| /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()
|
| D | kernel-call.cu | 5 __global__ void g1(int x) {} in g1()
|
| /external/tensorflow/tensorflow/core/kernels/ |
| D | population_count_op_gpu.cu.cc | 37 __global__ void PopulationCountKernel(const int size, const T* input, in PopulationCountKernel()
43 __global__ void PopulationCountKernel(const int size, const int8* input, in PopulationCountKernel()
52 __global__ void PopulationCountKernel(const int size, const int16* input, in PopulationCountKernel()
61 __global__ void PopulationCountKernel<int64>(const int size, const int64* input, in PopulationCountKernel()
|
| D | compare_and_bitpack_op_gpu.cu.cc | 36 __global__ void CompareAndBitpackKernel(const int size, const T* threshold, in CompareAndBitpackKernel()
58 __global__ void CompareAndBitpackKernel<bool>(const int size, in CompareAndBitpackKernel()
80 __global__ void CompareAndBitpackKernel<float>(const int size, in CompareAndBitpackKernel()
97 __global__ void CompareAndBitpackKernel<double>(const int size, in CompareAndBitpackKernel()
|
| D | bias_op_gpu.cu.cc | 56 __global__ void BiasNHWCKernel(int32 nthreads, const T* input, const T* bias, in BiasNHWCKernel()
65 __global__ void BiasNCHWKernel(int32 nthreads, const T* input, const T* bias, in BiasNCHWKernel()
102 __global__ void BiasGradNHWC_Naive(int32 nthreads, const T* output_backprop, in BiasGradNHWC_Naive()
112 __global__ void BiasGradNCHW_Naive(int32 nthreads, const T* output_backprop, in BiasGradNCHW_Naive()
125 __global__ void BiasGradNHWC_SharedAtomics(int32 nthreads, in BiasGradNHWC_SharedAtomics()
148 __global__ void BiasGradNCHW_SharedAtomics(const T* output_backprop, in BiasGradNCHW_SharedAtomics()
|
| D | maxpooling_op_gpu.cu.cc | 66 __global__ void MaxPoolForwardNCHW( in MaxPoolForwardNCHW()
108 __global__ void MaxPoolForwardNoMaskKernel_NCHW_VECT_C( in MaxPoolForwardNoMaskKernel_NCHW_VECT_C()
140 __global__ void MaxPoolForwardNHWC( in MaxPoolForwardNHWC()
179 __global__ void MaxPoolBackwardNoMaskNHWC( in MaxPoolBackwardNoMaskNHWC()
240 __global__ void MaxPoolBackward(const int nthreads, const dtype* top_diff, in MaxPoolBackward()
266 __global__ void MaxPoolGradBackwardNoMaskNCHW( in MaxPoolGradBackwardNoMaskNCHW()
306 __global__ void MaxPoolGradBackwardNoMaskNHWC( in MaxPoolGradBackwardNoMaskNHWC()
367 __global__ void MaxPoolGradBackward(const int nthreads, const dtype* top_diff, in MaxPoolGradBackward()
|
| D | cwise_op_clip_gpu.cu.cc | 27 __global__ void UnaryClipCustomKernel(const int32 size_in, const T *in0, in UnaryClipCustomKernel()
36 __global__ void BinaryRightClipCustomKernel(const int32 size_in, const T *in0, in BinaryRightClipCustomKernel()
46 __global__ void BinaryLeftClipCustomKernel(const int32 size_in, const T *in0, in BinaryLeftClipCustomKernel()
|
| D | resize_nearest_neighbor_op_gpu.cu.cc | 36 __global__ void ResizeNearestNeighborNHWC( in ResizeNearestNeighborNHWC()
67 __global__ void LegacyResizeNearestNeighborNHWC( in LegacyResizeNearestNeighborNHWC()
96 __global__ void ResizeNearestNeighborBackwardNHWC( in ResizeNearestNeighborBackwardNHWC()
127 __global__ void LegacyResizeNearestNeighborBackwardNHWC( in LegacyResizeNearestNeighborBackwardNHWC()
|
| D | fused_batch_norm_op.cu.cc | 29 __global__ void VarianceToInvVarianceKernel(int nthreads, const T* input, in VarianceToInvVarianceKernel()
47 __global__ void InvVarianceToVarianceKernel(int nthreads, double epsilon, in InvVarianceToVarianceKernel()
|
| D | matrix_set_diag_op_gpu.cu.cc | 30 __global__ void MatrixSetDiagKernel(const int num_threads, const int m, in MatrixSetDiagKernel()
