CodeGen: Cast alloca to expected address space
Alloca always returns a pointer in alloca address space, which may
be different from the type defined by the language. For example,
in C++ the auto variables are in the default address space. Therefore
cast alloca to the expected address space when necessary.
Differential Revision: https://reviews.llvm.org/D32248
llvm-svn: 303370
diff --git a/clang/test/CodeGen/address-space.c b/clang/test/CodeGen/address-space.c
index 5d57d5b..35e3dbd 100644
--- a/clang/test/CodeGen/address-space.c
+++ b/clang/test/CodeGen/address-space.c
@@ -1,6 +1,6 @@
// RUN: %clang_cc1 -triple x86_64-apple-darwin -emit-llvm < %s | FileCheck -check-prefixes=CHECK,GIZ %s
// RUN: %clang_cc1 -triple amdgcn -emit-llvm < %s | FileCheck -check-prefixes=CHECK,PIZ %s
-// RUN: %clang_cc1 -triple amdgcn---amdgiz -emit-llvm < %s | FileCheck -check-prefixes=CHeCK,GIZ %s
+// RUN: %clang_cc1 -triple amdgcn---amdgiz -emit-llvm < %s | FileCheck -check-prefixes=CHECK,GIZ %s
// CHECK: @foo = common addrspace(1) global
int foo __attribute__((address_space(1)));
@@ -40,8 +40,10 @@
} MyStruct;
// CHECK-LABEL: define void @test4(
-// CHECK: call void @llvm.memcpy.p0i8.p2i8
-// CHECK: call void @llvm.memcpy.p2i8.p0i8
+// GIZ: call void @llvm.memcpy.p0i8.p2i8
+// GIZ: call void @llvm.memcpy.p2i8.p0i8
+// PIZ: call void @llvm.memcpy.p4i8.p2i8
+// PIZ: call void @llvm.memcpy.p2i8.p4i8
void test4(MyStruct __attribute__((address_space(2))) *pPtr) {
MyStruct s = pPtr[0];
pPtr[0] = s;
diff --git a/clang/test/CodeGenCXX/amdgcn-automatic-variable.cpp b/clang/test/CodeGenCXX/amdgcn-automatic-variable.cpp
new file mode 100644
index 0000000..aab7207
--- /dev/null
+++ b/clang/test/CodeGenCXX/amdgcn-automatic-variable.cpp
@@ -0,0 +1,72 @@
+// RUN: %clang_cc1 -O0 -triple amdgcn---amdgiz -emit-llvm %s -o - | FileCheck %s
+
+// CHECK-LABEL: define void @_Z5func1Pi(i32* %x)
+void func1(int *x) {
+ // CHECK: %[[x_addr:.*]] = alloca i32*{{.*}}addrspace(5)
+ // CHECK: store i32* %x, i32* addrspace(5)* %[[x_addr]]
+ // CHECK: %[[r0:.*]] = load i32*, i32* addrspace(5)* %[[x_addr]]
+ // CHECK: store i32 1, i32* %[[r0]]
+ *x = 1;
+}
+
+// CHECK-LABEL: define void @_Z5func2v()
+void func2(void) {
+ // CHECK: %lv1 = alloca i32, align 4, addrspace(5)
+ // CHECK: %lv2 = alloca i32, align 4, addrspace(5)
+ // CHECK: %la = alloca [100 x i32], align 4, addrspace(5)
+ // CHECK: %lp1 = alloca i32*, align 4, addrspace(5)
+ // CHECK: %lp2 = alloca i32*, align 4, addrspace(5)
+ // CHECK: %lvc = alloca i32, align 4, addrspace(5)
+
+ // CHECK: %[[r0:.*]] = addrspacecast i32 addrspace(5)* %lv1 to i32*
+ // CHECK: store i32 1, i32* %[[r0]]
+ int lv1;
+ lv1 = 1;
+ // CHECK: %[[r1:.*]] = addrspacecast i32 addrspace(5)* %lv2 to i32*
+ // CHECK: store i32 2, i32* %[[r1]]
+ int lv2 = 2;
+
+ // CHECK: %[[r2:.*]] = addrspacecast [100 x i32] addrspace(5)* %la to [100 x i32]*
+ // CHECK: %[[arrayidx:.*]] = getelementptr inbounds [100 x i32], [100 x i32]* %[[r2]], i64 0, i64 0
+ // CHECK: store i32 3, i32* %[[arrayidx]], align 4
+ int la[100];
+ la[0] = 3;
+
+ // CHECK: %[[r3:.*]] = addrspacecast i32* addrspace(5)* %lp1 to i32**
+ // CHECK: store i32* %[[r0]], i32** %[[r3]], align 4
+ int *lp1 = &lv1;
+
+ // CHECK: %[[r4:.*]] = addrspacecast i32* addrspace(5)* %lp2 to i32**
+ // CHECK: %[[arraydecay:.*]] = getelementptr inbounds [100 x i32], [100 x i32]* %[[r2]], i32 0, i32 0
+ // CHECK: store i32* %[[arraydecay]], i32** %[[r4]], align 4
