Update amd.md

docs.it4i/cs/amd.md

@@ -10,7 +10,7 @@ salloc -N 1 -c 64 -A PROJECT-ID -p p03-amd --gres=gpu:4 --time=08:00:00
 where:
 
 - `-N 1` means allocating one server,
-- `-c 64` means allocation 64 cores, 
+- `-c 64` means allocation 64 cores,
 - `-A` is your project,
 - `-p p03-amd` is AMD partition,
 - `--gres=gpu:4` means allocating all 4 GPUs of the node,
@@ -96,7 +96,7 @@ int main()
     for(long long i = 0; i < count; i++)
         printf(" %7.2f", h_y[i]);
     printf("\n");
-    
+
     // allocation of memory on the GPU device
     float * d_x;
     float * d_y;
@@ -162,7 +162,7 @@ Y:    0.00  110.00  220.00  330.00  440.00  550.00  660.00  770.00  880.00  990.
 
 ## HIP and ROCm Libraries
 
-The list of official AMD libraries can be found here: [https://docs.amd.com/category/libraries][2]. 
+The list of official AMD libraries can be found here: [https://docs.amd.com/category/libraries][2].
 
 The libraries are installed in the same directory as ROCm
 
@@ -211,7 +211,7 @@ For this example we use `hipblas.hip.cpp`.
 
 
 int main()
-{    
+{
     srand(9600);
 
     int width = 10;
@@ -241,7 +241,7 @@ int main()
     for(int i = 0; i < width; i++)
         printf("%6.3f  ", h_x[i]);
     printf("\n");
-    
+
     float * h_y;
     hipHostMalloc(&h_y, height * sizeof(*h_y));
     for(int i = 0; i < height; i++)
@@ -251,7 +251,7 @@ int main()
         printf("%6.3f  ", h_x[i]);
     printf("\n");
 
-    
+
     // initialization of data in GPU memory
 
     float * d_A;
@@ -263,7 +263,7 @@ int main()
     float * d_x;
     hipMalloc(&d_x, width * sizeof(*d_x));
     hipMemcpy(d_x, h_x, width * sizeof(*d_x), hipMemcpyHostToDevice);
-    
+
     float * d_y;
     hipMalloc(&d_y, height * sizeof(*d_y));
     hipMemcpy(d_y, h_y, height * sizeof(*d_y), hipMemcpyHostToDevice);
@@ -282,8 +282,8 @@ int main()
     for(int i = 0; i < height; i++)
         printf("%6.3f  ", h_y[i]);
     printf("\n");
-    
-    
+
+
     // calculation of the result on the GPU using the hipBLAS library
 
     hipblasHandle_t blas_handle;
@@ -293,7 +293,7 @@ int main()
     hipDeviceSynchronize();
 
     hipblasDestroy(blas_handle);
-    
+
 
     // copy the GPU result to CPU memory and print it
     hipMemcpy(h_y, d_y, height * sizeof(*d_y), hipMemcpyDeviceToHost);
@@ -356,8 +356,8 @@ int main()
         for(int c = 0; c < size; c++)
             printf("%6.3f  ", h_A[r * h_A_ld + c]);
         printf("\n");
-    }    
-    
+    }
+
     std::vector<float> h_b(size);
     for(int i = 0; i < size; i++)
         h_b[i] = (10.0 * rand()) / RAND_MAX;
@@ -378,7 +378,7 @@ int main()
 
     float * d_b;
     hipMalloc(&d_b, size * sizeof(float));
-    
+
     float * d_x;
     hipMalloc(&d_x, size * sizeof(float));
 
@@ -390,7 +390,7 @@ int main()
 
     hipMemcpy2D(d_A, d_A_pitch, h_A.data(), h_A_pitch, size * sizeof(float), size, hipMemcpyHostToDevice);
     hipMemcpy(d_b, h_b.data(), size * sizeof(float), hipMemcpyHostToDevice);
-    
+
 
     // solving the system using hipSOLVER
 
@@ -403,7 +403,7 @@ int main()
     float * workspace;
     int wss = std::max(wss_trf, wss_trs);
     hipMalloc(&workspace, wss * sizeof(float));
-    
+
     hipsolverSgetrf(solverHandle, size, size, d_A, d_A_ld, workspace, wss, d_piv, info);
     hipsolverSgetrs(solverHandle, HIPSOLVER_OP_N, size, 1, d_A, d_A_ld, d_piv, d_b, size, workspace, wss, info);