forked from OSchip/llvm-project
[AMDGPU] Switch to the new addr space mapping by default
This requires corresponding llvm change. Differential Revision: https://reviews.llvm.org/D40956 llvm-svn: 324102
This commit is contained in:
Yaxun Liu
parent
2a22c5deff
commit
f5f45e5e63
|
|
@ -30,7 +30,7 @@ namespace targets {
|
|||
|
||||
static const char *const DataLayoutStringR600 =
|
||||
"e-p:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128"
|
||||
"-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64";
|
||||
"-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64-A5";
|
||||
|
||||
static const char *const DataLayoutStringSIPrivateIsZero =
|
||||
"e-p:32:32-p1:64:64-p2:64:64-p3:32:32-p4:64:64-p5:32:32"
|
||||
|
|
|
|||
|
|
@ -77,10 +77,7 @@ class LLVM_LIBRARY_VISIBILITY AMDGPUTargetInfo final : public TargetInfo {
|
|||
return TT.getArch() == llvm::Triple::amdgcn;
|
||||
}
|
||||
|
||||
static bool isGenericZero(const llvm::Triple &TT) {
|
||||
return TT.getEnvironmentName() == "amdgiz" ||
|
||||
TT.getEnvironmentName() == "amdgizcl";
|
||||
}
|
||||
static bool isGenericZero(const llvm::Triple &TT) { return true; }
|
||||
|
||||
public:
|
||||
AMDGPUTargetInfo(const llvm::Triple &Triple, const TargetOptions &Opts);
|
||||
|
|
|
|||
|
|
@ -1,5 +1,4 @@
|
|||
// RUN: %clang_cc1 -triple x86_64-apple-darwin -emit-llvm < %s | FileCheck -check-prefixes=CHECK,X86,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,AMDGIZ,GIZ %s
|
||||
|
||||
// CHECK: @foo = common addrspace(1) global
|
||||
|
|
@ -26,11 +25,9 @@ __attribute__((address_space(2))) int *A, *B;
|
|||
// CHECK-LABEL: define void @test3()
|
||||
// X86: load i32 addrspace(2)*, i32 addrspace(2)** @B
|
||||
// AMDGIZ: load i32 addrspace(2)*, i32 addrspace(2)** addrspacecast (i32 addrspace(2)* addrspace(1)* @B to i32 addrspace(2)**)
|
||||
// PIZ: load i32 addrspace(2)*, i32 addrspace(2)* addrspace(4)* addrspacecast (i32 addrspace(2)* addrspace(1)* @B to i32 addrspace(2)* addrspace(4)*)
|
||||
// CHECK: load i32, i32 addrspace(2)*
|
||||
// X86: load i32 addrspace(2)*, i32 addrspace(2)** @A
|
||||
// AMDGIZ: load i32 addrspace(2)*, i32 addrspace(2)** addrspacecast (i32 addrspace(2)* addrspace(1)* @A to i32 addrspace(2)**)
|
||||
// PIZ: load i32 addrspace(2)*, i32 addrspace(2)* addrspace(4)* addrspacecast (i32 addrspace(2)* addrspace(1)* @A to i32 addrspace(2)* addrspace(4)*)
|
||||
// CHECK: store i32 {{.*}}, i32 addrspace(2)*
|
||||
void test3() {
|
||||
*A = *B;
|
||||
|
|
@ -44,8 +41,6 @@ typedef struct {
|
|||
// CHECK-LABEL: define void @test4(
|
||||
// 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;
|
||||
|
|
|
|||
|
|
@ -1,39 +1,27 @@
|
|||
// RUN: %clang_cc1 -triple amdgcn -emit-llvm < %s | FileCheck -check-prefixes=PIZ,COM %s
|
||||
// RUN: %clang_cc1 -triple amdgcn---amdgiz -emit-llvm < %s | FileCheck -check-prefixes=CHECK,COM %s
|
||||
|
||||
// PIZ-DAG: @foo = common addrspace(1) global i32 0
|
||||
// CHECK-DAG: @foo = common addrspace(1) global i32 0
|
||||
int foo;
|
||||
|
||||
// PIZ-DAG: @ban = common addrspace(1) global [10 x i32] zeroinitializer
|
||||
// CHECK-DAG: @ban = common addrspace(1) global [10 x i32] zeroinitializer
|
||||
int ban[10];
|
||||
|
||||
// PIZ-DAG: @A = common addrspace(1) global i32 addrspace(4)* null
|
||||
// PIZ-DAG: @B = common addrspace(1) global i32 addrspace(4)* null
|
||||
// CHECK-DAG: @A = common addrspace(1) global i32* null
|
||||
// CHECK-DAG: @B = common addrspace(1) global i32* null
|
||||
int *A;
|
||||
int *B;
|
||||
|
||||
// COM-LABEL: define i32 @test1()
|
||||
// PIZ: load i32, i32 addrspace(4)* addrspacecast{{[^@]+}} @foo
|
||||
// CHECK: load i32, i32* addrspacecast{{[^@]+}} @foo
|
||||
int test1() { return foo; }
|
||||
|
||||
// COM-LABEL: define i32 @test2(i32 %i)
|
||||
// COM: %[[addr:.*]] = getelementptr
|
||||
// PIZ: load i32, i32 addrspace(4)* %[[addr]]
|
||||
// PIZ-NEXT: ret i32
|
||||
// CHECK: load i32, i32* %[[addr]]
|
||||
// CHECK-NEXT: ret i32
|
||||
int test2(int i) { return ban[i]; }
|
||||
|
||||
// COM-LABEL: define void @test3()
|
||||
// PIZ: load i32 addrspace(4)*, i32 addrspace(4)* addrspace(4)* addrspacecast{{[^@]+}} @B
|
||||
// PIZ: load i32, i32 addrspace(4)*
|
||||
// PIZ: load i32 addrspace(4)*, i32 addrspace(4)* addrspace(4)* addrspacecast{{[^@]+}} @A
|
||||
// PIZ: store i32 {{.*}}, i32 addrspace(4)*
|
||||
// CHECK: load i32*, i32** addrspacecast{{.*}} @B
|
||||
// CHECK: load i32, i32*
|
||||
// CHECK: load i32*, i32** addrspacecast{{.*}} @A
|
||||
|
|
@ -42,13 +30,6 @@ void test3() {
|
|||
*A = *B;
|
||||
}
|
||||
|
||||
// PIZ-LABEL: define void @test4(i32 addrspace(4)* %a)
|
||||
// PIZ: %[[alloca:.*]] = alloca i32 addrspace(4)*
|
||||
// PIZ: %[[a_addr:.*]] = addrspacecast{{.*}} %[[alloca]] to i32 addrspace(4)* addrspace(4)*
|
||||
// PIZ: store i32 addrspace(4)* %a, i32 addrspace(4)* addrspace(4)* %[[a_addr]]
|
||||
// PIZ: %[[r0:.*]] = load i32 addrspace(4)*, i32 addrspace(4)* addrspace(4)* %[[a_addr]]
|
||||
// PIZ: %[[arrayidx:.*]] = getelementptr inbounds i32, i32 addrspace(4)* %[[r0]]
|
||||
// PIZ: store i32 0, i32 addrspace(4)* %[[arrayidx]]
|
||||
// CHECK-LABEL: define void @test4(i32* %a)
|
||||
// CHECK: %[[alloca:.*]] = alloca i32*, align 8, addrspace(5)
|
||||
// CHECK: %[[a_addr:.*]] = addrspacecast{{.*}} %[[alloca]] to i32**
|
||||
|
|
|
|||
|
|
@ -124,20 +124,20 @@
|
|||
|
||||
// RUN: %clang_cc1 -triple r600-unknown -o - -emit-llvm %s | \
|
||||
// RUN: FileCheck %s -check-prefix=R600
|
||||
// R600: target datalayout = "e-p:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64"
|
||||
// R600: target datalayout = "e-p:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64-A5"
|
||||
|
||||
// RUN: %clang_cc1 -triple r600-unknown -target-cpu cayman -o - -emit-llvm %s \
|
||||
// RUN: | FileCheck %s -check-prefix=R600D
|
||||
// R600D: target datalayout = "e-p:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64"
|
||||
// R600D: target datalayout = "e-p:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64-A5"
|
||||
|
||||
// RUN: %clang_cc1 -triple amdgcn-unknown -target-cpu hawaii -o - -emit-llvm %s \
|
||||
// RUN: | FileCheck %s -check-prefix=R600SI
|
||||
// R600SI: target datalayout = "e-p:32:32-p1:64:64-p2:64:64-p3:32:32-p4:64:64-p5:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64"
|
||||
// R600SI: target datalayout = "e-p:64:64-p1:64:64-p2:64:64-p3:32:32-p4:32:32-p5:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64-A5"
|
||||
|
||||
// Test default -target-cpu
|
||||
// RUN: %clang_cc1 -triple amdgcn-unknown -o - -emit-llvm %s \
|
||||
// RUN: | FileCheck %s -check-prefix=R600SIDefault
|
||||
// R600SIDefault: target datalayout = "e-p:32:32-p1:64:64-p2:64:64-p3:32:32-p4:64:64-p5:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64"
|
||||
// R600SIDefault: target datalayout = "e-p:64:64-p1:64:64-p2:64:64-p3:32:32-p4:32:32-p5:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64-A5"
|
||||
|
||||
// RUN: %clang_cc1 -triple arm64-unknown -o - -emit-llvm %s | \
|
||||
// RUN: FileCheck %s -check-prefix=AARCH64
|
||||
|
|
|
|||
|
|
@ -1,11 +1,9 @@
|
|||
// RUN: %clang_cc1 %s -O0 -ffake-address-space-map -emit-llvm -o - | FileCheck %s --check-prefixes=CHECK,SPIR
|
||||
// RUN: %clang_cc1 %s -O0 -DCL20 -cl-std=CL2.0 -ffake-address-space-map -emit-llvm -o - | FileCheck %s --check-prefixes=CL20,CL20SPIR
|
||||
// RUN: %clang_cc1 %s -O0 -triple amdgcn-amd-amdhsa-opencl -emit-llvm -o - | FileCheck --check-prefixes=CHECK,SPIR %s
|
||||
// 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
|
||||
// RUN: %clang_cc1 %s -O0 -triple amdgcn-amd-amdhsa-opencl -emit-llvm -o - | FileCheck --check-prefixes=CHECK,GIZ %s
|
||||
// RUN: %clang_cc1 %s -O0 -triple amdgcn-amd-amdhsa-opencl -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,GIZ %s
|
||||
// RUN: %clang_cc1 %s -O0 -triple r600-- -emit-llvm -o - | FileCheck --check-prefixes=CHECK,GIZ %s
|
||||
|
||||
// SPIR: %struct.S = type { i32, i32, i32* }
|
||||
// CL20SPIR: %struct.S = type { i32, i32, i32 addrspace(4)* }
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
// REQUIRES: amdgpu-registered-target
|
||||
// RUN: %clang_cc1 -triple amdgcn-unknown-unknown-amdgiz -S -emit-llvm -o - %s | FileCheck -check-prefixes=CHECK,AMDGCN %s
|
||||
// RUN: %clang_cc1 -triple r600-unknown-unknown -S -emit-llvm -o - %s | FileCheck -check-prefixes=CHECK,R600 %s
|
||||
// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -S -emit-llvm -o - %s | FileCheck %s
|
||||
// RUN: %clang_cc1 -triple r600-unknown-unknown -S -emit-llvm -o - %s | FileCheck %s
|
||||
|
||||
typedef __attribute__(( ext_vector_type(2) )) char char2;
|
||||
typedef __attribute__(( ext_vector_type(3) )) char char3;
|
||||
|
|
@ -309,8 +309,7 @@ void func_single_struct_element_struct_arg(single_struct_element_struct_arg_t ar
|
|||
// CHECK: void @func_different_size_type_pair_arg(i64 %arg1.coerce0, i32 %arg1.coerce1)
|
||||
void func_different_size_type_pair_arg(different_size_type_pair arg1) { }
|
||||
|
||||
// AMDGCN: void @func_flexible_array_arg(%struct.flexible_array addrspace(5)* byval nocapture align 4 %arg)
|
||||
// R600: void @func_flexible_array_arg(%struct.flexible_array* byval nocapture align 4 %arg)
|
||||
// CHECK: void @func_flexible_array_arg(%struct.flexible_array addrspace(5)* byval nocapture align 4 %arg)
|
||||
void func_flexible_array_arg(flexible_array arg) { }
|
||||
|
||||
// CHECK: define float @func_f32_ret()
|
||||
|
|
@ -405,16 +404,14 @@ struct_arr16 func_ret_struct_arr16()
|
|||
return s;
|
||||
}
|
||||
|
||||
// AMDGCN: define void @func_ret_struct_arr32(%struct.struct_arr32 addrspace(5)* noalias nocapture sret %agg.result)
|
||||
// R600: define void @func_ret_struct_arr32(%struct.struct_arr32* noalias nocapture sret %agg.result)
|
||||
// CHECK: define void @func_ret_struct_arr32(%struct.struct_arr32 addrspace(5)* noalias nocapture sret %agg.result)
|
||||
struct_arr32 func_ret_struct_arr32()
|
||||
{
|
||||
struct_arr32 s = { 0 };
|
||||
return s;
|
||||
}
|
||||
|
||||
// AMDGCN: define void @func_ret_struct_arr33(%struct.struct_arr33 addrspace(5)* noalias nocapture sret %agg.result)
|
||||
// R600: define void @func_ret_struct_arr33(%struct.struct_arr33* noalias nocapture sret %agg.result)
|
||||
// CHECK: define void @func_ret_struct_arr33(%struct.struct_arr33 addrspace(5)* noalias nocapture sret %agg.result)
|
||||
struct_arr33 func_ret_struct_arr33()
|
||||
{
|
||||
struct_arr33 s = { 0 };
|
||||
|
|
@ -443,8 +440,7 @@ different_size_type_pair func_different_size_type_pair_ret()
|
|||
return s;
|
||||
}
|
||||
|
||||
// AMDGCN: define void @func_flexible_array_ret(%struct.flexible_array addrspace(5)* noalias nocapture sret %agg.result)
|
||||
// R600: define void @func_flexible_array_ret(%struct.flexible_array* noalias nocapture sret %agg.result)
|
||||
// CHECK: define void @func_flexible_array_ret(%struct.flexible_array addrspace(5)* noalias nocapture sret %agg.result)
|
||||
flexible_array func_flexible_array_ret()
|
||||
{
|
||||
flexible_array s = { 0 };
|
||||
|
|
@ -454,13 +450,11 @@ flexible_array func_flexible_array_ret()
|
|||
// CHECK: define void @func_reg_state_lo(<4 x i32> %arg0, <4 x i32> %arg1, <4 x i32> %arg2, i32 %arg3, i32 %s.coerce0, float %s.coerce1, i32 %s.coerce2)
|
||||
void func_reg_state_lo(int4 arg0, int4 arg1, int4 arg2, int arg3, struct_arg_t s) { }
|
||||
|
||||
// AMDGCN: define void @func_reg_state_hi(<4 x i32> %arg0, <4 x i32> %arg1, <4 x i32> %arg2, i32 %arg3, i32 %arg4, %struct.struct_arg addrspace(5)* byval nocapture align 4 %s)
|
||||
// R600: define void @func_reg_state_hi(<4 x i32> %arg0, <4 x i32> %arg1, <4 x i32> %arg2, i32 %arg3, i32 %arg4, %struct.struct_arg* byval nocapture align 4 %s)
|
||||
// CHECK: define void @func_reg_state_hi(<4 x i32> %arg0, <4 x i32> %arg1, <4 x i32> %arg2, i32 %arg3, i32 %arg4, %struct.struct_arg addrspace(5)* byval nocapture align 4 %s)
|
||||
void func_reg_state_hi(int4 arg0, int4 arg1, int4 arg2, int arg3, int arg4, struct_arg_t s) { }
|
||||
|
||||
// XXX - Why don't the inner structs flatten?
