maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/clang/test/CodeGenOpenCL/atomic-ops-libcall.cl

41 lines
4.3 KiB
Common Lisp
Raw Normal View History

Add OpenCL 2.0 atomic builtin functions as Clang builtin OpenCL 2.0 atomic builtin functions have a scope argument which is ideally represented as synchronization scope argument in LLVM atomic instructions. Clang supports translating Clang atomic builtin functions to LLVM atomic instructions. However it currently does not support synchronization scope of LLVM atomic instructions. Without this, users have to use LLVM assembly code to implement OpenCL atomic builtin functions. This patch adds OpenCL 2.0 atomic builtin functions as Clang builtin functions, which supports generating LLVM atomic instructions with synchronization scope operand. Currently only constant memory scope argument is supported. Support of non-constant memory scope argument will be added later. Differential Revision: https://reviews.llvm.org/D28691 llvm-svn: 310082
2017-08-05 02:16:31 +08:00
// RUN: %clang_cc1 < %s -cl-std=CL2.0 -finclude-default-header -triple spir64 -emit-llvm | FileCheck -check-prefix=SPIR %s
// RUN: %clang_cc1 < %s -cl-std=CL2.0 -finclude-default-header -triple armv5e-none-linux-gnueabi -emit-llvm | FileCheck -check-prefix=ARM %s
[OpenCL] Support variable memory scope in atomic builtins Differential Revision: https://reviews.llvm.org/D36580 llvm-svn: 310924
2017-08-16 00:02:49 +08:00
void f(atomic_int *i, atomic_uint *ui, int cmp, int order, int scope) {
Add OpenCL 2.0 atomic builtin functions as Clang builtin OpenCL 2.0 atomic builtin functions have a scope argument which is ideally represented as synchronization scope argument in LLVM atomic instructions. Clang supports translating Clang atomic builtin functions to LLVM atomic instructions. However it currently does not support synchronization scope of LLVM atomic instructions. Without this, users have to use LLVM assembly code to implement OpenCL atomic builtin functions. This patch adds OpenCL 2.0 atomic builtin functions as Clang builtin functions, which supports generating LLVM atomic instructions with synchronization scope operand. Currently only constant memory scope argument is supported. Support of non-constant memory scope argument will be added later. Differential Revision: https://reviews.llvm.org/D28691 llvm-svn: 310082
2017-08-05 02:16:31 +08:00
int x;
// SPIR: {{%[^ ]*}} = call i32 @__opencl_atomic_load_4(i8 addrspace(4)* {{%[0-9]+}}, i32 5, i32 1)
// ARM: {{%[^ ]*}} = call i32 @__opencl_atomic_load_4(i8* {{%[0-9]+}}, i32 5, i32 1)
x = __opencl_atomic_load(i, memory_order_seq_cst, memory_scope_work_group);
// SPIR: call void @__opencl_atomic_store_4(i8 addrspace(4)* {{%[0-9]+}}, i32 {{%[0-9]+}}, i32 5, i32 1)
// ARM: call void @__opencl_atomic_store_4(i8* {{%[0-9]+}}, i32 {{%[0-9]+}}, i32 5, i32 1)
__opencl_atomic_store(i, 1, memory_order_seq_cst, memory_scope_work_group);
// SPIR: {{%[^ ]*}} = call i32 @__opencl_atomic_fetch_add_4(i8 addrspace(4)* {{%[0-9]+}}, i32 {{%[0-9]+}}, i32 5, i32 1)
// ARM: {{%[^ ]*}} = call i32 @__opencl_atomic_fetch_add_4(i8* {{%[0-9]+}}, i32 {{%[0-9]+}}, i32 5, i32 1)
x = __opencl_atomic_fetch_add(i, 3, memory_order_seq_cst, memory_scope_work_group);
// SPIR: {{%[^ ]*}} = call i32 @__opencl_atomic_fetch_min_4(i8 addrspace(4)* {{%[0-9]+}}, i32 {{%[0-9]+}}, i32 5, i32 1)
// ARM: {{%[^ ]*}} = call i32 @__opencl_atomic_fetch_min_4(i8* {{%[0-9]+}}, i32 {{%[0-9]+}}, i32 5, i32 1)
x = __opencl_atomic_fetch_min(i, 3, memory_order_seq_cst, memory_scope_work_group);
// SPIR: {{%[^ ]*}} = call i32 @__opencl_atomic_fetch_umin_4(i8 addrspace(4)* {{%[0-9]+}}, i32 {{%[0-9]+}}, i32 5, i32 1)
