i32, i32* %array
+  %load.pos = icmp sgt i32 %load, 0
+  br i1 %load.pos, label %pos, label %neg
+
+pos:
+  %unwind0 = call i1 (...) @llvm.coro.suspend.retcon.i1(i32 %load)
+  br i1 %unwind0, label %cleanup, label %pos.cont
+
+pos.cont:
+  store i32 0, i32* %array, align 4
+  br label %cleanup
+
+neg:
+  %unwind1 = call i1 (...) @llvm.coro.suspend.retcon.i1(i32 0)
+  br i1 %unwind1, label %cleanup, label %neg.cont
+
+neg.cont:
+  store i32 10, i32* %array, align 4
+  br label %cleanup
+
+cleanup:
+  call i1 @llvm.coro.end(i8* %hdl, i1 0)
+  unreachable
+}
+
+;   Unfortunately, we don't seem to fully optimize this right now due
+;   to some sort of phase-ordering thing.
+
+declare token @llvm.coro.id.retcon.once(i32, i32, i8*, i8*, i8*, i8*)
+declare i8* @llvm.coro.begin(token, i8*)
+declare i1 @llvm.coro.suspend.retcon.i1(...)
+declare i1 @llvm.coro.end(i8*, i1)
+declare i8* @llvm.coro.prepare.retcon(i8*)
+
+declare void @prototype(i8*, i1 zeroext)
+
+declare noalias i8* @allocate(i32 %size)
+declare void @deallocate(i8* %ptr)
+
+declare void @print(i32)
+