Recommit r326946 after reducing CallArgList memory footprint

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@327634 91177308-0d34-0410-b5e6-96231b3b80d8

3 files changed, 131 insertions, 3 deletions

diff --git a/test/CodeGenCXX/amdgcn-func-arg.cpp b/test/CodeGenCXX/amdgcn-func-arg.cpp
new file mode 100644
index 0000000000..9ac143a520
--- /dev/null
+++ b/test/CodeGenCXX/amdgcn-func-arg.cpp
@@ -0,0 +1,94 @@
+// RUN: %clang_cc1 -O0 -triple amdgcn -emit-llvm %s -o - | FileCheck %s
+
+class A {
+public:
+  int x;
+  A():x(0) {}
+  ~A() {}
+};
+
+class B {
+int x[100];
+};
+
+A g_a;
+B g_b;
+
+void func_with_ref_arg(A &a);
+void func_with_ref_arg(B &b);
+
+// CHECK-LABEL: define void @_Z22func_with_indirect_arg1A(%class.A addrspace(5)* %a)
+// CHECK:  %p = alloca %class.A*, align 8, addrspace(5)
+// CHECK:  %[[r1:.+]] = addrspacecast %class.A* addrspace(5)* %p to %class.A**
+// CHECK:  %[[r0:.+]] = addrspacecast %class.A addrspace(5)* %a to %class.A*
+// CHECK:  store %class.A* %[[r0]], %class.A** %[[r1]], align 8
+void func_with_indirect_arg(A a) {
+  A *p = &a;
+}
+
+// CHECK-LABEL: define void @_Z22test_indirect_arg_autov()
+// CHECK:  %a = alloca %class.A, align 4, addrspace(5)
+// CHECK:  %[[r0:.+]] = addrspacecast %class.A addrspace(5)* %a to %class.A*
+// CHECK:  %agg.tmp = alloca %class.A, align 4, addrspace(5)
+// CHECK:  %[[r1:.+]] = addrspacecast %class.A addrspace(5)* %agg.tmp to %class.A*
+// CHECK:  call void @_ZN1AC1Ev(%class.A* %[[r0]])
+// CHECK:  call void @llvm.memcpy.p0i8.p0i8.i64
+// CHECK:  %[[r4:.+]] = addrspacecast %class.A* %[[r1]] to %class.A addrspace(5)*
+// CHECK:  call void @_Z22func_with_indirect_arg1A(%class.A addrspace(5)* %[[r4]])
+// CHECK:  call void @_ZN1AD1Ev(%class.A* %[[r1]])
+// CHECK:  call void @_Z17func_with_ref_argR1A(%class.A* dereferenceable(4) %[[r0]])
+// CHECK:  call void @_ZN1AD1Ev(%class.A* %[[r0]])
+void test_indirect_arg_auto() {
+  A a;
+  func_with_indirect_arg(a);
+  func_with_ref_arg(a);
+}
+
+// CHECK: define void @_Z24test_indirect_arg_globalv()
+// CHECK:  %agg.tmp = alloca %class.A, align 4, addrspace(5)
+// CHECK:  %[[r0:.+]] = addrspacecast %class.A addrspace(5)* %agg.tmp to %class.A*
+// CHECK:  call void @llvm.memcpy.p0i8.p0i8.i64
+// CHECK:  %[[r2:.+]] = addrspacecast %class.A* %[[r0]] to %class.A addrspace(5)*
+// CHECK:  call void @_Z22func_with_indirect_arg1A(%class.A addrspace(5)* %[[r2]])
+// CHECK:  call void @_ZN1AD1Ev(%class.A* %[[r0]])
+// CHECK:  call void @_Z17func_with_ref_argR1A(%class.A* dereferenceable(4) addrspacecast (%class.A addrspace(1)* @g_a to %class.A*))
+void test_indirect_arg_global() {
+  func_with_indirect_arg(g_a);
+  func_with_ref_arg(g_a);
+}
+
