Skip to content

[MAINT] Save repeated expression in accumulation functor operator to a variable #1896

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.

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
merged 1 commit into from
Nov 18, 2024
Merged
Changes from all commits
Commits
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: 9 additions & 10 deletions dpctl/tensor/libtensor/include/kernels/accumulators.hpp
Original file line number Diff line number Diff line change
Expand Up @@ -227,23 +227,22 @@ inclusive_scan_base_step(sycl::queue &exec_q,

#pragma unroll
for (nwiT m_wi = 0; m_wi < n_wi; ++m_wi) {
const size_t i_m_wi = i + m_wi;
if constexpr (!include_initial) {
local_iscan[m_wi] =
(i + m_wi < acc_nelems)
? transformer(
input[inp_iter_offset +
inp_indexer(s0 + s1 * (i + m_wi))])
(i_m_wi < acc_nelems)
? transformer(input[inp_iter_offset +
inp_indexer(s0 + s1 * i_m_wi)])
: identity;
}
else {
// shift input to the left by a single element relative to
// output
local_iscan[m_wi] =
(i + m_wi < acc_nelems && i + m_wi > 0)
(i_m_wi < acc_nelems && i_m_wi > 0)
? transformer(
input[inp_iter_offset +
inp_indexer((s0 + s1 * (i + m_wi)) -
1)])
inp_indexer((s0 + s1 * i_m_wi) - 1)])
: identity;
}
}
Expand Down Expand Up @@ -280,9 +279,9 @@ inclusive_scan_base_step(sycl::queue &exec_q,
local_iscan[m_wi] = scan_op(local_iscan[m_wi], addand);
}

for (nwiT m_wi = 0; (m_wi < n_wi) && (i + m_wi < acc_nelems);
++m_wi)
{
const nwiT m_max =
std::min<nwiT>(n_wi, std::max(i, acc_nelems) - i);
for (nwiT m_wi = 0; m_wi < m_max; ++m_wi) {
output[out_iter_offset + out_indexer(i + m_wi)] =
local_iscan[m_wi];
}
Expand Down
Loading