|
||||
// AMDGCN: define void @func_reg_state_num_regs_nested_struct(<4 x i32> %arg0, i32 %arg1, i32 %arg2.coerce0, %struct.nested %arg2.coerce1, i32 %arg3.coerce0, %struct.nested %arg3.coerce1, %struct.num_regs_nested_struct addrspace(5)* byval nocapture align 8 %arg4)
|
||||
// R600: define void @func_reg_state_num_regs_nested_struct(<4 x i32> %arg0, i32 %arg1, i32 %arg2.coerce0, %struct.nested %arg2.coerce1, i32 %arg3.coerce0, %struct.nested %arg3.coerce1, %struct.num_regs_nested_struct* byval nocapture align 8 %arg4)
|
||||
// CHECK: define void @func_reg_state_num_regs_nested_struct(<4 x i32> %arg0, i32 %arg1, i32 %arg2.coerce0, %struct.nested %arg2.coerce1, i32 %arg3.coerce0, %struct.nested %arg3.coerce1, %struct.num_regs_nested_struct addrspace(5)* byval nocapture align 8 %arg4)
|
||||
void func_reg_state_num_regs_nested_struct(int4 arg0, int arg1, num_regs_nested_struct arg2, num_regs_nested_struct arg3, num_regs_nested_struct arg4) { }
|
||||
|
||||
// CHECK: define void @func_double_nested_struct_arg(<4 x i32> %arg0, i32 %arg1, i32 %arg2.coerce0, %struct.double_nested %arg2.coerce1, i16 %arg2.coerce2)
|
||||
|
|
@ -475,8 +469,7 @@ double_nested_struct func_double_nested_struct_ret(int4 arg0, int arg1) {
|
|||
// CHECK: define void @func_large_struct_padding_arg_direct(i8 %arg.coerce0, i32 %arg.coerce1, i8 %arg.coerce2, i32 %arg.coerce3, i8 %arg.coerce4, i8 %arg.coerce5, i16 %arg.coerce6, i16 %arg.coerce7, [3 x i8] %arg.coerce8, i64 %arg.coerce9, i32 %arg.coerce10, i8 %arg.coerce11, i32 %arg.coerce12, i16 %arg.coerce13, i8 %arg.coerce14)
|
||||
void func_large_struct_padding_arg_direct(large_struct_padding arg) { }
|
||||
|
||||
// AMDGCN: define void @func_large_struct_padding_arg_store(%struct.large_struct_padding addrspace(1)* nocapture %out, %struct.large_struct_padding addrspace(5)* byval nocapture readonly align 8 %arg)
|
||||
// R600: define void @func_large_struct_padding_arg_store(%struct.large_struct_padding addrspace(1)* nocapture %out, %struct.large_struct_padding* byval nocapture readonly align 8 %arg)
|
||||
// CHECK: define void @func_large_struct_padding_arg_store(%struct.large_struct_padding addrspace(1)* nocapture %out, %struct.large_struct_padding addrspace(5)* byval nocapture readonly align 8 %arg)
|
||||
void func_large_struct_padding_arg_store(global large_struct_padding* out, large_struct_padding arg) {
|
||||
*out = arg;
|
||||
}
|
||||
|
|
@ -486,8 +479,7 @@ void v3i32_reg_count(int3 arg1, int3 arg2, int3 arg3, int3 arg4, struct_arg_t ar
|
|||
|
||||
// Function signature from blender, nothing should be passed byval. The v3i32
|
||||
// should not count as 4 passed registers.
|
||||
// AMDGCN: define void @v3i32_pair_reg_count(%struct.int3_pair addrspace(5)* nocapture %arg0, <3 x i32> %arg1.coerce0, <3 x i32> %arg1.coerce1, <3 x i32> %arg2, <3 x i32> %arg3.coerce0, <3 x i32> %arg3.coerce1, <3 x i32> %arg4, float %arg5)
|
||||
// R600: define void @v3i32_pair_reg_count(%struct.int3_pair* nocapture %arg0, <3 x i32> %arg1.coerce0, <3 x i32> %arg1.coerce1, <3 x i32> %arg2, <3 x i32> %arg3.coerce0, <3 x i32> %arg3.coerce1, <3 x i32> %arg4, float %arg5)
|
||||
// CHECK: define void @v3i32_pair_reg_count(%struct.int3_pair addrspace(5)* nocapture %arg0, <3 x i32> %arg1.coerce0, <3 x i32> %arg1.coerce1, <3 x i32> %arg2, <3 x i32> %arg3.coerce0, <3 x i32> %arg3.coerce1, <3 x i32> %arg4, float %arg5)
|
||||
void v3i32_pair_reg_count(int3_pair *arg0, int3_pair arg1, int3 arg2, int3_pair arg3, int3 arg4, float arg5) { }
|
||||
|
||||
// Each short4 should fit pack into 2 registers.
|
||||
|
|
@ -495,8 +487,7 @@ void v3i32_pair_reg_count(int3_pair *arg0, int3_pair arg1, int3 arg2, int3_pair
|
|||
void v4i16_reg_count(short4 arg0, short4 arg1, short4 arg2, short4 arg3,
|
||||
short4 arg4, short4 arg5, struct_4regs arg6) { }
|
||||
|
||||
// AMDGCN: define void @v4i16_pair_reg_count_over(<4 x i16> %arg0, <4 x i16> %arg1, <4 x i16> %arg2, <4 x i16> %arg3, <4 x i16> %arg4, <4 x i16> %arg5, <4 x i16> %arg6, %struct.struct_4regs addrspace(5)* byval nocapture align 4 %arg7)
|
||||
// R600: define void @v4i16_pair_reg_count_over(<4 x i16> %arg0, <4 x i16> %arg1, <4 x i16> %arg2, <4 x i16> %arg3, <4 x i16> %arg4, <4 x i16> %arg5, <4 x i16> %arg6, %struct.struct_4regs* byval nocapture align 4 %arg7)
|
||||
// CHECK: define void @v4i16_pair_reg_count_over(<4 x i16> %arg0, <4 x i16> %arg1, <4 x i16> %arg2, <4 x i16> %arg3, <4 x i16> %arg4, <4 x i16> %arg5, <4 x i16> %arg6, %struct.struct_4regs addrspace(5)* byval nocapture align 4 %arg7)
|
||||
void v4i16_pair_reg_count_over(short4 arg0, short4 arg1, short4 arg2, short4 arg3,
|
||||
short4 arg4, short4 arg5, short4 arg6, struct_4regs arg7) { }
|
||||
|
||||
|
|
@ -504,8 +495,7 @@ void v4i16_pair_reg_count_over(short4 arg0, short4 arg1, short4 arg2, short4 arg
|
|||
void v3i16_reg_count(short3 arg0, short3 arg1, short3 arg2, short3 arg3,
|
||||
short3 arg4, short3 arg5, struct_4regs arg6) { }
|
||||
|
||||
// AMDGCN: define void @v3i16_reg_count_over(<3 x i16> %arg0, <3 x i16> %arg1, <3 x i16> %arg2, <3 x i16> %arg3, <3 x i16> %arg4, <3 x i16> %arg5, <3 x i16> %arg6, %struct.struct_4regs addrspace(5)* byval nocapture align 4 %arg7)
|
||||
// R600: define void @v3i16_reg_count_over(<3 x i16> %arg0, <3 x i16> %arg1, <3 x i16> %arg2, <3 x i16> %arg3, <3 x i16> %arg4, <3 x i16> %arg5, <3 x i16> %arg6, %struct.struct_4regs* byval nocapture align 4 %arg7)
|
||||
// CHECK: define void @v3i16_reg_count_over(<3 x i16> %arg0, <3 x i16> %arg1, <3 x i16> %arg2, <3 x i16> %arg3, <3 x i16> %arg4, <3 x i16> %arg5, <3 x i16> %arg6, %struct.struct_4regs addrspace(5)* byval nocapture align 4 %arg7)
|
||||
void v3i16_reg_count_over(short3 arg0, short3 arg1, short3 arg2, short3 arg3,
|
||||
short3 arg4, short3 arg5, short3 arg6, struct_4regs arg7) { }
|
||||
|
||||
|
|
@ -515,8 +505,7 @@ void v2i16_reg_count(short2 arg0, short2 arg1, short2 arg2, short2 arg3,
|
|||
short2 arg8, short2 arg9, short2 arg10, short2 arg11,
|
||||
struct_4regs arg13) { }
|
||||
|
||||
// AMDGCN: define void @v2i16_reg_count_over(<2 x i16> %arg0, <2 x i16> %arg1, <2 x i16> %arg2, <2 x i16> %arg3, <2 x i16> %arg4, <2 x i16> %arg5, <2 x i16> %arg6, <2 x i16> %arg7, <2 x i16> %arg8, <2 x i16> %arg9, <2 x i16> %arg10, <2 x i16> %arg11, <2 x i16> %arg12, %struct.struct_4regs addrspace(5)* byval nocapture align 4 %arg13)
|
||||
// R600: define void @v2i16_reg_count_over(<2 x i16> %arg0, <2 x i16> %arg1, <2 x i16> %arg2, <2 x i16> %arg3, <2 x i16> %arg4, <2 x i16> %arg5, <2 x i16> %arg6, <2 x i16> %arg7, <2 x i16> %arg8, <2 x i16> %arg9, <2 x i16> %arg10, <2 x i16> %arg11, <2 x i16> %arg12, %struct.struct_4regs* byval nocapture align 4 %arg13)
|
||||
// CHECK: define void @v2i16_reg_count_over(<2 x i16> %arg0, <2 x i16> %arg1, <2 x i16> %arg2, <2 x i16> %arg3, <2 x i16> %arg4, <2 x i16> %arg5, <2 x i16> %arg6, <2 x i16> %arg7, <2 x i16> %arg8, <2 x i16> %arg9, <2 x i16> %arg10, <2 x i16> %arg11, <2 x i16> %arg12, %struct.struct_4regs addrspace(5)* byval nocapture align 4 %arg13)
|
||||
void v2i16_reg_count_over(short2 arg0, short2 arg1, short2 arg2, short2 arg3,
|
||||
short2 arg4, short2 arg5, short2 arg6, short2 arg7,
|
||||
short2 arg8, short2 arg9, short2 arg10, short2 arg11,
|
||||
|
|
@ -526,8 +515,7 @@ void v2i16_reg_count_over(short2 arg0, short2 arg1, short2 arg2, short2 arg3,
|
|||
void v2i8_reg_count(char2 arg0, char2 arg1, char2 arg2, char2 arg3,
|
||||
char2 arg4, char2 arg5, struct_4regs arg6) { }
|
||||
|
||||
// AMDGCN: define void @v2i8_reg_count_over(<2 x i8> %arg0, <2 x i8> %arg1, <2 x i8> %arg2, <2 x i8> %arg3, <2 x i8> %arg4, <2 x i8> %arg5, i32 %arg6, %struct.struct_4regs addrspace(5)* byval nocapture align 4 %arg7)
|
||||
// R600: define void @v2i8_reg_count_over(<2 x i8> %arg0, <2 x i8> %arg1, <2 x i8> %arg2, <2 x i8> %arg3, <2 x i8> %arg4, <2 x i8> %arg5, i32 %arg6, %struct.struct_4regs* byval nocapture align 4 %arg7)
|
||||
// CHECK: define void @v2i8_reg_count_over(<2 x i8> %arg0, <2 x i8> %arg1, <2 x i8> %arg2, <2 x i8> %arg3, <2 x i8> %arg4, <2 x i8> %arg5, i32 %arg6, %struct.struct_4regs addrspace(5)* byval nocapture align 4 %arg7)
|
||||
void v2i8_reg_count_over(char2 arg0, char2 arg1, char2 arg2, char2 arg3,
|
||||
char2 arg4, char2 arg5, int arg6, struct_4regs arg7) { }
|
||||
|
||||
|
|
|
|||
|
|
@ -336,91 +336,91 @@ kernel void local_memory_alignment_arg(
|
|||
}
|
||||
|
||||
// CHECK-LABEL: @private_memory_alignment_alloca(
|
||||
// CHECK: %private_i8 = alloca [4 x i8], align 1
|
||||
// CHECK: %private_v2i8 = alloca [4 x <2 x i8>], align 2
|
||||
// CHECK: %private_v3i8 = alloca [4 x <3 x i8>], align 4
|
||||
// CHECK: %private_v4i8 = alloca [4 x <4 x i8>], align 4
|
||||
// CHECK: %private_v8i8 = alloca [4 x <8 x i8>], align 8
|
||||
// CHECK: %private_v16i8 = alloca [4 x <16 x i8>], align 16
|
||||
// CHECK: %private_i16 = alloca [4 x i16], align 2
|
||||
// CHECK: %private_v2i16 = alloca [4 x <2 x i16>], align 4
|
||||
// CHECK: %private_v3i16 = alloca [4 x <3 x i16>], align 8
|
||||
// CHECK: %private_v4i16 = alloca [4 x <4 x i16>], align 8
|
||||
// CHECK: %private_v8i16 = alloca [4 x <8 x i16>], align 16
|
||||
// CHECK: %private_v16i16 = alloca [4 x <16 x i16>], align 32
|
||||
// CHECK: %private_i32 = alloca [4 x i32], align 4
|
||||
// CHECK: %private_v2i32 = alloca [4 x <2 x i32>], align 8
|
||||
// CHECK: %private_v3i32 = alloca [4 x <3 x i32>], align 16
|
||||
// CHECK: %private_v4i32 = alloca [4 x <4 x i32>], align 16
|
||||
// CHECK: %private_v8i32 = alloca [4 x <8 x i32>], align 32
|
||||
// CHECK: %private_v16i32 = alloca [4 x <16 x i32>], align 64
|
||||
// CHECK: %private_i64 = alloca [4 x i64], align 8
|
||||
// CHECK: %private_v2i64 = alloca [4 x <2 x i64>], align 16
|
||||
// CHECK: %private_v3i64 = alloca [4 x <3 x i64>], align 32
|
||||
// CHECK: %private_v4i64 = alloca [4 x <4 x i64>], align 32
|
||||
// CHECK: %private_v8i64 = alloca [4 x <8 x i64>], align 64
|
||||
// CHECK: %private_v16i64 = alloca [4 x <16 x i64>], align 128
|
||||
// CHECK: %private_f16 = alloca [4 x half], align 2
|
||||
// CHECK: %private_v2f16 = alloca [4 x <2 x half>], align 4
|
||||
// CHECK: %private_v3f16 = alloca [4 x <3 x half>], align 8
|
||||
// CHECK: %private_v4f16 = alloca [4 x <4 x half>], align 8
|
||||
// CHECK: %private_v8f16 = alloca [4 x <8 x half>], align 16
|
||||
