summaryrefslogtreecommitdiff
path: root/test/CodeGenOpenCL
diff options
context:
space:
mode:
Diffstat (limited to 'test/CodeGenOpenCL')
-rw-r--r--test/CodeGenOpenCL/address-spaces.cl2
-rw-r--r--test/CodeGenOpenCL/amdgcn-automatic-variable.cl8
-rw-r--r--test/CodeGenOpenCL/amdgpu-nullptr.cl48
-rw-r--r--test/CodeGenOpenCL/amdgpu-sizeof-alignof.cl70
4 files changed, 100 insertions, 28 deletions
diff --git a/test/CodeGenOpenCL/address-spaces.cl b/test/CodeGenOpenCL/address-spaces.cl
index 7c665286547a..488b8f9d480e 100644
--- a/test/CodeGenOpenCL/address-spaces.cl
+++ b/test/CodeGenOpenCL/address-spaces.cl
@@ -4,6 +4,8 @@
// RUN: %clang_cc1 %s -O0 -triple amdgcn-amd-amdhsa-opencl -DCL20 -cl-std=CL2.0 -emit-llvm -o - | FileCheck %s --check-prefixes=CL20,CL20SPIR
// RUN: %clang_cc1 %s -O0 -triple amdgcn-amd-amdhsa-amdgizcl -emit-llvm -o - | FileCheck %s -check-prefixes=CHECK,GIZ
// RUN: %clang_cc1 %s -O0 -triple amdgcn-amd-amdhsa-amdgizcl -DCL20 -cl-std=CL2.0 -emit-llvm -o - | FileCheck %s --check-prefixes=CL20,CL20GIZ
+// RUN: %clang_cc1 %s -O0 -triple amdgcn-mesa-mesa3d -emit-llvm -o - | FileCheck --check-prefixes=CHECK,SPIR %s
+// RUN: %clang_cc1 %s -O0 -triple r600-- -emit-llvm -o - | FileCheck --check-prefixes=CHECK,SPIR %s
// SPIR: i32* %arg
// GIZ: i32 addrspace(5)* %arg
diff --git a/test/CodeGenOpenCL/amdgcn-automatic-variable.cl b/test/CodeGenOpenCL/amdgcn-automatic-variable.cl
index 29309567ec71..19287c7d8998 100644
--- a/test/CodeGenOpenCL/amdgcn-automatic-variable.cl
+++ b/test/CodeGenOpenCL/amdgcn-automatic-variable.cl
@@ -22,8 +22,8 @@ void func2(void) {
// 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)
+ // CL20: %lp1 = alloca i32*, align 8, addrspace(5)
+ // CL20: %lp2 = alloca i32*, align 8, addrspace(5)
// CHECK: %lvc = alloca i32, align 4, addrspace(5)
// CHECK: store i32 1, i32 addrspace(5)* %lv1
@@ -39,13 +39,13 @@ void func2(void) {
// 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
+ // CL20: store i32* %[[r0]], i32* addrspace(5)* %lp1, align 8
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
+ // CL20: store i32* %[[r1]], i32* addrspace(5)* %lp2, align 8
int *lp2 = la;
// CL12: call void @func1(i32 addrspace(5)* %lv1)
diff --git a/test/CodeGenOpenCL/amdgpu-nullptr.cl b/test/CodeGenOpenCL/amdgpu-nullptr.cl
index 402be5760cf7..69f54fcaa483 100644
--- a/test/CodeGenOpenCL/amdgpu-nullptr.cl
+++ b/test/CodeGenOpenCL/amdgpu-nullptr.cl
@@ -27,13 +27,13 @@ private char *private_p = 0;
// CHECK: @local_p = local_unnamed_addr addrspace(1) global i8 addrspace(3)* addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*), align 4
local char *local_p = 0;
-// CHECK: @global_p = local_unnamed_addr addrspace(1) global i8 addrspace(1)* null, align 4
+// CHECK: @global_p = local_unnamed_addr addrspace(1) global i8 addrspace(1)* null, align 8
global char *global_p = 0;
-// CHECK: @constant_p = local_unnamed_addr addrspace(1) global i8 addrspace(2)* null, align 4
+// CHECK: @constant_p = local_unnamed_addr addrspace(1) global i8 addrspace(2)* null, align 8
constant char *constant_p = 0;
-// CHECK: @generic_p = local_unnamed_addr addrspace(1) global i8 addrspace(4)* null, align 4
+// CHECK: @generic_p = local_unnamed_addr addrspace(1) global i8 addrspace(4)* null, align 8
generic char *generic_p = 0;
// Test NULL as initializer.