+// CHECK-LABEL: define void @_Z19func_with_byval_arg1B(%class.B addrspace(5)* byval align 4 %b)
+// CHECK:  %p = alloca %class.B*, align 8, addrspace(5)
+// CHECK:  %[[r1:.+]] = addrspacecast %class.B* addrspace(5)* %p to %class.B**
+// CHECK:  %[[r0:.+]] = addrspacecast %class.B addrspace(5)* %b to %class.B*
+// CHECK:  store %class.B* %[[r0]], %class.B** %[[r1]], align 8
+void func_with_byval_arg(B b) {
+  B *p = &b;
+}
+
+// CHECK-LABEL: define void @_Z19test_byval_arg_autov()
+// CHECK:  %b = alloca %class.B, align 4, addrspace(5)
+// CHECK:  %[[r0:.+]] = addrspacecast %class.B addrspace(5)* %b to %class.B*
+// CHECK:  %agg.tmp = alloca %class.B, align 4, addrspace(5)
+// CHECK:  %[[r1:.+]] = addrspacecast %class.B addrspace(5)* %agg.tmp to %class.B*
+// CHECK:  call void @llvm.memcpy.p0i8.p0i8.i64
+// CHECK:  %[[r4:.+]] = addrspacecast %class.B* %[[r1]] to %class.B addrspace(5)*
+// CHECK:  call void @_Z19func_with_byval_arg1B(%class.B addrspace(5)* byval align 4 %[[r4]])
+// CHECK:  call void @_Z17func_with_ref_argR1B(%class.B* dereferenceable(400) %[[r0]])
+void test_byval_arg_auto() {
+  B b;
+  func_with_byval_arg(b);
+  func_with_ref_arg(b);
+}
+
+// CHECK-LABEL: define void @_Z21test_byval_arg_globalv()
+// CHECK:  %agg.tmp = alloca %class.B, align 4, addrspace(5)
+// CHECK:  %[[r0:.+]] = addrspacecast %class.B addrspace(5)* %agg.tmp to %class.B*
+// CHECK:  call void @llvm.memcpy.p0i8.p0i8.i64
+// CHECK:  %[[r2:.+]] = addrspacecast %class.B* %[[r0]] to %class.B addrspace(5)*
+// CHECK:  call void @_Z19func_with_byval_arg1B(%class.B addrspace(5)* byval align 4 %[[r2]])
+// CHECK:  call void @_Z17func_with_ref_argR1B(%class.B* dereferenceable(400) addrspacecast (%class.B addrspace(1)* @g_b to %class.B*))
+void test_byval_arg_global() {
+  func_with_byval_arg(g_b);
+  func_with_ref_arg(g_b);
+}
diff --git a/test/CodeGenOpenCL/addr-space-struct-arg.cl b/test/CodeGenOpenCL/addr-space-struct-arg.cl
index 01ae1b32ed..f8d7073f92 100644
--- a/test/CodeGenOpenCL/addr-space-struct-arg.cl
+++ b/test/CodeGenOpenCL/addr-space-struct-arg.cl
@@ -1,5 +1,6 @@
 // RUN: %clang_cc1 %s -emit-llvm -o - -O0 -finclude-default-header -ffake-address-space-map -triple i686-pc-darwin | FileCheck -enable-var-scope -check-prefixes=COM,X86 %s
-// RUN: %clang_cc1 %s -emit-llvm -o - -O0 -finclude-default-header -triple amdgcn-amdhsa-amd | FileCheck -enable-var-scope -check-prefixes=COM,AMDGCN %s
+// RUN: %clang_cc1 %s -emit-llvm -o - -O0 -finclude-default-header -triple amdgcn | FileCheck -enable-var-scope -check-prefixes=COM,AMDGCN %s
+// RUN: %clang_cc1 %s -emit-llvm -o - -cl-std=CL2.0 -O0 -finclude-default-header -triple amdgcn | FileCheck -enable-var-scope -check-prefixes=COM,AMDGCN,AMDGCN20 %s
 
