/dports/devel/hyperscan/boost_1_75_0/boost/fiber/cuda/ |
H A D | waitfor.hpp | 37 static void trampoline( cudaStream_t st, cudaError_t status, void * vp) { in trampoline() 44 single_stream_rendezvous( cudaStream_t st) { in single_stream_rendezvous() 54 void notify( cudaStream_t st, cudaError_t status) noexcept { in notify() 63 std::tuple< cudaStream_t, cudaError_t > wait() { in wait() 72 cudaStream_t st_{}; 82 for ( cudaStream_t st : stx_) { 93 void notify( cudaStream_t st, cudaError_t status) noexcept { in notify() 103 std::vector< std::tuple< cudaStream_t, cudaError_t > > wait() { in wait() 112 std::set< cudaStream_t > stx_; 121 std::tuple< cudaStream_t, cudaError_t > waitfor_all( cudaStream_t st) { in waitfor_all() [all …]
|
/dports/science/py-scipy/scipy-1.7.1/scipy/_lib/boost/boost/fiber/cuda/ |
H A D | waitfor.hpp | 37 static void trampoline( cudaStream_t st, cudaError_t status, void * vp) { in trampoline() 44 single_stream_rendezvous( cudaStream_t st) { in single_stream_rendezvous() 54 void notify( cudaStream_t st, cudaError_t status) noexcept { in notify() 63 std::tuple< cudaStream_t, cudaError_t > wait() { in wait() 72 cudaStream_t st_{}; 82 for ( cudaStream_t st : stx_) { 93 void notify( cudaStream_t st, cudaError_t status) noexcept { in notify() 103 std::vector< std::tuple< cudaStream_t, cudaError_t > > wait() { in wait() 112 std::set< cudaStream_t > stx_; 121 std::tuple< cudaStream_t, cudaError_t > waitfor_all( cudaStream_t st) { in waitfor_all() [all …]
|
/dports/math/stanmath/math-4.2.0/lib/boost_1.75.0/boost/fiber/cuda/ |
H A D | waitfor.hpp | 37 static void trampoline( cudaStream_t st, cudaError_t status, void * vp) { in trampoline() 44 single_stream_rendezvous( cudaStream_t st) { in single_stream_rendezvous() 54 void notify( cudaStream_t st, cudaError_t status) noexcept { in notify() 63 std::tuple< cudaStream_t, cudaError_t > wait() { in wait() 72 cudaStream_t st_{}; 82 for ( cudaStream_t st : stx_) { 93 void notify( cudaStream_t st, cudaError_t status) noexcept { in notify() 103 std::vector< std::tuple< cudaStream_t, cudaError_t > > wait() { in wait() 112 std::set< cudaStream_t > stx_; 121 std::tuple< cudaStream_t, cudaError_t > waitfor_all( cudaStream_t st) { in waitfor_all() [all …]
|
/dports/devel/boost-libs/boost_1_72_0/boost/fiber/cuda/ |
H A D | waitfor.hpp | 37 static void trampoline( cudaStream_t st, cudaError_t status, void * vp) { in trampoline() 44 single_stream_rendezvous( cudaStream_t st) { in single_stream_rendezvous() 54 void notify( cudaStream_t st, cudaError_t status) noexcept { in notify() 63 std::tuple< cudaStream_t, cudaError_t > wait() { in wait() 72 cudaStream_t st_{}; 82 for ( cudaStream_t st : stx_) { 93 void notify( cudaStream_t st, cudaError_t status) noexcept { in notify() 103 std::vector< std::tuple< cudaStream_t, cudaError_t > > wait() { in wait() 112 std::set< cudaStream_t > stx_; 121 std::tuple< cudaStream_t, cudaError_t > waitfor_all( cudaStream_t st) { in waitfor_all() [all …]
|
/dports/devel/boost-python-libs/boost_1_72_0/boost/fiber/cuda/ |
