This book is intended to present the design of significant scientific
applications on GPUs. Scientific applications require more and more
computational power in a large variety of fields: biology, physics,
-chemisty, phenomon model and prediction, simulation, mathematics, etc.
+chemistry, phenomon model and prediction, simulation, mathematics, etc.
In order to be able to handle more complex applications, the use of
parallel architectures is the solution to decrease the execution
-times of these applications. Using simulataneously many computing
-cores can significantly speed up the processing time.
+times of these applications. Using many computing
+cores simulataneously can significantly speed up the processing time.
Nevertheless using parallel architectures is not so easy and has always required
an endeavor to parallelize an application. Nowadays with general purpose
graphics processing units (GPGPU), it is possible to use either general graphic
cards or dedicated graphic cards to benefit from the computational power of all
-the cores available inside these cards. The NVidia company introduced Compute
+the cores available inside these cards. The NVIDIA company introduced Compute
Unified Device Architecture (CUDA) in 2007 to unify the programming model to use
their video card. CUDA is currently the most used environment for designing GPU
-applications although some alternatives are available, for example,
-Open Computing Language (OpenCL). According to applications and the GPU considered, a speed up from 5 up
-to 50, or even more can be expected using a GPU over computing with a CPU.
+applications although some alternatives are available, such as Open Computing
+Language (OpenCL). According to applications and the GPU considered, a speed up
+from 5 up to 50, or even more can be expected using a GPU over computing with a
+CPU.
The programming model of GPU is quite different from the one of
CPU. It is well adapted to data parallelism applications. Several
