Understanding and Designing New Server Architectures for Emerging Warehouse-Computing Environments
- 1 June 2008
- journal article
- Published by Association for Computing Machinery (ACM) in ACM SIGARCH Computer Architecture News
- Vol. 36 (3), 315-326
- https://doi.org/10.1145/1394608.1382148
Abstract
This paper seeks to understand and design next-generation servers for emerging "warehouse-computing" environments. We make two key contributions. First, we put together a detailed evaluation infrastructure including a new benchmark suite for warehouse-computing workloads, and detailed performance, cost, and power models, to quantitatively characterize bottlenecks. Second, we study a new solution that incorporates volume non-server-class components in novel packaging solutions, with memory sharing and flash-based disk caching. Our results show that this approach has promise, with a 2X improvement on average in performance-per-dollar for our benchmark suite.Keywords
This publication has 13 references indexed in Scilit:
- Fabric convergence implications on systems architecture2008 IEEE 14th International Symposium on High Performance Computer Architecture, 2008
- Youtube traffic characterizationPublished by Association for Computing Machinery (ACM) ,2007
- Power provisioning for a warehouse-sized computerPublished by Association for Computing Machinery (ACM) ,2007
- Combining Simulation and Virtualization through Dynamic SamplingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- FlashCachePublished by Association for Computing Machinery (ACM) ,2006
- Ensemble-level Power Management for Dense Blade ServersPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- A Cost-Effective Main Memory Organization for Future ServersPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- On the performance and use of dense serversIBM Journal of Research and Development, 2003
- Web search for a planet: the google cluster architectureIEEE Micro, 2003
- Power aware page allocationPublished by Association for Computing Machinery (ACM) ,2000