Another Trip to the Wall
Open Access
- 5 October 2015
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 31-36
Abstract
First defined two decades ago, the memory wall remains a fundamental limitation to system performance. Recent innovations in 3D-stacking technology enable DRAM devices with much higher bandwidths than traditional DIMMs. The first such products will soon hit the market, and some of the publicity claims that they will break through the memory wall. Here we summarize our analysis and expectations of how such 3D-stacked DRAMs will affect the memory wall for a set of representative HPC applications. We conclude that although 3D-stacked DRAM is a major technological innovation, it cannot eliminate the memory wall.Keywords
Funding Information
- Generalitat de Catalunya (2014-SGR-1272,2014-SGR-1051)
- Seventh Framework Programme (288777,610402)
- Ministerio de Economía y Competitividad (TIN2012-34557,SEV-2011-00067,SVP-2014-068501)
This publication has 11 references indexed in Scilit:
- EUROSERVER: Energy Efficient Node for European Micro-Servers2014
- DTail2014
- 4th generation Intel™ Core processor, codenamed Haswell2013
- Power7: IBM's Next-Generation Server ProcessorIEEE Micro, 2010
- Roofline: An Insightful Visual Performance Model for Floating-Point Programs and Multicore Architectures2009
- The Memory System: You Can't Avoid It, You Can't Ignore It, You Can't Fake ItSynthesis Lectures on Computer Architecture, 2009
- A case for intelligent RAMIEEE Micro, 1997
- Direct RAMbus technology: the new main memory standardIEEE Micro, 1997
- Memory bandwidth limitations of future microprocessors1996
- A set of level 3 basic linear algebra subprogramsACM Transactions on Mathematical Software, 1990