Projects that utilize volunteer computation can potentially access millions of central processing units (CPUs) that provide PFLOPS (thousands of trillions of floating-point operations per second) of processing power.
GPUs vs. CPUs
Graphical processing units (GPUs) are used in mobile phones, personal computers, workstations, and game consoles. As the name implies, GPUs are efficient at processing and manipulating computer graphics much faster than a traditional processor − a central processing unit or CPU.
Today, the majority of processing power in volunteer computing is from GPUs. More than 90% of new desktop and notebook computers have integrated GPUs, which are currently 10 to 50 times faster than CPUs, and this gap is increasing. Volunteer computing is ahead of high performance computing with 100 million GPUs in the public pool already, and tens of thousands are being used for volunteer computing today.
GPUs also have a structure that make them more effective than CPUs for carrying out algorithms where processing of large blocks of data is done in parallel. A parallel calculation can be split into many smaller sub-calculations. This means that each sub-calculation can be worked on by a different processor, so that many sub-calculations can be worked on "in parallel". This allows you to speed up your computation.Want to know more about different computational problems check outGridCafe.