Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

gemv: call fallback impl in transpose mode with M==0 #551

Merged
merged 2 commits into from
Dec 20, 2019
Merged

gemv: call fallback impl in transpose mode with M==0 #551

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
485faca
gemv: call fallback impl in transpose mode with M==0
ndellingwood Dec 19, 2019
24bebbc
gemv: remove fallback when Cuda is exec space
ndellingwood Dec 20, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 17 additions & 2 deletions src/blas/KokkosBlas2_gemv.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -138,8 +138,23 @@ gemv (const char trans[],
typename KokkosKernels::Impl::GetUnifiedLayout<YViewType>::array_layout,
typename YViewType::device_type,
Kokkos::MemoryTraits<Kokkos::Unmanaged> > YVT;
typedef Impl::GEMV<AVT, XVT, YVT> impl_type;
impl_type::gemv (trans, alpha, A, x, beta, y);

if ((trans[0] == 'T' || trans[0] == 't') && A.extent(0) == 0
#ifdef KOKKOS_ENABLE_CUDA
&& !std::is_same<typename AViewType::device_type::execution_space, Kokkos::Cuda>::value
#endif
)
{
const bool eti_spec_avail = KokkosBlas::Impl::gemv_eti_spec_avail<AVT, XVT, YVT>::value;
typedef Impl::GEMV<AVT, XVT, YVT, false, eti_spec_avail> fallback_impl_type;
fallback_impl_type::gemv (trans, alpha, A, x, beta, y);
}
else
{
typedef Impl::GEMV<AVT, XVT, YVT> impl_type;
impl_type::gemv (trans, alpha, A, x, beta, y);
}

}

} // namespace KokkosBlas
Expand Down
4 changes: 2 additions & 2 deletions src/sparse/impl/KokkosSparse_spgemm_impl_triangle.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -238,7 +238,7 @@ struct KokkosSPGEMM
const nnz_lno_t team_row_end = KOKKOSKERNELS_MACRO_MIN(team_row_begin + team_row_chunk_size, numrows);

//dense accumulators
nnz_lno_t *indices = NULL;
//nnz_lno_t *indices = NULL;
nnz_lno_t *sets = NULL;

volatile nnz_lno_t * tmp = NULL;
Expand Down Expand Up @@ -480,7 +480,7 @@ struct KokkosSPGEMM
const nnz_lno_t team_row_end = KOKKOSKERNELS_MACRO_MIN(team_row_begin + team_row_chunk_size, numrows);

//dense accumulators
nnz_lno_t *indices = NULL;
//nnz_lno_t *indices = NULL;
nnz_lno_t *sets = NULL;

volatile nnz_lno_t * tmp = NULL;
Expand Down