Multicore and gpu programming pdf

Driven by the insatiable market demand for realtime, high-definition 3D graphics, the programmable Graphic Processor Unit or GPU has evolved into a highly parallel, multithreaded, manycore processor with tremendous computational horsepower and very high memory bandwidth, as illustrated by Figure 1 and Figure 2. The reason behind the discrepancy in floating-point capability between the CPU and the GPU is that the GPU is specialized for compute-intensive, highly parallel computation - exactly what graphics rendering is about - and therefore designed such that more transistors are devoted to data processing rather than data caching and flow control, as schematically illustrated by Figure 3. More specifically, the GPU is especially well-suited to address problems that can be expressed as data-parallel computations - the same program is executed on many data elements in parallel - with high arithmetic intensity - the ratio of arithmetic operations to memory operations. Because the same program is executed for each data element, there is a lower requirement for sophisticated flow control, and because it is executed on many data elements and has high arithmetic intensity, the memory access latency can be hidden with calculations instead of big data caches. Data-parallel processing maps data elements to parallel processing threads.

Concurrent Programming, as a scientific discipline, has been focused on recent developments to support the high-performance parallelization of multithreaded and multitasked software, derived from the emergence of multicore processors and also GPUs. Not only in the personal computers field but also in tablets and mobile phones, are these considered to be the reference hardware platforms in the future. The new journal will fill a gap and become a niche in the world of high-impact scientific journals, within the generic field known as Parallel and Distributed Systems on Multicore and GPU Platforms. Moreover, the new journal can provide a basis for the developing sub-discipline of Multicore Programming. This can become an independent discipline with a scientific legacy of its own and be maintained over time.