149
Application Mapping on Network-on-Chip
presented a different one-dimensional chaotic mapping technique onto NoC.
GBMAP, an evolutionary approach for mapping cores onto the NoC architecture, was proposed by Tavanpour et al. (2010), which reduces energy consumption and the total bandwidth requirement of NoC. Fekr et al. (2010) proposed
a PSO-based application mapping technique for NoC in which merit of the
scheme is not clear, as no comparison was made with the existing approaches.
A mapping technique based on discrete PSO was presented by Lei and Xiang
(2010). However, it only considers improvement over a GA-based method and
reports relative improvements only. Benyamina et al. (2010) proposed a hybrid
multiobjective algorithm, where Dijkstra’s shortest path algorithm is used to
find the shortest path among the communicating cores to satisfy the bandwidth constraints and then a multiobjective pareto-based PSO technique is
applied upon that to improve performance. GMAR, a GA-based mapping and
routing approach proposed by Fen and Ning (2010), addresses a two-phase
mapping of IP cores onto the NoC architecture and generates a deterministic
deadlock-free minimal routing path for each communication to minimize the
total communication energy and maximize the link bandwidth utilization of
the NoC architecture. In the first phase, GMAR maps IP cores onto different
resource nodes of the mesh-based NoC architecture. In the second phase, it
generates deterministic deadlock-free minimal routing path for each communication trace. Jang and Pan (2010) proposed an architecture-aware analytic
mapping algorithm (A3MAP) for NoC with homogeneous and heterogeneous
cores on regular and irregular mesh or custom architecture. The task mapping
problem is solved by two effective heuristics: a successive relaxation algorithm
as a fast algorithm and a GA to find better mapping solutions. Choudhary et al.
(2010) proposed a GA-based mapping technique for a customized NoC architecture to reduce the communication energy. Choudhary et al. (2011) proposed
a GA-based congestion-aware mapping technique for an irregular customized
NoC architecture to reduce the communication energy. A multiobjective adaptive immune algorithm (MAIA), based on an evolutionary approach, was proposed by Sepulveda et al. (2009), which maps the application tasks onto NoC
to reduce the power consumption and overall network latency. The adaptive
immune algorithms integrate a wide set of features that improve local search
while preventing the premature convergence by preserving the diversity of
solutions in the population. Sepulveda et al. (2011) proposed an improved version of MAIA to solve the multiapplication NoC problem. It produces a set
of mapping alternatives by exploring the mapping space. Wang et al. (2011)
proposed an ACO-based algorithm for application task mapping onto NoC
to minimize the bandwidth requirement. The results were compared with
random mapping techniques. Sahu et al. (2011c), proposed PSMAP, a metaheuristic strategy using PSO technique, to reduce both static and dynamic
costs of NoC for 2D mesh-based application mapping.