Skip to content

[SYCL] Fix types and transparent functors recognition in reduction #1709

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

Merged
v-klochkov merged 3 commits into from
May 20, 2020
Merged

[SYCL] Fix types and transparent functors recognition in reduction #1709

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
65c378e
[SYCL] Fix types and transparent functors recognition in reduction
v-klochkov May 18, 2020
7057ebe
[SYCL] Fix statically known identity values for MIN/MAX reductions
v-klochkov May 19, 2020
d2d355f
[SYCL][NFC] Fix clang-format issues in LIT test utitlity header file
v-klochkov May 19, 2020
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
6 changes: 3 additions & 3 deletions sycl/include/CL/sycl/handler.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -853,7 +853,7 @@ class __SYCL_EXPORT handler {
int Dims, typename Reduction>
detail::enable_if_t<Reduction::accessor_mode == access::mode::read_write &&
Reduction::has_fast_atomics>
parallel_for(nd_range<Dims> Range, Reduction &Redu, KernelType KernelFunc) {
parallel_for(nd_range<Dims> Range, Reduction Redu, KernelType KernelFunc) {
if (Reduction::is_usm)
Redu.associateWithHandler(*this);
shared_ptr_class<detail::queue_impl> QueueCopy = MQueue;
Expand Down Expand Up @@ -886,7 +886,7 @@ class __SYCL_EXPORT handler {
int Dims, typename Reduction>
detail::enable_if_t<Reduction::accessor_mode == access::mode::discard_write &&
Reduction::has_fast_atomics>
parallel_for(nd_range<Dims> Range, Reduction &Redu, KernelType KernelFunc) {
parallel_for(nd_range<Dims> Range, Reduction Redu, KernelType KernelFunc) {
shared_ptr_class<detail::queue_impl> QueueCopy = MQueue;
auto RWAcc = Redu.getReadWriteScalarAcc(*this);
intel::detail::reduCGFunc<KernelName>(*this, KernelFunc, Range, Redu,
Expand Down Expand Up @@ -920,7 +920,7 @@ class __SYCL_EXPORT handler {
template <typename KernelName = detail::auto_name, typename KernelType,
int Dims, typename Reduction>
detail::enable_if_t<!Reduction::has_fast_atomics>
parallel_for(nd_range<Dims> Range, Reduction &Redu, KernelType KernelFunc) {
parallel_for(nd_range<Dims> Range, Reduction Redu, KernelType KernelFunc) {
size_t NWorkGroups = Range.get_group_range().size();

// This parallel_for() is lowered to the following sequence:
Expand Down
Loading