// CHECK: %private_v16f16 = alloca [4 x <16 x half>], align 32
|
||||
// CHECK: %private_f32 = alloca [4 x float], align 4
|
||||
// CHECK: %private_v2f32 = alloca [4 x <2 x float>], align 8
|
||||
// CHECK: %private_v3f32 = alloca [4 x <3 x float>], align 16
|
||||
// CHECK: %private_v4f32 = alloca [4 x <4 x float>], align 16
|
||||
// CHECK: %private_v8f32 = alloca [4 x <8 x float>], align 32
|
||||
// CHECK: %private_v16f32 = alloca [4 x <16 x float>], align 64
|
||||
// CHECK: %private_f64 = alloca [4 x double], align 8
|
||||
// CHECK: %private_v2f64 = alloca [4 x <2 x double>], align 16
|
||||
// CHECK: %private_v3f64 = alloca [4 x <3 x double>], align 32
|
||||
// CHECK: %private_v4f64 = alloca [4 x <4 x double>], align 32
|
||||
// CHECK: %private_v8f64 = alloca [4 x <8 x double>], align 64
|
||||
// CHECK: %private_v16f64 = alloca [4 x <16 x double>], align 128
|
||||
// CHECK: %private_i8 = alloca [4 x i8], align 1, addrspace(5)
|
||||
// CHECK: %private_v2i8 = alloca [4 x <2 x i8>], align 2, addrspace(5)
|
||||
// CHECK: %private_v3i8 = alloca [4 x <3 x i8>], align 4, addrspace(5)
|
||||
// CHECK: %private_v4i8 = alloca [4 x <4 x i8>], align 4, addrspace(5)
|
||||
// CHECK: %private_v8i8 = alloca [4 x <8 x i8>], align 8, addrspace(5)
|
||||
// CHECK: %private_v16i8 = alloca [4 x <16 x i8>], align 16, addrspace(5)
|
||||
// CHECK: %private_i16 = alloca [4 x i16], align 2, addrspace(5)
|
||||
// CHECK: %private_v2i16 = alloca [4 x <2 x i16>], align 4, addrspace(5)
|
||||
// CHECK: %private_v3i16 = alloca [4 x <3 x i16>], align 8, addrspace(5)
|
||||
// CHECK: %private_v4i16 = alloca [4 x <4 x i16>], align 8, addrspace(5)
|
||||
// CHECK: %private_v8i16 = alloca [4 x <8 x i16>], align 16, addrspace(5)
|
||||
// CHECK: %private_v16i16 = alloca [4 x <16 x i16>], align 32, addrspace(5)
|
||||
// CHECK: %private_i32 = alloca [4 x i32], align 4, addrspace(5)
|
||||
// CHECK: %private_v2i32 = alloca [4 x <2 x i32>], align 8, addrspace(5)
|
||||
// CHECK: %private_v3i32 = alloca [4 x <3 x i32>], align 16, addrspace(5)
|
||||
// CHECK: %private_v4i32 = alloca [4 x <4 x i32>], align 16, addrspace(5)
|
||||
// CHECK: %private_v8i32 = alloca [4 x <8 x i32>], align 32, addrspace(5)
|
||||
// CHECK: %private_v16i32 = alloca [4 x <16 x i32>], align 64, addrspace(5)
|
||||
// CHECK: %private_i64 = alloca [4 x i64], align 8, addrspace(5)
|
||||
// CHECK: %private_v2i64 = alloca [4 x <2 x i64>], align 16, addrspace(5)
|
||||
// CHECK: %private_v3i64 = alloca [4 x <3 x i64>], align 32, addrspace(5)
|
||||
// CHECK: %private_v4i64 = alloca [4 x <4 x i64>], align 32, addrspace(5)
|
||||
// CHECK: %private_v8i64 = alloca [4 x <8 x i64>], align 64, addrspace(5)
|
||||
// CHECK: %private_v16i64 = alloca [4 x <16 x i64>], align 128, addrspace(5)
|
||||
// CHECK: %private_f16 = alloca [4 x half], align 2, addrspace(5)
|
||||
// CHECK: %private_v2f16 = alloca [4 x <2 x half>], align 4, addrspace(5)
|
||||
// CHECK: %private_v3f16 = alloca [4 x <3 x half>], align 8, addrspace(5)
|
||||
// CHECK: %private_v4f16 = alloca [4 x <4 x half>], align 8, addrspace(5)
|
||||
// CHECK: %private_v8f16 = alloca [4 x <8 x half>], align 16, addrspace(5)
|
||||
// CHECK: %private_v16f16 = alloca [4 x <16 x half>], align 32, addrspace(5)
|
||||
// CHECK: %private_f32 = alloca [4 x float], align 4, addrspace(5)
|
||||
// CHECK: %private_v2f32 = alloca [4 x <2 x float>], align 8, addrspace(5)
|
||||
// CHECK: %private_v3f32 = alloca [4 x <3 x float>], align 16, addrspace(5)
|
||||
// CHECK: %private_v4f32 = alloca [4 x <4 x float>], align 16, addrspace(5)
|
||||
// CHECK: %private_v8f32 = alloca [4 x <8 x float>], align 32, addrspace(5)
|
||||
// CHECK: %private_v16f32 = alloca [4 x <16 x float>], align 64, addrspace(5)
|
||||
// CHECK: %private_f64 = alloca [4 x double], align 8, addrspace(5)
|
||||
// CHECK: %private_v2f64 = alloca [4 x <2 x double>], align 16, addrspace(5)
|
||||
// CHECK: %private_v3f64 = alloca [4 x <3 x double>], align 32, addrspace(5)
|
||||
// CHECK: %private_v4f64 = alloca [4 x <4 x double>], align 32, addrspace(5)
|
||||
// CHECK: %private_v8f64 = alloca [4 x <8 x double>], align 64, addrspace(5)
|
||||
// CHECK: %private_v16f64 = alloca [4 x <16 x double>], align 128, addrspace(5)
|
||||
|
||||
// CHECK: store volatile i8 0, i8* %arraydecay, align 1
|
||||
// CHECK: store volatile <2 x i8> zeroinitializer, <2 x i8>* %arraydecay{{[0-9]+}}, align 2
|
||||
// CHECK: store volatile <4 x i8> <i8 0, i8 0, i8 0, i8 undef>, <4 x i8>* %storetmp, align 4
|
||||
// CHECK: store volatile <4 x i8> zeroinitializer, <4 x i8>* %arraydecay{{[0-9]+}}, align 4
|
||||
// CHECK: store volatile <8 x i8> zeroinitializer, <8 x i8>* %arraydecay{{[0-9]+}}, align 8
|
||||
// CHECK: store volatile <16 x i8> zeroinitializer, <16 x i8>* %arraydecay{{[0-9]+}}, align 16
|
||||
// CHECK: store volatile i16 0, i16* %arraydecay{{[0-9]+}}, align 2
|
||||
// CHECK: store volatile <2 x i16> zeroinitializer, <2 x i16>* %arraydecay{{[0-9]+}}, align 4
|
||||
// CHECK: store volatile <4 x i16> <i16 0, i16 0, i16 0, i16 undef>, <4 x i16>* %storetmp{{[0-9]+}}, align 8
|
||||
// CHECK: store volatile <4 x i16> zeroinitializer, <4 x i16>* %arraydecay{{[0-9]+}}, align 8
|
||||
// CHECK: store volatile <8 x i16> zeroinitializer, <8 x i16>* %arraydecay{{[0-9]+}}, align 16
|
||||
// CHECK: store volatile <16 x i16> zeroinitializer, <16 x i16>* %arraydecay{{[0-9]+}}, align 32
|
||||
// CHECK: store volatile i32 0, i32* %arraydecay{{[0-9]+}}, align 4
|
||||
// CHECK: store volatile <2 x i32> zeroinitializer, <2 x i32>* %arraydecay{{[0-9]+}}, align 8
|
||||
// CHECK: store volatile <4 x i32> <i32 0, i32 0, i32 0, i32 undef>, <4 x i32>* %storetmp16, align 16
|
||||
// CHECK: store volatile <4 x i32> zeroinitializer, <4 x i32>* %arraydecay{{[0-9]+}}, align 16
|
||||
// CHECK: store volatile <8 x i32> zeroinitializer, <8 x i32>* %arraydecay{{[0-9]+}}, align 32
|
||||
// CHECK: store volatile <16 x i32> zeroinitializer, <16 x i32>* %arraydecay{{[0-9]+}}, align 64
|
||||
// CHECK: store volatile i64 0, i64* %arraydecay{{[0-9]+}}, align 8
|
||||
// CHECK: store volatile <2 x i64> zeroinitializer, <2 x i64>* %arraydecay{{[0-9]+}}, align 16
|
||||
// CHECK: store volatile <4 x i64> <i64 0, i64 0, i64 0, i64 undef>, <4 x i64>* %storetmp23, align 32
|
||||
// CHECK: store volatile <4 x i64> zeroinitializer, <4 x i64>* %arraydecay{{[0-9]+}}, align 32
|
||||
// CHECK: store volatile <8 x i64> zeroinitializer, <8 x i64>* %arraydecay{{[0-9]+}}, align 64
|
||||
// CHECK: store volatile <16 x i64> zeroinitializer, <16 x i64>* %arraydecay{{[0-9]+}}, align 128
|
||||
// CHECK: store volatile half 0xH0000, half* %arraydecay{{[0-9]+}}, align 2
|
||||
// CHECK: store volatile <2 x half> zeroinitializer, <2 x half>* %arraydecay{{[0-9]+}}, align 4
|
||||
// CHECK: store volatile <4 x half> <half 0xH0000, half 0xH0000, half 0xH0000, half undef>, <4 x half>* %storetmp{{[0-9]+}}, align 8
|
||||
// CHECK: store volatile <4 x half> zeroinitializer, <4 x half>* %arraydecay{{[0-9]+}}, align 8
|
||||
// CHECK: store volatile <8 x half> zeroinitializer, <8 x half>* %arraydecay{{[0-9]+}}, align 16
|
||||
// CHECK: store volatile <16 x half> zeroinitializer, <16 x half>* %arraydecay{{[0-9]+}}, align 32
|
||||
// CHECK: store volatile float 0.000000e+00, float* %arraydecay34, align 4
|
||||
// CHECK: store volatile <2 x float> zeroinitializer, <2 x float>* %arraydecay{{[0-9]+}}, align 8
|
||||
// CHECK: store volatile <4 x float> <float 0.000000e+00, float 0.000000e+00, float 0.000000e+00, float undef>, <4 x float>* %storetmp{{[0-9]+}}, align 16
|
||||
// CHECK: store volatile <4 x float> zeroinitializer, <4 x float>* %arraydecay{{[0-9]+}}, align 16
|
||||
// CHECK: store volatile <8 x float> zeroinitializer, <8 x float>* %arraydecay{{[0-9]+}}, align 32
|
||||
// CHECK: store volatile <16 x float> zeroinitializer, <16 x float>* %arraydecay{{[0-9]+}}, align 64
|
||||
// CHECK: store volatile double 0.000000e+00, double* %arraydecay{{[0-9]+}}, align 8
|
||||
// CHECK: store volatile <2 x double> zeroinitializer, <2 x double>* %arraydecay{{[0-9]+}}, align 16
|
||||
// CHECK: store volatile <4 x double> <double 0.000000e+00, double 0.000000e+00, double 0.000000e+00, double undef>, <4 x double>* %storetmp{{[0-9]+}}, align 32
|
||||
// CHECK: store volatile <4 x double> zeroinitializer, <4 x double>* %arraydecay{{[0-9]+}}, align 32
|
||||
// CHECK: store volatile <8 x double> zeroinitializer, <8 x double>* %arraydecay{{[0-9]+}}, align 64
|
||||
// CHECK: store volatile <16 x double> zeroinitializer, <16 x double>* %arraydecay{{[0-9]+}}, align 128
|
||||
// CHECK: store volatile i8 0, i8 addrspace(5)* %arraydecay, align 1
|
||||
// CHECK: store volatile <2 x i8> zeroinitializer, <2 x i8> addrspace(5)* %arraydecay{{[0-9]+}}, align 2
|
||||
// CHECK: store volatile <4 x i8> <i8 0, i8 0, i8 0, i8 undef>, <4 x i8> addrspace(5)* %storetmp, align 4
|
||||
// CHECK: store volatile <4 x i8> zeroinitializer, <4 x i8> addrspace(5)* %arraydecay{{[0-9]+}}, align 4
|
||||
// CHECK: store volatile <8 x i8> zeroinitializer, <8 x i8> addrspace(5)* %arraydecay{{[0-9]+}}, align 8
|
||||
// CHECK: store volatile <16 x i8> zeroinitializer, <16 x i8> addrspace(5)* %arraydecay{{[0-9]+}}, align 16
|
||||
// CHECK: store volatile i16 0, i16 addrspace(5)* %arraydecay{{[0-9]+}}, align 2
|
||||
// CHECK: store volatile <2 x i16> zeroinitializer, <2 x i16> addrspace(5)* %arraydecay{{[0-9]+}}, align 4
|
||||
// CHECK: store volatile <4 x i16> <i16 0, i16 0, i16 0, i16 undef>, <4 x i16> addrspace(5)* %storetmp{{[0-9]+}}, align 8
|
||||
// CHECK: store volatile <4 x i16> zeroinitializer, <4 x i16> addrspace(5)* %arraydecay{{[0-9]+}}, align 8
|
||||
// CHECK: store volatile <8 x i16> zeroinitializer, <8 x i16> addrspace(5)* %arraydecay{{[0-9]+}}, align 16
|
||||
// CHECK: store volatile <16 x i16> zeroinitializer, <16 x i16> addrspace(5)* %arraydecay{{[0-9]+}}, align 32
|
||||
// CHECK: store volatile i32 0, i32 addrspace(5)* %arraydecay{{[0-9]+}}, align 4
|
||||
// CHECK: store volatile <2 x i32> zeroinitializer, <2 x i32> addrspace(5)* %arraydecay{{[0-9]+}}, align 8
|
||||
// CHECK: store volatile <4 x i32> <i32 0, i32 0, i32 0, i32 undef>, <4 x i32> addrspace(5)* %storetmp16, align 16
|
||||
// CHECK: store volatile <4 x i32> zeroinitializer, <4 x i32> addrspace(5)* %arraydecay{{[0-9]+}}, align 16
|
||||
