[NFC] Add a comment to member-function-pointer-calls.cpp

Looking at this test I did not see why MinGW was using a different command
line until I looked at the git history. Add a comment explaining what this
RUN line is actually testing. Also add two more RUN lines to show that
indirectly passed member pointers don't inhibit the optimization.

diff --git a/clang/test/CodeGenCXX/member-function-pointer-calls.cpp b/clang/test/CodeGenCXX/member-function-pointer-calls.cpp
index f2e485b..24d70b3 100644 (file)
--- a/clang/test/CodeGenCXX/member-function-pointer-calls.cpp
+++ b/clang/test/CodeGenCXX/member-function-pointer-calls.cpp
@@ -1,6 +1,10 @@
 // RUN: %clang_cc1 %s -triple=x86_64-apple-darwin10 -emit-llvm -O3 -fno-experimental-new-pass-manager  -o - | FileCheck %s
 // RUN: %clang_cc1 %s -triple=x86_64-apple-darwin10 -emit-llvm -O3 -fexperimental-new-pass-manager  -o - | FileCheck %s
+/// Check that we pass the member pointers indirectly for MinGW64
 // RUN: %clang_cc1 %s -triple=x86_64-windows-gnu -emit-llvm -o - | FileCheck %s -check-prefix MINGW64
+/// We should be able to optimize calls via the indirectly passed member pointers
+// RUN: %clang_cc1 %s -triple=x86_64-windows-gnu -emit-llvm -O3 -fno-experimental-new-pass-manager  -o - | FileCheck %s
+// RUN: %clang_cc1 %s -triple=x86_64-windows-gnu -emit-llvm -O3 -fexperimental-new-pass-manager  -o - | FileCheck %s
 struct A {
   virtual int vf1() { return 1; }
   virtual int vf2() { return 2; }