Fix padding the dependencies of copy_for_roll

Author: ndgrigorian

CHANGELOG.md

@@ -101,7 +101,7 @@ This release is compatible with NumPy 2.5.
 * 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 the list of events the copy kernels of `dpnp.reshape`, `dpnp.tensor.reshape`, `dpnp.roll` and `dpnp.tensor.roll` wait 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/source/copy_for_roll.cpp

@@ -233,9 +233,10 @@ std::pair<sycl::event, sycl::event>
     sycl::event copy_shape_ev = std::get<2>(ptr_size_event_tuple);
     const py::ssize_t *shape_strides = shape_strides_owner.get();
 
-    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_roll_event =
         fn(exec_q, offset, src_nelems, src_nd, shape_strides, src_data,
@@ -357,9 +358,10 @@ std::pair<sycl::event, sycl::event>
     sycl::event copy_shape_ev = std::get<2>(ptr_size_event_tuple);
     const py::ssize_t *shape_strides_shifts = shape_strides_shifts_owner.get();
 
-    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_roll_event =
         fn(exec_q, src_nelems, src_nd, shape_strides_shifts, src_data,