@@ -44,19 +44,19 @@ private char *private_p_NULL = NULL;
// CHECK: @local_p_NULL = local_unnamed_addr addrspace(1) global i8 addrspace(3)* addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*), align 4
local char *local_p_NULL = NULL;
-// CHECK: @global_p_NULL = local_unnamed_addr addrspace(1) global i8 addrspace(1)* null, align 4
+// CHECK: @global_p_NULL = local_unnamed_addr addrspace(1) global i8 addrspace(1)* null, align 8
global char *global_p_NULL = NULL;
-// CHECK: @constant_p_NULL = local_unnamed_addr addrspace(1) global i8 addrspace(2)* null, align 4
+// CHECK: @constant_p_NULL = local_unnamed_addr addrspace(1) global i8 addrspace(2)* null, align 8
constant char *constant_p_NULL = NULL;
-// CHECK: @generic_p_NULL = local_unnamed_addr addrspace(1) global i8 addrspace(4)* null, align 4
+// CHECK: @generic_p_NULL = local_unnamed_addr addrspace(1) global i8 addrspace(4)* null, align 8
generic char *generic_p_NULL = NULL;
// Test constant folding of null pointer.
// A null pointer should be folded to a null pointer in the target address space.
-// CHECK: @fold_generic = local_unnamed_addr addrspace(1) global i32 addrspace(4)* null, align 4
+// CHECK: @fold_generic = local_unnamed_addr addrspace(1) global i32 addrspace(4)* null, align 8
generic int *fold_generic = (global int*)(generic float*)(private char*)0;
// CHECK: @fold_priv = local_unnamed_addr addrspace(1) global i16* null, align 4
@@ -104,8 +104,8 @@ int fold_int5_local = (int) &((local StructTy1*)0)->p2;
// NOOPT: @test_static_var_private.sp3 = internal addrspace(1) global i8* null, align 4
// NOOPT: @test_static_var_private.sp4 = internal addrspace(1) global i8* null, align 4
// NOOPT: @test_static_var_private.sp5 = internal addrspace(1) global i8* null, align 4
-// NOOPT: @test_static_var_private.SS1 = internal addrspace(1) global %struct.StructTy1 { i8* null, i8 addrspace(3)* addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*), i8 addrspace(2)* null, i8 addrspace(1)* null, i8 addrspace(4)* null }, align 4
-// NOOPT: @test_static_var_private.SS2 = internal addrspace(1) global %struct.StructTy2 zeroinitializer, align 4
+// NOOPT: @test_static_var_private.SS1 = internal addrspace(1) global %struct.StructTy1 { i8* null, i8 addrspace(3)* addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*), i8 addrspace(2)* null, i8 addrspace(1)* null, i8 addrspace(4)* null }, align 8
+// NOOPT: @test_static_var_private.SS2 = internal addrspace(1) global %struct.StructTy2 zeroinitializer, align 8
void test_static_var_private(void) {
static private char *sp1 = 0;
@@ -123,8 +123,8 @@ void test_static_var_private(void) {
// NOOPT: @test_static_var_local.sp3 = internal addrspace(1) global i8 addrspace(3)* addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*), align 4
// NOOPT: @test_static_var_local.sp4 = internal addrspace(1) global i8 addrspace(3)* null, align 4
// NOOPT: @test_static_var_local.sp5 = internal addrspace(1) global i8 addrspace(3)* null, align 4
-// NOOPT: @test_static_var_local.SS1 = internal addrspace(1) global %struct.StructTy1 { i8* null, i8 addrspace(3)* addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*), i8 addrspace(2)* null, i8 addrspace(1)* null, i8 addrspace(4)* null }, align 4
-// NOOPT: @test_static_var_local.SS2 = internal addrspace(1) global %struct.StructTy2 zeroinitializer, align 4
