Diversas são as aplicações que podem ser expressas por meio de grafos [2]. Algoritmos [3] e modelos de visualização [15] podem ser encontrados amplamente na literatura. Todos os problemas de grafos possuem uma base em comum: um modelo genérico que nasce da própria natureza dos elementos e das relações que podem ser expressas entre eles, diferindo apenas pelo tipo de resposta que queremos obter desta complexa malha. Além disso, é natural que, para problemas que sejam de áreas distintas, mas que sejam semelhantes quanto ao processamento interno, apenas o que mude, seja a visualização dos elementos que o compõe (nós, arestas, etc.). Da mesma forma, independente do tipo de processamento interno, os grafos devem manter a estrutura original de grafos, ou seja, ainda deve haver uma malha que descreve os nós e suas ligações. Neste aspecto, fundamentamos nosso estudo: propomos neste trabalho, desenvolver uma API que possa ser estendida para os mais diversos problemas na área de grafos, tanto na parte visual como na representação matemática do modelo e dos algoritmos, porém, robusta, no sentido de manter a complexidade dos algoritmos envolvidos na área de grafos, além de ser completamente dirigida as necessidades de cada aplicação, podendo-se alterar apenas algumas partes da aplicação para obter um produto específico ao trabalho do usuário / There are several applications that can be expressed by means of graphs [2]. Algorithms [3] and visualization models [15] can be widely found in the literature. All graph problems have a common base: create a generic model that arises not only from the nature of their elements, but also from the relationships which these elements can express, differing just by the type of response we want to get from this complex mesh. Moreover, it is natural for problems that are in different fields, but similar in internal processing, that the only change is related to how elements are visualized (nodes, edges, and so on). Likewise, regardless the internal processing, the graphs must keep their original structure, i.e., they must still be a mesh that describes the nodes and their connections. Based on that, this study proposes to develop an API that is generic enough to be extended to several problems in the graphs area. This API can be applied in both visual and mathematical representation of models and algorithms. Besides that, it must be robust to maintain the complexity of the algorithms involved in the graph. Also, it has to be flexible so that only some parts of the application can be changed to get a specific product to the user´s need

Diversas são as aplicações que podem ser expressas por meio de grafos [2]. Algoritmos [3] e modelos de visualização [15] podem ser encontrados amplamente na literatura. Todos os problemas de grafos possuem uma base em comum: um modelo genérico que nasce da própria natureza dos elementos e das relações que podem ser expressas entre eles, diferindo apenas pelo tipo de resposta que queremos obter desta complexa malha. Além disso, é natural que, para problemas que sejam de áreas distintas, mas que sejam semelhantes quanto ao processamento interno, apenas o que mude, seja a visualização dos elementos que o compõe (nós, arestas, etc.). Da mesma forma, independente do tipo de processamento interno, os grafos devem manter a estrutura original de grafos, ou seja, ainda deve haver uma malha que descreve os nós e suas ligações. Neste aspecto, fundamentamos nosso estudo: propomos neste trabalho, desenvolver uma API que possa ser estendida para os mais diversos problemas na área de grafos, tanto na parte visual como na representação matemática do modelo e dos algoritmos, porém, robusta, no sentido de manter a complexidade dos algoritmos envolvidos na área de grafos, além de ser completamente dirigida as necessidades de cada aplicação, podendo-se alterar apenas algumas partes da aplicação para obter um produto específico ao trabalho do usuário / There are several applications that can be expressed by means of graphs [2]. Algorithms [3] and visualization models [15] can be widely found in the literature. All graph problems have a common base: create a generic model that arises not only from the nature of their elements, but also from the relationships which these elements can express, differing just by the type of response we want to get from this complex mesh. Moreover, it is natural for problems that are in different fields, but similar in internal processing, that the only change is related to how elements are visualized (nodes, edges, and so on). Likewise, regardless the internal processing, the graphs must keep their original structure, i.e., they must still be a mesh that describes the nodes and their connections. Based on that, this study proposes to develop an API that is generic enough to be extended to several problems in the graphs area. This API can be applied in both visual and mathematical representation of models and algorithms. Besides that, it must be robust to maintain the complexity of the algorithms involved in the graph. Also, it has to be flexible so that only some parts of the application can be changed to get a specific product to the user´s need

Graphs model relationships across real-world entities in web graphs, social network graphs, and road network graphs. Graph algorithms analyze and transform a graph to discover graph properties or to apply a computation. For instance, a pagerank algorithm computes a rank for each page in a webgraph, and a community detection algorithm discovers likely communities in a social network, while a shortest path algorithm computes the quickest way to reach a place from another, in a road network. In Domains such as social information systems, the number of edges can be in billions or trillions. Such large graphs are processed on distributed computer systems or clusters. Graph algorithms can be executed on multi-core CPUs, GPUs with thousands of cores, multi-GPU devices, and CPU+GPU clusters, depending on the size of the graph object. While programming such algorithms on heterogeneous targets, a programmer is required to deal with parallelism and and also manage explicit data communication between distributed devices. This implies that a programmer is required to learn CUDA, OpenMP, MPI, etc., and also the details of the hardware architecture. Such codes are error prone and di cult to debug. A Domain Speci c Language (DSL) which hides all the hardware details and lets the programmer concentrate only the algorithmic logic will be very useful. With this as the research goal, Falcon, graph DSL and its compiler have been developed. Falcon programs are explicitly parallel and Falcon hides all the hardware details from the programmer. Large graphs that do not t into the memory of a single device are automatically partitioned by the Falcon compiler. Another feature of Falcon is that it supports mutation of graph objects and thus enables programming dynamic graph algorithms. The Falcon compiler converts a single DSL code to heterogeneous targets such as multi-core CPUs, GPUs, multi-GPU devices, and CPU+GPU clusters. Compiled codes of Falcon match or outperform state-of-the-art graph frameworks for di erent target platforms and benchmarks.