Parallel Patterns + Macro Data Flow for Multi-core Programming

Abstract

Abstract-Data flow techniques have been around since the early '70s when they were used in compilers for sequential languages. Shortly after their introduction they were also considered as a possible model for parallel computing, although the impact here was limited. Recently, however, data flow has been identified as a candidate for efficient implementation of various programming models on multi-core architectures. In most cases, however, the burden of determining data flow "macro" instructions is left to the programmer, while the compiler/run time system manages only the efficient scheduling of these instructions. We discuss a structured parallel programming approach supporting automatic compilation of programs to macro data flow and we show experimental results demonstrating the feasibility of the approach and the efficiency of the resulting "object" code on different classes of state-of-the-art multi-core architectures. The experimental results use different base mechanisms to implement the macro data flow run time support, from plain pthreads with condition variables to more modern and effective lock-and fence-free parallel frameworks. Experimental results comparing efficiency of the proposed approach with those achieved using other, more classical, parallel frameworks are also presented.

Why High-Performance Modelling and Simulation for Big Data Applications Matters

“…In the Dataflow model, applications as a directed graph of actors. In its "modern" macro-data flow version [71], it naturally models independent (thus parallelizable) kernels starting from a graph of true data dependencies, where a kernel's execution is triggered by data availability.…”

Targeting Heterogeneous Architectures via Macro Data Flow

“…3 shows the graph derived from classic Cholesky factorization. A more detailed description of how MDF graphs are generated from HLL and/or libraries may be found in [15].…”

FastFlow tutorial

“…Writes to the global result array need not to be synchronized as each worker writes different positions in the array (the TASK tags are unique). i n t t a s k ; } ; i n t main ( i n t argc , char * argv [ ] ) { i n t nworkers=a t o i ( argv [ 1 ] ) ; i n t s t r e a m l e n=a t o i ( argv [ 2 ] ) ;…”

“…A number of different papers and technical reports discuss the different features of this programming environment [11,6,2], the kind of results achieved while parallelizing different applications [13,9,10,3,8,7] and the usage of FastFlow as software accelerator, i.e. as a mechanisms suitable to exploit unused cores of a multicore architecture to speedup execution of sequential code [4,5].…”