+ int *lp2 = la;
+
+ // CHECK: call void @_Z5func1Pi(i32* %[[r0]])
+ func1(&lv1);
+
+ // CHECK: %[[r5:.*]] = addrspacecast i32 addrspace(5)* %lvc to i32*
+ // CHECK: store i32 4, i32* %[[r5]]
+ // CHECK: store i32 4, i32* %[[r0]]
+ const int lvc = 4;
+ lv1 = lvc;
+}
+
+void destroy(int x);
+
+class A {
+int x;
+public:
+ A():x(0) {}
+ ~A() {
+ destroy(x);
+ }
+};
+
+// CHECK-LABEL: define void @_Z5func3v
+void func3() {
+ // CHECK: %[[a:.*]] = alloca %class.A, align 4, addrspace(5)
+ // CHECK: %[[r0:.*]] = addrspacecast %class.A addrspace(5)* %[[a]] to %class.A*
+ // CHECK: call void @_ZN1AC1Ev(%class.A* %[[r0]])
+ // CHECK: call void @_ZN1AD1Ev(%class.A* %[[r0]])
+ A a;
+}
diff --git a/clang/test/CodeGenOpenCL/amdgcn-automatic-variable.cl b/clang/test/CodeGenOpenCL/amdgcn-automatic-variable.cl
new file mode 100644
index 0000000..2930956
--- /dev/null
+++ b/clang/test/CodeGenOpenCL/amdgcn-automatic-variable.cl
@@ -0,0 +1,60 @@
+// RUN: %clang_cc1 -O0 -cl-std=CL1.2 -triple amdgcn---amdgizcl -emit-llvm %s -o - | FileCheck -check-prefixes=CHECK,CL12 %s
+// RUN: %clang_cc1 -O0 -cl-std=CL2.0 -triple amdgcn---amdgizcl -emit-llvm %s -o - | FileCheck -check-prefixes=CHECK,CL20 %s
+
+// CL12-LABEL: define void @func1(i32 addrspace(5)* %x)
+// CL20-LABEL: define void @func1(i32* %x)
+void func1(int *x) {
+ // CL12: %[[x_addr:.*]] = alloca i32 addrspace(5)*{{.*}}addrspace(5)
+ // CL12: store i32 addrspace(5)* %x, i32 addrspace(5)* addrspace(5)* %[[x_addr]]
+ // CL12: %[[r0:.*]] = load i32 addrspace(5)*, i32 addrspace(5)* addrspace(5)* %[[x_addr]]
+ // CL12: store i32 1, i32 addrspace(5)* %[[r0]]
+ // CL20: %[[x_addr:.*]] = alloca i32*{{.*}}addrspace(5)
+ // CL20: store i32* %x, i32* addrspace(5)* %[[x_addr]]
+ // CL20: %[[r0:.*]] = load i32*, i32* addrspace(5)* %[[x_addr]]
+ // CL20: store i32 1, i32* %[[r0]]
+ *x = 1;
+}
+
+// CHECK-LABEL: define void @func2()
+void func2(void) {
+ // CHECK: %lv1 = alloca i32, align 4, addrspace(5)
+ // CHECK: %lv2 = alloca i32, align 4, addrspace(5)
+ // CHECK: %la = alloca [100 x i32], align 4, addrspace(5)
+ // CL12: %lp1 = alloca i32 addrspace(5)*, align 4, addrspace(5)
+ // CL12: %lp2 = alloca i32 addrspace(5)*, align 4, addrspace(5)
+ // CL20: %lp1 = alloca i32*, align 4, addrspace(5)
+ // CL20: %lp2 = alloca i32*, align 4, addrspace(5)
+ // CHECK: %lvc = alloca i32, align 4, addrspace(5)
+
+ // CHECK: store i32 1, i32 addrspace(5)* %lv1
+ int lv1;
+ lv1 = 1;
+ // CHECK: store i32 2, i32 addrspace(5)* %lv2
+ int lv2 = 2;
+
+ // CHECK: %[[arrayidx:.*]] = getelementptr inbounds [100 x i32], [100 x i32] addrspace(5)* %la, i64 0, i64 0
+ // CHECK: store i32 3, i32 addrspace(5)* %[[arrayidx]], align 4
+ int la[100];
+ la[0] = 3;
+
+ // CL12: store i32 addrspace(5)* %lv1, i32 addrspace(5)* addrspace(5)* %lp1, align 4
+ // CL20: %[[r0:.*]] = addrspacecast i32 addrspace(5)* %lv1 to i32*
+ // CL20: store i32* %[[r0]], i32* addrspace(5)* %lp1, align 4
+ int *lp1 = &lv1;
+
+ // CHECK: %[[arraydecay:.*]] = getelementptr inbounds [100 x i32], [100 x i32] addrspace(5)* %la, i32 0, i32 0
+ // CL12: store i32 addrspace(5)* %[[arraydecay]], i32 addrspace(5)* addrspace(5)* %lp2, align 4
+ // CL20: %[[r1:.*]] = addrspacecast i32 addrspace(5)* %[[arraydecay]] to i32*
+ // CL20: store i32* %[[r1]], i32* addrspace(5)* %lp2, align 4
+ int *lp2 = la;
+
+ // CL12: call void @func1(i32 addrspace(5)* %lv1)
