def __mul__(self, other):
if cupy.isscalar(other):
self.sum_duplicates()
return self._with_data(self.data * other)
elif isspmatrix_csr(other):
self.sum_duplicates()
other.sum_duplicates()
if cusparse.check_availability('csrgemm2'):
return cusparse.csrgemm2(self, other)
elif cusparse.check_availability('csrgemm'):
return cusparse.csrgemm(self, other)
else:
raise NotImplementedError
elif csc.isspmatrix_csc(other):
self.sum_duplicates()
other.sum_duplicates()
if cusparse.check_availability('csrgemm'):
return cusparse.csrgemm(self, other.T, transb=True)
elif cusparse.check_availability('csrgemm2'):
b = other.tocsr()
b.sum_duplicates()
return cusparse.csrgemm2(self, b)
else:
raise NotImplementedError
elif base.isspmatrix(other):
return self * other.tocsr()
elif base.isdense(other):
if other.ndim == 0:
self.sum_duplicates()
return self._with_data(self.data * other)
elif other.ndim == 1:
self.sum_duplicates()
other = cupy.asfortranarray(other)
# need extra padding to ensure not stepping on the CUB bug,
# see cupy/cupy#3679 for discussion
is_cub_safe = (self.indptr.data.mem.size >
self.indptr.size * self.indptr.dtype.itemsize)
for accelerator in _accelerator.get_routine_accelerators():
if (accelerator == _accelerator.ACCELERATOR_CUB
and is_cub_safe and other.flags.c_contiguous):
return cub.device_csrmv(self.shape[0], self.shape[1],
self.nnz, self.data,
self.indptr, self.indices,
other)
if (cusparse.check_availability('csrmvEx') and self.nnz > 0
and cusparse.csrmvExIsAligned(self, other)):
# csrmvEx does not work if nnz == 0
csrmv = cusparse.csrmvEx
elif cusparse.check_availability('csrmv'):
csrmv = cusparse.csrmv
elif cusparse.check_availability('spmv'):
csrmv = cusparse.spmv
else:
raise NotImplementedError
return csrmv(self, other)
elif other.ndim == 2:
self.sum_duplicates()
if cusparse.check_availability('csrmm2'):
csrmm = cusparse.csrmm2
elif cusparse.check_availability('spmm'):
csrmm = cusparse.spmm
else:
raise NotImplementedError
return csrmm(self, cupy.asfortranarray(other))
else:
raise ValueError('could not interpret dimensions')
else:
return NotImplemented
def __mul__(self, other):
if cupy.isscalar(other):
self.sum_duplicates()
return self._with_data(self.data * other)
elif isspmatrix_csr(other):
self.sum_duplicates()
other.sum_duplicates()
if cusparse.check_availability('csrgemm2'):
return cusparse.csrgemm2(self, other)
elif cusparse.check_availability('csrgemm'):
return cusparse.csrgemm(self, other)
else:
raise NotImplementedError
elif csc.isspmatrix_csc(other):
self.sum_duplicates()
other.sum_duplicates()
if cusparse.check_availability('csrgemm'):
return cusparse.csrgemm(self, other.T, transb=True)
elif cusparse.check_availability('csrgemm2'):
b = other.tocsr()
b.sum_duplicates()
return cusparse.csrgemm2(self, b)
else:
raise NotImplementedError
elif base.isspmatrix(other):
return self * other.tocsr()
elif base.isdense(other):
if other.ndim == 0:
self.sum_duplicates()
return self._with_data(self.data * other)
elif other.ndim == 1:
self.sum_duplicates()
other = cupy.asfortranarray(other)
# csrmvEx does not work if nnz == 0
if self.nnz > 0 and cusparse.csrmvExIsAligned(self, other):
for accelerator in _accelerator.get_routine_accelerators():
if (accelerator == _accelerator.ACCELERATOR_CUB
and other.flags.c_contiguous):
return cub.device_csrmv(self.shape[0],
self.shape[1], self.nnz,
self.data, self.indptr,
self.indices, other)
return cusparse.csrmvEx(self, other)
else:
if cusparse.check_availability('csrmv'):
csrmv = cusparse.csrmv
elif cusparse.check_availability('spmv'):
csrmv = cusparse.spmv
else:
raise NotImplementedError
return csrmv(self, other)
elif other.ndim == 2:
self.sum_duplicates()
if cusparse.check_availability('csrmm2'):
csrmm = cusparse.csrmm2
elif cusparse.check_availability('spmm'):
csrmm = cusparse.spmm
else:
raise NotImplementedError
return csrmm(self, cupy.asfortranarray(other))
else:
raise ValueError('could not interpret dimensions')
else:
return NotImplemented
def __mul__(self, other):
if cupy.isscalar(other):
self.sum_duplicates()
return self._with_data(self.data * other)
elif isspmatrix_csr(other):
self.sum_duplicates()
other.sum_duplicates()
if cusparse.check_availability('spgemm'):
return cusparse.spgemm(self, other)
elif cusparse.check_availability('csrgemm2'):
return cusparse.csrgemm2(self, other)
elif cusparse.check_availability('csrgemm'):
return cusparse.csrgemm(self, other)
else:
raise NotImplementedError
elif _csc.isspmatrix_csc(other):
self.sum_duplicates()
other.sum_duplicates()
if cusparse.check_availability('csrgemm') and not runtime.is_hip:
# trans=True is still buggy as of ROCm 4.2.0
return cusparse.csrgemm(self, other.T, transb=True)
elif cusparse.check_availability('spgemm'):
b = other.tocsr()
b.sum_duplicates()
return cusparse.spgemm(self, b)
elif cusparse.check_availability('csrgemm2'):
b = other.tocsr()
b.sum_duplicates()
return cusparse.csrgemm2(self, b)
else:
raise NotImplementedError
elif _base.isspmatrix(other):
return self * other.tocsr()
elif _base.isdense(other):
if other.ndim == 0:
self.sum_duplicates()
return self._with_data(self.data * other)
elif other.ndim == 1:
self.sum_duplicates()
other = cupy.asfortranarray(other)
# need extra padding to ensure not stepping on the CUB bug,
# see cupy/cupy#3679 for discussion
is_cub_safe = (self.indptr.data.mem.size >
self.indptr.size * self.indptr.dtype.itemsize)
# CUB spmv is buggy since CUDA 11.0, see
# https://github.com/cupy/cupy/issues/3822#issuecomment-782607637
is_cub_safe &= (cub._get_cuda_build_version() < 11000)
for accelerator in _accelerator.get_routine_accelerators():
if (accelerator == _accelerator.ACCELERATOR_CUB
and not runtime.is_hip and is_cub_safe
and other.flags.c_contiguous):
return cub.device_csrmv(self.shape[0], self.shape[1],
self.nnz, self.data,
self.indptr, self.indices,
other)
if (cusparse.check_availability('csrmvEx') and self.nnz > 0
and cusparse.csrmvExIsAligned(self, other)):
# csrmvEx does not work if nnz == 0
csrmv = cusparse.csrmvEx
elif cusparse.check_availability('csrmv'):
csrmv = cusparse.csrmv
elif cusparse.check_availability('spmv'):
csrmv = cusparse.spmv
else:
raise NotImplementedError
return csrmv(self, other)
elif other.ndim == 2:
self.sum_duplicates()
if cusparse.check_availability('csrmm2'):
csrmm = cusparse.csrmm2
elif cusparse.check_availability('spmm'):
csrmm = cusparse.spmm
else:
raise NotImplementedError
return csrmm(self, cupy.asfortranarray(other))
else:
raise ValueError('could not interpret dimensions')
else:
return NotImplemented