indent correction for square.cu

Change-Id: I2ca008e260b920ac3a503ad2a4bb28cd32300c98


[ROCm/hip commit: 1f28d992d3]

projects/hip/samples/0_Intro/square/square.cu

@@ -26,9 +26,9 @@ THE SOFTWARE.
 {\
     cudaError_t error  = cmd;\
     if (error != cudaSuccess) { \
-      fprintf(stderr, "error: '%s'(%d) at %s:%d\n", cudaGetErrorString(error), error,__FILE__, __LINE__); \
+        fprintf(stderr, "error: '%s'(%d) at %s:%d\n", cudaGetErrorString(error), error,__FILE__, __LINE__); \
-    exit(EXIT_FAILURE);\
+        exit(EXIT_FAILURE);\
-	}\
+	  }\
 }
 
 
@@ -43,55 +43,55 @@ vector_square(T *C_d, const T *A_d, size_t N)
     size_t stride = blockDim.x * gridDim.x ;
 
     for (size_t i=offset; i<N; i+=stride) {
-		C_d[i] = A_d[i] * A_d[i];
+        C_d[i] = A_d[i] * A_d[i];
-	}
+    }
 }
 
 
 int main(int argc, char *argv[])
 {
-	float *A_d, *C_d;
+    float *A_d, *C_d;
-	float *A_h, *C_h;
+    float *A_h, *C_h;
-	size_t N = 1000000;
+    size_t N = 1000000;
-	size_t Nbytes = N * sizeof(float);
+    size_t Nbytes = N * sizeof(float);
 
-	cudaDeviceProp props;
+    cudaDeviceProp props;
-	CHECK(cudaGetDeviceProperties(&props, 0/*deviceID*/));
+    CHECK(cudaGetDeviceProperties(&props, 0/*deviceID*/));
-	printf ("info: running on device %s\n", props.name);
+    printf ("info: running on device %s\n", props.name);
 
-	printf ("info: allocate host mem (%6.2f MB)\n", 2*Nbytes/1024.0/1024.0);
+    printf ("info: allocate host mem (%6.2f MB)\n", 2*Nbytes/1024.0/1024.0);
-	A_h = (float*)malloc(Nbytes);
+    A_h = (float*)malloc(Nbytes);
-	CHECK(A_h == 0 ? cudaErrorMemoryAllocation : cudaSuccess );
+    CHECK(A_h == 0 ? cudaErrorMemoryAllocation : cudaSuccess );
-	C_h = (float*)malloc(Nbytes);
+    C_h = (float*)malloc(Nbytes);
-	CHECK(C_h == 0 ? cudaErrorMemoryAllocation : cudaSuccess );
+    CHECK(C_h == 0 ? cudaErrorMemoryAllocation : cudaSuccess );
-	// Fill with Phi + i
+    // Fill with Phi + i
     for (size_t i=0; i<N; i++) 
-	{
+    {
-		A_h[i] = 1.618f + i; 
+        A_h[i] = 1.618f + i; 
-	}
+    }
 
-	printf ("info: allocate device mem (%6.2f MB)\n", 2*Nbytes/1024.0/1024.0);
+    printf ("info: allocate device mem (%6.2f MB)\n", 2*Nbytes/1024.0/1024.0);
-	CHECK(cudaMalloc(&A_d, Nbytes));
+    CHECK(cudaMalloc(&A_d, Nbytes));
-	CHECK(cudaMalloc(&C_d, Nbytes));
+    CHECK(cudaMalloc(&C_d, Nbytes));
 
 
-	printf ("info: copy Host2Device\n");
+    printf ("info: copy Host2Device\n");
     CHECK ( cudaMemcpy(A_d, A_h, Nbytes, cudaMemcpyHostToDevice));
 
-	const unsigned blocks = 512;
+    const unsigned blocks = 512;
-	const unsigned threadsPerBlock = 256;
+    const unsigned threadsPerBlock = 256;
 
-	printf ("info: launch 'vector_square' kernel\n");
+    printf ("info: launch 'vector_square' kernel\n");
-	vector_square <<<blocks, threadsPerBlock>>> (C_d, A_d, N);
+    vector_square <<<blocks, threadsPerBlock>>> (C_d, A_d, N);
 
-	printf ("info: copy Device2Host\n");
+    printf ("info: copy Device2Host\n");
     CHECK ( cudaMemcpy(C_h, C_d, Nbytes, cudaMemcpyDeviceToHost));
 
-	printf ("info: check result\n");
+    printf ("info: check result\n");
     for (size_t i=0; i<N; i++)  {
-		if (C_h[i] != A_h[i] * A_h[i]) {
+        if (C_h[i] != A_h[i] * A_h[i]) {
-			CHECK(cudaErrorUnknown);
+            CHECK(cudaErrorUnknown);
-		}
+        }
-	}
+    }
-	printf ("PASSED!\n");
+    printf ("PASSED!\n");
 }