Replace hipLaunchKernel -> hipLaunchKernelGGL

Change-Id: I4d99009e1199811d417becf1e1b934ec4d4e30be

samples/0_Intro/bit_extract/bit_extract.cpp

@@ -38,7 +38,7 @@ THE SOFTWARE.
         }                                                                                          \
     }
 
-__global__ void bit_extract_kernel(hipLaunchParm lp, uint32_t* C_d, const uint32_t* A_d, size_t N) {
+__global__ void bit_extract_kernel(uint32_t* C_d, const uint32_t* A_d, size_t N) {
     size_t offset = (hipBlockIdx_x * hipBlockDim_x + hipThreadIdx_x);
     size_t stride = hipBlockDim_x * hipGridDim_x;
 
@@ -85,7 +85,7 @@ int main(int argc, char* argv[]) {
     printf("info: launch 'bit_extract_kernel' \n");
     const unsigned blocks = 512;
     const unsigned threadsPerBlock = 256;
-    hipLaunchKernel(bit_extract_kernel, dim3(blocks), dim3(threadsPerBlock), 0, 0, C_d, A_d, N);
+    hipLaunchKernelGGL(bit_extract_kernel, dim3(blocks), dim3(threadsPerBlock), 0, 0, C_d, A_d, N);
 
     printf("info: copy Device2Host\n");
     CHECK(hipMemcpy(C_h, C_d, Nbytes, hipMemcpyDeviceToHost));

samples/0_Intro/hcc_dialects/vadd_hip.cpp

@@ -22,7 +22,7 @@ THE SOFTWARE.
 
 #include "hip/hip_runtime.h"
 
-__global__ void vadd_hip(hipLaunchParm lp, const float* a, const float* b, float* c, int N) {
+__global__ void vadd_hip(const float* a, const float* b, float* c, int N) {
     int idx = (hipBlockIdx_x * hipBlockDim_x + hipThreadIdx_x);
 
     if (idx < N) {
@@ -60,7 +60,7 @@ int main(int argc, char* argv[]) {
     // Launch kernel onto default accelerator
     int blockSize = 256;                                      // pick arbitrary block size
     int blocks = (sizeElements + blockSize - 1) / blockSize;  // round up to launch enough blocks
-    hipLaunchKernel(vadd_hip, dim3(blocks), dim3(blockSize), 0, 0, A_d, B_d, C_d, sizeElements);
+    hipLaunchKernelGGL(vadd_hip, dim3(blocks), dim3(blockSize), 0, 0, A_d, B_d, C_d, sizeElements);
 
     // D2H Copy
     hipMemcpy(C_h, C_d, sizeBytes, hipMemcpyDeviceToHost);

samples/0_Intro/square/square.hipref.cpp

@@ -37,7 +37,7 @@ THE SOFTWARE.
  * Square each element in the array A and write to array C.
  */
 template <typename T>
-__global__ void vector_square(hipLaunchParm lp, T* C_d, const T* A_d, size_t N) {
+__global__ void vector_square(T* C_d, const T* A_d, size_t N) {
     size_t offset = (hipBlockIdx_x * hipBlockDim_x + hipThreadIdx_x);
     size_t stride = hipBlockDim_x * hipGridDim_x;
 
@@ -81,7 +81,7 @@ int main(int argc, char* argv[]) {
     const unsigned threadsPerBlock = 256;
 
     printf("info: launch 'vector_square' kernel\n");
-    hipLaunchKernel(vector_square, dim3(blocks), dim3(threadsPerBlock), 0, 0, C_d, A_d, N);
+    hipLaunchKernelGGL(vector_square, dim3(blocks), dim3(threadsPerBlock), 0, 0, C_d, A_d, N);
 
     printf("info: copy Device2Host\n");
     CHECK(hipMemcpy(C_h, C_d, Nbytes, hipMemcpyDeviceToHost));