+ // CL20: %[[r2:.*]] = addrspacecast i32 addrspace(5)* %lv1 to i32*
+ // CL20: call void @func1(i32* %[[r2]])
+ func1(&lv1);
+
+ // CHECK: store i32 4, i32 addrspace(5)* %lvc
+ // CHECK: store i32 4, i32 addrspace(5)* %lv1
+ const int lvc = 4;
+ lv1 = lvc;
+}
diff --git a/clang/test/CodeGenOpenCL/amdgpu-alignment.cl b/clang/test/CodeGenOpenCL/amdgpu-alignment.cl
index 35a8342..714e724 100644
--- a/clang/test/CodeGenOpenCL/amdgpu-alignment.cl
+++ b/clang/test/CodeGenOpenCL/amdgpu-alignment.cl
@@ -1,5 +1,5 @@
// REQUIRES: amdgpu-registered-target
-// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -S -disable-llvm-passes -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -triple amdgcn-unknown-unknown-opencl -S -disable-llvm-passes -emit-llvm -o - %s | FileCheck %s
#pragma OPENCL EXTENSION cl_khr_fp64 : enable
#pragma OPENCL EXTENSION cl_khr_fp16 : enable
diff --git a/clang/test/CodeGenOpenCL/amdgpu-debug-info-pointer-address-space.cl b/clang/test/CodeGenOpenCL/amdgpu-debug-info-pointer-address-space.cl
index 7baee5e..061ce2c 100644
--- a/clang/test/CodeGenOpenCL/amdgpu-debug-info-pointer-address-space.cl
+++ b/clang/test/CodeGenOpenCL/amdgpu-debug-info-pointer-address-space.cl
@@ -1,4 +1,4 @@
-// RUN: %clang -cl-std=CL2.0 -emit-llvm -g -O0 -S -target amdgcn-amd-amdhsa -mcpu=fiji -o - %s | FileCheck %s
+// RUN: %clang -cl-std=CL2.0 -emit-llvm -g -O0 -S -target amdgcn-amd-amdhsa-opencl -mcpu=fiji -o - %s | FileCheck %s
// CHECK-DAG: ![[DWARF_ADDRESS_SPACE_NONE:[0-9]+]] = !DIDerivedType(tag: DW_TAG_pointer_type, baseType: !{{[0-9]+}}, size: {{[0-9]+}})
// CHECK-DAG: ![[DWARF_ADDRESS_SPACE_LOCAL:[0-9]+]] = !DIDerivedType(tag: DW_TAG_pointer_type, baseType: !{{[0-9]+}}, size: {{[0-9]+}}, dwarfAddressSpace: 2)
diff --git a/clang/test/CodeGenOpenCL/amdgpu-debug-info-variable-expression.cl b/clang/test/CodeGenOpenCL/amdgpu-debug-info-variable-expression.cl
index c0a4c21..8cf086b 100644
--- a/clang/test/CodeGenOpenCL/amdgpu-debug-info-variable-expression.cl
+++ b/clang/test/CodeGenOpenCL/amdgpu-debug-info-variable-expression.cl
@@ -1,4 +1,4 @@
-// RUN: %clang -cl-std=CL2.0 -emit-llvm -g -O0 -S -target amdgcn-amd-amdhsa -mcpu=fiji -o - %s | FileCheck %s
+// RUN: %clang -cl-std=CL2.0 -emit-llvm -g -O0 -S -target amdgcn-amd-amdhsa-opencl -mcpu=fiji -o - %s | FileCheck %s
// CHECK-DAG: ![[LOCAL:[0-9]+]] = !DIExpression(DW_OP_constu, 2, DW_OP_swap, DW_OP_xderef)
// CHECK-DAG: ![[PRIVATE:[0-9]+]] = !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)
diff --git a/clang/test/CodeGenOpenCL/amdgpu-nullptr.cl b/clang/test/CodeGenOpenCL/amdgpu-nullptr.cl
index 37c7469..3e54cd5 100644
--- a/clang/test/CodeGenOpenCL/amdgpu-nullptr.cl
+++ b/clang/test/CodeGenOpenCL/amdgpu-nullptr.cl
@@ -1,5 +1,5 @@
-// RUN: %clang_cc1 %s -cl-std=CL2.0 -include opencl-c.h -triple amdgcn -emit-llvm -o - | FileCheck %s
-// RUN: %clang_cc1 %s -O0 -cl-std=CL2.0 -include opencl-c.h -triple amdgcn -emit-llvm -o - | FileCheck --check-prefix=NOOPT %s
+// RUN: %clang_cc1 %s -cl-std=CL2.0 -include opencl-c.h -triple amdgcn---opencl -emit-llvm -o - | FileCheck %s
+// RUN: %clang_cc1 %s -O0 -cl-std=CL2.0 -include opencl-c.h -triple amdgcn---opencl -emit-llvm -o - | FileCheck --check-prefix=NOOPT %s
typedef struct {
private char *p1;
diff --git a/clang/test/CodeGenOpenCL/builtins-amdgcn.cl b/clang/test/CodeGenOpenCL/builtins-amdgcn.cl
index a19ce2f..fdbae9b 100644
--- a/clang/test/CodeGenOpenCL/builtins-amdgcn.cl