// ARM: {{%[^ ]*}} = call i32 @__opencl_atomic_fetch_umin_4(i8* {{%[0-9]+}}, i32 {{%[0-9]+}}, i32 5, i32 1)
x = __opencl_atomic_fetch_min(ui, 3, memory_order_seq_cst, memory_scope_work_group);
// SPIR: {{%[^ ]*}} = call zeroext i1 @__opencl_atomic_compare_exchange_4(i8 addrspace(4)* {{%[0-9]+}}, i8 addrspace(4)* {{%[0-9]+}}, i32 {{%[0-9]+}}, i32 5, i32 5, i32 1)
// ARM: {{%[^ ]*}} = call zeroext i1 @__opencl_atomic_compare_exchange_4(i8* {{%[0-9]+}}, i8* {{%[0-9]+}}, i32 {{%[0-9]+}}, i32 5, i32 5, i32 1)
x = __opencl_atomic_compare_exchange_strong(i, &cmp, 1, memory_order_seq_cst, memory_order_seq_cst, memory_scope_work_group);
// SPIR: {{%[^ ]*}} = call zeroext i1 @__opencl_atomic_compare_exchange_4(i8 addrspace(4)* {{%[0-9]+}}, i8 addrspace(4)* {{%[0-9]+}}, i32 {{%[0-9]+}}, i32 5, i32 5, i32 1)
// ARM: {{%[^ ]*}} = call zeroext i1 @__opencl_atomic_compare_exchange_4(i8* {{%[0-9]+}}, i8* {{%[0-9]+}}, i32 {{%[0-9]+}}, i32 5, i32 5, i32 1)
x = __opencl_atomic_compare_exchange_weak(i, &cmp, 1, memory_order_seq_cst, memory_order_seq_cst, memory_scope_work_group);
// SPIR: {{%[^ ]*}} = call zeroext i1 @__opencl_atomic_compare_exchange_4(i8 addrspace(4)* {{%[0-9]+}}, i8 addrspace(4)* {{%[0-9]+}}, i32 {{%[0-9]+}}, i32 5, i32 5, i32 2)
// ARM: {{%[^ ]*}} = call zeroext i1 @__opencl_atomic_compare_exchange_4(i8* {{%[0-9]+}}, i8* {{%[0-9]+}}, i32 {{%[0-9]+}}, i32 5, i32 5, i32 2)
x = __opencl_atomic_compare_exchange_weak(i, &cmp, 1, memory_order_seq_cst, memory_order_seq_cst, memory_scope_device);
// SPIR: {{%[^ ]*}} = call zeroext i1 @__opencl_atomic_compare_exchange_4(i8 addrspace(4)* {{%[0-9]+}}, i8 addrspace(4)* {{%[0-9]+}}, i32 {{%[0-9]+}}, i32 5, i32 5, i32 3)
// ARM: {{%[^ ]*}} = call zeroext i1 @__opencl_atomic_compare_exchange_4(i8* {{%[0-9]+}}, i8* {{%[0-9]+}}, i32 {{%[0-9]+}}, i32 5, i32 5, i32 3)
x = __opencl_atomic_compare_exchange_weak(i, &cmp, 1, memory_order_seq_cst, memory_order_seq_cst, memory_scope_all_svm_devices);
#ifdef cl_khr_subgroups
// SPIR: {{%[^ ]*}} = call zeroext i1 @__opencl_atomic_compare_exchange_4(i8 addrspace(4)* {{%[0-9]+}}, i8 addrspace(4)* {{%[0-9]+}}, i32 {{%[0-9]+}}, i32 5, i32 5, i32 4)
x = __opencl_atomic_compare_exchange_weak(i, &cmp, 1, memory_order_seq_cst, memory_order_seq_cst, memory_scope_sub_group);
#endif
[OpenCL] Support variable memory scope in atomic builtins Differential Revision: https://reviews.llvm.org/D36580 llvm-svn: 310924
2017-08-16 00:02:49 +08:00
// SPIR: {{%[^ ]*}} = call zeroext i1 @__opencl_atomic_compare_exchange_4(i8 addrspace(4)* {{%[0-9]+}}, i8 addrspace(4)* {{%[0-9]+}}, i32 {{%[0-9]+}}, i32 %{{.*}}, i32 %{{.*}}, i32 %{{.*}})
// ARM: {{%[^ ]*}} = call zeroext i1 @__opencl_atomic_compare_exchange_4(i8* {{%[0-9]+}}, i8* {{%[0-9]+}}, i32 {{%[0-9]+}}, i32 %{{.*}}, i32 %{{.*}}, i32 %{{.*}})
x = __opencl_atomic_compare_exchange_weak(i, &cmp, 1, order, order, scope);
Add OpenCL 2.0 atomic builtin functions as Clang builtin OpenCL 2.0 atomic builtin functions have a scope argument which is ideally represented as synchronization scope argument in LLVM atomic instructions. Clang supports translating Clang atomic builtin functions to LLVM atomic instructions. However it currently does not support synchronization scope of LLVM atomic instructions. Without this, users have to use LLVM assembly code to implement OpenCL atomic builtin functions. This patch adds OpenCL 2.0 atomic builtin functions as Clang builtin functions, which supports generating LLVM atomic instructions with synchronization scope operand. Currently only constant memory scope argument is supported. Support of non-constant memory scope argument will be added later. Differential Revision: https://reviews.llvm.org/D28691 llvm-svn: 310082
2017-08-05 02:16:31 +08:00
}