// CHECK: store volatile <8 x i32> zeroinitializer, <8 x i32> addrspace(5)* %arraydecay{{[0-9]+}}, align 32
|
||||
// CHECK: store volatile <16 x i32> zeroinitializer, <16 x i32> addrspace(5)* %arraydecay{{[0-9]+}}, align 64
|
||||
// CHECK: store volatile i64 0, i64 addrspace(5)* %arraydecay{{[0-9]+}}, align 8
|
||||
// CHECK: store volatile <2 x i64> zeroinitializer, <2 x i64> addrspace(5)* %arraydecay{{[0-9]+}}, align 16
|
||||
// CHECK: store volatile <4 x i64> <i64 0, i64 0, i64 0, i64 undef>, <4 x i64> addrspace(5)* %storetmp23, align 32
|
||||
// CHECK: store volatile <4 x i64> zeroinitializer, <4 x i64> addrspace(5)* %arraydecay{{[0-9]+}}, align 32
|
||||
// CHECK: store volatile <8 x i64> zeroinitializer, <8 x i64> addrspace(5)* %arraydecay{{[0-9]+}}, align 64
|
||||
// CHECK: store volatile <16 x i64> zeroinitializer, <16 x i64> addrspace(5)* %arraydecay{{[0-9]+}}, align 128
|
||||
// CHECK: store volatile half 0xH0000, half addrspace(5)* %arraydecay{{[0-9]+}}, align 2
|
||||
// CHECK: store volatile <2 x half> zeroinitializer, <2 x half> addrspace(5)* %arraydecay{{[0-9]+}}, align 4
|
||||
// CHECK: store volatile <4 x half> <half 0xH0000, half 0xH0000, half 0xH0000, half undef>, <4 x half> addrspace(5)* %storetmp{{[0-9]+}}, align 8
|
||||
// CHECK: store volatile <4 x half> zeroinitializer, <4 x half> addrspace(5)* %arraydecay{{[0-9]+}}, align 8
|
||||
// CHECK: store volatile <8 x half> zeroinitializer, <8 x half> addrspace(5)* %arraydecay{{[0-9]+}}, align 16
|
||||
// CHECK: store volatile <16 x half> zeroinitializer, <16 x half> addrspace(5)* %arraydecay{{[0-9]+}}, align 32
|
||||
// CHECK: store volatile float 0.000000e+00, float addrspace(5)* %arraydecay34, align 4
|
||||
// CHECK: store volatile <2 x float> zeroinitializer, <2 x float> addrspace(5)* %arraydecay{{[0-9]+}}, align 8
|
||||
// CHECK: store volatile <4 x float> <float 0.000000e+00, float 0.000000e+00, float 0.000000e+00, float undef>, <4 x float> addrspace(5)* %storetmp{{[0-9]+}}, align 16
|
||||
// CHECK: store volatile <4 x float> zeroinitializer, <4 x float> addrspace(5)* %arraydecay{{[0-9]+}}, align 16
|
||||
// CHECK: store volatile <8 x float> zeroinitializer, <8 x float> addrspace(5)* %arraydecay{{[0-9]+}}, align 32
|
||||
// CHECK: store volatile <16 x float> zeroinitializer, <16 x float> addrspace(5)* %arraydecay{{[0-9]+}}, align 64
|
||||
// CHECK: store volatile double 0.000000e+00, double addrspace(5)* %arraydecay{{[0-9]+}}, align 8
|
||||
// CHECK: store volatile <2 x double> zeroinitializer, <2 x double> addrspace(5)* %arraydecay{{[0-9]+}}, align 16
|
||||
// CHECK: store volatile <4 x double> <double 0.000000e+00, double 0.000000e+00, double 0.000000e+00, double undef>, <4 x double> addrspace(5)* %storetmp{{[0-9]+}}, align 32
|
||||
// CHECK: store volatile <4 x double> zeroinitializer, <4 x double> addrspace(5)* %arraydecay{{[0-9]+}}, align 32
|
||||
// CHECK: store volatile <8 x double> zeroinitializer, <8 x double> addrspace(5)* %arraydecay{{[0-9]+}}, align 64
|
||||
// CHECK: store volatile <16 x double> zeroinitializer, <16 x double> addrspace(5)* %arraydecay{{[0-9]+}}, align 128
|
||||
kernel void private_memory_alignment_alloca()
|
||||
{
|
||||
volatile private char private_i8[4];
|
||||
|
|
|
|||
|
|
@ -51,31 +51,31 @@ int *constant FileVar14 = 0;
|
|||
|
||||
kernel void kernel1(
|
||||
// CHECK-DAG: ![[KERNELARG0:[0-9]+]] = !DILocalVariable(name: "KernelArg0", arg: {{[0-9]+}}, scope: !{{[0-9]+}}, file: !{{[0-9]+}}, line: {{[0-9]+}}, type: !{{[0-9]+}})
|
||||
// CHECK-DAG: call void @llvm.dbg.declare(metadata i32 addrspace(1)** {{.*}}, metadata ![[KERNELARG0]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
|
||||
// CHECK-DAG: call void @llvm.dbg.declare(metadata i32 addrspace(1)* addrspace(5)* {{.*}}, metadata ![[KERNELARG0]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
|
||||
global int *KernelArg0,
|
||||
// CHECK-DAG: ![[KERNELARG1:[0-9]+]] = !DILocalVariable(name: "KernelArg1", arg: {{[0-9]+}}, scope: !{{[0-9]+}}, file: !{{[0-9]+}}, line: {{[0-9]+}}, type: !{{[0-9]+}})
|
||||
// CHECK-DAG: call void @llvm.dbg.declare(metadata i32 addrspace(2)** {{.*}}, metadata ![[KERNELARG1]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
|
||||
// CHECK-DAG: call void @llvm.dbg.declare(metadata i32 addrspace(2)* addrspace(5)* {{.*}}, metadata ![[KERNELARG1]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
|
||||
constant int *KernelArg1,
|
||||
// CHECK-DAG: ![[KERNELARG2:[0-9]+]] = !DILocalVariable(name: "KernelArg2", arg: {{[0-9]+}}, scope: !{{[0-9]+}}, file: !{{[0-9]+}}, line: {{[0-9]+}}, type: !{{[0-9]+}})
|
||||
// CHECK-DAG: call void @llvm.dbg.declare(metadata i32 addrspace(3)** {{.*}}, metadata ![[KERNELARG2]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
|
||||
// CHECK-DAG: call void @llvm.dbg.declare(metadata i32 addrspace(3)* addrspace(5)* {{.*}}, metadata ![[KERNELARG2]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
|
||||
local int *KernelArg2) {
|
||||
private int *Tmp0;
|
||||
int *Tmp1;
|
||||
|
||||
// CHECK-DAG: ![[FUNCVAR0:[0-9]+]] = !DILocalVariable(name: "FuncVar0", scope: !{{[0-9]+}}, file: !{{[0-9]+}}, line: {{[0-9]+}}, type: !{{[0-9]+}})
|
||||
// CHECK-DAG: call void @llvm.dbg.declare(metadata i32 addrspace(1)** {{.*}}, metadata ![[FUNCVAR0]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
|
||||
// CHECK-DAG: call void @llvm.dbg.declare(metadata i32 addrspace(1)* addrspace(5)* {{.*}}, metadata ![[FUNCVAR0]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
|
||||
global int *FuncVar0 = KernelArg0;
|
||||
// CHECK-DAG: ![[FUNCVAR1:[0-9]+]] = !DILocalVariable(name: "FuncVar1", scope: !{{[0-9]+}}, file: !{{[0-9]+}}, line: {{[0-9]+}}, type: !{{[0-9]+}})
|
||||
// CHECK-DAG: call void @llvm.dbg.declare(metadata i32 addrspace(2)** {{.*}}, metadata ![[FUNCVAR1]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
|
||||
// CHECK-DAG: call void @llvm.dbg.declare(metadata i32 addrspace(2)* addrspace(5)* {{.*}}, metadata ![[FUNCVAR1]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
|
||||
constant int *FuncVar1 = KernelArg1;
|
||||
// CHECK-DAG: ![[FUNCVAR2:[0-9]+]] = !DILocalVariable(name: "FuncVar2", scope: !{{[0-9]+}}, file: !{{[0-9]+}}, line: {{[0-9]+}}, type: !{{[0-9]+}})
|
||||
// CHECK-DAG: call void @llvm.dbg.declare(metadata i32 addrspace(3)** {{.*}}, metadata ![[FUNCVAR2]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
|
||||
// CHECK-DAG: call void @llvm.dbg.declare(metadata i32 addrspace(3)* addrspace(5)* {{.*}}, metadata ![[FUNCVAR2]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
|
||||
local int *FuncVar2 = KernelArg2;
|
||||
// CHECK-DAG: ![[FUNCVAR3:[0-9]+]] = !DILocalVariable(name: "FuncVar3", scope: !{{[0-9]+}}, file: !{{[0-9]+}}, line: {{[0-9]+}}, type: !{{[0-9]+}})
|
||||
// CHECK-DAG: call void @llvm.dbg.declare(metadata i32** {{.*}}, metadata ![[FUNCVAR3]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
|
||||
// CHECK-DAG: call void @llvm.dbg.declare(metadata i32 addrspace(5)* addrspace(5)* {{.*}}, metadata ![[FUNCVAR3]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
|
||||
private int *FuncVar3 = Tmp0;
|
||||
// CHECK-DAG: ![[FUNCVAR4:[0-9]+]] = !DILocalVariable(name: "FuncVar4", scope: !{{[0-9]+}}, file: !{{[0-9]+}}, line: {{[0-9]+}}, type: !{{[0-9]+}})
|
||||
// CHECK-DAG: call void @llvm.dbg.declare(metadata i32 addrspace(4)** {{.*}}, metadata ![[FUNCVAR4]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
|
||||
// CHECK-DAG: call void @llvm.dbg.declare(metadata i32* addrspace(5)* {{.*}}, metadata ![[FUNCVAR4]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
|
||||
int *FuncVar4 = Tmp1;
|
||||
|
||||
// CHECK-DAG: ![[FUNCVAR5:[0-9]+]] = distinct !DIGlobalVariable(name: "FuncVar5", scope: !{{[0-9]+}}, file: !{{[0-9]+}}, line: {{[0-9]+}}, type: !{{[0-9]+}}, isLocal: true, isDefinition: true)
|
||||
|
|
@ -111,18 +111,18 @@ kernel void kernel1(
|
|||
int *local FuncVar14; FuncVar14 = Tmp1;
|
||||
|
||||
// CHECK-DAG: ![[FUNCVAR15:[0-9]+]] = !DILocalVariable(name: "FuncVar15", scope: !{{[0-9]+}}, file: !{{[0-9]+}}, line: {{[0-9]+}}, type: !{{[0-9]+}})
|
||||
// CHECK-DAG: call void @llvm.dbg.declare(metadata i32 addrspace(1)** {{.*}}, metadata ![[FUNCVAR15]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
|
||||
// CHECK-DAG: call void @llvm.dbg.declare(metadata i32 addrspace(1)* addrspace(5)* {{.*}}, metadata ![[FUNCVAR15]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
|
||||
global int *private FuncVar15 = KernelArg0;
|
||||
// CHECK-DAG: ![[FUNCVAR16:[0-9]+]] = !DILocalVariable(name: "FuncVar16", scope: !{{[0-9]+}}, file: !{{[0-9]+}}, line: {{[0-9]+}}, type: !{{[0-9]+}})
|
||||
// CHECK-DAG: call void @llvm.dbg.declare(metadata i32 addrspace(2)** {{.*}}, metadata ![[FUNCVAR16]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
|
||||
// CHECK-DAG: call void @llvm.dbg.declare(metadata i32 addrspace(2)* addrspace(5)* {{.*}}, metadata ![[FUNCVAR16]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
|
||||
constant int *private FuncVar16 = KernelArg1;
|
||||
// CHECK-DAG: ![[FUNCVAR17:[0-9]+]] = !DILocalVariable(name: "FuncVar17", scope: !{{[0-9]+}}, file: !{{[0-9]+}}, line: {{[0-9]+}}, type: !{{[0-9]+}})
|
||||
// CHECK-DAG: call void @llvm.dbg.declare(metadata i32 addrspace(3)** {{.*}}, metadata ![[FUNCVAR17]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
|
||||
// CHECK-DAG: call void @llvm.dbg.declare(metadata i32 addrspace(3)* addrspace(5)* {{.*}}, metadata ![[FUNCVAR17]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
|
||||
local int *private FuncVar17 = KernelArg2;
|
||||
// CHECK-DAG: ![[FUNCVAR18:[0-9]+]] = !DILocalVariable(name: "FuncVar18", scope: !{{[0-9]+}}, file: !{{[0-9]+}}, line: {{[0-9]+}}, type: !{{[0-9]+}})
|
||||
// CHECK-DAG: call void @llvm.dbg.declare(metadata i32** {{.*}}, metadata ![[FUNCVAR18]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
|
||||
// CHECK-DAG: call void @llvm.dbg.declare(metadata i32 addrspace(5)* addrspace(5)* {{.*}}, metadata ![[FUNCVAR18]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
|
||||
private int *private FuncVar18 = Tmp0;
|
||||
// CHECK-DAG: ![[FUNCVAR19:[0-9]+]] = !DILocalVariable(name: "FuncVar19", scope: !{{[0-9]+}}, file: !{{[0-9]+}}, line: {{[0-9]+}}, type: !{{[0-9]+}})
|
||||
// CHECK-DAG: call void @llvm.dbg.declare(metadata i32 addrspace(4)** {{.*}}, metadata ![[FUNCVAR19]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
