• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Computational Biology and Bioinformatics, IEEE/ACM Transactions on >Boosting the FM-Index on the GPU: Effective Techniques to Mitigate Random Memory Access
【24h】

Boosting the FM-Index on the GPU: Effective Techniques to Mitigate Random Memory Access

机译：提高GPU上的FM索引：缓解随机内存访问的有效技术

获取原文
获取原文并翻译 | 示例
       
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

The recent advent of high-throughput sequencing machines producing big amounts of short reads has boosted the interest in efficient string searching techniques. As of today, many mainstream sequence alignment software tools rely on a special data structure, called the FM-index, which allows for fast exact searches in large genomic references. However, such searches translate into a pseudo-random memory access pattern, thus making memory access the limiting factor of all computation-efficient implementations, both on CPUs and GPUs. Here, we show that several strategies can be put in place to remove the memory bottleneck on the GPU: more compact indexes can be implemented by having more threads work cooperatively on larger memory blocks, and a -step FM-index can be used to further reduce the number of memory accesses. The combination of those and other optimisations yields an implementation that is able to process about two Gbases of queries per second on our test platform, being about 8 faster than a comparable multi-core CPU version, and about 3 to 5 faster than the FM-index implementation on the GPU provided by the recently announced Nvidia NVBIO bioinformatics library.
机译：最近产生大量短读的高通量测序仪的出现激发了人们对高效字符串搜索技术的兴趣。到目前为止，许多主流的序列比对软件工具都依赖于称为FM-index的特殊数据结构，该结构可在大型基因组参考文献中进行快速准确的搜索。但是，此类搜索会转换为伪随机内存访问模式，从而使内存访问成为CPU和GPU上所有计算效率高的实现的限制因素。在这里，我们展示了可以采用几种策略来消除GPU上的内存瓶颈：通过使更多线程在更大的内存块上协同工作，可以实现更紧凑的索引，并且-step FM-index可以用于进一步减少内存访问次数。这些优化措施和其他优化措施的结合，可以在我们的测试平台上每秒处理大约两个Gbase查询，比同类多核CPU版本快8个左右，比FM-快3到5个。最近宣布的Nvidia NVBIO生物信息学库提供的GPU上的索引实现。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号