diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
old mode 100755
new mode 100644
index edbc8446fbc..556f4cf833a
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -235,8 +235,8 @@ jobs:
             mkdir build &&
             cd build &&
             cmake -DCMAKE_CXX_STANDARD=23 -DCMAKE_CXX_COMPILER=icpx -DONEDPL_BACKEND=dpcpp -DCMAKE_BUILD_TYPE=Release .. &&
-            cmake --build . --target shp-all-tests -j${nproc} &&
-            ctest --test-dir . -L SHP -j 4"
+            cmake --build . --target shp-all-tests -j${BUILD_CONCURRENCY} &&
+            ctest --test-dir . -L SHP -j${BUILD_CONCURRENCY}"
           docker logs -f dr-test
           exit_code=$(docker inspect dr-test --format='{{.State.ExitCode}}')
           docker rm -f dr-test
diff --git a/include/oneapi/dpl/distributed-ranges b/include/oneapi/dpl/distributed-ranges
index 18690d0615b..75588c75eda 100644
--- a/include/oneapi/dpl/distributed-ranges
+++ b/include/oneapi/dpl/distributed-ranges
@@ -19,4 +19,4 @@
 #error "C++23 required to use Distributed Ranges"
 #endif
 
-#endif /* _ONEDPL_DISTRIBUTED_RANGES */
+#endif // _ONEDPL_DISTRIBUTED_RANGES
diff --git a/include/oneapi/dpl/internal/distributed_ranges_impl/shp.hpp b/include/oneapi/dpl/internal/distributed_ranges_impl/shp.hpp
index 38795eae3d6..0eb3f29ed3c 100644
--- a/include/oneapi/dpl/internal/distributed_ranges_impl/shp.hpp
+++ b/include/oneapi/dpl/internal/distributed_ranges_impl/shp.hpp
@@ -4,7 +4,6 @@
 
 #pragma once
 
-// #include "detail/logger.hpp"
 #include "shp/algorithms/algorithms.hpp"
 #include "shp/detail.hpp"
 #include "shp/distributed_span.hpp"
diff --git a/include/oneapi/dpl/internal/distributed_ranges_impl/shp/algorithms/copy.hpp b/include/oneapi/dpl/internal/distributed_ranges_impl/shp/algorithms/copy.hpp
index 92cff9224ed..9f3b574c055 100644
--- a/include/oneapi/dpl/internal/distributed_ranges_impl/shp/algorithms/copy.hpp
+++ b/include/oneapi/dpl/internal/distributed_ranges_impl/shp/algorithms/copy.hpp
@@ -23,7 +23,6 @@ template <std::contiguous_iterator InputIt, std::contiguous_iterator OutputIt>
 requires __detail::is_syclmemcopyable<std::iter_value_t<InputIt>, std::iter_value_t<OutputIt>> sycl::event
 copy_async(InputIt first, InputIt last, OutputIt d_first)
 {
-    // auto &&q = __detail::default_queue();
     auto&& q = __detail::get_queue_for_pointers(first, d_first);
     return q.memcpy(std::to_address(d_first), std::to_address(first),
                     sizeof(std::iter_value_t<InputIt>) * (last - first));
@@ -43,7 +42,6 @@ template <std::contiguous_iterator Iter, typename T>
 requires __detail::is_syclmemcopyable<std::iter_value_t<Iter>, T> sycl::event
 copy_async(Iter first, Iter last, device_ptr<T> d_first)
 {
-    // auto &&q = __detail::default_queue();
     auto&& q = __detail::get_queue_for_pointers(first, d_first);
     return q.memcpy(d_first.get_raw_pointer(), std::to_address(first), sizeof(T) * (last - first));
 }
@@ -61,7 +59,6 @@ template <typename T, std::contiguous_iterator Iter>
 requires __detail::is_syclmemcopyable<T, std::iter_value_t<Iter>> sycl::event
 copy_async(device_ptr<T> first, device_ptr<T> last, Iter d_first)
 {
-    // auto &&q = __detail::default_queue();
     auto&& q = __detail::get_queue_for_pointers(first, d_first);
     return q.memcpy(std::to_address(d_first), first.get_raw_pointer(), sizeof(T) * (last - first));
 }
@@ -79,7 +76,6 @@ template <typename T>
 requires(!std::is_const_v<T> && std::is_trivially_copyable_v<T>) sycl::event
     copy_async(device_ptr<std::add_const_t<T>> first, device_ptr<std::add_const_t<T>> last, device_ptr<T> d_first)
 {
-    // auto &&q = __detail::default_queue();
     auto&& q = __detail::get_queue_for_pointers(first, d_first);
     return q.memcpy(d_first.get_raw_pointer(), first.get_raw_pointer(), sizeof(T) * (last - first));
 }
diff --git a/include/oneapi/dpl/internal/distributed_ranges_impl/shp/algorithms/fill.hpp b/include/oneapi/dpl/internal/distributed_ranges_impl/shp/algorithms/fill.hpp
index 94d07078cfd..878d02f924c 100644
--- a/include/oneapi/dpl/internal/distributed_ranges_impl/shp/algorithms/fill.hpp
+++ b/include/oneapi/dpl/internal/distributed_ranges_impl/shp/algorithms/fill.hpp
@@ -24,7 +24,7 @@ requires(!std::is_const_v<std::iter_value_t<Iter>> && std::is_trivially_copyable
 {
     auto&& q = __detail::get_queue_for_pointer(first);
     std::iter_value_t<Iter>* arr = std::to_address(first);
-    // not using q.fill because of CMPLRLLVM-46438
+    // not using q.fill because p2p communication is not working when using sycl::queue.fill or sycl::queue.parallel_for with nondefault KernelName (CMPLRLLVM-46438)
     return dr::__detail::parallel_for(q, sycl::range<>(last - first), [=](auto idx) { arr[idx] = value; });
 }
 