|
||||
// CHECK-DAG: call void @llvm.dbg.declare(metadata i32* addrspace(5)* {{.*}}, metadata ![[FUNCVAR19]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
|
||||
int *private FuncVar19 = Tmp1;
|
||||
}
|
||||
|
|
|
|||
|
|
@ -26,20 +26,20 @@ kernel void test(global char *a, char b, global long *c, long d) {
|
|||
}, 100);
|
||||
}
|
||||
|
||||
// CHECK-LABEL: define internal amdgpu_kernel void @__test_block_invoke_kernel(<{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i8 }>)
|
||||
// CHECK-LABEL: define internal amdgpu_kernel void @__test_block_invoke_kernel(<{ i32, i32, i8*, i8 addrspace(1)*, i8 }>)
|
||||
// CHECK-SAME: #[[ATTR:[0-9]+]] !kernel_arg_addr_space !{{.*}} !kernel_arg_access_qual !{{.*}} !kernel_arg_type !{{.*}} !kernel_arg_base_type !{{.*}} !kernel_arg_type_qual !{{.*}}
|
||||
// CHECK: entry:
|
||||
// CHECK: %1 = alloca <{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i8 }>, align 8
|
||||
// CHECK: store <{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i8 }> %0, <{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i8 }>* %1, align 8
|
||||
// CHECK: %2 = addrspacecast <{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i8 }>* %1 to i8 addrspace(4)*
|
||||
// CHECK: call void @__test_block_invoke(i8 addrspace(4)* %2)
|
||||
// CHECK: %1 = alloca <{ i32, i32, i8*, i8 addrspace(1)*, i8 }>, align 8, addrspace(5)
|
||||
// CHECK: store <{ i32, i32, i8*, i8 addrspace(1)*, i8 }> %0, <{ i32, i32, i8*, i8 addrspace(1)*, i8 }> addrspace(5)* %1, align 8
|
||||
// CHECK: %2 = addrspacecast <{ i32, i32, i8*, i8 addrspace(1)*, i8 }> addrspace(5)* %1 to i8*
|
||||
// CHECK: call void @__test_block_invoke(i8* %2)
|
||||
// CHECK: ret void
|
||||
// CHECK:}
|
||||
|
||||
// CHECK-LABEL: define internal amdgpu_kernel void @__test_block_invoke_2_kernel(<{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }>)
|
||||
// CHECK-LABEL: define internal amdgpu_kernel void @__test_block_invoke_2_kernel(<{ i32, i32, i8*, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }>)
|
||||
// CHECK-SAME: #[[ATTR]] !kernel_arg_addr_space !{{.*}} !kernel_arg_access_qual !{{.*}} !kernel_arg_type !{{.*}} !kernel_arg_base_type !{{.*}} !kernel_arg_type_qual !{{.*}}
|
||||
|
||||
// CHECK-LABEL: define internal amdgpu_kernel void @__test_block_invoke_3_kernel(<{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }>, i8 addrspace(3)*)
|
||||
// CHECK-LABEL: define internal amdgpu_kernel void @__test_block_invoke_3_kernel(<{ i32, i32, i8*, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }>, i8 addrspace(3)*)
|
||||
// CHECK-SAME: #[[ATTR]] !kernel_arg_addr_space !{{.*}} !kernel_arg_access_qual !{{.*}} !kernel_arg_type !{{.*}} !kernel_arg_base_type !{{.*}} !kernel_arg_type_qual !{{.*}}
|
||||
|
||||
// CHECK: attributes #[[ATTR]] = { nounwind "enqueued-block" }
|
||||
|
|
|
|||
|
|
@ -1,9 +1,5 @@
|
|||
// RUN: %clang_cc1 %s -O0 -triple amdgcn -emit-llvm -o - | FileCheck %s
|
||||
// RUN: %clang_cc1 %s -O0 -triple amdgcn---opencl -emit-llvm -o - | FileCheck %s
|
||||
// RUN: %clang_cc1 %s -O0 -triple amdgcn---amdgiz -emit-llvm -o - | FileCheck -check-prefix=GIZ %s
|
||||
// RUN: %clang_cc1 %s -O0 -triple amdgcn---amdgizcl -emit-llvm -o - | FileCheck -check-prefix=GIZ %s
|
||||
|
||||
// CHECK: target datalayout = "e-p:32:32-p1:64:64-p2:64:64-p3:32:32-p4:64:64-p5:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64"
|
||||
// GIZ: target datalayout = "e-p:64:64-p1:64:64-p2:64:64-p3:32:32-p4:32:32-p5:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64-A5"
|
||||
// CHECK: target datalayout = "e-p:64:64-p1:64:64-p2:64:64-p3:32:32-p4:32:32-p5:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64-A5"
|
||||
void foo(void) {}
|
||||
|
||||
|
|
|
|||
|
|
@ -21,10 +21,10 @@ typedef struct {
|
|||
|
||||
// Test 0 as initializer.
|
||||
|
||||
// CHECK: @private_p = local_unnamed_addr addrspace(1) global i8* null, align 4
|
||||
// CHECK: @private_p = local_unnamed_addr addrspace(1) global i8 addrspace(5)* null, align 4
|
||||
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
|
||||
// CHECK: @local_p = local_unnamed_addr addrspace(1) global i8 addrspace(3)* addrspacecast (i8* 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 8
|
||||
|
|
@ -33,15 +33,15 @@ global char *global_p = 0;
|
|||
// 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 8
|
||||
// CHECK: @generic_p = local_unnamed_addr addrspace(1) global i8* null, align 8
|
||||
generic char *generic_p = 0;
|
||||
|
||||
// Test NULL as initializer.
|
||||
|
||||
// CHECK: @private_p_NULL = local_unnamed_addr addrspace(1) global i8* null, align 4
|
||||
// CHECK: @private_p_NULL = local_unnamed_addr addrspace(1) global i8 addrspace(5)* null, align 4
|
||||
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
|
||||
// CHECK: @local_p_NULL = local_unnamed_addr addrspace(1) global i8 addrspace(3)* addrspacecast (i8* 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 8
|
||||
|
|
@ -50,19 +50,19 @@ global char *global_p_NULL = NULL;
|
|||
// 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 8
|
||||
// CHECK: @generic_p_NULL = local_unnamed_addr addrspace(1) global i8* 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 8
|
||||
// CHECK: @fold_generic = local_unnamed_addr addrspace(1) global i32* 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
|
||||
// CHECK: @fold_priv = local_unnamed_addr addrspace(1) global i16 addrspace(5)* null, align 4
|
||||
private short *fold_priv = (private short*)(generic int*)(global void*)0;
|
||||
|
||||
// CHECK: @fold_priv_arith = local_unnamed_addr addrspace(1) global i8* inttoptr (i32 10 to i8*), align 4
|
||||
// CHECK: @fold_priv_arith = local_unnamed_addr addrspace(1) global i8 addrspace(5)* inttoptr (i32 10 to i8 addrspace(5)*), align 4
|
||||
private char *fold_priv_arith = (private char*)0 + 10;
|
||||
|
||||
// CHECK: @fold_int = local_unnamed_addr addrspace(1) global i32 14, align 4
|
||||
|
|
@ -99,12 +99,12 @@ int fold_int5_local = (int) &((local StructTy1*)0)->p2;
|
|||
|
||||
// Test static variable initialization.
|
||||
|
||||
// NOOPT: @test_static_var_private.sp1 = internal addrspace(1) global i8* null, align 4
|
||||
// NOOPT: @test_static_var_private.sp2 = internal addrspace(1) global i8* null, align 4
|
||||
// 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 8
|
||||
// NOOPT: @test_static_var_private.sp1 = internal addrspace(1) global i8 addrspace(5)* null, align 4
|
||||
// NOOPT: @test_static_var_private.sp2 = internal addrspace(1) global i8 addrspace(5)* null, align 4
|
||||
// NOOPT: @test_static_var_private.sp3 = internal addrspace(1) global i8 addrspace(5)* null, align 4
|
||||
// NOOPT: @test_static_var_private.sp4 = internal addrspace(1) global i8 addrspace(5)* null, align 4
|
||||
// NOOPT: @test_static_var_private.sp5 = internal addrspace(1) global i8 addrspace(5)* null, align 4
|
||||
// NOOPT: @test_static_var_private.SS1 = internal addrspace(1) global %struct.StructTy1 { i8 addrspace(5)* null, i8 addrspace(3)* addrspacecast (i8* null to i8 addrspace(3)*), i8 addrspace(2)* null, i8 addrspace(1)* null, i8* null }, align 8
|
||||
// NOOPT: @test_static_var_private.SS2 = internal addrspace(1) global %struct.StructTy2 zeroinitializer, align 8
|
||||
|
||||
void test_static_var_private(void) {
|
||||
|
|
@ -118,12 +118,12 @@ void test_static_var_private(void) {
|
|||
static StructTy2 SS2;
|
||||
}
|
||||
|
||||
// NOOPT: @test_static_var_local.sp1 = internal addrspace(1) global i8 addrspace(3)* addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*), align 4
|
||||
// NOOPT: @test_static_var_local.sp2 = internal addrspace(1) global i8 addrspace(3)* addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*), align 4
|
||||
// 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.sp1 = internal addrspace(1) global i8 addrspace(3)* addrspacecast (i8* null to i8 addrspace(3)*), align 4
|
||||
// NOOPT: @test_static_var_local.sp2 = internal addrspace(1) global i8 addrspace(3)* addrspacecast (i8* null to i8 addrspace(3)*), align 4
|
||||
// NOOPT: @test_static_var_local.sp3 = internal addrspace(1) global i8 addrspace(3)* addrspacecast (i8* 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 8
|
||||
// NOOPT: @test_static_var_local.SS1 = internal addrspace(1) global %struct.StructTy1 { i8 addrspace(5)* null, i8 addrspace(3)* addrspacecast (i8* null to i8 addrspace(3)*), i8 addrspace(2)* null, i8 addrspace(1)* null, i8* 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;
|
||||
|
|
@ -138,14 +138,14 @@ void test_static_var_local(void) {
|
|||
|
||||
// Test function-scope variable initialization.
|
||||
// NOOPT-LABEL: @test_func_scope_var_private(
|
||||
// NOOPT: store i8* null, i8** %sp1, align 4
|
||||
// NOOPT: store i8* null, i8** %sp2, align 4
|
||||
// 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* align 8 %[[SS1]], i8 addrspace(2)* align 8 bitcast (%struct.StructTy1 addrspace(2)* @test_func_scope_var_private.SS1 to i8 addrspace(2)*), i64 32, i1 false)
|
||||
// NOOPT: %[[SS2:.*]] = bitcast %struct.StructTy2* %SS2 to i8*
|
||||
// NOOPT: call void @llvm.memset.p0i8.i64(i8* align 8 %[[SS2]], i8 0, i64 24, i1 false)
|
||||
// NOOPT: store i8 addrspace(5)* null, i8 addrspace(5)* addrspace(5)* %sp1, align 4
|
||||
// NOOPT: store i8 addrspace(5)* null, i8 addrspace(5)* addrspace(5)* %sp2, align 4
|
||||
// NOOPT: store i8 addrspace(5)* null, i8 addrspace(5)* addrspace(5)* %sp3, align 4
|
||||
// NOOPT: store i8 addrspace(5)* null, i8 addrspace(5)* addrspace(5)* %sp4, align 4
|
||||
// NOOPT: %[[SS1:.*]] = bitcast %struct.StructTy1 addrspace(5)* %SS1 to i8 addrspace(5)*
|
||||
// NOOPT: call void @llvm.memcpy.p5i8.p2i8.i64(i8 addrspace(5)* align 8 %[[SS1]], i8 addrspace(2)* align 8 bitcast (%struct.StructTy1 addrspace(2)* @test_func_scope_var_private.SS1 to i8 addrspace(2)*), i64 32, i1 false)
|
||||
// NOOPT: %[[SS2:.*]] = bitcast %struct.StructTy2 addrspace(5)* %SS2 to i8 addrspace(5)*
|
||||
// NOOPT: call void @llvm.memset.p5i8.i64(i8 addrspace(5)* align 8 %[[SS2]], i8 0, i64 24, i1 false)
|
||||
void test_func_scope_var_private(void) {
|
||||
private char *sp1 = 0;
|
||||
private char *sp2 = NULL;
|
||||
|
|
@ -158,14 +158,14 @@ void test_func_scope_var_private(void) {
|
|||
|
||||
// Test function-scope variable initialization.