H A D | waitfor.hpp | 37 static void trampoline( cudaStream_t st, cudaError_t status, void * vp) { in trampoline() 44 single_stream_rendezvous( cudaStream_t st) { in single_stream_rendezvous() 54 void notify( cudaStream_t st, cudaError_t status) noexcept { in notify() 63 std::tuple< cudaStream_t, cudaError_t > wait() { in wait() 72 cudaStream_t st_{}; 82 for ( cudaStream_t st : stx_) { 93 void notify( cudaStream_t st, cudaError_t status) noexcept { in notify() 103 std::vector< std::tuple< cudaStream_t, cudaError_t > > wait() { in wait() 112 std::set< cudaStream_t > stx_; 121 std::tuple< cudaStream_t, cudaError_t > waitfor_all( cudaStream_t st) { in waitfor_all() [all …]
|
/dports/math/py-pystan/pystan-2.19.0.0/pystan/stan/lib/stan_math/lib/boost_1.69.0/boost/fiber/cuda/ |
H A D | waitfor.hpp | 37 static void trampoline( cudaStream_t st, cudaError_t status, void * vp) { 44 single_stream_rendezvous( cudaStream_t st) { 54 void notify( cudaStream_t st, cudaError_t status) noexcept { 63 std::tuple< cudaStream_t, cudaError_t > wait() { 72 cudaStream_t st_{}; 82 for ( cudaStream_t st : stx_) { 93 void notify( cudaStream_t st, cudaError_t status) noexcept { 103 std::vector< std::tuple< cudaStream_t, cudaError_t > > wait() { 112 std::set< cudaStream_t > stx_; 121 std::tuple< cudaStream_t, cudaError_t > waitfor_all( cudaStream_t st) { [all …]
|
/dports/devel/boost-docs/boost_1_72_0/boost/fiber/cuda/ |
H A D | waitfor.hpp | 37 static void trampoline( cudaStream_t st, cudaError_t status, void * vp) { in trampoline() 44 single_stream_rendezvous( cudaStream_t st) { in single_stream_rendezvous() 54 void notify( cudaStream_t st, cudaError_t status) noexcept { in notify() 63 std::tuple< cudaStream_t, cudaError_t > wait() { in wait() 72 cudaStream_t st_{}; 82 for ( cudaStream_t st : stx_) { 93 void notify( cudaStream_t st, cudaError_t status) noexcept { in notify() 103 std::vector< std::tuple< cudaStream_t, cudaError_t > > wait() { in wait() 112 std::set< cudaStream_t > stx_; 121 std::tuple< cudaStream_t, cudaError_t > waitfor_all( cudaStream_t st) { in waitfor_all() [all …]
|
/dports/math/faiss/faiss-1.7.1/faiss/gpu/ |
H A D | GpuResources.h | 115 cudaStream_t stream; 119 AllocInfo makeDevAlloc(AllocType at, cudaStream_t st); 122 AllocInfo makeTempAlloc(AllocType at, cudaStream_t st); 138 cudaStream_t st, in AllocRequest() 155 cudaStream_t str, 171 cudaStream_t stream; 192 virtual cudaStream_t getDefaultStream(int device) = 0; 221 virtual cudaStream_t getAsyncCopyStream(int device) = 0; 231 cudaStream_t getDefaultStreamCurrentDevice(); 248 std::vector<cudaStream_t> getAlternateStreamsCurrentDevice(); [all …]
|
H A D | StandardGpuResources.h | 49 void setDefaultStream(int device, cudaStream_t stream) override; 59 cudaStream_t getDefaultStream(int device) override; 77 std::vector<cudaStream_t> getAlternateStreams(int device) override; 93 cudaStream_t getAsyncCopyStream(int device) override; 112 std::unordered_map<int, cudaStream_t> defaultStreams_; 116 std::unordered_map<int, cudaStream_t> userDefaultStreams_; 119 std::unordered_map<int, std::vector<cudaStream_t>> alternateStreams_; 122 std::unordered_map<int, cudaStream_t> asyncCopyStreams_; 173 void setDefaultStream(int device, cudaStream_t stream); 188 cudaStream_t getDefaultStream(int device);
