Joint Exploration of Hardware Prefetching and Bandwidth Partitioning in Chip Multiprocessors
نویسندگان
چکیده
In this paper, we propose an analytical model-based study to investigate how hardware prefetching and memory bandwidth partitioning impact Chip Multi-Processors (CMP) system performance and how they interact. The model includes a composite prefetching metric that can help determine under which conditions prefetching can improve system performance, a bandwidth partitioning model that takes into account prefetching effects, and derives weighted speedup optimum bandwidth partition sizes for different cores. Simulation results show that selective prefetching, guided by the composite prefetching metric, coupled with dynamic bandwidth partitioning can improve system performance by 19.5% and 21.8% on a dual-core CMP and quad-core CMP respectively.
منابع مشابه
Accelerating sequential programs on Chip Multiprocessors via Dynamic Prefetching Thread
A Dynamic Prefetching Thread scheme is proposed in this paper to accelerate sequential programs on Chip Multiprocessors. This scheme belongs to the hardware-generated thread-based prefetching technique and can decouple the performance and correctness to some extent. This paper describes the necessary hardware infrastructure supporting Dynamic Prefetching Thread on traditional Chip Multiprocesso...
متن کاملEffective Instruction Prefetching In Chip Multiprocessors
threaded application performance, often achieved through instruction level parallelism per chip is increasing, the software and hardware techniques to exploit the potential of studies mostly involve distributed shared memory multiprocessors and fetching will not be fully effective at masking the remote fetch latency. the effective address of the load instructions along that path based upon a hi...
متن کاملA Hybrid Hardware/Software Generated Prefetching Thread Mechanism on Chip Multiprocessors
This paper proposes a hybrid hardware/software generated prefetching thread mechanism on Chip Multiprocessors(CMP). Two kinds of prefetching threads appear in our hybrid mechanism. Most threads belong to Dynamic Prefetching Thread, which are automatically generated, triggered, spawn and managed by hardware; The others are of Static Prefetching Thread, targeting at the critical delinquent loads ...
متن کاملHardware Prefetching in Bus-Based Multiprocessors: Pattern Characterization and Cost-Effective Hardware
Data prefetching has been widely studied as a technique to hide memory access latency in multiprocessors. Most recent research on hardware prefetching focuses either on uniprocessors, or on distributed shared memory (DSM) and other non bus-based organizations. However, in the context of bus-based SMPs, prefetching poses a number of problems related to the lack of scalability and limited bus ban...
متن کاملA Preliminary Evaluation of Cache-miss-initiated Prefetching Techniques in Scalable Multiprocessors
Prefetching is an important technique for reducing the average latency of memory accesses in scalable cache-coherent multiprocessors. Aggressive prefetching can signiicantly reduce the number of cache misses, but may introduce bursty network and memory traac, and increase data sharing and cache pollution. Given that we anticipate enormous increases in both network bandwidth and latency, we exam...
متن کامل