shtns_cuda.h declares transforms and initialization functions for cuda-enabled GPU. More...

#include <cuda_runtime.h>

Typedefs
typedef cudaStream_t	shtns_gpu_stream_t

Functions
void	cushtns_profiling (shtns_cfg, int on)

double	cushtns_profiling_read_time (shtns_cfg, double time_1, double time_2)

const char *	cushtns_get_cfg_info (shtns_cfg)

Transforms
void	cu_spat_to_SH (shtns_cfg shtns, double Vr, cplx Qlm, int ltr)
	Same as spat_to_SH, but working on data residing on the GPU.

void	cu_spat_to_SH_float (shtns_cfg shtns, float Vr, cplx_f Qlm, int ltr)
	Same as cu_spat_to_SH, but working on single precision data.

void	cu_SH_to_spat (shtns_cfg shtns, cplx Qlm, double Vr, int ltr)
	Same as SH_to_spat, but working on data residing on the GPU.

void	cu_SH_to_spat_float (shtns_cfg shtns, cplx_f Qlm, float Vr, int ltr)
	Same as cu_SH_to_spat, but working on single precision data.

void	cu_spat_to_SHsphtor (shtns_cfg, double Vt, double Vp, cplx Slm, cplx Tlm, int ltr)
	Same as spat_to_SHsphtor, but working on data residing on the GPU.

void	cu_spat_to_SHsphtor_float (shtns_cfg, float Vt, float Vp, cplx_f Slm, cplx_f Tlm, int ltr)

void	cu_SHsphtor_to_spat (shtns_cfg, cplx Slm, cplx Tlm, double Vt, double Vp, int ltr)
	Same as SHsphtor_to_spat, but working on data residing on the GPU.

void	cu_SHsphtor_to_spat_float (shtns_cfg, cplx_f Slm, cplx_f Tlm, float Vt, float Vp, int ltr)

void	cu_SHsph_to_spat (shtns_cfg, cplx Slm, double Vt, double *Vp, int ltr)
	Same as SHsph_to_spat, but working on data residing on the GPU.

void	cu_SHsph_to_spat_float (shtns_cfg, cplx_f Slm, float Vt, float *Vp, int ltr)

void	cu_SHtor_to_spat (shtns_cfg, cplx Tlm, double Vt, double *Vp, int ltr)
	Same as SHtor_to_spat, but working on data residing on the GPU.

void	cu_SHtor_to_spat_float (shtns_cfg, cplx_f Tlm, float Vt, float *Vp, int ltr)

void	cu_spat_to_SHqst (shtns_cfg, double Vr, double Vt, double Vp, cplx Qlm, cplx Slm, cplx Tlm, int ltr)
	Same as spat_to_SHqst, but working on data residing on the GPU.

void	cu_spat_to_SHqst_float (shtns_cfg, float Vr, float Vt, float Vp, cplx_f Qlm, cplx_f Slm, cplx_f Tlm, int ltr)

void	cu_SHqst_to_spat (shtns_cfg, cplx Qlm, cplx Slm, cplx Tlm, double Vr, double Vt, double Vp, int ltr)
	Same as SHqst_to_spat, but working on data residing on the GPU.

void	cu_SHqst_to_spat_float (shtns_cfg, cplx_f Qlm, cplx_f Slm, cplx_f Tlm, float Vr, float Vt, float Vp, int ltr)

Initialization
int	cushtns_init_gpu (shtns_cfg shtns)
	Initialize given config to work on the current (or default) GPU, allowing to call GPU transforms cu_* above, working on data residing in the memory of this GPU.

shtns_cfg	cushtns_clone (shtns_cfg shtns, shtns_gpu_stream_t compute_stream, shtns_gpu_stream_t transfer_stream)
	Clone a gpu-enabled shtns config, and assign it to different streams (to allow compute overlap and/or usage from multiple threads).

void	cushtns_set_streams (shtns_cfg shtns, shtns_gpu_stream_t compute_stream, shtns_gpu_stream_t transfer_stream)
	Set user-specified streams for compute (including fft) and transfer.

void	cushtns_release_gpu (shtns_cfg)
	Release resources needed for GPU transforms, which won't work after this call.

Detailed Description

shtns_cuda.h declares transforms and initialization functions for cuda-enabled GPU.

Typedefs

Functions

Detailed Description