NVMain Extension for Multi-Level Cache Systems
نویسندگان
چکیده
In this paper, we present an extension of the NVMain memory simulator. The objective is to facilitate computer architects to model complex memory designs for future computing systems in an accurate simulation framework. The simulator supports commodity memory models for DRAM as well as emerging non-volatile memories technologies such STT-RAM, ReRAM, PCRAM and hybrid models. The current publicly available version of NVMain, NVMain 2.0, offers support for main memory (using DRAM and NVM technologies) and a die-stacked DRAM cache. We extend the cache model of the simulator by introducing an SRAM cache model and its supporting modules. With this addition, designers can model hybrid multi-level cache hierarchies by using the die-stacked DRAM cache and SRAM caches. We provide a reference implementation of an optimized cache organization scheme for die-stacked DRAM cache along with a tag-cache unit that, together, reduces cache miss latency. To enable integration of the new features in the existing memory hierarchy, we make necessary changes to the memory controller. We provide functional verification of the new modules and put forward our approach for timing and power verification. We run random mixes of the SPEC2006 benchmarks and observe±10% difference in simulation results.
منابع مشابه
AMC: an adaptive multi-level cache algorithm in hybrid storage systems
Hybrid storage systems that consist of flash-based solid state drives (SSDs) and traditional disks are now widely used. In hybrid storage systems, there exists a two-level cache hierarchy that regard dynamic random access memory (DRAM) as the first level cache and SSD as the second level cache for disk storage. However, this two-level cache hierarchy typically uses independent cache replacement...
متن کاملTiming Predictions for Multi-Level Caches
This paper describes a framework to extend timing predictions of real-time applications from architectures with primary caches to architectures with multi-level caches. First, general problems of extending timing analysis frameworks to multi-level memory hierarchies are discussed, including a method for dealing with uni-ed caches. Second, an existing data-ow framework for cache analysis, the fr...
متن کاملA Power-Aware Multi-Level Cache Organization Effective for Multi-Core Embedded Systems
Recent system design trends suggest multicore architecture for all computing platforms including distributed and embedded systems running real-time applications. Multilevel caches in a multicore system pose serious challenges as cache requires huge amount of energy to be operated and cache increases unpredictability due to its dynamic behavior. Bandwidth and synchronization problems are also cr...
متن کاملThe Cost of Uncore in Throughput-Oriented Many-Core Processors
Achieving performance through traditional techniques such as extracting more instruction level parallelism or increasing clock frequencies are losing their effectiveness due to the power wall. Multi-core processors have been put forth as a more power-performance efficient means of continuing performance scaling while coping with the realities of a power-limited design. Extrapolating the increas...
متن کاملPerformance Models for Electronic Structure Methods on Modern Computer Architectures
Electronic structure codes are computationally intensive scientific applications used to probe and elucidate chemical processes at an atomic level. Maximizing the performance of these applications on any given hardware platform is vital in order to facilitate larger and more accurate computations. An important part of this endeavor is the development of protocols for measuring performance, and ...
متن کامل