fixed ipynb inline code

Author: krisrak

DirectProgramming/C++SYCL/Jupyter/cuda-to-sycl-migration-training/01_SYCL_Migration_Simple_VectorAdd/01_SYCL_Migration_Simple_VectorAdd.ipynb

@@ -399,12 +399,12 @@
     "\n",
     "int main()\n",
     "{\n",
-    "        // sycl queue with out of order execution allowed        dpct::device_ext &dev_ct1 = dpct::get_current_device();\r\n",
-    "        sycl::queue &q_ct1 = dev_ct1out_ofn_order_queue();\r\n",
-    "        //# Print device name\r\n",
-    "        dpct::device_info dev;\r\n",
-    "        dpct::get_device_info(dev, dpct::dev_mgr::instance().get_device(0));\r\n",
-    "        std::cout << \"Device: \" << dev.get_name() << \"\\n\";;\n",
+    "        dpct::device_ext &dev_ct1 = dpct::get_current_device();\n",
+    "        sycl::queue &q_ct1 = dev_ct1.out_of_order_queue();\n",
+    "        //# Print device name\n",
+    "        dpct::device_info dev;\n",
+    "        dpct::get_device(0).get_device_info(dev);\n",
+    "        std::cout << \"Device: \" << dev.get_name() << \"\\n\";\n",
     "\n",
     "        //# Initialize vectors on host\n",
     "        float A[N] = {1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1};\n",
@@ -418,27 +418,28 @@
     "        d_C = sycl::malloc_device<float>(N, q_ct1);\n",
     "\n",
     "        //# copy vector data from host to device\n",
-    "        auto e1 = q_ct1.memcpy(d_A, A, N * sizeof(float));\n",
-    "        auto e2 = q_ct1.memcpy(d_B, B, N * sizeof(float));\n",
+    "        q_ct1.memcpy(d_A, A, N * sizeof(float));\n",
+    "        q_ct1.memcpy(d_B, B, N * sizeof(float));\n",
+    "        q_ct1.wait();\n",
     "\n",
     "        //# sumbit task to compute VectorAdd on device\n",
-    "        auto e3 = q_ct1.parallel_for(\n",
-    "            sycl::nd_range<3>(sycl::range<3>(1, 1, N), sycl::range<3>(1, 1, N)), {e1, e2},\n",
+    "        q_ct1.parallel_for(\n",
+    "            sycl::nd_range<3>(sycl::range<3>(1, 1, N), sycl::range<3>(1, 1, N)),\n",
     "            [=](sycl::nd_item<3> item_ct1) {\n",
     "                    VectorAddKernel(d_A, d_B, d_C, item_ct1);\n",
-    "            });\n",
+    "            }).wait();\n",
     "\n",
     "        //# copy result of vector data from device to host\n",
-    "        q_ct1.memcpy(C, d_C, N * sizeof(float), e3).wait();\n",
+    "        q_ct1.memcpy(C, d_C, N * sizeof(float)).wait();\n",
     "\n",
     "        //# print result on host\n",
     "        for (int i = 0; i < N; i++) std::cout<< C[i] << \" \";\n",
     "        std::cout << \"\\n\";\n",
     "\n",
     "        //# free allocation on device\n",
-    "        sycl::free(d_A, q_ct1);\n",
-    "        sycl::free(d_B, q_ct1);\n",
-    "        sycl::free(d_C, q_ct1);\n",
+    "        dpct::dpct_free(d_A, q_ct1);\n",
+    "        dpct::dpct_free(d_B, q_ct1);\n",
+    "        dpct::dpct_free(d_C, q_ct1);\n",
     "        return 0;\n",
     "}\n",
     "```"