P2G: A Framework for Distributed Real-Time Processing of Multimedia Data

Abstract

Abstract-The computational demands of multimedia data processing are steadily increasing as consumers call for progressively more complex and intelligent multimedia services. New multi-core hardware architectures provide the required resources, but writing parallel, distributed applications remains a labor-intensive task compared to their sequential counter-part. For this reason, Google and Microsoft implemented their respective processing frameworks MapReduce [10] and Dryad [19], as they allow the developer to think sequentially, yet benefit from parallel and distributed execution. An inherent limitation in the design of these batch processing frameworks is their inability to express arbitrarily complex workloads. The dependency graphs of the frameworks are often limited to directed acyclic graphs, or even pre-determined stages. This is particularly problematic for video encoding and other algorithms that depend on iterative execution.With the Nornir runtime system for parallel programs [39], which is a Kahn Process Network implementation, we addressed and solved several of these limitations. However, it is more difficult to use than other frameworks due to its complex programming model. In this paper, we build on the knowledge gained from Nornir and present a new framework, called P2G, designed specifically for developing and processing distributed real-time multimedia data. P2G supports arbitrarily complex dependency graphs with cycles, branches and deadlines, and provides both data-and task-parallelism. The framework is implemented to scale transparently with available (heterogeneous) resources, a concept familiar from the cloud computing paradigm. We have implemented an (interchangeable) P2G kernel language to ease development. In this paper, we present a proof of concept implementation of a P2G execution node and some experimental examples using complex workloads like Motion JPEG and Kmeans clustering. The results show that the P2G system is a feasible approach to multimedia processing.

Low-Level Scheduling Implications for Data-Intensive Cyclic Workloads on Modern Microarchitectures

“…The implication of the very different behaviors observed on the different microarchitectures is a demand for scheduling that can adapt to varying conditions using instrumentation data collected at runtime. Our next step is therefore to design such a low-level scheduler in the context of our P2G processing framework [7] using our improvements for the work-stealing approach as a starting point [17].…”

“…However, these frameworks are limited by their design for batch processing with few dependencies across a large cluster of machines. We are therefore currently working on a framework aimed for distributed real-time multimedia processing called P2G [7]. In this work, we have identified several challenges with respect to low level scheduling.…”

A logical memory model for scaling parallel multimedia workloads

“…18 Creates a pair of orientation matrices (X and Y) and stores results. 19 Fetches orientation matrices, scales, and orientations. Creates odd and even Gabor filters and stores results.…”

“…The system that we imagine draws from ideas presented in our P2G proof-of-concept [19], which exposed parallelization and scheduled minimal code blocks at runtime. This approach is only feasible for coarse parallelism, whereas the P2G framework can expose parallelism at the finest possible granularity.…”

Processing of multimedia data using the P2G framework

“…Large processing frameworks like Google's MapReduce [1] and Microsoft's Dryad [3] are steps in the right direction, but they are targeted towards batch processing. As such, we present P2G [2], a framework designed to integrate concepts from modern batch processing frameworks into the world of real-time multimedia processing. We seek to scale transparently with the available resources (following the cloud computing paradigm) and to support heterogeneous computing resources, such as GPU processing cores.…”