Showing papers by "Moinuddin K. Qureshi published in 2007"

Adaptive insertion policies for high performance caching

Abstract: The commonly used LRU replacement policy is susceptible to thrashing for memory-intensive workloads that have a working set greater than the available cache size. For such applications, the majority of lines traverse from the MRU position to the LRU position without receiving any cache hits, resulting in inefficient use of cache space. Cache performance can be improved if some fraction of the working set is retained in the cache so that at least that fraction of the working set can contribute to cache hits.We show that simple changes to the insertion policy can significantly reduce cache misses for memory-intensive workloads. We propose the LRU Insertion Policy (LIP) which places the incoming line in the LRU position instead of the MRU position. LIP protects the cache from thrashing and results in close to optimal hitrate for applications that have a cyclic reference pattern. We also propose the Bimodal Insertion Policy (BIP) as an enhancement of LIP that adapts to changes in the working set while maintaining the thrashing protection of LIP. We finally propose a Dynamic Insertion Policy (DIP) to choose between BIP and the traditional LRU policy depending on which policy incurs fewer misses. The proposed insertion policies do not require any change to the existing cache structure, are trivial to implement, and have a storage requirement of less than two bytes. We show that DIP reduces the average MPKI of the baseline 1MB 16-way L2 cache by 21%, bridging two-thirds of the gap between LRU and OPT.

Line Distillation: Increasing Cache Capacity by Filtering Unused Words in Cache Lines

Abstract: Caches are organized at a line-size granularity to exploit spatial locality. However, when spatial locality is low, many words in the cache line are not used. Unused words occupy cache space but do not contribute to cache hits. Filtering these words can allow the cache to store more cache lines. We show that unused words in a cache line are unlikely to be accessed in the less recent part of the LRU stack. We propose line distillation (LDIS), a technique that retains only the used words and evicts the unused words in a cache line. We also propose distill cache, a cache organization to utilize the capacity created by LDIS. Our experiments with 16 memory-intensive benchmarks show that LDIS reduces the average misses for a 1MB 8-way L2 cache by 30% and improves the average IPC by 12%

Context look ahead storage structures

Abstract: A memory storage structure includes a memory storage device, and a first meta-structure having a first size and operating at a first speed. The first speed is faster than a second speed for storing meta-information based on information stored in a memory. A second meta-structure is hierarchically associated with the first meta-structure. The second meta-structure has a second size larger than the first size and operates at the second speed such that faster and more accurate prefetching is provided by coaction of the first and second meta-structures. A method is provided to assemble the meta-information in the first meta-structure and copy this information to the second meta-structure, and prefetching the stored information from the second meta-structure to the first meta-structure ahead of its use.

Method and apparatus improving performance of a digital memory array device

Abstract: A method for improving performance of a digital memory array device including a plurality of memory cells; each respective memory cell storing a first digital value and a second digital value being an inverse of the first digital value; storing of the first and second digital values being controlled by a first digital signal effecting selection of a specified memory cell for storing; includes: (a) determining an extant value relating to the first digital signal; (b) if the extant value has a first value, effecting a bit flip operation in the specified memory cell to invert values of at least one of the stored first digital and the second digital values; (c) if the extant value does not have the first value, foregoing the bit flip operation in the specified memory cell.