Fix event dependency bugs and initial displacement initialization

CHANGELOG.md

@@ -100,6 +100,9 @@ This release is compatible with NumPy 2.5.
 * Fixed `dpnp.cumsum`, `dpnp.cumprod`, and their `nan`/`cumulative_*` variants (including `dpnp.tensor.cumulative_sum`/`cumulative_prod`) silently returning incorrect results when accumulating along an axis of an array with more than one row [#3063](https://github.com/IntelPython/dpnp/pull/3063)
 * Fixed `dpnp.einsum` returning a result whose memory layout differs from NumPy for the default `order="K"`, and ignoring `out` and `order` for a contraction over a size-0 dimension [#3058](https://github.com/IntelPython/dpnp/pull/3058)
 * Fixed operations on a boolean array whose bytes are not `0x00`/`0x01` [#3055](https://github.com/IntelPython/dpnp/pull/3055)
+* Fixed the strided kernel of `dpnp.full` and `dpnp.tensor.full` not waiting on the events passed to the binding [#3073](https://github.com/IntelPython/dpnp/pull/3073)
+* Fixed the list of events the copy kernel of `dpnp.reshape` and `dpnp.tensor.reshape` waits on being padded with default-constructed events [#3073](https://github.com/IntelPython/dpnp/pull/3073)
+* Fixed `simplify_iteration_three_strides` and `simplify_iteration_four_strides` accumulating into their third and fourth output displacements without zeroing them first, which required the caller to initialize them [#3073](https://github.com/IntelPython/dpnp/pull/3073)
 
 ### Security
 

dpnp/tensor/libtensor/include/utils/strided_iters.hpp

@@ -606,6 +606,7 @@ int simplify_iteration_three_strides(const int nd,
 {
     disp1 = StridesTy(0);
     disp2 = StridesTy(0);
+    disp3 = StridesTy(0);
     if (nd < 2)
         return nd;
 
@@ -770,6 +771,8 @@ int simplify_iteration_four_strides(const int nd,
 {
     disp1 = StridesTy(0);
     disp2 = StridesTy(0);
+    disp3 = StridesTy(0);
+    disp4 = StridesTy(0);
     if (nd < 2)
         return nd;
 

dpnp/tensor/libtensor/source/copy_for_reshape.cpp

@@ -152,9 +152,10 @@ std::pair<sycl::event, sycl::event>
     const char *src_data = src.get_data();
     char *dst_data = dst.get_data();
 
-    std::vector<sycl::event> all_deps(depends.size() + 1);
-    all_deps.push_back(copy_shape_ev);
+    std::vector<sycl::event> all_deps;
+    all_deps.reserve(depends.size() + 1);
     all_deps.insert(std::end(all_deps), std::begin(depends), std::end(depends));
+    all_deps.push_back(copy_shape_ev);
 
     sycl::event copy_for_reshape_event =
         fn(exec_q, src_nelems, src_nd, dst_nd, shape_strides, src_data,

dpnp/tensor/libtensor/source/full_ctor.cpp

@@ -278,9 +278,15 @@ std::pair<sycl::event, sycl::event>
         const sycl::event &copy_shape_ev = std::get<2>(ptr_size_event_tuple);
         py::ssize_t *shape_strides = shape_strides_owner.get();
 
+        std::vector<sycl::event> all_deps;
+        all_deps.reserve(depends.size() + 1);
+        all_deps.insert(std::end(all_deps), std::begin(depends),
+                        std::end(depends));
+        all_deps.push_back(copy_shape_ev);
+
         const sycl::event &full_strided_ev =
             fn(exec_q, nd, dst_nelems, shape_strides, py_value, dst_data,
-               {copy_shape_ev});
+               all_deps);
 
         // free shape_strides
         const auto &temporaries_cleanup_ev =