|
/dports/science/qmcpack/qmcpack-3.11.0/src/QMCWaveFunctions/detail/CUDA/ |
H A D | matrix_update_helper.hpp | 30 cudaError_t copyAinvRow_saveGL_cuda(cudaStream_t& hstream, 43 cudaError_t copyAinvRow_saveGL_cuda(cudaStream_t& hstream, 56 cudaError_t copyAinvRow_saveGL_cuda(cudaStream_t& hstream, 83 cudaError_t calcGradients_cuda(cudaStream_t& hstream, 90 cudaError_t calcGradients_cuda(cudaStream_t& hstream, 97 cudaError_t calcGradients_cuda(cudaStream_t& hstream, 104 cudaError_t calcGradients_cuda(cudaStream_t& hstream, 179 cudaError_t applyW_batched(cudaStream_t& hstream, 186 cudaError_t applyW_batched(cudaStream_t& hstream, 193 cudaError_t applyW_batched(cudaStream_t& hstream, [all …]
|
H A D | delayed_update_helper.h | 25 cudaStream_t& hstream); 30 cudaStream_t& hstream); 35 cudaStream_t& hstream); 40 cudaStream_t& hstream); 44 void make_identity_matrix_cuda(const int nrows, double* mat, const int lda, cudaStream_t& hstream); 46 …tity_matrix_cuda(const int nrows, std::complex<double>* mat, const int lda, cudaStream_t& hstream); 50 …gonal_cuda(const int nrows, const double* mat, const int lda, double* diag, cudaStream_t& hstream); 52 …const std::complex<double>* mat, const int lda, std::complex<double>* diag, cudaStream_t& hstream); 56 … ncols, const double* mat_in, const int lda, float* mat_out, const int ldb, cudaStream_t& hstream); 58 … ncols, const float* mat_in, const int lda, double* mat_out, const int ldb, cudaStream_t& hstream); [all …]
|
/dports/multimedia/schroedinger/schroedinger-1.0.11/schroedinger/cuda/ |
H A D | cudawavelet.cu | 3 extern void cuda_iwt_13_5(int16_t *d_data, int lwidth, int lheight, int stride, cudaStream_t stream… 4 extern void cuda_iiwt_13_5(int16_t *d_data, int lwidth, int lheight, int stride, cudaStream_t strea… 5 extern void cuda_iwt_5_3(int16_t *d_data, int lwidth, int lheight, int stride, cudaStream_t stream); 6 extern void cuda_iiwt_5_3(int16_t *d_data, int lwidth, int lheight, int stride, cudaStream_t stream… 7 extern void cuda_iwt_9_3(int16_t *d_data, int lwidth, int lheight, int stride, cudaStream_t stream); 8 extern void cuda_iiwt_9_3(int16_t *d_data, int lwidth, int lheight, int stride, cudaStream_t stream… 9 extern void cuda_iwt_9_7(int16_t *d_data, int lwidth, int lheight, int stride, cudaStream_t stream); 10 extern void cuda_iiwt_9_7(int16_t *d_data, int lwidth, int lheight, int stride, cudaStream_t stream… 11 extern void cuda_iwt_fidelity(int16_t *d_data, int lwidth, int lheight, int stride, cudaStream_t st… 12 extern void cuda_iiwt_fidelity(int16_t *d_data, int lwidth, int lheight, int stride, cudaStream_t s… [all …]
|
/dports/math/stanmath/math-4.2.0/lib/sundials_5.7.0/include/sundials/ |
