Update guided matmul 0727

Tools/ApplicationDebugger/array-transform/README.md

@@ -6,10 +6,10 @@ through this sample *after* you familiarize yourself with the basics of
 SYCL programming, and *before* you start using the debugger.
 
 
-| Area                | Description
-|---------------------|--------------
-| What you will learn | Essential debugger features for effective debugging on CPU, GPU (Linux only), and FPGA emulator
-| Time to complete    | 20 minutes for CPU or FPGA emulator; 30 minutes for GPU
+| Area                | Description                                                                                     |
+|---------------------|-------------------------------------------------------------------------------------------------|
+| What you will learn | Essential debugger features for effective debugging on CPU, GPU (Linux only), and FPGA emulator |
+| Time to complete    | 20 minutes for CPU or FPGA emulator; 30 minutes for GPU                                         |
 
 This sample accompanies
 [Get Started with Intel® Distribution for GDB* on Linux* OS Host](https://software.intel.com/en-us/get-started-with-debugging-dpcpp)
@@ -34,16 +34,16 @@ of the application debugger.
 
 ## Prerequisites
 
-| Optimized for                                    | Description
-|--------------------------------------------------|--------------
-| OS                                               | Linux* Ubuntu* 20.04 to 22.04 <br> CentOS* 8 <br> Fedora* 30 <br> SLES 15 <br> Windows* 10, 11
-| Hardware to debug offloaded <br> kernels on GPUs | Intel® Arc(tm) <br> Intel® Data Center GPU Flex Series
-| Software                                         | Intel&reg; oneAPI DPC++/C++ Compiler
+| Optimized for                                    | Description                                                                                    |
+|--------------------------------------------------|------------------------------------------------------------------------------------------------|
+| OS                                               | Linux* Ubuntu* 20.04 to 22.04 <br> CentOS* 8 <br> Fedora* 30 <br> SLES 15 <br> Windows* 10, 11 |
+| Hardware to debug offloaded <br> kernels on GPUs | Intel® Arc(tm) <br> Intel® Data Center GPU Flex Series                                         |
+| Software                                         | Intel&reg; oneAPI DPC++/C++ Compiler                                                           |
 
 > **Note** although the sample can be run on all supported by Intel® oneAPI
 > Base Toolkit platforms, the GPU debugger can debug only kernels offloaded
 > onto devices specified at “Hardware to debug offloaded kernels on GPUs”
-> while running with the L0 backend.  When the GPU device is different from
+> while running with the L0 backend. When the GPU device is different from
 > the listed above, e.g., an integrated graphics device, breakpoints inside
 > the kernel won't be hit.  In such case, try to switch the offload to a CPU
 > device by using ONEAPI_DEVICE_SELECTOR environment variable.

Tools/ApplicationDebugger/guided_matrix_mult_BadBuffers/CMakeLists.txt

@@ -1,4 +1,4 @@
-cmake_minimum_required (VERSION 3.4)
+cmake_minimum_required (VERSION 3.5)
 set (CMAKE_CXX_COMPILER "icpx")
 project (matrix_mul LANGUAGES CXX)
 

Tools/ApplicationDebugger/guided_matrix_mult_BadBuffers/src/b1_matrix_mul_null_usm.cpp

@@ -132,6 +132,14 @@ int main() {
     q.memcpy(&c_back[0], dev_c, M*P * sizeof(float));
 
     q.wait();
+
+    sycl::free(dev_a, q);   // For the purposes of this demo, since we lost the original pointer value
+                            // and will crash before this point, this free is effectively a no-op and a
+                            // bug in its own right (we should be checking pointers best we can before
+                            // trying to free them).   
+                            // All USM allocations should be released after use.
+    sycl::free(dev_b, q);
+    sycl::free(dev_c, q);
   }
 
   int result;

Tools/ApplicationDebugger/guided_matrix_mult_BadBuffers/src/b2_matrix_mul_usm.cpp

@@ -130,6 +130,10 @@ int main() {
     q.memcpy(&c_back[0], dev_c, M*P * sizeof(float));
 
     q.wait();
+
+    sycl::free(dev_a, q);
+    sycl::free(dev_b, q);
+    sycl::free(dev_c, q);
   }
 
   int result;

Tools/ApplicationDebugger/guided_matrix_mult_Exceptions/CMakeLists.txt

@@ -1,4 +1,4 @@
-cmake_minimum_required (VERSION 3.4)
+cmake_minimum_required (VERSION 3.5)
 set (CMAKE_CXX_COMPILER "icpx")
 project (matrix_mul LANGUAGES CXX)
 

Tools/ApplicationDebugger/guided_matrix_mult_Exceptions/src/1_matrix_mul_null_pointer.cpp

@@ -130,6 +130,10 @@ int main() {
     q.memcpy(&c_back[0], dev_c, M*P * sizeof(float));
 
     q.wait();
+
+    sycl::free(dev_a, q);
+    sycl::free(dev_b, q);
+    sycl::free(dev_c, q);
   }
 
   int result;

Tools/ApplicationDebugger/guided_matrix_mult_Exceptions/src/2_matrix_mul_multi_offload.cpp

@@ -131,6 +131,10 @@ int main() {
     q.memcpy(&c_back[0], dev_c, M*P * sizeof(float));
 
     q.wait();
+
+    sycl::free(dev_a, q);
+    sycl::free(dev_b, q);
+    sycl::free(dev_c, q);
   }
 
   int result;

Tools/ApplicationDebugger/guided_matrix_mult_Exceptions/src/3_matrix_mul.cpp

@@ -130,6 +130,10 @@ int main() {
     q.memcpy(&c_back[0], dev_c, M*P * sizeof(float));
 
     q.wait();
+
+    sycl::free(dev_a, q);
+    sycl::free(dev_b, q);
+    sycl::free(dev_c, q);
   }
 
   int result;

Tools/ApplicationDebugger/guided_matrix_mult_InvalidContexts/CMakeLists.txt

@@ -1,4 +1,4 @@
-cmake_minimum_required (VERSION 3.4)
+cmake_minimum_required (VERSION 3.5)
 set (CMAKE_CXX_COMPILER "icpx")
 project (matrix_mul LANGUAGES CXX)