Computing Community Consortium Blog

The goal of the Computing Community Consortium (CCC) is to catalyze the computing research community to debate longer range, more audacious research challenges; to build consensus around research visions; to evolve the most promising visions toward clearly defined initiatives; and to work with the funding organizations to move challenges and visions toward funding initiatives. The purpose of this blog is to provide a more immediate, online mechanism for dissemination of visioning concepts and community discussion/debate about them.

Arch2030: A Vision of Computer Architecture Research over the Next 15 Years

December 12th, 2016 / in Announcements, CCC, conference reports, Research News / by Helen Wright

The following blog post is by CCC Vice Chair and Executive Council member and University of Wisconsin-Madison Professor Mark D. Hill and co-author of the report.

In June 2016, I blogged about the successful Architecture 2030 Visioning Workshop, organized by Luis Ceze of the University of Washington and Thomas Wenisch of the University of Michigan, and partially sponsored by the Computing Community Consortium (CCC) in conjunction with ISCA’16 in Seoul, South Korea.

Recently CCC released the final report Arch2030: A Vision of Computer Architecture Research over the Next 15 Years with the endorsement of more forty research leaders in the field.

Key findings are below. Progress on these is necessary to provide the cost-performance improvements that information technology creators and beneficiaries have come to depend on.

  • The Specialization Gap: Democratizing Hardware Design: Developing hardware must become as easy, inexpensive, and agile as developing software to continue the virtuous history of computer industry innovation.

  • The Cloud as an Abstraction for Architecture Innovation: By leveraging scale and virtualization, Cloud computing providers can offer hardware innovations transparently and at low cost to even the smallest of their customers.

  • Going Vertical: 3D integration provides a new dimension of scalability.

  • Architectures “Closer to Physics”: The end of classical scaling invites more radical changes to the computing substrate.

  • Machine Learning as a Key Workload: Machine Learning is changing the way we implement applications. Hardware advancement makes machine learning over big data possible.

See the full report to learn more. It is going the be a fun journey!

Arch2030: A Vision of Computer Architecture Research over the Next 15 Years