@@ -41,7 +41,7 @@ requires(std::indirectly_writable<device_ptr<T>, U>) sycl::event
 {
     auto&& q = __detail::get_queue_for_pointer(first);
     auto* arr = first.get_raw_pointer();
-    // not using q.fill because of CMPLRLLVM-46438
+    // not using q.fill because p2p communication is not working when using sycl::queue.fill or sycl::queue.parallel_for with nondefault KernelName (CMPLRLLVM-46438)
     return dr::__detail::parallel_for(q, sycl::range<>(last - first), [=](auto idx) { arr[idx] = value; });
 }
 
@@ -57,7 +57,7 @@ fill_async(R&& r, const T& value)
 {
     auto&& q = __detail::queue(ranges::rank(r));
     auto* arr = std::to_address(rng::begin(ranges::local(r)));
-    // not using q.fill because of CMPLRLLVM-46438
+    // not using q.fill because p2p communication is not working when using sycl::queue.fill or sycl::queue.parallel_for with nondefault KernelName (CMPLRLLVM-46438)
     return dr::__detail::parallel_for(q, sycl::range<>(rng::distance(r)), [=](auto idx) { arr[idx] = value; });
 }
 
diff --git a/include/oneapi/dpl/internal/distributed_ranges_impl/shp/init.hpp b/include/oneapi/dpl/internal/distributed_ranges_impl/shp/init.hpp
index 0eaa5e298ab..004c96fc9b3 100644
--- a/include/oneapi/dpl/internal/distributed_ranges_impl/shp/init.hpp
+++ b/include/oneapi/dpl/internal/distributed_ranges_impl/shp/init.hpp
@@ -122,7 +122,7 @@ queue(std::size_t rank)
     return queues_[rank];
 }
 
-// Retrieve global queues because of CMPLRLLVM-47008
+// Retrieve global queues because of observed significantly reduced copy performance when using newly constructed queues versus using pre-constructed global queues. (CMPLRLLVM-47008)
 inline sycl::queue&
 queue(const sycl::device& device)
 {