| /libCEED/include/ceed/jit-source/hip/ |
| H A D | hip-ref-basis-nontensor.h | 21 extern "C" __global__ void Interp(const CeedInt num_elem, const CeedScalar *__restrict__ d_B, const… in Interp()
29 …C" __global__ void InterpTranspose(const CeedInt num_elem, const CeedScalar *__restrict__ d_B, con… in InterpTranspose()
40 extern "C" __global__ void Deriv(const CeedInt num_elem, const CeedScalar *__restrict__ d_B, const … in Deriv()
48 …"C" __global__ void DerivTranspose(const CeedInt num_elem, const CeedScalar *__restrict__ d_B, con… in DerivTranspose()
|
| H A D | hip-ref-basis-nontensor-templates.h | 17 … const CeedInt strides_comp_V, const CeedInt strides_q_comp_V, const CeedScalar *__restrict__ d_B, in Contract()
44 … const CeedInt strides_comp_V, const CeedInt strides_q_comp_U, const CeedScalar *__restrict__ d_B, in ContractTranspose()
|
| H A D | hip-shared-basis-read-write-templates.h | 16 inline __device__ void LoadMatrix(SharedData_Hip &data, const CeedScalar *__restrict__ d_B, CeedSca… in LoadMatrix()
|
| H A D | hip-gen-templates.h | 16 inline __device__ void LoadMatrix(SharedData_Hip &data, const CeedScalar *__restrict__ d_B, CeedSca… in LoadMatrix()
|
| /libCEED/include/ceed/jit-source/cuda/ |
| H A D | cuda-ref-basis-nontensor.h | 21 extern "C" __global__ void Interp(const CeedInt num_elem, const CeedScalar *__restrict__ d_B, const… in Interp()
29 …C" __global__ void InterpTranspose(const CeedInt num_elem, const CeedScalar *__restrict__ d_B, con… in InterpTranspose()
40 extern "C" __global__ void Deriv(const CeedInt num_elem, const CeedScalar *__restrict__ d_B, const … in Deriv()
48 …"C" __global__ void DerivTranspose(const CeedInt num_elem, const CeedScalar *__restrict__ d_B, con… in DerivTranspose()
|
| H A D | cuda-ref-basis-nontensor-templates.h | 17 … const CeedInt strides_comp_V, const CeedInt strides_q_comp_V, const CeedScalar *__restrict__ d_B, in Contract()
44 … const CeedInt strides_comp_V, const CeedInt strides_q_comp_U, const CeedScalar *__restrict__ d_B, in ContractTranspose()
|
| H A D | cuda-shared-basis-read-write-templates.h | 16 inline __device__ void LoadMatrix(SharedData_Cuda &data, const CeedScalar *__restrict__ d_B, CeedSc… in LoadMatrix()
|
| H A D | cuda-gen-templates.h | 16 inline __device__ void LoadMatrix(SharedData_Cuda &data, const CeedScalar *__restrict__ d_B, CeedSc… in LoadMatrix()
|
| /libCEED/backends/magma/ |
| H A D | ceed-magma-gemm-nontensor.cpp | 25 …const CeedScalar *d_A, magma_int_t ldda, const CeedScalar *d_B, magma_int_t lddb, CeedScalar beta,… in magmablas_gemm()
40 … const CeedScalar *d_B, magma_int_t lddb, magma_int_t strideB, CeedScalar beta, CeedScalar *d_C, in magmablas_gemm_batched_strided()
54 …const CeedScalar *d_A, magma_int_t ldda, const CeedScalar *d_B, magma_int_t lddb, CeedScalar beta,… in devblas_gemm()
67 …dScalar alpha, const CeedScalar *d_A, magma_int_t ldda, magma_int_t strideA, const CeedScalar *d_B, in devblas_gemm_batched_strided()
84 …const CeedScalar *d_A, magma_int_t ldda, const CeedScalar *d_B, magma_int_t lddb, CeedScalar beta,… in magma_gemm_nontensor()
|
| /libCEED/include/ceed/jit-source/sycl/ |
| H A D | sycl-shared-basis-read-write-templates.h | 15 inline void loadMatrix(const CeedInt N, const CeedScalar *restrict d_B, CeedScalar *restrict B) { in loadMatrix()
|
| H A D | sycl-gen-templates.h | 20 inline void loadMatrix(const CeedInt N, const CeedScalar *restrict d_B, CeedScalar *restrict B) { in loadMatrix()
|
| /libCEED/backends/sycl-ref/ |
| H A D | ceed-sycl-ref-basis.sycl.cpp | 351 const CeedScalar *d_B = impl->d_interp; in CeedBasisApplyNonTensorInterp_Sycl() local
|