Apply remarks

Author: vlad-perevezentsev

dpctl_ext/tensor/libtensor/include/kernels/reductions.hpp

@@ -40,7 +40,6 @@
 #include <complex>
 #include <cstddef>
 #include <cstdint>
-#include <stdexcept>
 #include <type_traits>
 #include <utility>
 #include <vector>

dpctl_ext/tensor/libtensor/source/reductions/argmax.cpp

@@ -264,7 +264,6 @@ void init_argmax(py::module_ m)
         auto argmax_pyapi = [&](const arrayT &src, int trailing_dims_to_reduce,
                                 const arrayT &dst, sycl::queue &exec_q,
                                 const event_vecT &depends = {}) {
-            using dpctl::tensor::py_internal::py_search_over_axis;
             return py_search_over_axis(
                 src, trailing_dims_to_reduce, dst, exec_q, depends,
                 argmax_over_axis_strided_temps_dispatch_table,

dpctl_ext/tensor/libtensor/source/reductions/argmin.cpp

@@ -264,7 +264,6 @@ void init_argmin(py::module_ m)
         auto argmin_pyapi = [&](const arrayT &src, int trailing_dims_to_reduce,
                                 const arrayT &dst, sycl::queue &exec_q,
                                 const event_vecT &depends = {}) {
-            using dpctl::tensor::py_internal::py_search_over_axis;
             return py_search_over_axis(
                 src, trailing_dims_to_reduce, dst, exec_q, depends,
                 argmin_over_axis_strided_temps_dispatch_table,

dpctl_ext/tensor/libtensor/source/reductions/logsumexp.cpp

@@ -233,7 +233,6 @@ void init_logsumexp(py::module_ m)
                                    int trailing_dims_to_reduce,
                                    const arrayT &dst, sycl::queue &exec_q,
                                    const event_vecT &depends = {}) {
-            using dpctl::tensor::py_internal::py_tree_reduction_over_axis;
             return py_tree_reduction_over_axis(
                 src, trailing_dims_to_reduce, dst, exec_q, depends,
                 logsumexp_over_axis_strided_temps_dispatch_table,
@@ -246,7 +245,6 @@ void init_logsumexp(py::module_ m)
 
         auto logsumexp_dtype_supported = [&](const py::dtype &input_dtype,
                                              const py::dtype &output_dtype) {
-            using dpctl::tensor::py_internal::py_tree_reduction_dtype_supported;
             return py_tree_reduction_dtype_supported(
                 input_dtype, output_dtype,
                 logsumexp_over_axis_strided_temps_dispatch_table);

dpctl_ext/tensor/libtensor/source/reductions/max.cpp

@@ -391,7 +391,6 @@ void init_max(py::module_ m)
         auto max_pyapi = [&](const arrayT &src, int trailing_dims_to_reduce,
                              const arrayT &dst, sycl::queue &exec_q,
                              const event_vecT &depends = {}) {
-            using dpctl::tensor::py_internal::py_reduction_over_axis;
             return py_reduction_over_axis(
                 src, trailing_dims_to_reduce, dst, exec_q, depends,
                 max_over_axis_strided_atomic_dispatch_table,

dpctl_ext/tensor/libtensor/source/reductions/min.cpp

@@ -393,7 +393,6 @@ void init_min(py::module_ m)
         auto min_pyapi = [&](const arrayT &src, int trailing_dims_to_reduce,
                              const arrayT &dst, sycl::queue &exec_q,
                              const event_vecT &depends = {}) {
-            using dpctl::tensor::py_internal::py_reduction_over_axis;
             return py_reduction_over_axis(
                 src, trailing_dims_to_reduce, dst, exec_q, depends,
                 min_over_axis_strided_atomic_dispatch_table,

dpctl_ext/tensor/libtensor/source/reductions/prod.cpp

@@ -432,7 +432,6 @@ void init_prod(py::module_ m)
         auto prod_pyapi = [&](const arrayT &src, int trailing_dims_to_reduce,
                               const arrayT &dst, sycl::queue &exec_q,
                               const event_vecT &depends = {}) {
-            using dpctl::tensor::py_internal::py_reduction_over_axis;
             return py_reduction_over_axis(
                 src, trailing_dims_to_reduce, dst, exec_q, depends,
                 prod_over_axis_strided_atomic_dispatch_table,
@@ -450,7 +449,6 @@ void init_prod(py::module_ m)
         auto prod_dtype_supported =
             [&](const py::dtype &input_dtype, const py::dtype &output_dtype,
                 const std::string &dst_usm_type, sycl::queue &q) {
-                using dpctl::tensor::py_internal::py_reduction_dtype_supported;
                 return py_reduction_dtype_supported(
                     input_dtype, output_dtype, dst_usm_type, q,
                     prod_over_axis_strided_atomic_dispatch_table,

dpctl_ext/tensor/libtensor/source/reductions/reduce_hypot.cpp

@@ -44,9 +44,9 @@
 #include <pybind11/stl.h>
 
 #include "kernels/reductions.hpp"
+#include "utils/sycl_utils.hpp"
 #include "utils/type_dispatch_building.hpp"
 