+// NOOPT: @test_static_var_local.SS1 = internal addrspace(1) global %struct.StructTy1 { i8* null, i8 addrspace(3)* addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*), i8 addrspace(2)* null, i8 addrspace(1)* null, i8 addrspace(4)* null }, align 8
+// NOOPT: @test_static_var_local.SS2 = internal addrspace(1) global %struct.StructTy2 zeroinitializer, align 8
void test_static_var_local(void) {
static local char *sp1 = 0;
static local char *sp2 = NULL;
@@ -143,9 +143,9 @@ void test_static_var_local(void) {
// NOOPT: store i8* null, i8** %sp3, align 4
// NOOPT: store i8* null, i8** %sp4, align 4
// NOOPT: %[[SS1:.*]] = bitcast %struct.StructTy1* %SS1 to i8*
-// NOOPT: call void @llvm.memcpy.p0i8.p2i8.i64(i8* %[[SS1]], i8 addrspace(2)* bitcast (%struct.StructTy1 addrspace(2)* @test_func_scope_var_private.SS1 to i8 addrspace(2)*), i64 32, i32 4, i1 false)
+// NOOPT: call void @llvm.memcpy.p0i8.p2i8.i64(i8* %[[SS1]], i8 addrspace(2)* bitcast (%struct.StructTy1 addrspace(2)* @test_func_scope_var_private.SS1 to i8 addrspace(2)*), i64 32, i32 8, i1 false)
// NOOPT: %[[SS2:.*]] = bitcast %struct.StructTy2* %SS2 to i8*
-// NOOPT: call void @llvm.memset.p0i8.i64(i8* %[[SS2]], i8 0, i64 24, i32 4, i1 false)
+// NOOPT: call void @llvm.memset.p0i8.i64(i8* %[[SS2]], i8 0, i64 24, i32 8, i1 false)
void test_func_scope_var_private(void) {
private char *sp1 = 0;
private char *sp2 = NULL;
@@ -163,9 +163,9 @@ void test_func_scope_var_private(void) {
// NOOPT: store i8 addrspace(3)* null, i8 addrspace(3)** %sp3, align 4
// NOOPT: store i8 addrspace(3)* null, i8 addrspace(3)** %sp4, align 4
// NOOPT: %[[SS1:.*]] = bitcast %struct.StructTy1* %SS1 to i8*
-// NOOPT: call void @llvm.memcpy.p0i8.p2i8.i64(i8* %[[SS1]], i8 addrspace(2)* bitcast (%struct.StructTy1 addrspace(2)* @test_func_scope_var_local.SS1 to i8 addrspace(2)*), i64 32, i32 4, i1 false)
+// NOOPT: call void @llvm.memcpy.p0i8.p2i8.i64(i8* %[[SS1]], i8 addrspace(2)* bitcast (%struct.StructTy1 addrspace(2)* @test_func_scope_var_local.SS1 to i8 addrspace(2)*), i64 32, i32 8, i1 false)
// NOOPT: %[[SS2:.*]] = bitcast %struct.StructTy2* %SS2 to i8*
-// NOOPT: call void @llvm.memset.p0i8.i64(i8* %[[SS2]], i8 0, i64 24, i32 4, i1 false)
+// NOOPT: call void @llvm.memset.p0i8.i64(i8* %[[SS2]], i8 0, i64 24, i32 8, i1 false)
void test_func_scope_var_local(void) {
local char *sp1 = 0;
local char *sp2 = NULL;
@@ -189,28 +189,28 @@ private char *p1;
// CHECK: @p2 = weak local_unnamed_addr addrspace(1) global i8 addrspace(3)* addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*), align 4
local char *p2;
-// CHECK: @p3 = common local_unnamed_addr addrspace(1) global i8 addrspace(2)* null, align 4
+// CHECK: @p3 = common local_unnamed_addr addrspace(1) global i8 addrspace(2)* null, align 8
constant char *p3;
-// CHECK: @p4 = common local_unnamed_addr addrspace(1) global i8 addrspace(1)* null, align 4
+// CHECK: @p4 = common local_unnamed_addr addrspace(1) global i8 addrspace(1)* null, align 8
global char *p4;
-// CHECK: @p5 = common local_unnamed_addr addrspace(1) global i8 addrspace(4)* null, align 4
+// CHECK: @p5 = common local_unnamed_addr addrspace(1) global i8 addrspace(4)* null, align 8
generic char *p5;
// Test default initialization of sturcture.