+++ b/clang/test/CodeGenOpenCL/builtins-amdgcn.cl
@@ -1,5 +1,5 @@
// REQUIRES: amdgpu-registered-target
-// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -S -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -triple amdgcn-unknown-unknown-opencl -S -emit-llvm -o - %s | FileCheck %s
#pragma OPENCL EXTENSION cl_khr_fp64 : enable
diff --git a/clang/test/CodeGenOpenCL/byval.cl b/clang/test/CodeGenOpenCL/byval.cl
index 1a8105c..a7c5adf 100644
--- a/clang/test/CodeGenOpenCL/byval.cl
+++ b/clang/test/CodeGenOpenCL/byval.cl
@@ -1,4 +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
// RUN: %clang_cc1 -emit-llvm -o - -triple amdgcn---amdgizcl %s | FileCheck %s -check-prefix=AMDGIZ
struct A {
diff --git a/clang/test/CodeGenOpenCL/size_t.cl b/clang/test/CodeGenOpenCL/size_t.cl
index ed941e0..20f29fe 100644
--- a/clang/test/CodeGenOpenCL/size_t.cl
+++ b/clang/test/CodeGenOpenCL/size_t.cl
@@ -1,6 +1,6 @@
// RUN: %clang_cc1 %s -cl-std=CL2.0 -finclude-default-header -emit-llvm -O0 -triple spir-unknown-unknown -o - | FileCheck --check-prefix=SZ32 %s
// RUN: %clang_cc1 %s -cl-std=CL2.0 -finclude-default-header -emit-llvm -O0 -triple spir64-unknown-unknown -o - | FileCheck --check-prefix=SZ64 --check-prefix=SZ64ONLY %s
-// RUN: %clang_cc1 %s -cl-std=CL2.0 -finclude-default-header -emit-llvm -O0 -triple amdgcn-- -o - | FileCheck --check-prefix=SZ64 --check-prefix=AMDONLY %s
+// RUN: %clang_cc1 %s -cl-std=CL2.0 -finclude-default-header -emit-llvm -O0 -triple amdgcn---opencl -o - | FileCheck --check-prefix=SZ64 --check-prefix=AMDONLY %s
//SZ32: define{{.*}} i32 @test_ptrtoint_private(i8* %x)
//SZ32: ptrtoint i8* %{{.*}} to i32
diff --git a/clang/test/Sema/sizeof-struct-non-zero-as-member.cl b/clang/test/Sema/sizeof-struct-non-zero-as-member.cl
index 0e13c61..cd95973 100644
--- a/clang/test/Sema/sizeof-struct-non-zero-as-member.cl
+++ b/clang/test/Sema/sizeof-struct-non-zero-as-member.cl
@@ -1,4 +1,4 @@
-// RUN: %clang_cc1 -verify -fsyntax-only -triple amdgcn -target-cpu verde -S -emit-llvm -o - %s
+// RUN: %clang_cc1 -verify -fsyntax-only -triple amdgcn--opencl -target-cpu verde -S -emit-llvm -o - %s
// expected-no-diagnostics
// Record lowering was crashing on SI and newer targets, because it
diff --git a/clang/test/SemaOpenCL/storageclass-cl20.cl b/clang/test/SemaOpenCL/storageclass-cl20.cl
index 1eba64b..b12676f 100644
--- a/clang/test/SemaOpenCL/storageclass-cl20.cl
+++ b/clang/test/SemaOpenCL/storageclass-cl20.cl
@@ -12,7 +12,9 @@
constant int L1 = 0;
local int L2;
- global int L3; // expected-error{{function scope variable cannot be declared in global address space}}
+ global int L3; // expected-error{{function scope variable cannot be declared in global address space}}
+ generic int L4; // expected-error{{automatic variable qualified with an invalid address space}}
+ __attribute__((address_space(100))) int L5; // expected-error{{automatic variable qualified with an invalid address space}}
extern global int G5;
extern int G6; // expected-error{{extern variable must reside in global or constant address space}}
diff --git a/clang/test/SemaOpenCL/storageclass.cl b/clang/test/SemaOpenCL/storageclass.cl
index f457cfd..e611313 100644
--- a/clang/test/SemaOpenCL/storageclass.cl
+++ b/clang/test/SemaOpenCL/storageclass.cl
@@ -13,29 +13,37 @@
constant int L1 = 0;
local int L2;
- auto int L3 = 7; // expected-error{{OpenCL version 1.2 does not support the 'auto' storage class specifier}}