|
||||
// NOOPT-LABEL: @test_func_scope_var_local(
|
||||
// NOOPT: store i8 addrspace(3)* addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*), i8 addrspace(3)** %sp1, align 4
|
||||
// NOOPT: store i8 addrspace(3)* addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*), i8 addrspace(3)** %sp2, align 4
|
||||
// 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* align 8 %[[SS1]], i8 addrspace(2)* align 8 bitcast (%struct.StructTy1 addrspace(2)* @test_func_scope_var_local.SS1 to i8 addrspace(2)*), i64 32, i1 false)
|
||||
// NOOPT: %[[SS2:.*]] = bitcast %struct.StructTy2* %SS2 to i8*
|
||||
// NOOPT: call void @llvm.memset.p0i8.i64(i8* align 8 %[[SS2]], i8 0, i64 24, i1 false)
|
||||
// NOOPT: store i8 addrspace(3)* addrspacecast (i8* null to i8 addrspace(3)*), i8 addrspace(3)* addrspace(5)* %sp1, align 4
|
||||
// NOOPT: store i8 addrspace(3)* addrspacecast (i8* null to i8 addrspace(3)*), i8 addrspace(3)* addrspace(5)* %sp2, align 4
|
||||
// NOOPT: store i8 addrspace(3)* null, i8 addrspace(3)* addrspace(5)* %sp3, align 4
|
||||
// NOOPT: store i8 addrspace(3)* null, i8 addrspace(3)* addrspace(5)* %sp4, align 4
|
||||
// NOOPT: %[[SS1:.*]] = bitcast %struct.StructTy1 addrspace(5)* %SS1 to i8 addrspace(5)*
|
||||
// NOOPT: call void @llvm.memcpy.p5i8.p2i8.i64(i8 addrspace(5)* align 8 %[[SS1]], i8 addrspace(2)* align 8 bitcast (%struct.StructTy1 addrspace(2)* @test_func_scope_var_local.SS1 to i8 addrspace(2)*), i64 32, i1 false)
|
||||
// NOOPT: %[[SS2:.*]] = bitcast %struct.StructTy2 addrspace(5)* %SS2 to i8 addrspace(5)*
|
||||
// NOOPT: call void @llvm.memset.p5i8.i64(i8 addrspace(5)* align 8 %[[SS2]], i8 0, i64 24, i1 false)
|
||||
void test_func_scope_var_local(void) {
|
||||
local char *sp1 = 0;
|
||||
local char *sp2 = NULL;
|
||||
|
|
@ -183,10 +183,10 @@ void test_func_scope_var_local(void) {
|
|||
// cannot have common linkage since common linkage requires zero initialization
|
||||
// and does not have explicit section.
|
||||
|
||||
// CHECK: @p1 = common local_unnamed_addr addrspace(1) global i8* null, align 4
|
||||
// CHECK: @p1 = common local_unnamed_addr addrspace(1) global i8 addrspace(5)* null, align 4
|
||||
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
|
||||
// CHECK: @p2 = weak local_unnamed_addr addrspace(1) global i8 addrspace(3)* addrspacecast (i8* null to i8 addrspace(3)*), align 4
|
||||
local char *p2;
|
||||
|
||||
// CHECK: @p3 = common local_unnamed_addr addrspace(1) global i8 addrspace(2)* null, align 8
|
||||
|
|
@ -195,19 +195,19 @@ constant char *p3;
|
|||
// 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 8
|
||||
// CHECK: @p5 = common local_unnamed_addr addrspace(1) global i8* 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 8
|
||||
// CHECK: @S1 = weak local_unnamed_addr addrspace(1) global %struct.StructTy1 { i8 addrspace(5)* null, i8 addrspace(3)* addrspacecast (i8* null to i8 addrspace(3)*), i8 addrspace(2)* null, i8 addrspace(1)* null, i8* null }, align 8
|
||||
StructTy1 S1;
|
||||
|
||||
// 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 8
|
||||
// CHECK: @A1 = weak local_unnamed_addr addrspace(1) global [2 x %struct.StructTy1] [%struct.StructTy1 { i8 addrspace(5)* null, i8 addrspace(3)* addrspacecast (i8* null to i8 addrspace(3)*), i8 addrspace(2)* null, i8 addrspace(1)* null, i8* null }, %struct.StructTy1 { i8 addrspace(5)* null, i8 addrspace(3)* addrspacecast (i8* null to i8 addrspace(3)*), i8 addrspace(2)* null, i8 addrspace(1)* null, i8* null }], align 8
|
||||
StructTy1 A1[2];
|
||||
|
||||
// CHECK: @A2 = common local_unnamed_addr addrspace(1) global [2 x %struct.StructTy2] zeroinitializer, align 8
|
||||
|
|
@ -216,14 +216,14 @@ StructTy2 A2[2];
|
|||
// Test comparison with 0.
|
||||
|
||||
// CHECK-LABEL: cmp_private
|
||||
// CHECK: icmp eq i8* %p, null
|
||||
// CHECK: icmp eq i8 addrspace(5)* %p, null
|
||||
void cmp_private(private char* p) {
|
||||
if (p != 0)
|
||||
*p = 0;
|
||||
}
|
||||
|
||||
// CHECK-LABEL: cmp_local
|
||||
// CHECK: icmp eq i8 addrspace(3)* %p, addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*)
|
||||
// CHECK: icmp eq i8 addrspace(3)* %p, addrspacecast (i8* null to i8 addrspace(3)*)
|
||||
void cmp_local(local char* p) {
|
||||
if (p != 0)
|
||||
*p = 0;
|
||||
|
|
@ -246,7 +246,7 @@ char cmp_constant(constant char* p) {
|
|||
}
|
||||
|
||||
// CHECK-LABEL: cmp_generic
|
||||
// CHECK: icmp eq i8 addrspace(4)* %p, null
|
||||
// CHECK: icmp eq i8* %p, null
|
||||
void cmp_generic(generic char* p) {
|
||||
if (p != 0)
|
||||
*p = 0;
|
||||
|
|
@ -255,14 +255,14 @@ void cmp_generic(generic char* p) {
|
|||
// Test comparison with NULL.
|
||||
|
||||
// CHECK-LABEL: cmp_NULL_private
|
||||
// CHECK: icmp eq i8* %p, null
|
||||
// CHECK: icmp eq i8 addrspace(5)* %p, null
|
||||
void cmp_NULL_private(private char* p) {
|
||||
if (p != NULL)
|
||||
*p = 0;
|
||||
}
|
||||
|
||||
// CHECK-LABEL: cmp_NULL_local
|
||||
// CHECK: icmp eq i8 addrspace(3)* %p, addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*)
|
||||
// CHECK: icmp eq i8 addrspace(3)* %p, addrspacecast (i8* null to i8 addrspace(3)*)
|
||||
void cmp_NULL_local(local char* p) {
|
||||
if (p != NULL)
|
||||
*p = 0;
|
||||
|
|
@ -285,7 +285,7 @@ char cmp_NULL_constant(constant char* p) {
|
|||
}
|
||||
|
||||
// CHECK-LABEL: cmp_NULL_generic
|
||||
// CHECK: icmp eq i8 addrspace(4)* %p, null
|
||||
// CHECK: icmp eq i8* %p, null
|
||||
void cmp_NULL_generic(generic char* p) {
|
||||
if (p != NULL)
|
||||
*p = 0;
|
||||
|
|
@ -293,11 +293,11 @@ void cmp_NULL_generic(generic char* p) {
|
|||
|
||||
// Test storage 0 as null pointer.
|
||||
// CHECK-LABEL: test_storage_null_pointer
|
||||
// CHECK: store i8* null, i8* addrspace(4)* %arg_private
|
||||
// CHECK: store i8 addrspace(3)* addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*), i8 addrspace(3)* addrspace(4)* %arg_local
|
||||
// CHECK: store i8 addrspace(1)* null, i8 addrspace(1)* addrspace(4)* %arg_global
|
||||
// CHECK: store i8 addrspace(2)* null, i8 addrspace(2)* addrspace(4)* %arg_constant
|
||||
// CHECK: store i8 addrspace(4)* null, i8 addrspace(4)* addrspace(4)* %arg_generic
|
||||
// CHECK: store i8 addrspace(5)* null, i8 addrspace(5)** %arg_private
|
||||
// CHECK: store i8 addrspace(3)* addrspacecast (i8* null to i8 addrspace(3)*), i8 addrspace(3)** %arg_local
|
||||
// CHECK: store i8 addrspace(1)* null, i8 addrspace(1)** %arg_global
|
||||
// CHECK: store i8 addrspace(2)* null, i8 addrspace(2)** %arg_constant
|
||||
// CHECK: store i8* null, i8** %arg_generic
|
||||
void test_storage_null_pointer(private char** arg_private,
|
||||
local char** arg_local,
|
||||
global char** arg_global,
|
||||
|
|
@ -312,11 +312,11 @@ void test_storage_null_pointer(private char** arg_private,
|
|||
|
||||
// Test storage NULL as null pointer.
|
||||
// CHECK-LABEL: test_storage_null_pointer_NULL
|
||||
// CHECK: store i8* null, i8* addrspace(4)* %arg_private
|
||||
// CHECK: store i8 addrspace(3)* addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*), i8 addrspace(3)* addrspace(4)* %arg_local
|
||||
// CHECK: store i8 addrspace(1)* null, i8 addrspace(1)* addrspace(4)* %arg_global
|
||||
// CHECK: store i8 addrspace(2)* null, i8 addrspace(2)* addrspace(4)* %arg_constant
|
||||
// CHECK: store i8 addrspace(4)* null, i8 addrspace(4)* addrspace(4)* %arg_generic
|
||||
// CHECK: store i8 addrspace(5)* null, i8 addrspace(5)** %arg_private
|
||||
// CHECK: store i8 addrspace(3)* addrspacecast (i8* null to i8 addrspace(3)*), i8 addrspace(3)** %arg_local
|
||||
// CHECK: store i8 addrspace(1)* null, i8 addrspace(1)** %arg_global
|
||||
// CHECK: store i8 addrspace(2)* null, i8 addrspace(2)** %arg_constant
|
||||
// CHECK: store i8* null, i8** %arg_generic
|
||||
void test_storage_null_pointer_NULL(private char** arg_private,
|
||||
local char** arg_local,
|
||||
global char** arg_global,
|
||||
|
|
@ -337,8 +337,8 @@ void test_pass_null_pointer_arg_calee(private char* arg_private,
|
|||
generic char* arg_generic);
|
||||
|
||||
// CHECK-LABEL: test_pass_null_pointer_arg
|
||||
// CHECK: call void @test_pass_null_pointer_arg_calee(i8* null, i8 addrspace(3)* addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*), i8 addrspace(1)* null, i8 addrspace(2)* null, i8 addrspace(4)* null)
|
||||
// CHECK: call void @test_pass_null_pointer_arg_calee(i8* null, i8 addrspace(3)* addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*), i8 addrspace(1)* null, i8 addrspace(2)* null, i8 addrspace(4)* null)
|
||||
// CHECK: call void @test_pass_null_pointer_arg_calee(i8 addrspace(5)* null, i8 addrspace(3)* addrspacecast (i8* null to i8 addrspace(3)*), i8 addrspace(1)* null, i8 addrspace(2)* null, i8* null)
|
||||
// CHECK: call void @test_pass_null_pointer_arg_calee(i8 addrspace(5)* null, i8 addrspace(3)* addrspacecast (i8* null to i8 addrspace(3)*), i8 addrspace(1)* null, i8 addrspace(2)* null, i8* null)
|
||||
void test_pass_null_pointer_arg(void) {
|
||||
test_pass_null_pointer_arg_calee(0, 0, 0, 0, 0);
|
||||
test_pass_null_pointer_arg_calee(NULL, NULL, NULL, NULL, NULL);
|
||||
|
|
@ -352,8 +352,8 @@ void test_cast_null_pointer_to_sizet_calee(size_t arg_private,
|
|||
size_t arg_generic);
|
||||
|
||||
// CHECK-LABEL: test_cast_null_pointer_to_sizet
|
||||
// CHECK: call void @test_cast_null_pointer_to_sizet_calee(i64 0, i64 ptrtoint (i8 addrspace(3)* addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*) to i64), i64 0, i64 0, i64 0)
|
||||
// CHECK: call void @test_cast_null_pointer_to_sizet_calee(i64 0, i64 ptrtoint (i8 addrspace(3)* addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*) to i64), i64 0, i64 0, i64 0)
|
||||
// CHECK: call void @test_cast_null_pointer_to_sizet_calee(i64 0, i64 ptrtoint (i8 addrspace(3)* addrspacecast (i8* null to i8 addrspace(3)*) to i64), i64 0, i64 0, i64 0)
|
||||
// CHECK: call void @test_cast_null_pointer_to_sizet_calee(i64 0, i64 ptrtoint (i8 addrspace(3)* addrspacecast (i8* null to i8 addrspace(3)*) to i64), i64 0, i64 0, i64 0)
|
||||
void test_cast_null_pointer_to_sizet(void) {
|
||||
test_cast_null_pointer_to_sizet_calee((size_t)((private char*)0),
|
||||
(size_t)((local char*)0),
|
||||
|
|
@ -465,14 +465,14 @@ TEST_EQ00(constant, constant)
|
|||
// Test cast to bool.
|
||||
|
||||
// CHECK-LABEL: cast_bool_private
|
||||
// CHECK: icmp eq i8* %p, null
|
||||
// CHECK: icmp eq i8 addrspace(5)* %p, null
|
||||
void cast_bool_private(private char* p) {
|
||||
if (p)
|
||||
*p = 0;
|
||||
}
|
||||
|
||||
// CHECK-LABEL: cast_bool_local
|
||||
// CHECK: icmp eq i8 addrspace(3)* %p, addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*)
|
||||
// CHECK: icmp eq i8 addrspace(3)* %p, addrspacecast (i8* null to i8 addrspace(3)*)
|
||||
void cast_bool_local(local char* p) {
|
||||
if (p)
|
||||
*p = 0;
|
||||
|
|
@ -495,7 +495,7 @@ char cast_bool_constant(constant char* p) {
|
|||
}
|
||||
|
||||
// CHECK-LABEL: cast_bool_generic
|
||||
// CHECK: icmp eq i8 addrspace(4)* %p, null
|
||||
// CHECK: icmp eq i8* %p, null
|
||||
void cast_bool_generic(generic char* p) {
|
||||
if (p)
|
||||
*p = 0;
|
||||
|
|
@ -510,7 +510,7 @@ typedef struct {
|
|||
} StructTy3;
|
||||
|
||||
// CHECK-LABEL: test_memset_private
|
||||
// CHECK: call void @llvm.memset.p0i8.i64(i8* nonnull align 8 {{.*}}, i8 0, i64 40, i1 false)
|
||||
// CHECK: call void @llvm.memset.p5i8.i64(i8 addrspace(5)* align 8 {{.*}}, i8 0, i64 40, i1 false)
|
||||
void test_memset_private(private StructTy3 *ptr) {
|
||||
StructTy3 S3 = {0, 0, 0, 0, 0};
|
||||
*ptr = S3;
|
||||
|
|
@ -520,13 +520,13 @@ void test_memset_private(private StructTy3 *ptr) {
|
|||
// A 0 literal casted to pointer should become a null pointer.
