Transactional memory support for scalable and transparent parallelization of multiplayer games

Abstract

In this paper, we study parallelization of multiplayer games using software Transactional Memory (STM) support. We show that the STM provides not only ease of programming, but also better performance than that achievable with stateof-the-art lock-based programming, for this realistic high impact application.For this purpose, we use a game benchmark, SynQuake, that extracts the main data structures and the essential features of the popular game Quake. SynQuake can be driven with a synthetic workload generator that flexibly emulates client game actions and various hot-spot scenarios in the game world.We implement, evaluate and compare the STM version of SynQuake with a state-of-the-art lock-based parallelization of Quake, which we ported to SynQuake. While in STM-SynQuake support for maintaining the consistency of each complex game action is automatic, conservative locking of surrounding objects within a bounding box, for the duration of the game action is inherently needed in lockbased SynQuake. This leads to higher scalability of STMSynQuake versus lock-based SynQuake, due to a higher degree of false sharing in the latter. Task assignment to threads has a second-order effect on the scalability of STMSynQuake, due to its impact on the application's true sharing patterns. We show that a dynamic locality-aware task assignment to threads provides the best trade-off between load balancing and conflict reduction.

Towards Transactional Memory for OpenMP

“…Usually they are based on the use of software implementations of transactional memory, with varying results in terms of performance. Examples of such efforts include Delaunay triangulation [10], minimum spanning forest of sparse graphs [11] Lee routing algorithm [12], multiplayer game servers such as QuakeTM [13] and Atomic Quake [14] (based on a lock-based version of Quake [15]) and SynQuake [16]; or benchmarks (STMBench7 [17], STAMP [18] and RMS-TM [19], all of them composed of a number of applications representative of a variety of application domains.…”

“…Is Software Transactional Memory (STM) faster then locks in a real world application, and not just toy laboratory benchmarks? SynQuake [16] used a form of Quake, a game server reimplemented using pure Software TM (STM) from locks to examine the performance and scalability difference of TM without hardware support. Parallelization of multi-player game code for the purposes of scaling the game server is inherently difficult.…”

Investigating informative performance metrics for a multicore game world server

“…They were able to achieve better performance; however, the the overheads incurred by STM were again high. A subsequent study by Lupei et al [29,30] introduced SynQuake, an STM-based server derived from Quake III. These results were more promising, reporting better performance and scalability than lockbased strategies.…”

“…In most cases, one quantifiable metric such as server throughput ( [27]), or frame execution time ( [28] [29,30]) is used in an ad hoc fashion, without thorough consideration of how that metric relates to the underlying performance.…”

Transactionalizing legacy code

“…In the former category, studies by Rossbach et al [28] and Pankratius and Adl-Tabatabai [24] have shown that TM can simplify the creation of new software. Similarly, there are several microbenchmark and benchmark suites that demonstrate the use of TM, most notably STAMP [23], EigenBench [15], Atomic Quake [37], Lee-TM [2], SynQuake [20], and RMS-TM [16].…”