H A D | sundials_cuda_policies.hpp | 35 virtual const cudaStream_t* stream() const = 0; 51 CudaThreadDirectExecPolicy(const size_t blockDim, const cudaStream_t stream = 0) in CudaThreadDirectExecPolicy() 70 virtual const cudaStream_t* stream() const in stream() 82 const cudaStream_t stream_; 94 …CudaGridStrideExecPolicy(const size_t blockDim, const size_t gridDim, const cudaStream_t stream = … in CudaGridStrideExecPolicy() 112 virtual const cudaStream_t* stream() const in stream() 125 const cudaStream_t stream_; 140 …CudaBlockReduceExecPolicy(const size_t blockDim, const size_t gridDim = 0, const cudaStream_t stre… in CudaBlockReduceExecPolicy() 167 virtual const cudaStream_t* stream() const in stream() 180 const cudaStream_t stream_;
|
/dports/science/cantera/cantera-2.5.1-611-gc4d6ecc15/ext/sundials/include/sundials/ |
H A D | sundials_cuda_policies.hpp | 35 virtual cudaStream_t stream() const = 0; 51 CudaThreadDirectExecPolicy(const size_t blockDim, const cudaStream_t stream = 0) in CudaThreadDirectExecPolicy() 70 virtual cudaStream_t stream() const in stream() 81 const cudaStream_t stream_; 94 …CudaGridStrideExecPolicy(const size_t blockDim, const size_t gridDim, const cudaStream_t stream = … in CudaGridStrideExecPolicy() 112 virtual cudaStream_t stream() const in stream() 123 const cudaStream_t stream_; 140 …CudaBlockReduceExecPolicy(const size_t blockDim, const size_t gridDim = 0, const cudaStream_t stre… in CudaBlockReduceExecPolicy() 167 virtual cudaStream_t stream() const in stream() 178 const cudaStream_t stream_;
|
/dports/math/sundials/sundials-5.7.0/include/sundials/ |
H A D | sundials_cuda_policies.hpp | 35 virtual const cudaStream_t* stream() const = 0; 51 CudaThreadDirectExecPolicy(const size_t blockDim, const cudaStream_t stream = 0) in CudaThreadDirectExecPolicy() 70 virtual const cudaStream_t* stream() const in stream() 82 const cudaStream_t stream_; 94 …CudaGridStrideExecPolicy(const size_t blockDim, const size_t gridDim, const cudaStream_t stream = … in CudaGridStrideExecPolicy() 112 virtual const cudaStream_t* stream() const in stream() 125 const cudaStream_t stream_; 140 …CudaBlockReduceExecPolicy(const size_t blockDim, const size_t gridDim = 0, const cudaStream_t stre… in CudaBlockReduceExecPolicy() 167 virtual const cudaStream_t* stream() const in stream() 180 const cudaStream_t stream_;
|
/dports/graphics/opencv/opencv-4.5.3/contrib/modules/cudawarping/src/cuda/ |
H A D | warp.cu | 99 … <class Transform> void buildWarpMaps_caller(PtrStepSzf xmap, PtrStepSzf ymap, cudaStream_t stream) in buildWarpMaps_caller() 111 …buildWarpAffineMaps_gpu(float coeffs[2 * 3], PtrStepSzf xmap, PtrStepSzf ymap, cudaStream_t stream) in buildWarpAffineMaps_gpu() 118 …WarpPerspectiveMaps_gpu(float coeffs[3 * 3], PtrStepSzf xmap, PtrStepSzf ymap, cudaStream_t stream) in buildWarpPerspectiveMaps_gpu() 143 … void call(PtrStepSz<T> src, PtrStepSz<T> dst, const float* borderValue, cudaStream_t stream, bool) in call() 266 …hole, int xoff, int yoff, PtrStepSz<T> dst, const float* borderValue, cudaStream_t stream, bool cc… in call() 277 int borderMode, const