 typedef struct {
   int cells[9];
@@ -35,6 +36,9 @@ struct LargeStructTwoMember {
   int2 y[20];
 };
 
+#if __OPENCL_C_VERSION__ >= 200
+struct LargeStructOneMember g_s;
+#endif
 
 // X86-LABEL: define void @foo(%struct.Mat4X4* noalias sret %agg.result, %struct.Mat3X3* byval align 4 %in)
 // AMDGCN-LABEL: define %struct.Mat4X4 @foo([9 x i32] %in.coerce)
@@ -80,10 +84,42 @@ void FuncOneMember(struct StructOneMember u) {
 }
 
 // AMDGCN-LABEL: define void @FuncOneLargeMember(%struct.LargeStructOneMember addrspace(5)* byval align 8 %u)
+// AMDGCN-NOT: addrspacecast
+// AMDGCN:   store <2 x i32> %{{.*}}, <2 x i32> addrspace(5)*
 void FuncOneLargeMember(struct LargeStructOneMember u) {
   u.x[0] = (int2)(0, 0);
 }
 
+// AMDGCN20-LABEL: define void @test_indirect_arg_globl()
+// AMDGCN20:  %[[byval_temp:.*]] = alloca %struct.LargeStructOneMember, align 8, addrspace(5)
+// AMDGCN20:  %[[r0:.*]] = bitcast %struct.LargeStructOneMember addrspace(5)* %[[byval_temp]] to i8 addrspace(5)*
+// AMDGCN20:  call void @llvm.memcpy.p5i8.p1i8.i64(i8 addrspace(5)* align 8 %[[r0]], i8 addrspace(1)* align 8 bitcast (%struct.LargeStructOneMember addrspace(1)* @g_s to i8 addrspace(1)*), i64 800, i1 false)
+// AMDGCN20:  call void @FuncOneLargeMember(%struct.LargeStructOneMember addrspace(5)* byval align 8 %[[byval_temp]])
+#if __OPENCL_C_VERSION__ >= 200
+void test_indirect_arg_globl(void) {
+  FuncOneLargeMember(g_s);
+}
+#endif
+
+// AMDGCN-LABEL: define amdgpu_kernel void @test_indirect_arg_local()
+// AMDGCN: %[[byval_temp:.*]] = alloca %struct.LargeStructOneMember, align 8, addrspace(5)
+// AMDGCN: %[[r0:.*]] = bitcast %struct.LargeStructOneMember addrspace(5)* %[[byval_temp]] to i8 addrspace(5)*
+// AMDGCN: call void @llvm.memcpy.p5i8.p3i8.i64(i8 addrspace(5)* align 8 %[[r0]], i8 addrspace(3)* align 8 bitcast (%struct.LargeStructOneMember addrspace(3)* @test_indirect_arg_local.l_s to i8 addrspace(3)*), i64 800, i1 false)
+// AMDGCN: call void @FuncOneLargeMember(%struct.LargeStructOneMember addrspace(5)* byval align 8 %[[byval_temp]])
+kernel void test_indirect_arg_local(void) {
+  local struct LargeStructOneMember l_s;
+  FuncOneLargeMember(l_s);
+}
+
+// AMDGCN-LABEL: define void @test_indirect_arg_private()
+// AMDGCN: %[[p_s:.*]] = alloca %struct.LargeStructOneMember, align 8, addrspace(5)
+// AMDGCN-NOT: @llvm.memcpy
+// AMDGCN-NEXT: call void @FuncOneLargeMember(%struct.LargeStructOneMember addrspace(5)* byval align 8 %[[p_s]])
+void test_indirect_arg_private(void) {
+  struct LargeStructOneMember p_s;
+  FuncOneLargeMember(p_s);
+}
+
 // AMDGCN-LABEL: define amdgpu_kernel void @KernelOneMember
 // AMDGCN-SAME:  (<2 x i32> %[[u_coerce:.*]])
 // AMDGCN:  %[[u:.*]] = alloca %struct.StructOneMember, align 8, addrspace(5)
@@ -112,7 +148,6 @@ void FuncLargeTwoMember(struct LargeStructTwoMember u) {
   u.y[0] = (int2)(0, 0);
 }
 
-
 // AMDGCN-LABEL: define amdgpu_kernel void @KernelTwoMember
 // AMDGCN-SAME:  (%struct.StructTwoMember %[[u_coerce:.*]])
 // AMDGCN:  %[[u:.*]] = alloca %struct.StructTwoMember, align 8, addrspace(5)
diff --git a/test/CodeGenOpenCL/byval.cl b/test/CodeGenOpenCL/byval.cl
index 592d96ffa6..05c72c514c 100644
--- a/test/CodeGenOpenCL/byval.cl
+++ b/test/CodeGenOpenCL/byval.cl
@@ -1,5 +1,4 @@
 // RUN: %clang_cc1 -emit-llvm -o - -triple amdgcn %s | FileCheck %s
-// RUN: %clang_cc1 -emit-llvm -o - -triple amdgcn---opencl %s | FileCheck %s
 
 struct A {
   int x[100];