G e state of research id parallel simulation now demands u m m : / w l t h a o f synchronization, communication, and event executions. models I t is evident that large-scale simulations involving many interacting logical processes should be a As researchers active in the study of synchronization focal point of such experimentation, as large-scale methods and load balancing, we have undertaken the simulations will benefit the most from parallelism This lmplenlentatlon of a Parallel simulation testbed, Yet realization raises a number of issues. Large-scale parallel Anofhe7 W~t z d o~~l~2 g N e f~~k S 2 n l~l n f~ (YAWNS) simulations must aggregate many logical processes onto which addresses these problenls. YAWNS 1s being each machine in a distributed memory architecture. This implemented on Our Intel ipsc/21 and Will Serve as the fact creates internal management problen1s---how does basis for our studies in the parallel simulation of timed Petri-nets, queueing networks, Monte Carlo physical s i ni u 1 at i on s, h i g hl y mu 1 t i processor what computing systems YAWNS provides a software layer between the LPs, and the communication network All communication and synchronization between processors i s initiated and controlled by individual version of YAWNS running on each processor, as shown in figure 1.YAWNS uses a both a new synchronous synchronization pro t o c o 1, and a n e w " rn u 1 t ior d e r " p r i or i t y-qu e u e