Modifying the basic example VECADD to use the shared memory - cuda

Question

I wrote the following kernel to use the shared memory into the basic CUDA example vecadd (sum of two vectors). The code works, but the elapsed time for the kernel execution is the same as the basic original code. May someone suggest me a way to easily speed up such a code?
__global__ void vecAdd(float *in1, float *in2, float *out,long int len)
{
__shared__ float s_in1[THREADS_PER_BLOCK];
__shared__ float s_in2[THREADS_PER_BLOCK];
unsigned int xIndex = blockIdx.x * THREADS_PER_BLOCK + threadIdx.x;
s_in1[threadIdx.x]=in1[xIndex];
s_in2[threadIdx.x]=in2[xIndex];
out[xIndex]=s_in1[threadIdx.x]+s_in2[threadIdx.x];
}

Answer 1

May someone suggest me a way to easily speed up such a code
There are basically no useful optimizations to make on an operation like vector addition. Because of the nature of the calculation, the code could only ever hope to reach 50% peak arithmetic throughput, and the requirement for three memory transactions per FLOP makes this an intrinsically memory bandwidth bound operation.
As a result, this:
__global__ void vecAdd(float *in1, float *in2, float *out, unsigned int len)
{
unsigned int xIndex = blockIdx.x * blockDim.x + threadIdx.x;
if (xIndex < len) {
float x = in1[xIndex];
float y = in2[xIndex];
out[xIndex] = x + y;
}
}
is about the best performing variant on most recent hardware, if the block size is selected for maximum occupancy, and len is sufficiently large for example:
int minGrid, minBlockSize;
cudaOccupancyMaxPotentialBlockSize(&minGrid, &minBlockSize, vecAdd);
int nblocks = (len / minBlockSize) + ((len % minBlockSize > 0) ? 1 : 0);
vecAdd<<<nblocks, minBlockSize>>>(x, y, z, len);