[Coroutines][New pass manager] Move CoroElide pass to right position

Differential Revision: https://reviews.llvm.org/D75345

clang/test/CodeGenCoroutines/coro-newpm-pipeline.cpp

@@ -14,14 +14,14 @@
 // The first coro-split pass enqueues a second run of the entire CGSCC pipeline.
 // CHECK: Starting CGSCC pass manager run.
 // CHECK: Running pass: CoroSplitPass on (_Z3foov)
-// CHECK: Running pass:{{.*}}CoroElidePass{{.*}} on (_Z3foov)
+// CHECK: Running pass:{{.*}}CoroElidePass{{.*}} on {{.*}}_Z3foov{{.*}}
 // CHECK: Finished CGSCC pass manager run.
 //
 // The second coro-split pass splits coroutine 'foo' into funclets
 // 'foo.resume', 'foo.destroy', and 'foo.cleanup'.
 // CHECK: Starting CGSCC pass manager run.
 // CHECK: Running pass: CoroSplitPass on (_Z3foov)
-// CHECK: Running pass:{{.*}}CoroElidePass{{.*}} on (_Z3foov)
+// CHECK: Running pass:{{.*}}CoroElidePass{{.*}} on {{.*}}_Z3foov{{.*}}
 // CHECK: Finished CGSCC pass manager run.
 //
 // CHECK: Running pass:{{.*}}CoroCleanupPass

llvm/lib/Passes/PassBuilder.cpp

@@ -561,6 +561,9 @@ PassBuilder::buildFunctionSimplificationPipeline(OptimizationLevel Level,
         EnableMSSALoopDependency, DebugLogging));
   }
 
+  if (PTO.Coroutines)
+    FPM.addPass(CoroElidePass());
+
   for (auto &C : ScalarOptimizerLateEPCallbacks)
     C(FPM, Level);
 
@@ -847,10 +850,8 @@ PassBuilder::buildModuleSimplificationPipeline(OptimizationLevel Level,
 
   MainCGPipeline.addPass(AttributorCGSCCPass());
 
-  if (PTO.Coroutines) {
+  if (PTO.Coroutines)
     MainCGPipeline.addPass(CoroSplitPass());
-    MainCGPipeline.addPass(createCGSCCToFunctionPassAdaptor(CoroElidePass()));
-  }
 
   // Now deduce any function attributes based in the current code.
   MainCGPipeline.addPass(PostOrderFunctionAttrsPass());

llvm/test/Transforms/Coroutines/ex2.ll

@@ -40,8 +40,14 @@ entry:
   %hdl = call i8* @f(i32 4)
   call void @llvm.coro.resume(i8* %hdl)
   call void @llvm.coro.resume(i8* %hdl)
+  %to = icmp eq i8* %hdl, null
+  br i1 %to, label %return, label %destroy
+destroy:
   call void @llvm.coro.destroy(i8* %hdl)
+  br label %return
+return:
   ret i32 0
+; CHECK-NOT:  call i8* @CustomAlloc
 ; CHECK:      call void @print(i32 4)
 ; CHECK-NEXT: call void @print(i32 5)
 ; CHECK-NEXT: call void @print(i32 6)

llvm/test/Transforms/Coroutines/ex3.ll

@@ -6,11 +6,17 @@ define i8* @f(i32 %n) {
 entry:
   %id = call token @llvm.coro.id(i32 0, i8* null, i8* null, i8* null)
   %size = call i32 @llvm.coro.size.i32()
+  %need.dyn.alloc = call i1 @llvm.coro.alloc(token %id)
+  br i1 %need.dyn.alloc, label %dyn.alloc, label %coro.begin
+dyn.alloc:
   %alloc = call i8* @malloc(i32 %size)
-  %hdl = call noalias i8* @llvm.coro.begin(token %id, i8* %alloc)
+  br label %coro.begin
+coro.begin:
+  %phi = phi i8* [ null, %entry ], [ %alloc, %dyn.alloc ]
+  %hdl = call noalias i8* @llvm.coro.begin(token %id, i8* %phi)
   br label %loop
 loop:
-  %n.val = phi i32 [ %n, %entry ], [ %inc, %loop.resume ]
+  %n.val = phi i32 [ %n, %coro.begin ], [ %inc, %loop.resume ]
   call void @print(i32 %n.val) #4
   %0 = call i8 @llvm.coro.suspend(token none, i1 false)
   switch i8 %0, label %suspend [i8 0, label %loop.resume
@@ -37,8 +43,15 @@ entry:
   %hdl = call i8* @f(i32 4)
   call void @llvm.coro.resume(i8* %hdl)
   call void @llvm.coro.resume(i8* %hdl)
+  %c = ptrtoint i8* %hdl to i64
+  %to = icmp eq i64 %c, 0
+  br i1 %to, label %return, label %destroy
+destroy:
   call void @llvm.coro.destroy(i8* %hdl)
+  br label %return
+return:
   ret i32 0
+; CHECK-NOT:  i8* @malloc
 ; CHECK:      call void @print(i32 4)
 ; CHECK-NEXT: call void @print(i32 -5)
 ; CHECK-NEXT: call void @print(i32 5)