[SYCL][NATIVECPU] Implement events on Native CPU

sycl/cmake/modules/FetchUnifiedRuntime.cmake

@@ -116,7 +116,7 @@ if(SYCL_UR_USE_FETCH_CONTENT)
       CACHE PATH "Path to external '${name}' adapter source dir" FORCE)
   endfunction()
 
-  set(UNIFIED_RUNTIME_REPO "https://github.com/oneapi-src/unified-runtime.git")
+  set(UNIFIED_RUNTIME_REPO "https://github.com/PietroGhg/unified-runtime.git")
   include(${CMAKE_CURRENT_SOURCE_DIR}/cmake/modules/UnifiedRuntimeTag.cmake)
 
   set(UMF_BUILD_EXAMPLES OFF CACHE INTERNAL "EXAMPLES")

sycl/cmake/modules/UnifiedRuntimeTag.cmake

@@ -1,7 +1,7 @@
 # commit fa8cc8ec16c1a2cf0926cc64026edc6a254ff0c2
 # Merge: 3d58884b 1984ceb1
 # Author: aarongreig <[email protected]>
-# Date:   Fri Nov 1 10:03:37 2024 +0000
-#     Merge pull request #1833 from ayylol/old-opencl-check
-#     [OpenCL] Add OpenCL version check for independent forward progress query
-set(UNIFIED_RUNTIME_TAG fa8cc8ec16c1a2cf0926cc64026edc6a254ff0c2)
+# Date:   Thu Oct 31 14:05:55 2024 +0000
+#     Merge pull request #2228 from nrspruit/copy_engine_refactor
+#     [L0] Refactor Copy Engine Usage checks for Performance
+set(UNIFIED_RUNTIME_TAG pietro/events_rr)

sycl/test/native_cpu/scalar_args.cpp

@@ -12,39 +12,62 @@ const size_t N = 10;
 
 template <typename T> class init_a;
 
-template <typename T> bool test(queue myQueue) {
-  {
-    buffer<float, 1> a(range<1>{N});
-    const T test = rand() % 10;
-
-    myQueue.submit([&](handler &cgh) {
-      auto A = a.get_access<access::mode::write>(cgh);
-      cgh.parallel_for<init_a<T>>(range<1>{N},
-                                  [=](id<1> index) { A[index] = test; });
-    });
-
-    auto A = a.get_access<access::mode::read>();
-    std::cout << "Result:" << std::endl;
-    for (size_t i = 0; i < N; i++) {
-      if (A[i] != test) {
-        std::cout << "ERROR at pos " << i << " expected " << test << ", got "
-                  << A[i] << "\n";
-        return false;
-      }
-    }
+template <typename T, int M>
+bool compare(const sycl::vec<T, M> a, const sycl::vec<T, M> truth) {
+  bool res = true;
+  for (int i = 0; i < M; i++) {
+    res &= a[i] == truth[i];
   }
+  return res;
+}
 
-  std::cout << "Good computation!" << std::endl;
+template <typename T> bool compare(const T a, const T truth) {
+  return a == truth;
+}
+
+template <typename T> bool check(buffer<T, 1> &result, const T truth) {
+  auto A = result.get_host_access();
+  for (size_t i = 0; i < N; i++) {
+    if (!compare(A[i], truth)) {
+      return false;
+    }
+  }
   return true;
 }
 
+template <typename T> bool test(queue myQueue) {
+  buffer<T, 1> a(range<1>{N});
+  const T test{42};
+
+  myQueue.submit([&](handler &cgh) {
+    auto A = a.template get_access<access::mode::write>(cgh);
+    cgh.parallel_for<init_a<T>>(range<1>{N},
+                                [=](id<1> index) { A[index] = test; });
+  });
+
+  return check(a, test);
+}
+
 int main() {
   queue q;
-  int res1 = test<int>(q);
-  int res2 = test<unsigned>(q);
-  int res3 = test<float>(q);
-  int res4 = test<double>(q);
-  if (!(res1 && res2 && res3 && res4)) {
+
+  std::vector<bool> res;
+  res.push_back(test<int>(q));
+  res.push_back(test<unsigned>(q));
+  res.push_back(test<float>(q));
+  res.push_back(test<double>(q));
+  res.push_back(test<sycl::vec<int, 2>>(q));
+  res.push_back(test<sycl::vec<int, 3>>(q));
+  res.push_back(test<sycl::vec<int, 4>>(q));
+  res.push_back(test<sycl::vec<int, 8>>(q));
+  res.push_back(test<sycl::vec<int, 16>>(q));
+  res.push_back(test<sycl::vec<double, 2>>(q));
+  res.push_back(test<sycl::vec<double, 3>>(q));
+  res.push_back(test<sycl::vec<double, 4>>(q));
+  res.push_back(test<sycl::vec<double, 8>>(q));
+  res.push_back(test<sycl::vec<double, 16>>(q));
+
+  if (std::any_of(res.begin(), res.end(), [](bool b) { return !b; })) {
     return 1;
   }
   return 0;