Replace hipLaunchKernel -> hipLaunchKernelGGL

Change-Id: I4d99009e1199811d417becf1e1b934ec4d4e30be

samples/2_Cookbook/6_dynamic_shared/Readme.md

@@ -25,7 +25,7 @@ Shared memory is way more faster than that of global and constant memory and acc
 here the first parameter is the data type while the second one is the variable name.
 
 The other important change is:
-`  hipLaunchKernel(matrixTranspose,                                                   `
+`  hipLaunchKernelGGL(matrixTranspose,                                                   `
                   dim3(WIDTH/THREADS_PER_BLOCK_X, WIDTH/THREADS_PER_BLOCK_Y),
                   dim3(THREADS_PER_BLOCK_X, THREADS_PER_BLOCK_Y),
                   sizeof(float)*WIDTH*WIDTH, 0,

samples/2_Cookbook/6_dynamic_shared/dynamic_shared.cpp

@@ -33,8 +33,7 @@ THE SOFTWARE.
 #define THREADS_PER_BLOCK_Z 1
 
 // Device (Kernel) function, it must be void
-// hipLaunchParm provides the execution configuration
-__global__ void matrixTranspose(hipLaunchParm lp, float* out, float* in, const int width) {
+__global__ void matrixTranspose(float* out, float* in, const int width) {
     // declare dynamic shared memory
     HIP_DYNAMIC_SHARED(float, sharedMem);
 
@@ -90,7 +89,7 @@ int main() {
     hipMemcpy(gpuMatrix, Matrix, NUM * sizeof(float), hipMemcpyHostToDevice);
 
     // Lauching kernel from host
-    hipLaunchKernel(matrixTranspose, dim3(WIDTH / THREADS_PER_BLOCK_X, WIDTH / THREADS_PER_BLOCK_Y),
+    hipLaunchKernelGGL(matrixTranspose, dim3(WIDTH / THREADS_PER_BLOCK_X, WIDTH / THREADS_PER_BLOCK_Y),
                     dim3(THREADS_PER_BLOCK_X, THREADS_PER_BLOCK_Y), sizeof(float) * WIDTH * WIDTH,
                     0, gpuTransposeMatrix, gpuMatrix, WIDTH);