- global int L4; // expected-error{{function scope variable cannot be declared in global address space}}
+ auto int L3 = 7; // expected-error{{OpenCL version 1.2 does not support the 'auto' storage class specifier}}
+ global int L4; // expected-error{{function scope variable cannot be declared in global address space}}
+ __attribute__((address_space(100))) int L5; // expected-error{{automatic variable qualified with an invalid address space}}
- constant int L5 = x; // expected-error {{initializer element is not a compile-time constant}}
- global int *constant L6 = &G4;
- private int *constant L7 = &x; // expected-error {{initializer element is not a compile-time constant}}
- constant int *constant L8 = &L1;
- local int *constant L9 = &L2; // expected-error {{initializer element is not a compile-time constant}}
+ constant int L6 = x; // expected-error {{initializer element is not a compile-time constant}}
+ global int *constant L7 = &G4;
+ private int *constant L8 = &x; // expected-error {{initializer element is not a compile-time constant}}
+ constant int *constant L9 = &L1;
+ local int *constant L10 = &L2; // expected-error {{initializer element is not a compile-time constant}}
}
static void kernel bar() { // expected-error{{kernel functions cannot be declared static}}
}
void f() {
- constant int L1 = 0; // expected-error{{non-kernel function variable cannot be declared in constant address space}}
- local int L2; // expected-error{{non-kernel function variable cannot be declared in local address space}}
+ constant int L1 = 0; // expected-error{{non-kernel function variable cannot be declared in constant address space}}
+ local int L2; // expected-error{{non-kernel function variable cannot be declared in local address space}}
+ global int L3; // expected-error{{function scope variable cannot be declared in global address space}}
+ __attribute__((address_space(100))) int L4; // expected-error{{automatic variable qualified with an invalid address space}}
+
{
- constant int L1 = 0; // expected-error{{non-kernel function variable cannot be declared in constant address space}}
- local int L2; // expected-error{{non-kernel function variable cannot be declared in local address space}}
+ constant int L1 = 0; // expected-error{{non-kernel function variable cannot be declared in constant address space}}
+ local int L2; // expected-error{{non-kernel function variable cannot be declared in local address space}}
+ global int L3; // expected-error{{function scope variable cannot be declared in global address space}}
+ __attribute__((address_space(100))) int L4; // expected-error{{automatic variable qualified with an invalid address space}}
}
- global int L3; // expected-error{{function scope variable cannot be declared in global address space}}
- extern constant float L4;
- extern local float L5; // expected-error{{extern variable must reside in constant address space}}
- static int L6 = 0; // expected-error{{variables in function scope cannot be declared static}}
- static int L7; // expected-error{{variables in function scope cannot be declared static}}
+
+
+ extern constant float L5;
+ extern local float L6; // expected-error{{extern variable must reside in constant address space}}
+
+ static int L7 = 0; // expected-error{{variables in function scope cannot be declared static}}
+ static int L8; // expected-error{{variables in function scope cannot be declared static}}
}