def _univariate_pdf_call(cu_func, data, packed_params, get):
ndata = len(data)
nparams = len(packed_params)
func_regs = cu_func.num_regs
packed_params = util.prep_ndarray(packed_params)
data_per, params_per = util.tune_blocksize(data,
packed_params,
func_regs)
shared_mem = util.compute_shmem(data, packed_params,
data_per, params_per)
block_design = (data_per * params_per, 1, 1)
grid_design = (util.get_boxes(ndata, data_per),
util.get_boxes(nparams, params_per))
# see cufiles/univcaller.cu
#gpu_dest = to_gpu(np.zeros((ndata, nparams), dtype=np.float32))
gpu_dest = gpu_empty((ndata, nparams), dtype=np.float32)
gpu_data = data if isinstance(data, GPUArray) else to_gpu(data)
gpu_packed_params = to_gpu(packed_params)
design = np.array(((data_per, params_per) + # block design
(len(data),) +
packed_params.shape), # params spec
dtype=np.int32)
cu_func(gpu_dest,
gpu_data, gpu_packed_params, design[0],
design[1], design[2], design[3], design[4],
block=block_design, grid=grid_design, shared=shared_mem)
if get:
output = gpu_dest.get()
if nparams > 1:
output = output.reshape((nparams, ndata), order='C').T
return output
else:
return gpu_dest
def _multivariate_pdf_call(cu_func, data, packed_params, get, order,
datadim=None):
packed_params = util.prep_ndarray(packed_params)
func_regs = cu_func.num_regs
# Prep the data. Skip if gpudata ...
if isinstance(data, GPUArray):
padded_data = data
if datadim==None:
ndata, dim = data.shape
else:
ndata, dim = data.shape[0], datadim
else:
ndata, dim = data.shape
padded_data = util.pad_data(data)
nparams = len(packed_params)
data_per, params_per = util.tune_blocksize(padded_data,
packed_params,
func_regs)
blocksize = data_per * params_per
#print 'the blocksize is ' + str(blocksize)
#print 'data_per ' + str(data_per) + '. params_per ' + str(params_per)
shared_mem = util.compute_shmem(padded_data, packed_params,
data_per, params_per)
block_design = (data_per * params_per, 1, 1)
grid_design = (util.get_boxes(ndata, data_per),
util.get_boxes(nparams, params_per))
# see cufiles/mvcaller.cu
design = np.array(((data_per, params_per) + # block design
padded_data.shape + # data spec
(dim,) + # non-padded number of data columns
packed_params.shape), # params spec
dtype=np.int32)
if nparams == 1:
gpu_dest = gpu_empty(ndata, dtype=np.float32)
#gpu_dest = to_gpu(np.zeros(ndata, dtype=np.float32))
else:
gpu_dest = gpu_empty((ndata, nparams), dtype=np.float32, order='F')
#gpu_dest = to_gpu(np.zeros((ndata, nparams), dtype=np.float32, order='F'))
# Upload data if not already uploaded
if not isinstance(padded_data, GPUArray):
gpu_padded_data = to_gpu(padded_data)
else:
gpu_padded_data = padded_data
gpu_packed_params = to_gpu(packed_params)
params = (gpu_dest, gpu_padded_data, gpu_packed_params) + tuple(design)
kwds = dict(block=block_design, grid=grid_design, shared=shared_mem)
cu_func(*params, **kwds)
gpu_packed_params.gpudata.free()
if get:
if order=='F':
return gpu_dest.get()
else:
return np.asarray(gpu_dest.get(), dtype=np.float32, order='C')
#output = gpu_dest.get()
#if nparams > 1:
# output = output.reshape((nparams, ndata), order='C').T
#return output
else:
if order=='F' or nparams==1:
return gpu_dest
else:
res = gpu_transpose(util.GPUarray_reshape(gpu_dest, (nparams, ndata), "C"))
gpu_dest.gpudata.free()
return res
