| /external/clang/test/SemaCUDA/ |
| D | bad-attributes.cu | 22 __global__ int e1; // expected-warning {{attribute only applies to functions}}
23 __global__ void e2();
31 __device__ __global__ void z4(); // expected-error {{attributes are not compatible}}
35 __host__ __global__ void z6(); // expected-error {{attributes are not compatible}}
46 __global__ __device__ void z11(); // expected-error {{attributes are not compatible}}
48 __global__ __host__ void z12(); // expected-error {{attributes are not compatible}}
52 __global__ void foo() {}; // expected-error {{must be a free function or static member function}} in foo()
53 __global__ static void bar(); // expected-warning {{kernel function 'bar' is a member function}}
55 …__global__ static void baz() {}; // expected-warning {{kernel function 'baz' is a member function}} in baz()
58 __global__ static inline void foobar() {}; in foobar()
|
| D | amdgpu-num-gpr-attr.cu | 6 __global__ void test_num_vgpr() { } // expected-error {{'amdgpu_num_vgpr' attribute only applies to… in test_num_vgpr()
9 __global__ void test_num_sgpr() { } // expected-error {{'amdgpu_num_sgpr' attribute only applies to… in test_num_sgpr()
14 __global__ void test_num_vgpr_num_sgpr() { } in test_num_vgpr_num_sgpr()
|
| D | qualifiers.cu | 35 __global__ void g1(int x) {} in g1()
36 __global__ int g2(int x) { // expected-error {{must have void return type}} in g2()
|
| D | function-target.cu | 9 __global__ void h1g(void);
26 __global__ void d1g(void); // expected-note {{'d1g' declared here}}
|
| D | function-overload.cu | 88 __global__ void g() {} in g()
147 __global__ void globalf() { in globalf()
295 __global__ void friend_of_g(G &arg) { int x = arg.x; } // expected-note {{previous definition is he… in friend_of_g()
|
| /external/clang/test/CodeGenCUDA/ |
| D | launch-bounds.cu | 10 __global__ void
23 __global__ void
33 __global__ void
43 __global__ void
55 __global__ void
67 __global__ void
75 __global__ void
84 __global__ void __launch_bounds__(constint, constchar) Kernel8() {} in __launch_bounds__()
|
| D | ptx-kernels.cu | 15 __global__ void global_function() { in global_function()
21 template <typename T> __global__ void templated_kernel(T param) {} in templated_kernel()
25 __global__ void anonymous_ns_kernel() {} in anonymous_ns_kernel()
|
| /external/tensorflow/tensorflow/core/kernels/ |
| D | population_count_op_gpu.cu.cc | 36 __global__ void PopulationCountKernel(const int size, in PopulationCountKernel()
43 __global__ void PopulationCountKernel(const int size, in PopulationCountKernel()
53 __global__ void PopulationCountKernel(const int size, in PopulationCountKernel()
63 __global__ void PopulationCountKernel<int64_t>(const int size, in PopulationCountKernel()
|
| D | bias_op_gpu.cu.cc | 54 __global__ void BiasNHWCKernel(int32 nthreads, const T* __restrict__ input, in BiasNHWCKernel()
64 __global__ void BiasNCHWKernel(int32 nthreads, const T* __restrict__ input, in BiasNCHWKernel()
106 __global__ void BiasGradNHWC_Naive(int32 nthreads, in BiasGradNHWC_Naive()
118 __global__ void BiasGradNCHW_Naive(int32 nthreads, in BiasGradNCHW_Naive()
130 __global__ void BiasGradNHWC_SharedAtomics( in BiasGradNHWC_SharedAtomics()
154 __global__ void BiasGradNCHW_SharedAtomics( in BiasGradNCHW_SharedAtomics()
|