|
||||
|
||||
// CHECK-LABEL: test_cast_0_to_local_ptr
|
||||
// CHECK: ret i32 addrspace(3)* addrspacecast (i32 addrspace(4)* null to i32 addrspace(3)*)
|
||||
// CHECK: ret i32 addrspace(3)* addrspacecast (i32* null to i32 addrspace(3)*)
|
||||
local int* test_cast_0_to_local_ptr(void) {
|
||||
return (local int*)0;
|
||||
}
|
||||
|
||||
// CHECK-LABEL: test_cast_0_to_private_ptr
|
||||
// CHECK: ret i32* null
|
||||
// CHECK: ret i32 addrspace(5)* null
|
||||
private int* test_cast_0_to_private_ptr(void) {
|
||||
return (private int*)0;
|
||||
}
|
||||
|
|
@ -536,7 +536,7 @@ private int* test_cast_0_to_private_ptr(void) {
|
|||
// zero value.
|
||||
|
||||
// CHECK-LABEL: test_cast_int_to_ptr1_private
|
||||
// CHECK: ret i32* null
|
||||
// CHECK: ret i32 addrspace(5)* null
|
||||
private int* test_cast_int_to_ptr1_private(void) {
|
||||
return (private int*)((void)0, 0);
|
||||
}
|
||||
|
|
@ -548,7 +548,7 @@ local int* test_cast_int_to_ptr1_local(void) {
|
|||
}
|
||||
|
||||
// CHECK-LABEL: test_cast_int_to_ptr2
|
||||
// CHECK: ret i32* null
|
||||
// CHECK: ret i32 addrspace(5)* null
|
||||
private int* test_cast_int_to_ptr2(void) {
|
||||
int x = 0;
|
||||
return (private int*)x;
|
||||
|
|
@ -568,7 +568,7 @@ int test_and_nullptr(int a) {
|
|||
}
|
||||
|
||||
// CHECK-LABEL: test_not_private_ptr
|
||||
// CHECK: %[[lnot:.*]] = icmp eq i8* %p, null
|
||||
// CHECK: %[[lnot:.*]] = icmp eq i8 addrspace(5)* %p, null
|
||||
// CHECK: %[[lnot_ext:.*]] = zext i1 %[[lnot]] to i32
|
||||
// CHECK: ret i32 %[[lnot_ext]]
|
||||
int test_not_private_ptr(private char* p) {
|
||||
|
|
@ -576,7 +576,7 @@ int test_not_private_ptr(private char* p) {
|
|||
}
|
||||
|
||||
// CHECK-LABEL: test_not_local_ptr
|
||||
// CHECK: %[[lnot:.*]] = icmp eq i8 addrspace(3)* %p, addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*)
|
||||
// CHECK: %[[lnot:.*]] = icmp eq i8 addrspace(3)* %p, addrspacecast (i8* null to i8 addrspace(3)*)
|
||||
// CHECK: %[[lnot_ext:.*]] = zext i1 %[[lnot]] to i32
|
||||
// CHECK: ret i32 %[[lnot_ext]]
|
||||
int test_not_local_ptr(local char* p) {
|
||||
|
|
@ -585,8 +585,8 @@ int test_not_local_ptr(local char* p) {
|
|||
|
||||
|
||||
// CHECK-LABEL: test_and_ptr
|
||||
// CHECK: %[[tobool:.*]] = icmp ne i8* %p1, null
|
||||
// CHECK: %[[tobool1:.*]] = icmp ne i8 addrspace(3)* %p2, addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*)
|
||||
// CHECK: %[[tobool:.*]] = icmp ne i8 addrspace(5)* %p1, null
|
||||
// CHECK: %[[tobool1:.*]] = icmp ne i8 addrspace(3)* %p2, addrspacecast (i8* null to i8 addrspace(3)*)
|
||||
// CHECK: %[[res:.*]] = and i1 %[[tobool]], %[[tobool1]]
|
||||
// CHECK: %[[land_ext:.*]] = zext i1 %[[res]] to i32
|
||||
// CHECK: ret i32 %[[land_ext]]
|
||||
|
|
@ -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 8
|
||||
// NOOPT: store i32 addrspace(1)* null, i32 addrspace(1)* addrspace(5)* %glob, align 8
|
||||
// NOOPT: %{{.*}} = sub i64 %{{.*}}, 0
|
||||
// NOOPT: call void @test_fold_callee
|
||||
// NOOPT: %{{.*}} = add nsw i64 %{{.*}}, 0
|
||||
|
|
@ -612,10 +612,10 @@ 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 8
|
||||
// NOOPT: store i32 addrspace(1)* null, i32 addrspace(1)* addrspace(5)* %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)
|
||||
// NOOPT: %{{.*}} = add nsw i64 %{{.*}}, sext (i32 ptrtoint (i32 addrspace(3)* addrspacecast (i32* null to i32 addrspace(3)*) to i32) to i64)
|
||||
// NOOPT: %{{.*}} = sub nsw i64 %{{.*}}, 1
|
||||
void test_fold_local(void) {
|
||||
global int* glob = (test_fold_callee(), (global int*)(generic char*)0);
|
||||
|
|
|
|||
|
|
@ -1,12 +1,14 @@
|
|||
// RUN: %clang_cc1 %s -cl-std=CL2.0 -emit-llvm -o - -O0 -triple spir-unknown-unknown | FileCheck -check-prefixes=COMMON,SPIR %s
|
||||
// RUN: %clang_cc1 %s -cl-std=CL2.0 -emit-llvm -o - -O0 -triple amdgcn-amd-amdhsa-opencl | FileCheck -check-prefixes=COMMON,AMD %s
|
||||
|
||||
// COMMON: %struct.__opencl_block_literal_generic = type { i32, i32, i8 addrspace(4)* }
|
||||
// SPIR: %struct.__opencl_block_literal_generic = type { i32, i32, i8 addrspace(4)* }
|
||||
// AMD: %struct.__opencl_block_literal_generic = type { i32, i32, i8* }
|
||||
// SPIR: @__block_literal_global = internal addrspace(1) constant { i32, i32, i8 addrspace(4)* } { i32 12, i32 4, i8 addrspace(4)* addrspacecast (i8* bitcast (void (i8 addrspace(4)*, i8 addrspace(3)*)* @block_A_block_invoke to i8*) to i8 addrspace(4)*) }
|
||||
// AMD: @__block_literal_global = internal addrspace(1) constant { i32, i32, i8 addrspace(4)* } { i32 16, i32 8, i8 addrspace(4)* addrspacecast (i8* bitcast (void (i8 addrspace(4)*, i8 addrspace(3)*)* @block_A_block_invoke to i8*) to i8 addrspace(4)*) }
|
||||
// AMD: @__block_literal_global = internal addrspace(1) constant { i32, i32, i8* } { i32 16, i32 8, i8* bitcast (void (i8*, i8 addrspace(3)*)* @block_A_block_invoke to i8*) }
|
||||
// COMMON-NOT: .str
|
||||
|
||||
// COMMON-LABEL: define internal {{.*}}void @block_A_block_invoke(i8 addrspace(4)* %.block_descriptor, i8 addrspace(3)* %a)
|
||||
// SPIR-LABEL: define internal {{.*}}void @block_A_block_invoke(i8 addrspace(4)* %.block_descriptor, i8 addrspace(3)* %a)
|
||||
// AMD-LABEL: define internal {{.*}}void @block_A_block_invoke(i8* %.block_descriptor, i8 addrspace(3)* %a)
|
||||
void (^block_A)(local void *) = ^(local void *a) {
|
||||
return;
|
||||
};
|
||||
|
|
@ -18,27 +20,44 @@ void foo(){
|
|||
// COMMON-NOT: %block.flags
|
||||
// COMMON-NOT: %block.reserved
|
||||
// COMMON-NOT: %block.descriptor
|
||||
// COMMON: %[[block_size:.*]] = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i32 }>, <{ i32, i32, i8 addrspace(4)*, i32 }>* %block, i32 0, i32 0
|
||||
// SPIR: %[[block_size:.*]] = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i32 }>, <{ i32, i32, i8 addrspace(4)*, i32 }>* %block, i32 0, i32 0
|
||||
// AMD: %[[block_size:.*]] = getelementptr inbounds <{ i32, i32, i8*, i32 }>, <{ i32, i32, i8*, i32 }> addrspace(5)* %block, i32 0, i32 0
|
||||
// SPIR: store i32 16, i32* %[[block_size]]
|
||||
// AMD: store i32 20, i32* %[[block_size]]
|
||||
// COMMON: %[[block_align:.*]] = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i32 }>, <{ i32, i32, i8 addrspace(4)*, i32 }>* %block, i32 0, i32 1
|
||||
// AMD: store i32 20, i32 addrspace(5)* %[[block_size]]
|
||||
// SPIR: %[[block_align:.*]] = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i32 }>, <{ i32, i32, i8 addrspace(4)*, i32 }>* %block, i32 0, i32 1
|
||||
// AMD: %[[block_align:.*]] = getelementptr inbounds <{ i32, i32, i8*, i32 }>, <{ i32, i32, i8*, i32 }> addrspace(5)* %block, i32 0, i32 1
|
||||
// SPIR: store i32 4, i32* %[[block_align]]
|
||||
// AMD: store i32 8, i32* %[[block_align]]
|
||||
// COMMON: %[[block_invoke:.*]] = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i32 }>, <{ i32, i32, i8 addrspace(4)*, i32 }>* %[[block:.*]], i32 0, i32 2
|
||||
// COMMON: store i8 addrspace(4)* addrspacecast (i8* bitcast (i32 (i8 addrspace(4)*)* @__foo_block_invoke to i8*) to i8 addrspace(4)*), i8 addrspace(4)** %[[block_invoke]]
|
||||
// COMMON: %[[block_captured:.*]] = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i32 }>, <{ i32, i32, i8 addrspace(4)*, i32 }>* %[[block]], i32 0, i32 3
|
||||
// COMMON: %[[i_value:.*]] = load i32, i32* %i
|
||||
// COMMON: store i32 %[[i_value]], i32* %[[block_captured]],
|
||||
// COMMON: %[[blk_ptr:.*]] = bitcast <{ i32, i32, i8 addrspace(4)*, i32 }>* %[[block]] to i32 ()*
|
||||
// COMMON: %[[blk_gen_ptr:.*]] = addrspacecast i32 ()* %[[blk_ptr]] to i32 () addrspace(4)*
|
||||
// COMMON: store i32 () addrspace(4)* %[[blk_gen_ptr]], i32 () addrspace(4)** %[[block_B:.*]],
|
||||
// COMMON: %[[blk_gen_ptr:.*]] = load i32 () addrspace(4)*, i32 () addrspace(4)** %[[block_B]]
|
||||
// COMMON: %[[block_literal:.*]] = bitcast i32 () addrspace(4)* %[[blk_gen_ptr]] to %struct.__opencl_block_literal_generic addrspace(4)*
|
||||
// COMMON: %[[invoke_addr:.*]] = getelementptr inbounds %struct.__opencl_block_literal_generic, %struct.__opencl_block_literal_generic addrspace(4)* %[[block_literal]], i32 0, i32 2
|
||||
// COMMON: %[[blk_gen_ptr:.*]] = bitcast %struct.__opencl_block_literal_generic addrspace(4)* %[[block_literal]] to i8 addrspace(4)*
|
||||
// COMMON: %[[invoke_func_ptr:.*]] = load i8 addrspace(4)*, i8 addrspace(4)* addrspace(4)* %[[invoke_addr]]
|
||||
// COMMON: %[[invoke_func:.*]] = addrspacecast i8 addrspace(4)* %[[invoke_func_ptr]] to i32 (i8 addrspace(4)*)*
|
||||
// COMMON: call {{.*}}i32 %[[invoke_func]](i8 addrspace(4)* %[[blk_gen_ptr]])
|
||||
// AMD: store i32 8, i32 addrspace(5)* %[[block_align]]
|
||||
// SPIR: %[[block_invoke:.*]] = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i32 }>, <{ i32, i32, i8 addrspace(4)*, i32 }>* %[[block:.*]], i32 0, i32 2
|
||||
// SPIR: store i8 addrspace(4)* addrspacecast (i8* bitcast (i32 (i8 addrspace(4)*)* @__foo_block_invoke to i8*) to i8 addrspace(4)*), i8 addrspace(4)** %[[block_invoke]]
|
||||
// SPIR: %[[block_captured:.*]] = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i32 }>, <{ i32, i32, i8 addrspace(4)*, i32 }>* %[[block]], i32 0, i32 3
|
||||
// SPIR: %[[i_value:.*]] = load i32, i32* %i
|
||||
// SPIR: store i32 %[[i_value]], i32* %[[block_captured]],
|
||||
// SPIR: %[[blk_ptr:.*]] = bitcast <{ i32, i32, i8 addrspace(4)*, i32 }>* %[[block]] to i32 ()*
|
||||
// SPIR: %[[blk_gen_ptr:.*]] = addrspacecast i32 ()* %[[blk_ptr]] to i32 () addrspace(4)*
|
||||
// SPIR: store i32 () addrspace(4)* %[[blk_gen_ptr]], i32 () addrspace(4)** %[[block_B:.*]],
|
||||
// SPIR: %[[blk_gen_ptr:.*]] = load i32 () addrspace(4)*, i32 () addrspace(4)** %[[block_B]]
|
||||
// SPIR: %[[block_literal:.*]] = bitcast i32 () addrspace(4)* %[[blk_gen_ptr]] to %struct.__opencl_block_literal_generic addrspace(4)*