-#include "reduction_atomic_support.hpp"
 #include "reduction_over_axis.hpp"
 
 namespace dpctl::tensor::py_internal
@@ -229,7 +229,6 @@ void init_reduce_hypot(py::module_ m)
         auto hypot_pyapi = [&](const arrayT &src, int trailing_dims_to_reduce,
                                const arrayT &dst, sycl::queue &exec_q,
                                const event_vecT &depends = {}) {
-            using dpctl::tensor::py_internal::py_tree_reduction_over_axis;
             return py_tree_reduction_over_axis(
                 src, trailing_dims_to_reduce, dst, exec_q, depends,
                 hypot_over_axis_strided_temps_dispatch_table,
@@ -242,7 +241,6 @@ void init_reduce_hypot(py::module_ m)
 
         auto hypot_dtype_supported = [&](const py::dtype &input_dtype,
                                          const py::dtype &output_dtype) {
-            using dpctl::tensor::py_internal::py_tree_reduction_dtype_supported;
             return py_tree_reduction_dtype_supported(
                 input_dtype, output_dtype,
                 hypot_over_axis_strided_temps_dispatch_table);

dpctl_ext/tensor/libtensor/source/reductions/reduction_atomic_support.hpp

@@ -34,7 +34,6 @@
 //===---------------------------------------------------------------------===//
 
 #pragma once
-#include <complex>
 #include <type_traits>
 
 #include <sycl/sycl.hpp>

dpctl_ext/tensor/libtensor/source/reductions/reduction_over_axis.hpp

@@ -37,8 +37,8 @@
 
 #include <algorithm>
 #include <cstddef>
-#include <cstdint>
 #include <exception>
+#include <iterator>
 #include <stdexcept>
 #include <type_traits>
 #include <utility>
@@ -49,7 +49,6 @@
 #include "dpnp4pybind11.hpp"
 #include <pybind11/numpy.h>
 #include <pybind11/pybind11.h>
-#include <pybind11/stl.h>
 
 #include "kernels/reductions.hpp"
 #include "simplify_iteration_space.hpp"
@@ -325,9 +324,6 @@ std::pair<sycl::event, sycl::event> py_reduction_over_axis(
         }
     }
 
-    using dpctl::tensor::py_internal::simplify_iteration_space;
-    using dpctl::tensor::py_internal::simplify_iteration_space_1;
-
     // TODO: not used anywhere
     auto const &src_shape_vecs = src.get_shape_vector();
     auto const &src_strides_vecs = src.get_strides_vector();
@@ -637,9 +633,6 @@ std::pair<sycl::event, sycl::event> py_tree_reduction_over_axis(
         }
     }
 
-    using dpctl::tensor::py_internal::simplify_iteration_space;
-    using dpctl::tensor::py_internal::simplify_iteration_space_1;
-
     auto const &src_shape_vecs = src.get_shape_vector();
     auto const &src_strides_vecs = src.get_strides_vector();
     auto const &dst_strides_vecs = dst.get_strides_vector();
@@ -912,8 +905,6 @@ std::pair<sycl::event, sycl::event> py_search_over_axis(
         }
     }
 
-    using dpctl::tensor::py_internal::simplify_iteration_space;
-
     auto const &src_shape_vecs = src.get_shape_vector();
     auto const &src_strides_vecs = src.get_strides_vector();
     auto const &dst_strides_vecs = dst.get_strides_vector();
@@ -1205,7 +1196,6 @@ std::pair<sycl::event, sycl::event>
     shT simplified_red_src_strides;
     py::ssize_t red_src_offset(0);
 
-    using dpctl::tensor::py_internal::simplify_iteration_space_1;
     simplify_iteration_space_1(
         simplified_red_nd, src_shape_ptr + dst_nd, red_src_strides,
         // output
@@ -1231,7 +1221,6 @@ std::pair<sycl::event, sycl::event>
         simplified_iter_dst_strides.push_back(0);
     }
     else {
-        using dpctl::tensor::py_internal::simplify_iteration_space;
         simplify_iteration_space(
             iter_nd, src_shape_ptr, iter_src_strides, iter_dst_strides,
             // output