• Corpus ID: 8053056

Performance Analysis of On-Chip Cache and Main Memory Compression Systems for High-End Parallel Computers

  title={Performance Analysis of On-Chip Cache and Main Memory Compression Systems for High-End Parallel Computers},
  author={Keun Soo YIM and Jihong Kim and Kern Koh},
Cache and memory compression systems have been developed for improving memory system performance of high-performance parallel computers. Cache compression systems can reduce onchip cache miss rate and off-chip memory traffic by storing and transferring cache lines in compressed form, while memory compression systems can expand main memory capacity by storing memory pages in compressed form. However, these systems have not been quantitatively evaluated on an identical condition, making it… 

Figures and Tables from this paper

A Space-Efficient On-Chip Compressed Cache Organization for High Performance Computing

This paper presents the fine-grained compressed cache line management which addresses the fragmentation problem, while avoiding an increase in the metadata size such as tag field and VM page table.

C-Pack: A High-Performance Microprocessor Cache Compression Algorithm

This work presents a lossless compression algorithm that has been designed for fast on-line data compression, and cache compression in particular, and reduces the proposed algorithm to a register transfer level hardware design, permitting performance, power consumption, and area estimation.


A lossless cache compression algorithm is proposed and designed for high performance processor that allows Parallel compression of multiple words using dictionary mode and compression ratio is not degraded in the performance.

A Space-Efficient Virtual Memory Organization for On-Chip Compressed Caches

A spaceefficient virtual memory organization technique for the on-chip compressed caches is presented, which expands the main memory capacity by 104-150% with the SPEC benchmark suite, which is about twice larger than that achievable with an existing on- chip compressed cache.

Transparent memory hierarchy compression and migration

This dissertation presents several new operating system and architecture techniques that use elements of the virtual and physical memory system to improve the functionality, power consumption, and performance of embedded systems such as multimedia devices and wireless sensor network nodes.


This work proposes a lossless compression algorithm that has been designed for high performance, fast on-line data compression and particularly for cache compression, including combining pairs of compressed lines into one cache line and allowing parallel compression of multiple words while using a single dictionary.

Improving disk bandwidth-bound applications through main memory compression

This paper implements and evaluates in the Linux OS a full SMP capable main memory compression subsystem that takes advantage of a current multicore and multiprocessor system to increase the performance of bandwidth sensitive applications like the SPECweb2005 benchmark with promising results.

Accelerating software memory compression on the Cell/B.E.

A software memory compression system for the Linux kernel is proposed and implemented, that offload the CPU–intensive compression task to the specialized processor units present in the Cell/B.E.

Design and Implementation of a High-Performance Microprocessor Cache Compression Algorithm

This work presents a lossless compression algorithm that has been designed for on-line memory hierarchy compression, and cache compression in particular, and reduces the algorithm to a register transfer level hardware implementation, permitting performance, power consumption, and area estimation.

A compression layer for NAND type flash memory systems

This paper improved the compression layer for NandFlash, which can be coordinated with the X-RL algorithm, to avoid overhead and reduce the degree of internal fragmentation in the compressed data pages and can improve the compression rate.



Hardware Compressed Main Memory: Operating System Support and Performance Evaluation

This paper describes operating system techniques that can deal with dynamically changing memory sizes and shows that the hardware compression of memory has a negligible performance penalty compared to a standard memory for many applications and improves the performance significantly.

IBM Memory Expansion Technology (MXT)

This architecture is the first of its kind to employ real-time main-memory content compression at a performance competitive with the best the market has to offer.

Frequent value compression in data caches

The design and evaluation of the compression cache (CC) is presented which is a first level cache that has been designed so that each cache line can either hold one uncompressed line or two cache lines which have been compressed to at least half their lengths.

Performance evaluation of computer architectures with main memory data compression

Hardware-assisted data compression for energy minimization in systems with embedded processors

A novel and efficient architecture for on-the-fly data compression and decompression whose field of operation is the cache-to-memory path of a core-based system running standard benchmark programs is proposed.

The Compression Cache: Using On-line Compression to Extend Physical Memory

Measurements using Sprite on a DECstation 1 5000/200 workstation with a local disk indicate that some memory-intensive applications running with a compression cache can run two to three times faster than on an unmodiied system.

Design and performance of a main memory hardware data compressor

  • M. KjelsøM. GoochS. Jones
  • Computer Science
    Proceedings of EUROMICRO 96. 22nd Euromicro Conference. Beyond 2000: Hardware and Software Design Strategies
  • 1996
It is demonstrated that paging due to insufficient memory resources can reduce system performance several fold, and it is argued that hardware memory compression can eliminate this paging hence providing a substantial performance improvement.

The Case for Compressed Caching in Virtual Memory Systems

This study shows that technology trends favor compressed virtual memory--it is attractive now, offering reduction of paging costs of several tens of percent, and it will be increasingly attractive as CPU speeds increase faster than disk speeds.

Compressed caching and modern virtual memory simulation

This dissertation begins by outlining an approach to reducing reference traces for use in simulations of virtual memory, and uses reference traces to explore compressed caching—the insertion of a new, compressed level of RAM into the memory hierarchy.

A very fast algorithm for RAM compression

It is shown that in many cases memory pages contain highly compressible data, with a very large amount of zero-valued elements, which suggests the replacement of slow, adaptive compression algorithms with very fast ones based on static Huffman codes.