A Novel CSR-Based Sparse Matrix-Vector Multiplication on GPUs

Table 1

Symbols used in this study.

Symbol	Description
	Sparse matrix
	Input vector
	Output vector
	Size of the input and output vectors
	Number of nonzero elements in
threadsPerBlock (TB)	Number of threads per block
blocksPerGrid (BG)	Number of blocks per grid
elementsPerThread	Number of elements calculated by each thread
sizeSharedMemory	Size of shared memory
	Number of GPUs