-// CHECK: @S1 = weak local_unnamed_addr addrspace(1) global %struct.StructTy1 { i8* null, i8 addrspace(3)* addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*), i8 addrspace(2)* null, i8 addrspace(1)* null, i8 addrspace(4)* null }, align 4
+// CHECK: @S1 = weak local_unnamed_addr addrspace(1) global %struct.StructTy1 { i8* null, i8 addrspace(3)* addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*), i8 addrspace(2)* null, i8 addrspace(1)* null, i8 addrspace(4)* null }, align 8
StructTy1 S1;
-// CHECK: @S2 = common local_unnamed_addr addrspace(1) global %struct.StructTy2 zeroinitializer, align 4
+// CHECK: @S2 = common local_unnamed_addr addrspace(1) global %struct.StructTy2 zeroinitializer, align 8
StructTy2 S2;
// Test default initialization of array.
-// CHECK: @A1 = weak local_unnamed_addr addrspace(1) global [2 x %struct.StructTy1] [%struct.StructTy1 { i8* null, i8 addrspace(3)* addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*), i8 addrspace(2)* null, i8 addrspace(1)* null, i8 addrspace(4)* null }, %struct.StructTy1 { i8* null, i8 addrspace(3)* addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*), i8 addrspace(2)* null, i8 addrspace(1)* null, i8 addrspace(4)* null }], align 4
+// CHECK: @A1 = weak local_unnamed_addr addrspace(1) global [2 x %struct.StructTy1] [%struct.StructTy1 { i8* null, i8 addrspace(3)* addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*), i8 addrspace(2)* null, i8 addrspace(1)* null, i8 addrspace(4)* null }, %struct.StructTy1 { i8* null, i8 addrspace(3)* addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*), i8 addrspace(2)* null, i8 addrspace(1)* null, i8 addrspace(4)* null }], align 8
StructTy1 A1[2];
-// CHECK: @A2 = common local_unnamed_addr addrspace(1) global [2 x %struct.StructTy2] zeroinitializer, align 4
+// CHECK: @A2 = common local_unnamed_addr addrspace(1) global [2 x %struct.StructTy2] zeroinitializer, align 8
StructTy2 A2[2];
// Test comparison with 0.
@@ -597,7 +597,7 @@ int test_and_ptr(private char* p1, local char* p2) {
// Test folding of null pointer in function scope.
// NOOPT-LABEL: test_fold_private
// NOOPT: call void @test_fold_callee
-// NOOPT: store i32 addrspace(1)* null, i32 addrspace(1)** %glob, align 4
+// NOOPT: store i32 addrspace(1)* null, i32 addrspace(1)** %glob, align 8
// NOOPT: %{{.*}} = sub i64 %{{.*}}, 0
// NOOPT: call void @test_fold_callee
// NOOPT: %{{.*}} = add nsw i64 %{{.*}}, 0
@@ -612,7 +612,7 @@ void test_fold_private(void) {
// NOOPT-LABEL: test_fold_local
// NOOPT: call void @test_fold_callee
-// NOOPT: store i32 addrspace(1)* null, i32 addrspace(1)** %glob, align 4
+// NOOPT: store i32 addrspace(1)* null, i32 addrspace(1)** %glob, align 8
// NOOPT: %{{.*}} = sub i64 %{{.*}}, 0
// NOOPT: call void @test_fold_callee
