Searched refs:TORCH_CUDA_CU_API (Results 1 – 11 of 11) sorted by relevance
202 TORCH_CUDA_CU_API void trsm<float>(CUDABLAS_TRSM_ARGTYPES(float));204 TORCH_CUDA_CU_API void trsm<double>(CUDABLAS_TRSM_ARGTYPES(double));206 TORCH_CUDA_CU_API void trsm<c10::complex<float>>(CUDABLAS_TRSM_ARGTYPES(c10::complex<float>));208 TORCH_CUDA_CU_API void trsm<c10::complex<double>>(CUDABLAS_TRSM_ARGTYPES(c10::complex<double>));222 TORCH_CUDA_CU_API void trsmBatched<float>(CUDABLAS_TRSM_BATCHED_ARGTYPES(float));224 TORCH_CUDA_CU_API void trsmBatched<double>(CUDABLAS_TRSM_BATCHED_ARGTYPES(double));226 TORCH_CUDA_CU_API void trsmBatched<c10::complex<float>>(CUDABLAS_TRSM_BATCHED_ARGTYPES(c10::complex…228 TORCH_CUDA_CU_API void trsmBatched<c10::complex<double>>(CUDABLAS_TRSM_BATCHED_ARGTYPES(c10::comple…298 TORCH_CUDA_CU_API void getrsBatched<float>(CUDABLAS_GETRS_ARGTYPES(float));300 TORCH_CUDA_CU_API void getrsBatched<double>(CUDABLAS_GETRS_ARGTYPES(double));[all …]
8 TORCH_CUDA_CU_API void sleep(int64_t cycles);11 TORCH_CUDA_CU_API void flush_icache();
7 TORCH_CUDA_CU_API void Xcoo2csr(15 TORCH_CUDA_CU_API void csrmm2(33 TORCH_CUDA_CU_API void CreateIdentityPermutation(int64_t nnz, int* P);34 TORCH_CUDA_CU_API void Xcsrsort_bufferSizeExt(41 TORCH_CUDA_CU_API void Xcsrsort(49 TORCH_CUDA_CU_API void Xcoosort_bufferSizeExt(56 TORCH_CUDA_CU_API void XcoosortByRow(
16 TORCH_CUDA_CU_API std::vector<at::Tensor>& broadcast_out(19 TORCH_CUDA_CU_API std::vector<at::Tensor> broadcast(22 TORCH_CUDA_CU_API tensor_list2d broadcast_coalesced(27 TORCH_CUDA_CU_API std::vector<at::Tensor>& scatter_out(34 TORCH_CUDA_CU_API std::vector<at::Tensor> scatter(42 TORCH_CUDA_CU_API at::Tensor& gather_out(47 TORCH_CUDA_CU_API at::Tensor gather(
12 TORCH_CUDA_CU_API void _record_memory_history(19 TORCH_CUDA_CU_API void _record_memory_history(25 TORCH_CUDA_CU_API std::string _memory_snapshot_pickled();
119 #define TORCH_CUDA_CU_API C10_EXPORT macro121 #define TORCH_CUDA_CU_API C10_IMPORT macro135 #define TORCH_CUDA_CU_API C10_EXPORT macro138 #define TORCH_CUDA_CU_API C10_IMPORT macro
17 TORCH_CUDA_CU_API void codegenOutputQuery(25 struct TORCH_CUDA_CU_API FusedKernelCUDA
16 struct TORCH_CUDA_CU_API Scatter : public Node {35 struct TORCH_CUDA_CU_API Gather : public Node {
12 TORCH_CUDA_CU_API bool CudaIPCCollect();49 TORCH_CUDA_CU_API at::DataPtr GetNewRefCountedSentData(
9 TORCH_CUDA_CU_API bool maybeOverlappingIndices(const at::TensorBase &t);
197 class TORCH_CUDA_CU_API CudaCodeGen : public CodeGen {