|
||||
// SPIR: %[[invoke_addr:.*]] = getelementptr inbounds %struct.__opencl_block_literal_generic, %struct.__opencl_block_literal_generic addrspace(4)* %[[block_literal]], i32 0, i32 2
|
||||
// SPIR: %[[blk_gen_ptr:.*]] = bitcast %struct.__opencl_block_literal_generic addrspace(4)* %[[block_literal]] to i8 addrspace(4)*
|
||||
// SPIR: %[[invoke_func_ptr:.*]] = load i8 addrspace(4)*, i8 addrspace(4)* addrspace(4)* %[[invoke_addr]]
|
||||
// SPIR: %[[invoke_func:.*]] = addrspacecast i8 addrspace(4)* %[[invoke_func_ptr]] to i32 (i8 addrspace(4)*)*
|
||||
// SPIR: call {{.*}}i32 %[[invoke_func]](i8 addrspace(4)* %[[blk_gen_ptr]])
|
||||
// AMD: %[[block_invoke:.*]] = getelementptr inbounds <{ i32, i32, i8*, i32 }>, <{ i32, i32, i8*, i32 }> addrspace(5)* %[[block:.*]], i32 0, i32 2
|
||||
// AMD: store i8* bitcast (i32 (i8*)* @__foo_block_invoke to i8*), i8* addrspace(5)* %[[block_invoke]]
|
||||
// AMD: %[[block_captured:.*]] = getelementptr inbounds <{ i32, i32, i8*, i32 }>, <{ i32, i32, i8*, i32 }> addrspace(5)* %[[block]], i32 0, i32 3
|
||||
// AMD: %[[i_value:.*]] = load i32, i32 addrspace(5)* %i
|
||||
// AMD: store i32 %[[i_value]], i32 addrspace(5)* %[[block_captured]],
|
||||
// AMD: %[[blk_ptr:.*]] = bitcast <{ i32, i32, i8*, i32 }> addrspace(5)* %[[block]] to i32 () addrspace(5)*
|
||||
// AMD: %[[blk_gen_ptr:.*]] = addrspacecast i32 () addrspace(5)* %[[blk_ptr]] to i32 ()*
|
||||
// AMD: store i32 ()* %[[blk_gen_ptr]], i32 ()* addrspace(5)* %[[block_B:.*]],
|
||||
// AMD: %[[blk_gen_ptr:.*]] = load i32 ()*, i32 ()* addrspace(5)* %[[block_B]]
|
||||
// AMD: %[[block_literal:.*]] = bitcast i32 ()* %[[blk_gen_ptr]] to %struct.__opencl_block_literal_generic*
|
||||
// AMD: %[[invoke_addr:.*]] = getelementptr inbounds %struct.__opencl_block_literal_generic, %struct.__opencl_block_literal_generic* %[[block_literal]], i32 0, i32 2
|
||||
// AMD: %[[blk_gen_ptr:.*]] = bitcast %struct.__opencl_block_literal_generic* %[[block_literal]] to i8*
|
||||
// AMD: %[[invoke_func_ptr:.*]] = load i8*, i8** %[[invoke_addr]]
|
||||
// AMD: %[[invoke_func:.*]] = bitcast i8* %[[invoke_func_ptr]] to i32 (i8*)*
|
||||
// AMD: call {{.*}}i32 %[[invoke_func]](i8* %[[blk_gen_ptr]])
|
||||
|
||||
int (^ block_B)(void) = ^{
|
||||
return i;
|
||||
|
|
@ -46,9 +65,13 @@ void foo(){
|
|||
block_B();
|
||||
}
|
||||
|
||||
// COMMON-LABEL: define internal {{.*}}i32 @__foo_block_invoke(i8 addrspace(4)* %.block_descriptor)
|
||||
// COMMON: %[[block:.*]] = bitcast i8 addrspace(4)* %.block_descriptor to <{ i32, i32, i8 addrspace(4)*, i32 }> addrspace(4)*
|
||||
// COMMON: %[[block_capture_addr:.*]] = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i32 }>, <{ i32, i32, i8 addrspace(4)*, i32 }> addrspace(4)* %[[block]], i32 0, i32 3
|
||||
// COMMON: %[[block_capture:.*]] = load i32, i32 addrspace(4)* %[[block_capture_addr]]
|
||||
// SPIR-LABEL: define internal {{.*}}i32 @__foo_block_invoke(i8 addrspace(4)* %.block_descriptor)
|
||||
// SPIR: %[[block:.*]] = bitcast i8 addrspace(4)* %.block_descriptor to <{ i32, i32, i8 addrspace(4)*, i32 }> addrspace(4)*
|
||||
// SPIR: %[[block_capture_addr:.*]] = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i32 }>, <{ i32, i32, i8 addrspace(4)*, i32 }> addrspace(4)* %[[block]], i32 0, i32 3
|
||||
// SPIR: %[[block_capture:.*]] = load i32, i32 addrspace(4)* %[[block_capture_addr]]
|
||||
// AMD-LABEL: define internal {{.*}}i32 @__foo_block_invoke(i8* %.block_descriptor)
|
||||
// AMD: %[[block:.*]] = bitcast i8* %.block_descriptor to <{ i32, i32, i8*, i32 }>*
|
||||
// AMD: %[[block_capture_addr:.*]] = getelementptr inbounds <{ i32, i32, i8*, i32 }>, <{ i32, i32, i8*, i32 }>* %[[block]], i32 0, i32 3
|
||||
// AMD: %[[block_capture:.*]] = load i32, i32* %[[block_capture_addr]]
|
||||
|
||||
// COMMON-NOT: define{{.*}}@__foo_block_invoke_kernel
|
||||
|
|
|
|||
|
|
@ -1,6 +1,5 @@
|
|||
// 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 {
|
||||
int x[100];
|
||||
|
|
@ -10,10 +9,8 @@ int f(struct A a);
|
|||
|
||||
int g() {
|
||||
struct A a;
|
||||
// CHECK: call i32 @f(%struct.A* byval{{.*}}%a)
|
||||
// AMDGIZ: call i32 @f(%struct.A addrspace(5)* byval{{.*}}%a)
|
||||
// CHECK: call i32 @f(%struct.A addrspace(5)* byval{{.*}}%a)
|
||||
return f(a);
|
||||
}
|
||||
|
||||
// CHECK: declare i32 @f(%struct.A* byval{{.*}})
|
||||
// AMDGIZ: declare i32 @f(%struct.A addrspace(5)* byval{{.*}})
|
||||
// CHECK: declare i32 @f(%struct.A addrspace(5)* byval{{.*}})
|
||||
|
|
|
|||
|
|
@ -41,7 +41,8 @@ kernel void foo(image1d_t img) {
|
|||
sampler_t smp = CLK_ADDRESS_CLAMP_TO_EDGE|CLK_NORMALIZED_COORDS_TRUE|CLK_FILTER_LINEAR;
|
||||
// CHECK-COM: alloca %opencl.sampler_t addrspace(2)*
|
||||
event_t evt;
|
||||
// CHECK-COM: alloca %opencl.event_t*
|
||||
// CHECK-SPIR: alloca %opencl.event_t*
|
||||
// CHECK-AMDGCN: alloca %opencl.event_t addrspace(5)*
|
||||
clk_event_t clk_evt;
|
||||
// CHECK-SPIR: alloca %opencl.clk_event_t*
|
||||
// CHECK-AMDGCN: alloca %opencl.clk_event_t addrspace(1)*
|
||||
|
|
|
|||
|
|
@ -1,12 +1,14 @@
|
|||
// 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
|
||||
// RUN: %clang_cc1 %s -cl-std=CL2.0 -finclude-default-header -emit-llvm -O0 -triple amdgcn -o - | FileCheck --check-prefix=SZ64 --check-prefix=AMDGCN %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=AMDGCN %s
|
||||
|
||||
//SZ32: define{{.*}} i32 @test_ptrtoint_private(i8* %x)
|
||||
//SZ32: ptrtoint i8* %{{.*}} to i32
|
||||
//SZ64: define{{.*}} i64 @test_ptrtoint_private(i8* %x)
|
||||
//SZ64: ptrtoint i8* %{{.*}} to i64
|
||||
//SZ64ONLY: define{{.*}} i64 @test_ptrtoint_private(i8* %x)
|
||||
//SZ64ONLY: ptrtoint i8* %{{.*}} to i64
|
||||
//AMDGCN: define{{.*}} i64 @test_ptrtoint_private(i8 addrspace(5)* %x)
|
||||
//AMDGCN: ptrtoint i8 addrspace(5)* %{{.*}} to i64
|
||||
size_t test_ptrtoint_private(private char* x) {
|
||||
return (size_t)x;
|
||||
}
|
||||
|
|
@ -37,18 +39,21 @@ size_t test_ptrtoint_local(local char* x) {
|
|||
|
||||
//SZ32: define{{.*}} i32 @test_ptrtoint_generic(i8 addrspace(4)* %x)
|
||||
//SZ32: ptrtoint i8 addrspace(4)* %{{.*}} to i32
|
||||
//SZ64: define{{.*}} i64 @test_ptrtoint_generic(i8 addrspace(4)* %x)
|
||||
//SZ64: ptrtoint i8 addrspace(4)* %{{.*}} to i64
|
||||
//SZ64ONLY: define{{.*}} i64 @test_ptrtoint_generic(i8 addrspace(4)* %x)
|
||||
//SZ64ONLY: ptrtoint i8 addrspace(4)* %{{.*}} to i64
|
||||
//AMDGCN: define{{.*}} i64 @test_ptrtoint_generic(i8* %x)
|
||||
//AMDGCN: ptrtoint i8* %{{.*}} to i64
|
||||
size_t test_ptrtoint_generic(generic char* x) {
|
||||
return (size_t)x;
|
||||
}
|
||||
|
||||
//SZ32: define{{.*}} i8* @test_inttoptr_private(i32 %x)
|
||||
//SZ32: inttoptr i32 %{{.*}} to i8*
|
||||
//SZ64: define{{.*}} i8* @test_inttoptr_private(i64 %x)
|
||||
//AMDONLY: trunc i64 %{{.*}} to i32
|
||||
//AMDONLY: inttoptr i32 %{{.*}} to i8*
|
||||
//SZ64ONLY: define{{.*}} i8* @test_inttoptr_private(i64 %x)
|
||||
//SZ64ONLY: inttoptr i64 %{{.*}} to i8*
|
||||
//AMDGCN: define{{.*}} i8 addrspace(5)* @test_inttoptr_private(i64 %x)
|
||||
//AMDGCN: trunc i64 %{{.*}} to i32
|
||||
//AMDGCN: inttoptr i32 %{{.*}} to i8 addrspace(5)*
|
||||
private char* test_inttoptr_private(size_t x) {
|
||||
return (private char*)x;
|
||||
}
|
||||
|
|
@ -64,8 +69,8 @@ global char* test_inttoptr_global(size_t x) {
|
|||
//SZ32: define{{.*}} i8 addrspace(3)* @test_add_local(i8 addrspace(3)* %x, i32 %y)
|
||||
//SZ32: getelementptr inbounds i8, i8 addrspace(3)* %{{.*}}, i32
|
||||
//SZ64: define{{.*}} i8 addrspace(3)* @test_add_local(i8 addrspace(3)* %x, i64 %y)
|
||||
//AMDONLY: trunc i64 %{{.*}} to i32
|
||||
//AMDONLY: getelementptr inbounds i8, i8 addrspace(3)* %{{.*}}, i32
|
||||
//AMDGCN: trunc i64 %{{.*}} to i32
|
||||
//AMDGCN: getelementptr inbounds i8, i8 addrspace(3)* %{{.*}}, i32
|
||||
//SZ64ONLY: getelementptr inbounds i8, i8 addrspace(3)* %{{.*}}, i64
|
||||
local char* test_add_local(local char* x, ptrdiff_t y) {
|
||||
return x + y;
|
||||
|
|
@ -92,9 +97,12 @@ ptrdiff_t test_sub_local(local char* x, local char *y) {
|
|||
//SZ32: define{{.*}} i32 @test_sub_private(i8* %x, i8* %y)
|
||||
//SZ32: ptrtoint i8* %{{.*}} to i32
|
||||
//SZ32: ptrtoint i8* %{{.*}} to i32
|
||||
//SZ64: define{{.*}} i64 @test_sub_private(i8* %x, i8* %y)
|
||||
//SZ64: ptrtoint i8* %{{.*}} to i64
|
||||
//SZ64: ptrtoint i8* %{{.*}} to i64
|
||||
//SZ64ONLY: define{{.*}} i64 @test_sub_private(i8* %x, i8* %y)
|
||||
//SZ64ONLY: ptrtoint i8* %{{.*}} to i64
|
||||
//SZ64ONLY: ptrtoint i8* %{{.*}} to i64
|
||||
//AMDGCN: define{{.*}} i64 @test_sub_private(i8 addrspace(5)* %x, i8 addrspace(5)* %y)
|
||||
//AMDGCN: ptrtoint i8 addrspace(5)* %{{.*}} to i64
|
||||
//AMDGCN: ptrtoint i8 addrspace(5)* %{{.*}} to i64
|
||||
ptrdiff_t test_sub_private(private char* x, private char *y) {
|
||||
return x - y;
|
||||
}
|
||||
|
|
@ -102,9 +110,12 @@ ptrdiff_t test_sub_private(private char* x, private char *y) {
|
|||
//SZ32: define{{.*}} i32 @test_sub_mix(i8* %x, i8 addrspace(4)* %y)
|
||||
//SZ32: ptrtoint i8* %{{.*}} to i32
|
||||
//SZ32: ptrtoint i8 addrspace(4)* %{{.*}} to i32
|
||||
//SZ64: define{{.*}} i64 @test_sub_mix(i8* %x, i8 addrspace(4)* %y)
|
||||
//SZ64: ptrtoint i8* %{{.*}} to i64
|
||||
//SZ64: ptrtoint i8 addrspace(4)* %{{.*}} to i64
|
||||
//SZ64ONLY: define{{.*}} i64 @test_sub_mix(i8* %x, i8 addrspace(4)* %y)
|
||||
//SZ64ONLY: ptrtoint i8* %{{.*}} to i64
|
||||
//SZ64ONLY: ptrtoint i8 addrspace(4)* %{{.*}} to i64
|
||||
//AMDGCN: define{{.*}} i64 @test_sub_mix(i8 addrspace(5)* %x, i8* %y)
|
||||
//AMDGCN: ptrtoint i8 addrspace(5)* %{{.*}} to i64
|
||||
//AMDGCN: ptrtoint i8* %{{.*}} to i64
|
||||
ptrdiff_t test_sub_mix(private char* x, generic char *y) {
|
||||
return x - y;
|
||||
}
|
||||
|
|
|
|||
Loading…
Reference in New Issue