The Researchers from North Carolina State University have created a new technique which allows graphics processing units (GPUs) & central processing units CPUs on a single chip to collaborate – boosting processor performance by an average of more than 20 percent.
Chip manufacturers are now creating processors which have a fused architecture, that meaning, they include CPUs & GPUs on a single chip, says by Dr. Huiyang Zhou, an experienced associate professor of electrical & computer Science engineering that co-authored a paper on the research. This approach decreases production costs or makes computers more energy efficient. Thus, the CPU cores & GPU cores still work almost among exclusively on separate functions. They rarely collaborate to execute any given program and so they aren’t as efficient as they could be. That was the issue we were trying to resolve.
GPUs were initially intended to execute graphics programs or they are capable of executing several individual functions very quickly. CPUs or the brains of a computer have less computational power but are better able to execute more complex tasks.
Our approach is to follow the GPU cores to execute computational functions & have CPU cores pre fetch the data the GPUs shall need from off-chip main memory, it was said by Zhou.
This is more effective and efficient because this allows CPUs & GPUs to do what they are good at. GPUs are good at executing and performing computations. CPUs are good at making decisions & flexible data retrieval.
Tags: computer Programming Assignment Help
Comments
Post a Comment