// NOOPT: %{{.*}} = add nsw i64 %{{.*}}, sext (i32 ptrtoint (i32 addrspace(3)* addrspacecast (i32 addrspace(4)* null to i32 addrspace(3)*) to i32) to i64)
diff --git a/test/CodeGenOpenCL/amdgpu-sizeof-alignof.cl b/test/CodeGenOpenCL/amdgpu-sizeof-alignof.cl
new file mode 100644
index 000000000000..a5d438933fa4
--- /dev/null
+++ b/test/CodeGenOpenCL/amdgpu-sizeof-alignof.cl
@@ -0,0 +1,70 @@
+// RUN: %clang_cc1 -triple r600 -cl-std=CL1.2 %s -emit-llvm -o - | FileCheck %s
+// RUN: %clang_cc1 -triple amdgcn-mesa-mesa3d -cl-std=CL1.2 %s -emit-llvm -o - | FileCheck %s
+// RUN: %clang_cc1 -triple amdgcn---opencl -cl-std=CL1.2 %s -emit-llvm -o - | FileCheck %s
+// RUN: %clang_cc1 -triple amdgcn---opencl -cl-std=CL2.0 %s -emit-llvm -o - | FileCheck %s
+// RUN: %clang_cc1 -triple amdgcn---amdgizcl -cl-std=CL1.2 %s -emit-llvm -o - | FileCheck %s
+// RUN: %clang_cc1 -triple amdgcn---amdgizcl -cl-std=CL2.0 %s -emit-llvm -o - | FileCheck %s
+
+#ifdef __AMDGCN__
+#define PTSIZE 8
+#else
+#define PTSIZE 4
+#endif
+
+#ifdef cl_khr_fp64
+#pragma OPENCL EXTENSION cl_khr_fp64 : enable
+#endif
+#ifdef cl_khr_fp16
+#pragma OPENCL EXTENSION cl_khr_fp16 : enable
+#endif
+
+typedef __SIZE_TYPE__ size_t;
+typedef __PTRDIFF_TYPE__ ptrdiff_t;
+typedef __INTPTR_TYPE__ intptr_t;
+typedef __UINTPTR_TYPE__ uintptr_t;
+typedef global void *global_ptr_t;
+typedef constant void *constant_ptr_t;
+typedef local void *local_ptr_t;
+typedef private void *private_ptr_t;
+
+void check(bool);
+
+void test() {
+ // CHECK-NOT: call void @check(i1 zeroext false)
+ check(sizeof(size_t) == PTSIZE);
+ check(__alignof__(size_t) == PTSIZE);
+ check(sizeof(intptr_t) == PTSIZE);
+ check(__alignof__(intptr_t) == PTSIZE);
+ check(sizeof(uintptr_t) == PTSIZE);
+ check(__alignof__(uintptr_t) == PTSIZE);
+ check(sizeof(ptrdiff_t) == PTSIZE);
+ check(__alignof__(ptrdiff_t) == PTSIZE);
+
+ check(sizeof(char) == 1);
+ check(__alignof__(char) == 1);
+ check(sizeof(short) == 2);
+ check(__alignof__(short) == 2);
+ check(sizeof(int) == 4);
+ check(__alignof__(int) == 4);
+ check(sizeof(long) == 8);
+ check(__alignof__(long) == 8);
+#ifdef cl_khr_fp16
+ check(sizeof(half) == 2);
+ check(__alignof__(half) == 2);
+#endif
+ check(sizeof(float) == 4);
+ check(__alignof__(float) == 4);
+#ifdef cl_khr_fp64
+ check(sizeof(double) == 8);
+ check(__alignof__(double) == 8);
+#endif
+
+ check(sizeof(void*) == (__OPENCL_C_VERSION__ >= 200 ? 8 : 4));
+ check(__alignof__(void*) == (__OPENCL_C_VERSION__ >= 200 ? 8 : 4));
+ check(sizeof(global_ptr_t) == PTSIZE);
+ check(__alignof__(global_ptr_t) == PTSIZE);
+ check(sizeof(constant_ptr_t) == PTSIZE);
+ check(__alignof__(constant_ptr_t) == PTSIZE);
+ check(sizeof(local_ptr_t) == 4);
+ check(__alignof__(private_ptr_t) == 4);
+}
generated by cgit v1.2.3 (git 2.25.1) at 2025-11-04 01:42:31 +0000