Aiming to ease the parallel programming for heterogeneous architectures, we propose and implement a high-level OpenCL runtime that conceptually merges multiple heterogeneous hardware devices into one virtual heterogeneous compute device (VHCD). Moreover, automated workload distribution among the devices is based on offline profiling, together with new programming directives that define the device-independent data access range per work-group. Therefore, an OpenCL program originally written for a single compute device can, after inserting a small number of programming directives, run efficiently on a platform consisting of heterogeneous compute devices. Performance is ensured by introducing the technique of virtual cache management, which minimizes the amount of host-device data transfer. Our new OpenCL runtime is evaluated by a diverse set of OpenCL benchmarks, demonstrating good performance on various configurations of a heterogeneous system.

Many congestion control mechanisms have been proposed to solve the problems of a high loss rate and inefficient utilization of network resources in the present Internet. This problem is caused by competition between traffic flows while the network is congested. Differentiated Services (DiffServ) architecture permits the allocation of various levels of traffic resource requirements needed for Quality of Service (QoS). Random Early Detection (RED) is an efficient mechanism to pre-drop packets before actual congestion occurs, and it is capable of introducing a random early packet dropping scheme, and based on the queue length in reaching a certain degree of fairness for resource utilization. However, it still suffers from a lack of robustness among light traffic load, or in heavy traffic load using fixed RED parameters. In this paper, we modified the RED scheme and proposed a novel adaptive RED model, which we named the OURED model, to enhance the robustness of resource utilization so that it could be utilized in the DiffServ edge router. The OURED model introduces two additional packet dropping traces, one is Over Random Early Detection (ORED), which is used to speed up the dropping of packets when the actual rate is higher than the target rate, and the other one is the Under Random Early Detection (URED), used to slow down the packet dropping rate in the reverse situation. The simulation results show that OURED is not only more robust than MRED in resource utilization, but that it also can be implement efficiently in the DiffServ edge router.

This paper presents a study of the applicability of clusters of GPUs to high-resolution 3D simulations of cardiac electrophysiology. By experimenting with representative cardiac cell models and ODE solvers, in association with solving the monodomain equation, we quantitatively analyze the obtainable computational capacity of GPU clusters. It is found that for a 501×501×101 3D mesh, which entails a 0.1mm spatial resolution, a 128-GPU cluster only needs a few minutes to carry out a 100,000-time-step cardiac excitation simulation that involves a four-variable cell model. Even higher spatial and temporal resolutions are achievable for such simplified mathematical models. On the other hand, our experiments also show that a dramatically larger cluster of GPUs is needed to handle a very detailed cardiac cell model.