| D | debug_ops_gpu.cu.cc | 39 __global__ void CurtHealthKernel(const Tin* __restrict__ data, int size, in CurtHealthKernel()
57 __global__ void ConciseHealthKernel(const Tin* __restrict__ data, int size, in ConciseHealthKernel()
88 __global__ void FullHealthKernel(const Tin* __restrict__ data, int size, in FullHealthKernel()
131 __global__ void ReduceInfNanThreeSlotsKernel(const Tin* __restrict__ data, in ReduceInfNanThreeSlotsKernel()
|
| D | maxpooling_op_gpu.cu.cc | 67 __global__ void MaxPoolForwardNCHW( in MaxPoolForwardNCHW()
111 __global__ void MaxPoolForwardNoMaskKernel_NCHW_VECT_C( in MaxPoolForwardNoMaskKernel_NCHW_VECT_C()
144 __global__ void MaxPoolForwardNHWC( in MaxPoolForwardNHWC()
203 __global__ void MaxPoolBackward(const int nthreads, in MaxPoolBackward()
230 __global__ void MaxPoolGradBackwardNoMaskNCHW( in MaxPoolGradBackwardNoMaskNCHW()
271 __global__ void MaxPoolGradBackwardNoMaskNHWC( in MaxPoolGradBackwardNoMaskNHWC()
332 __global__ void MaxPoolGradBackward(const int nthreads, in MaxPoolGradBackward()
|
| D | cwise_op_clip_gpu.cu.cc | 27 __global__ void UnaryClipCustomKernel(const int32 size_in, in UnaryClipCustomKernel()
39 __global__ void BinaryRightClipCustomKernel(const int32 size_in, in BinaryRightClipCustomKernel()
51 __global__ void BinaryLeftClipCustomKernel(const int32 size_in, in BinaryLeftClipCustomKernel()
|
| D | check_numerics_op_gpu.cu.cc | 39 __global__ void CheckNumericsKernel(const T* __restrict__ data, int size, in CheckNumericsKernel()
62 __global__ void CheckNumericsKernelV2(const T* __restrict__ data, int size, in CheckNumericsKernelV2()
|
| D | sparse_fill_empty_rows_op_gpu.cu.cc | 87 __global__ __launch_bounds__(1024) void CountElementsPerRowKernel( in CountElementsPerRowKernel()
108 __global__ __launch_bounds__(1024) void CopyRowIndicesKernel( in CopyRowIndicesKernel()
117 __global__ __launch_bounds__(1024) void ComputeEmptyRowIndicatorKernel( in ComputeEmptyRowIndicatorKernel()
129 __global__ __launch_bounds__(1024) void ScatterInputElementsKernel( in ScatterInputElementsKernel()
151 __global__ __launch_bounds__(1024) void ScatterNewElementsKernel( in ScatterNewElementsKernel()
489 __global__ __launch_bounds__(1024) void GatherOriginalGradValuesKernel( in GatherOriginalGradValuesKernel()
|
| D | diag_op_gpu.cu.cc | 32 __global__ void DiagGpuKernel(const int num_threads, const int64 size, in DiagGpuKernel()
82 __global__ void DiagPartGpuKernel(const int num_threads, const int64 size, in DiagPartGpuKernel()
|
| D | depthtospace_op_gpu.cu.cc | 33 __global__ void D2S_NHWC(const int32 nthreads, in D2S_NHWC()
64 __global__ void D2S_NCHW(const int32 nthreads, in D2S_NCHW()
101 __global__ void D2S_NCHW_LOOP(const int32 nthreads, in D2S_NCHW_LOOP()
|
| D | bincount_op_gpu.cu.cc | 116 __global__ void BincountReduceKernel(const Tidx* in, T* out, const int nthreads, in BincountReduceKernel()
144 __global__ void BincountColReduceKernel(const Tidx* in, const T* weights, in BincountColReduceKernel()
165 __global__ void BincountColReduceSharedKernel(const Tidx* in, const T* weights, in BincountColReduceSharedKernel()
|
| D | sparse_to_dense_op_gpu.cu.cc | 36 __global__ void SparseToDenseKernel(const Index* __restrict__ indices, in SparseToDenseKernel()
55 __global__ void SetDefaultValue(const T default_value, const int64 dense_size, in SetDefaultValue()
