r7vme · July 8, 2019 21:32
diff --git a/rsqrt_kernel.cu b/rsqrt_kernel.cu
 __global__ void rsqrtKernel(
    const int n,
    const float* x,
    float* y)
 {
    for (int i = blockIdx.x * blockDim.x + threadIdx.x;
         i < n; i += gridDim.x * blockDim.x)
    {
        y[i] = rsqrtf(x[i]);
    }
 }
	__global__ void rsqrtKernel(
	const int n,
	const float* x,
	float* y)
	{
	for (int i = blockIdx.x * blockDim.x + threadIdx.x;
	i < n; i += gridDim.x * blockDim.x)
	{
	y[i] = rsqrtf(x[i]);
	}
	}