/external/OpenCL-CTS/test_conformance/extensions/cl_ext_cxx_for_opencl/ |
D | cxx_for_opencl_ext.cpp | 25 clKernelWrapper kernel2; in test_cxx_for_opencl() local 48 kernel2 = clCreateKernel(program, "k2", &error); in test_cxx_for_opencl() 64 error = clSetKernelArg(kernel2, 0, sizeof(out_buffer), &out_buffer); in test_cxx_for_opencl() 72 error = clEnqueueNDRangeKernel(queue, kernel2, 1, nullptr, &global_size, in test_cxx_for_opencl()
|
/external/OpenCL-CTS/test_conformance/device_execution/ |
D | host_queue_order.cpp | 132 clKernelWrapper kernel1, kernel2; in test_host_queue_order() local 142 context, &program2, &kernel2, arr_size(enqueue_block_second_kernel), in test_host_queue_order() 162 err_ret = clSetKernelArg(kernel2, 0, sizeof(num), &num); in test_host_queue_order() 164 err_ret = clSetKernelArg(kernel2, 1, sizeof(cl_mem), &res_mem); in test_host_queue_order() 167 err_ret = clEnqueueNDRangeKernel(queue, kernel2, 1, NULL, &size, &size, 0, NULL, &kernel_event); in test_host_queue_order()
|
/external/OpenCL-CTS/test_conformance/basic/ |
D | test_kernel_call_kernel_function.cpp | 67 clKernelWrapper kernel1, kernel2, kernel_to_call; in test_kernel_call_kernel_function() local 158 kernel2 = clCreateKernel(program, "test_call_function", &error); in test_kernel_call_kernel_function() 161 error = clSetKernelArg(kernel2, 0, sizeof( streams[0] ), &streams[0]); in test_kernel_call_kernel_function() 163 error = clSetKernelArg(kernel2, 1, sizeof( streams[1] ), &streams[1]); in test_kernel_call_kernel_function() 165 error = clSetKernelArg(kernel2, 2, sizeof( times ), ×); in test_kernel_call_kernel_function() 168 error = clEnqueueNDRangeKernel( queue, kernel2, 1, NULL, threads, NULL, 0, NULL, NULL ); in test_kernel_call_kernel_function()
|
/external/llvm-project/llvm/test/Transforms/OpenMP/ |
D | gpu_kernel_detection_remarks.ll | 5 ; CHECK-DAG: remark: <unknown>:0:0: OpenMP GPU kernel kernel2 11 define void @kernel2() { 27 !3 = !{void ()* @kernel2, !"kernel", i32 1}
|
/external/llvm/test/CodeGen/NVPTX/ |
D | lower-kernel-ptr-arg.ll | 19 define void @kernel2(float addrspace(1)* %input, float addrspace(1)* %output) { 20 ; CHECK-LABEL: .visible .entry kernel2( 46 !1 = !{void (float addrspace(1)*, float addrspace(1)*)* @kernel2, !"kernel", i32 1}
|
/external/clang/test/CodeGenOpenCL/ |
D | kernel-attributes.cl | 8 …ute__((vec_type_hint(uint4))) __attribute__((work_group_size_hint(8,16,32))) void kernel2(int a) {} 9 // CHECK: define void @kernel2(i32 {{[^%]*}}%a) {{[^{]+}} !vec_type_hint ![[MD3:[0-9]+]] !work_grou…
|
/external/llvm-project/llvm/test/CodeGen/AMDGPU/ |
D | propagate-attributes-single-set.ll | 9 ; OPT: define amdgpu_kernel void @kernel2() local_unnamed_addr #2 31 ; LLC: kernel2: 65 define amdgpu_kernel void @kernel2() #0 {
|
D | uniform-work-group-prevent-attribute-propagation.ll | 16 ; CHECK: define amdgpu_kernel void @kernel2() #[[KERNEL2:[0-9]+]] { 17 define amdgpu_kernel void @kernel2() #2 {
|
D | uniform-work-group-propagate-attribute.ll | 21 ; CHECK: define amdgpu_kernel void @kernel2() #[[KERNEL2:[0-9]+]] { 22 define amdgpu_kernel void @kernel2() #2 {
|
D | propagate-attributes-clone.ll | 30 ; OPT: define amdgpu_kernel void @kernel2() local_unnamed_addr #3 82 ; LLC: kernel2: 126 define amdgpu_kernel void @kernel2() #2 {
|
/external/llvm/test/CodeGen/AMDGPU/ |
D | inline-calls.ll | 20 ; CHECK: {{^}}kernel2: 21 define void @kernel2(i32 addrspace(1)* %out) {
|
/external/llvm-project/clang/test/CodeGenOpenCL/ |
D | kernel-attributes.cl | 8 …ute__((vec_type_hint(uint4))) __attribute__((work_group_size_hint(8,16,32))) void kernel2(int a) {} 9 // CHECK: define {{(dso_local )?}}spir_kernel void @kernel2(i32 {{[^%]*}}%a) {{[^{]+}} !vec_type_hi…
|
/external/OpenCL-CTS/test_conformance/api/ |