float* borderValue, cudaStream_t stream, bool cc20) in warp_caller() 279 …hole, int xoff, int yoff, PtrStepSz<T> dst, const float* borderValue, cudaStream_t stream, bool cc… in warp_caller() 311 … int borderMode, const float* borderValue, cudaStream_t stream, bool cc20) in warpAffine_gpu() 318 …Szb dst, int interpolation, int borderMode, const float* borderValue, cudaStream_t stream, bool cc… 320 …Szb dst, int interpolation, int borderMode, const float* borderValue, cudaStream_t stream, bool cc… [all …]
|
H A D | pyr_down.cu | 195 template void pyrDown_gpu<uchar>(PtrStepSzb src, PtrStepSzb dst, cudaStream_t stream); 197 template void pyrDown_gpu<uchar3>(PtrStepSzb src, PtrStepSzb dst, cudaStream_t stream); 198 template void pyrDown_gpu<uchar4>(PtrStepSzb src, PtrStepSzb dst, cudaStream_t stream); 205 template void pyrDown_gpu<ushort>(PtrStepSzb src, PtrStepSzb dst, cudaStream_t stream); 210 template void pyrDown_gpu<short>(PtrStepSzb src, PtrStepSzb dst, cudaStream_t stream); 212 template void pyrDown_gpu<short3>(PtrStepSzb src, PtrStepSzb dst, cudaStream_t stream); 213 template void pyrDown_gpu<short4>(PtrStepSzb src, PtrStepSzb dst, cudaStream_t stream); 215 template void pyrDown_gpu<int>(PtrStepSzb src, PtrStepSzb dst, cudaStream_t stream); 217 template void pyrDown_gpu<int3>(PtrStepSzb src, PtrStepSzb dst, cudaStream_t stream); 218 template void pyrDown_gpu<int4>(PtrStepSzb src, PtrStepSzb dst, cudaStream_t stream); [all …]
|
H A D | pyr_up.cu | 164 template void pyrUp_gpu<uchar>(PtrStepSzb src, PtrStepSzb dst, cudaStream_t stream); 166 template void pyrUp_gpu<uchar3>(PtrStepSzb src, PtrStepSzb dst, cudaStream_t stream); 167 template void pyrUp_gpu<uchar4>(PtrStepSzb src, PtrStepSzb dst, cudaStream_t stream); 174 template void pyrUp_gpu<ushort>(PtrStepSzb src, PtrStepSzb dst, cudaStream_t stream); 176 template void pyrUp_gpu<ushort3>(PtrStepSzb src, PtrStepSzb dst, cudaStream_t stream); 179 template void pyrUp_gpu<short>(PtrStepSzb src, PtrStepSzb dst, cudaStream_t stream); 181 template void pyrUp_gpu<short3>(PtrStepSzb src, PtrStepSzb dst, cudaStream_t stream); 182 template void pyrUp_gpu<short4>(PtrStepSzb src, PtrStepSzb dst, cudaStream_t stream); 189 template void pyrUp_gpu<float>(PtrStepSzb src, PtrStepSzb dst, cudaStream_t stream); 191 template void pyrUp_gpu<float3>(PtrStepSzb src, PtrStepSzb dst, cudaStream_t stream); [all …]
|
/dports/math/faiss/faiss-1.7.1/faiss/gpu/impl/ |
H A D | BroadcastSum.cuh | 19 cudaStream_t stream); 24 cudaStream_t stream); 30 cudaStream_t stream); 35 cudaStream_t stream); 43 cudaStream_t stream); 49 cudaStream_t stream);
|
/dports/devel/thrust/thrust-1.9.5/thrust/system/cuda/detail/ |
H A D | par.h | 44 cudaStream_t 52 cudaStream_t 77 cudaStream_t stream; 81 execute_on_stream_base(cudaStream_t stream_ = default_stream()) 86 on(cudaStream_t const &s) const in on() 95 cudaStream_t 126 execute_on_stream(cudaStream_t stream) : base_t(stream){}; in execute_on_stream() 147 on(cudaStream_t const &stream) const in on()
|
