Optimizing Reaching Definitions Overhead in Queue Processors
نویسندگان
چکیده
Queue computers are a viable option for embedded systems design. Queue computers feature a dense instruction set, high parallelism, low hardware complexity. In this paper we propose an optimization technique to reduce the overhead of long reaching definitions of variables in queue processors. Long reaching definitions have direct relationship with the queue register file utilization of the processor, and also to the bits in the instruction set reserved to reference operands. Using integer and embedded benchmarks, we demonstrate that our technique effectively reduces the length of reaching definitions up to 90%.
منابع مشابه
Amortizing Software Queue Overhead for Pipelined Inter-Thread Communication
Future chip multiprocessors are expected to contain multiple ondie processing cores. Increased memory system contention and wire delays will result in high inter-core latencies in these processors. Thus, parallelizing applications to efficiently execute on multiple contexts is key to achieving continued performance improvements. Recently proposed pipelined multithreading (PMT) techniques have s...
متن کاملString Concatenation Optimization on Java Bytecode
String concatenation via the “+” operator is one of the most convenient things to do in Java, and also one of the most expensive, in terms of memory and performance. In this paper, we present a comprehensive approach to reduce the overhead of consuming string concatenation operations by implicitly transforming the Java bytecode. The transformation is based on the results of the liveness analysi...
متن کاملSmart priority queue algorithms for self-optimizing event storage
Low run-time overhead, self-adapting storage policies for priority queues called Smart Priority Queue (SPQ) techniques are developed and evaluated. The proposed SPQ policies employ a lowcomplexity linear queue for near-head activities and a rapid-indexing variable bin-width calendar queue for distant events. The SPQ configuration is determined by monitoring queue access behavior using cost-scor...
متن کاملDynamic Scheduling Strategies for Shared-memory Multiprocessors
Efficiently scheduling parallel tasks on to the processors of a shared-memory multiprocessor is critical to achieving high performance. Given perfect information at compile-time, a static scheduling strategy can produce an assignment of tasks to processors that ideally balances the load among the processors while minimizing the run-time scheduling overhead and the average memory referencing del...
متن کاملAnalyzing Queuing Systems with Coupled Processors through Semidefinite Programming
We consider queuing systems with coupled processors, where the service rate at each queue varies depending on the set of queues in the system with non-zero queue lengths. In general, such queuing systems are very difficult to analyze and steady state queue length distributions are known only for two-queue systems. The coupled-processors model arises naturally in the study of several systems whe...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- JCIT
دوره 2 شماره
صفحات -
تاریخ انتشار 2007