63 __global__ void CheckIndicesValid(const Index* __restrict__ indices, in CheckIndicesValid()
|
| D | spacetodepth_op_gpu.cu.cc | 32 __global__ void S2D_NHWC(const int32 nthreads, in S2D_NHWC()
64 __global__ void S2D_NCHW(const int32 nthreads, in S2D_NCHW()
102 __global__ void S2D_NCHW_LOOP(const int32 nthreads, in S2D_NCHW_LOOP()
|
| D | searchsorted_op_gpu.cu.cc | 34 __global__ void UpperBoundKernel(const T* __restrict__ sorted_inputs, in UpperBoundKernel()
47 __global__ void LowerBoundKernel(const T* __restrict__ sorted_inputs, in LowerBoundKernel()
|
| /external/tensorflow/tensorflow/core/profiler/backends/gpu/ |
| D | cuda_test.cu.cc | 36 __global__ void simple_print() { printf("hello, world!\n"); } in simple_print()
39 __global__ void empty() {} in empty()
42 __global__ void access(int *addr) { *addr = *addr * 2; } in access()
|
| /external/tensorflow/tensorflow/core/util/ |
| D | gpu_kernel_helper_test.cu.cc | 46 __global__ void SetOutbufZero(GpuLaunchConfig config, in SetOutbufZero()
52 __global__ void Count1D(GpuLaunchConfig config, int bufsize, in Count1D()
61 __global__ void Count2D(Gpu2DLaunchConfig config, int bufsize, in Count2D()
76 __global__ void Count3D(Gpu3DLaunchConfig config, int bufsize, in Count3D()
99 __global__ void GpuShuffleGetSrcLaneTest(unsigned* __restrict__ failure_count) { in GpuShuffleGetSrcLaneTest()
|
| /external/tensorflow/tensorflow/core/kernels/image/ |
| D | resize_nearest_neighbor_op_gpu.cu.cc | 35 __global__ void ResizeNearestNeighborNHWC( in ResizeNearestNeighborNHWC()
66 __global__ void LegacyResizeNearestNeighborNHWC( in LegacyResizeNearestNeighborNHWC()
95 __global__ void ResizeNearestNeighborBackwardNHWC( in ResizeNearestNeighborBackwardNHWC()
126 __global__ void LegacyResizeNearestNeighborBackwardNHWC( in LegacyResizeNearestNeighborBackwardNHWC()
|
| D | resize_bilinear_op_gpu.cu.cc | 36 __global__ void ResizeBilinearKernel_faster( in ResizeBilinearKernel_faster()
116 __global__ void ResizeBilinearKernel( in ResizeBilinearKernel()
166 __global__ void ResizeBilinearGradKernel(const int32 nthreads, in ResizeBilinearGradKernel()
231 __global__ void ResizeBilinearDeterministicGradKernel( in ResizeBilinearDeterministicGradKernel()
284 __global__ void LegacyResizeBilinearKernel( in LegacyResizeBilinearKernel()
334 __global__ void LegacyResizeBilinearGradKernel( in LegacyResizeBilinearGradKernel()
|
| /external/tensorflow/tensorflow/core/kernels/sparse/ |
| D | kernels_gpu.cu.cc | 136 __global__ void SparseTensorToCOOMatrixKernel(const int64* indices, in SparseTensorToCOOMatrixKernel()
169 __global__ void COOMatrixToSparseTensorKernel2D(const int* coo_rows, in COOMatrixToSparseTensorKernel2D()
193 __global__ void COOMatrixToSparseTensorKernel3D( in COOMatrixToSparseTensorKernel3D()
259 __global__ void CSRSparseMatrixBatchMulVecKernel3D( in CSRSparseMatrixBatchMulVecKernel3D()
370 __global__ void CSRSparseMatrixSoftmaxKernel2D(const int rows, in CSRSparseMatrixSoftmaxKernel2D()
395 __global__ void CSRSparseMatrixSoftmaxKernel3D( in CSRSparseMatrixSoftmaxKernel3D()
545 __global__ void CSRSparseMatrixSoftmaxGradKernel2D( in CSRSparseMatrixSoftmaxGradKernel2D()
564 __global__ void CSRSparseMatrixSoftmaxGradKernel3D( in CSRSparseMatrixSoftmaxGradKernel3D()
|