/dports/graphics/opencv/opencv-4.5.3/contrib/modules/cudafeatures2d/src/cuda/ |
H A D | bf_radius_match.cu | 134 cudaStream_t stream) in matchUnrolled() 224 cudaStream_t stream) in match() 242 cudaStream_t stream) in match() 277 cudaStream_t stream) in matchDispatcher() 308 cudaStream_t stream) in matchDispatcher() 341 cudaStream_t stream) in matchL1_gpu() 366 cudaStream_t stream) in matchL2_gpu() 391 cudaStream_t stream) in matchHamming_gpu() 415 cudaStream_t stream) in matchL1_gpu() 431 cudaStream_t stream) in matchL2_gpu() [all …]
|
/dports/science/qmcpack/qmcpack-3.11.0/src/einspline/ |
H A D | multi_bspline_eval_cuda.h | 88 float *coefs, int device_nr, cudaStream_t s); 109 float *coefs, int device_nr, cudaStream_t s); 120 double *coefs, int device_nr, cudaStream_t s); 131 double *coefs, int device_nr, cudaStream_t s); 147 double *coefs, int device_nr, cudaStream_t s); 158 double *coefs, int device_nr, cudaStream_t s); 169 float *pos_d, complex_float *vals_d[], int num, float *coefs, int device_nr, cudaStream_t s); 186 float *coefs, int device_nr, cudaStream_t s); 198 double *pos_d, complex_double *vals_d[], int num, double *coefs, int device_nr, cudaStream_t s); 214 …plex_double *grad_lapl_d[], int num, int row_stride, double *coefs, int device_nr, cudaStream_t s);
|
/dports/math/faiss/faiss-1.7.1/faiss/gpu/utils/ |
H A D | StackDeviceMemory.h | 36 void* allocMemory(cudaStream_t stream, size_t size); 37 void deallocMemory(int device, cudaStream_t, size_t size, void* p); 46 inline Range(char* s, char* e, cudaStream_t str) in Range() 52 cudaStream_t stream_; 67 char* getAlloc(size_t size, cudaStream_t stream); 70 void returnAlloc(char* p, size_t size, cudaStream_t stream);
|
/dports/misc/tvm/incubator-tvm-0.6.1/src/runtime/cuda/ |
H A D | cuda_device_api.cc | 137 cudaStream_t cu_stream = static_cast<cudaStream_t>(stream); in CopyDataFromTo() 162 cudaStream_t retval; in CreateStream() 169 cudaStream_t cu_stream = static_cast<cudaStream_t>(stream); in FreeStream() 175 cudaStream_t src_stream = static_cast<cudaStream_t>(event_src); in SyncStreamFromTo() 176 cudaStream_t dst_stream = static_cast<cudaStream_t>(event_dst); in SyncStreamFromTo() 186 CUDA_CALL(cudaStreamSynchronize(static_cast<cudaStream_t>(stream))); in StreamSync() 191 ->stream = static_cast<cudaStream_t>(stream); in SetStream() 213 cudaStream_t stream) { in GPUCopy()
|
/dports/misc/py-tvm/incubator-tvm-0.6.1/src/runtime/cuda/ |
H A D | cuda_device_api.cc | 137 cudaStream_t cu_stream = static_cast<cudaStream_t>(stream); in CopyDataFromTo() 162 cudaStream_t retval; in CreateStream() 169 cudaStream_t cu_stream = static_cast<cudaStream_t>(stream); in FreeStream() 175 cudaStream_t src_stream = static_cast<cudaStream_t>(event_src); in SyncStreamFromTo() 176 cudaStream_t dst_stream = static_cast<cudaStream_t>(event_dst); in SyncStreamFromTo() 186 CUDA_CALL(cudaStreamSynchronize(static_cast<cudaStream_t>(stream))); in StreamSync() 191 ->stream = static_cast<cudaStream_t>(stream); in SetStream() 213 cudaStream_t stream) { in GPUCopy()
|