43 __global__ void MatrixCopyInputAndSetDiagKernel( in MatrixCopyInputAndSetDiagKernel()
|
| D | diag_op_gpu.cu.cc | 31 __global__ void DiagCudaKernel(const int num_threads, const int64 size, in DiagCudaKernel()
85 __global__ void DiagPartCudaKernel(const int num_threads, const int64 size, in DiagPartCudaKernel()
|
| D | resize_bilinear_op_gpu.cu.cc | 36 __global__ void ResizeBilinearKernel(const int32 nthreads, const T* images, in ResizeBilinearKernel()
88 __global__ void ResizeBilinearGradKernel( in ResizeBilinearGradKernel()
150 __global__ void LegacyResizeBilinearKernel(const int32 nthreads, in LegacyResizeBilinearKernel()
202 __global__ void LegacyResizeBilinearGradKernel( in LegacyResizeBilinearGradKernel()
|
| D | depthtospace_op_gpu.cu.cc | 34 __global__ void D2S_NHWC(const int32 nthreads, in D2S_NHWC()
65 __global__ void D2S_NCHW(const int32 nthreads, in D2S_NCHW()
102 __global__ void D2S_NCHW_LOOP(const int32 nthreads, in D2S_NCHW_LOOP()
|
| D | spacetodepth_op_gpu.cu.cc | 33 __global__ void S2D_NHWC(const int32 nthreads, const dtype* input_ptr, 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 | 35 __global__ void UpperBoundKernel(const T* sorted_inputs, int batch_size, in UpperBoundKernel()
47 __global__ void LowerBoundKernel(const T* sorted_inputs, int batch_size, in LowerBoundKernel()
|
| D | split_lib_gpu.cu.cc | 78 __global__ void SplitOpKernel(const T* input, int32 prefix_dim_size, in SplitOpKernel()
116 __global__ void split_v_kernel(const T* input_ptr, in split_v_kernel()
173 __global__ void SplitVOpKernel_fixed(const T* input, int32 prefix_dim_size, in SplitVOpKernel_fixed()
|
| D | relu_op_gpu.cu.cc | 37 __global__ void ReluGradHalfKernel(const Eigen::half* gradient, in ReluGradHalfKernel()
115 __global__ void Relu_int8x4_kernel(int vect_count, const int32* input, in Relu_int8x4_kernel()
|
| /external/tensorflow/tensorflow/core/util/ |
| D | cuda_kernel_helper_test.cu.cc | 43 __global__ void SetOutbufZero(CudaLaunchConfig config, int* outbuf) { in SetOutbufZero()
48 __global__ void Count1D(CudaLaunchConfig config, int bufsize, int* outbuf) { in Count1D()
56 __global__ void Count2D(Cuda2DLaunchConfig config, int bufsize, int* outbuf) { in Count2D()
70 __global__ void Count3D(Cuda3DLaunchConfig config, int bufsize, int* outbuf) { in Count3D()
92 __global__ void CudaShuffleGetSrcLaneTest(unsigned* failure_count) { in CudaShuffleGetSrcLaneTest()
|
| /external/eigen/unsupported/Eigen/CXX11/src/Tensor/ |
| D | TensorReductionCuda.h | 114 __global__ void ReductionInitKernel(const CoeffType val, Index num_preserved_coeffs, CoeffType* out… in ReductionInitKernel()
125 __global__ void FullReductionKernel(Reducer reducer, const Self input, Index num_coeffs, in FullReductionKernel()
191 __global__ void ReductionInitFullReduxKernelHalfFloat(Reducer reducer, const Self input, Index num_… in ReductionInitFullReduxKernelHalfFloat()
204 __global__ void ReductionInitKernelHalfFloat(Reducer reducer, const Self input, Index num_coeffs, h… in ReductionInitKernelHalfFloat()
219 __global__ void FullReductionKernelHalfFloat(Reducer reducer, const Self input, Index num_coeffs, in FullReductionKernelHalfFloat()
264 __global__ void ReductionCleanupKernelHalfFloat(Op& reducer, half* output, half2* scratch) { in ReductionCleanupKernelHalfFloat()
374 __global__ void InnerReductionKernel(Reducer reducer, const Self input, Index num_coeffs_to_reduce,…
446 __global__ void InnerReductionKernelHalfFloat(Reducer reducer, const Self input, Index num_coeffs_t…
667 __global__ void OuterReductionKernel(Reducer reducer, const Self input, Index num_coeffs_to_reduce,…
|