D | test_create_kernels.cpp | 326 clKernelWrapper kernel1, kernel2; in test_load_two_kernels_manually() local 343 kernel2 = clCreateKernel( program, "sample_test", &error ); in test_load_two_kernels_manually() 345 if( kernel2 == NULL ) in test_load_two_kernels_manually() 357 clKernelWrapper kernel1, kernel2; in test_get_program_info_kernel_names() local 425 kernel2 = clCreateKernel( program, "sample_test2", &error ); in test_get_program_info_kernel_names() 426 if( kernel2 == NULL ) in test_get_program_info_kernel_names()
|
/external/OpenCL-CTS/test_conformance/events/ |
D | test_event_dependencies.cpp | 61 clKernelWrapper kernel1[TEST_COUNT], kernel2[TEST_COUNT]; in test_event_enqueue_wait_for_events_run_test() local 193 kernel2[i] = clCreateKernel(program, "write_down", &error); in test_event_enqueue_wait_for_events_run_test() 196 error = clSetKernelArg(kernel2[i], 0, sizeof(data), &data); in test_event_enqueue_wait_for_events_run_test() 197 error |= clSetKernelArg(kernel2[i], 1, sizeof(max_count), &max_count); in test_event_enqueue_wait_for_events_run_test() 280 …error = clEnqueueNDRangeKernel(queues[queue_to_use], kernel2[loop_count], 1, NULL, threads, NULL, … in test_event_enqueue_wait_for_events_run_test() 283 …error = clEnqueueNDRangeKernel(queues[queue_to_use], kernel2[loop_count], 1, NULL, threads, NULL, … in test_event_enqueue_wait_for_events_run_test()
|
/external/llvm-project/llvm/test/DebugInfo/AMDGPU/ |
D | code-pointer-size.ll | 11 ; kernel void kernel2(global int addrspace(5)*B) { 31 define amdgpu_kernel void @kernel2(i32 addrspace(1)* %B) !dbg !22 { 68 !22 = distinct !DISubprogram(name: "kernel2", scope: !1, file: !1, line: 5, type: !8, isLocal: fals…
|
D | dwarfdump-relocs.ll | 11 ; kernel void kernel2(global int addrspace(5)*B) { 32 define amdgpu_kernel void @kernel2(i32 addrspace(1)* %B) !dbg !22 { 69 !22 = distinct !DISubprogram(name: "kernel2", scope: !1, file: !1, line: 5, type: !8, isLocal: fals…
|
/external/llvm-project/llvm/test/CodeGen/NVPTX/ |
D | lower-kernel-ptr-arg.ll | 19 define void @kernel2(float addrspace(1)* %input, float addrspace(1)* %output) { 20 ; CHECK-LABEL: .visible .entry kernel2( 64 !1 = !{void (float addrspace(1)*, float addrspace(1)*)* @kernel2, !"kernel", i32 1}
|
/external/tensorflow/tensorflow/python/profiler/internal/ |
D | model_analyzer_testlib.py | 85 kernel2 = variable_scope.get_variable( 89 r2 = nn_ops.conv2d(image, kernel2, [1, 2, 2, 1], padding='SAME')
|
/external/llvm-project/clang/test/SemaCUDA/ |
D | call-kernel-from-kernel.cu | 7 __global__ void kernel2() { in kernel2() function
|
/external/llvm-project/clang/test/CodeGenCUDA/ |
D | amdgpu-kernel-arg-pointer-type.cu | 37 __global__ void kernel2(int &x) { in kernel2() function
|
/external/llvm-project/llvm/test/Transforms/LoopVectorize/AArch64/ |
D | gather-cost.ll | 5 @kernel2 = global [512 x float] zeroinitializer, align 16 38 %arrayidx4 = getelementptr inbounds [512 x float], [512 x float]* @kernel2, i64 0, i64 %v.055
|
/external/llvm/test/Transforms/LoopVectorize/ARM/ |
D | gather-cost.ll | 6 @kernel2 = global [512 x float] zeroinitializer, align 4 41 %arrayidx4 = getelementptr inbounds [512 x float], [512 x float]* @kernel2, i32 0, i32 %v.055
|
/external/llvm/test/Transforms/LoopVectorize/X86/ |
D | gather-cost.ll | 5 @kernel2 = global [512 x float] zeroinitializer, align 16 39 %arrayidx4 = getelementptr inbounds [512 x float], [512 x float]* @kernel2, i64 0, i64 %v.055
|
/external/llvm-project/llvm/test/Transforms/LoopVectorize/ARM/ |
D | gather-cost.ll | 6 @kernel2 = global [512 x float] zeroinitializer, align 4 41 %arrayidx4 = getelementptr inbounds [512 x float], [512 x float]* @kernel2, i32 0, i32 %v.055
|
/external/llvm-project/llvm/test/Transforms/LoopVectorize/X86/ |
D | gather-cost.ll | 5 @kernel2 = global [512 x float] zeroinitializer, align 16 39 %arrayidx4 = getelementptr inbounds [512 x float], [512 x float]* @kernel2, i64 0, i64 %v.055
|