Travelled to:
1 × Mexico
1 × Spain
2 × France
21 × USA
Collaborated with:
∅ A.Chang L.Peh J.S.Keen A.A.Chien M.Erez S.W.Keckler B.Towles G.Michelogiannakis J.H.Ahn S.Rixner U.J.Kapasi J.D.Owens J.D.Balfour S.Fiske P.R.Nuth E.Spertus P.Agrawal P.R.Mattson C.Malachowsky B.Khailany N.P.Carter R.Tutundjian W.Horwat Y.Turakhia G.Bejerano N.Jiang D.U.Becker N.Jayasena M.Houston J.Y.Park M.Ren T.J.Knight K.Fatahalian A.Aiken P.Hanrahan J.Park S.Park D.Black-Schaffer C.Kozyrakis A.K.Ezzat W.C.Fischer H.V.Jagadish A.S.Krishnakumar
Talks about:
architectur (4) processor (4) regist (4) network (3) hardwar (3) design (3) custom (3) chip (3) log (3) interconnect (2)
Person: William J. Dally
DBLP: Dally:William_J=
Contributed to:
Wrote 29 papers:
- DAC-2013-DallyMK #design #tool support
- 21st century digital design tools (WJD, CM, SWK), p. 6.
- HPCA-2012-JiangBMD #network
- Network congestion avoidance through Speculative Reservation (NJ, DUB, GM, WJD), pp. 443–454.
- HPCA-2009-MichelogiannakisBD #network
- Elastic-buffer flow control for on-chip networks (GM, JDB, WJD), pp. 151–162.
- PPoPP-2008-HoustonPRKFADH #interface #memory management #multi #runtime
- A portable runtime interface for multi-level memory hierarchies (MH, JYP, MR, TJK, KF, AA, WJD, PH), pp. 143–152.
- DATE-2007-ParkPBBKD #architecture #embedded #performance #pointer
- Register pointer architecture for efficient embedded processors (JP, SBP, JDB, DBS, CK, WJD), pp. 600–605.
- HPCA-2007-Dally
- Interconnect-Centric Computing (WJD), p. 1.
- PPoPP-2007-KnightPRHEFADH #compilation #memory management
- Compilation for explicitly managed memory hierarchies (TJK, JYP, MR, MH, ME, KF, AA, WJD, PH), pp. 226–236.
- DAC-2005-ChangD #perspective
- Explaining the gap between ASIC and custom power: a custom perspective (AC, WJD), pp. 281–284.
- HPCA-2005-AhnED #architecture #parallel
- Scatter-Add in Data Parallel Architectures (JHA, ME, WJD), pp. 132–142.
- HPCA-2004-JayasenaEAD
- Stream Register Files with Indexed Access (NJ, ME, JHA, WJD), pp. 60–72.
- HPCA-2003-KhailanyDRKOT #scalability
- Exploring the VLSI Scalability of Stream Processors (BK, WJD, SR, UJK, JDO, BT), pp. 153–164.
- DAC-2001-DallyT #network
- Route Packets, Not Wires: On-Chip Interconnection Networks (WJD, BT), pp. 684–689.
- HPCA-2001-PehD #architecture #pipes and filters
- A Delay Model and Speculative Architecture for Pipelined Routers (LSP, WJD), pp. 255–266.
- ASPLOS-2000-MattsonDRKO #communication #scheduling
- Communication Scheduling (PRM, WJD, SR, UJK, JDO), pp. 82–92.
- DAC-2000-DallyC #design
- The role of custom design in ASIC Chips (WJD, AC), pp. 643–647.
- HPCA-2000-PehD
- Flit-Reservation Flow Control (LSP, WJD), pp. 73–84.
- HPCA-2000-RixnerDKMKO
- Register Organization for Media Processing (SR, WJD, BK, PRM, UJK, JDO), pp. 375–386.
- HPCA-1995-FiskeD #concurrent #parallel #scheduling #thread
- Thread Prioritization: A Thread Scheduling Mechanism for Multiple-Context Parallel Processors (SF, WJD), pp. 210–221.
- HPCA-1995-NuthD #implementation #performance
- The Named-State Register File: Implementation and Performance (PRN, WJD), pp. 4–13.
- PPoPP-1995-SpertusD #locality
- Evaluating the Locality Benefits of Active Messages (ES, WJD), pp. 189–198.
- ASPLOS-1994-CarterKD #hardware #performance
- Hardware Support for Fast Capability-based Addressing (NPC, SWK, WJD), pp. 319–327.
- CIKM-1994-KeenD #named
- XEL: Extended Ephemeral Logging for Log Storage Management (JSK, WJD), pp. 312–321.
- SIGMOD-1993-KeenD #evaluation #performance
- Performance Evaluation of Ephemeral Logging (JSK, WJD), pp. 187–196.
- PPoPP-1990-ChienD #concurrent
- Concurrent Aggregates (CA) (AAC, WJD), pp. 187–196.
- ASPLOS-1989-Dally #float
- Micro-Optimization of Floating Point Operations (WJD), pp. 283–289.
- DAC-1989-AgrawalTD #algorithm #hardware #logic
- Algorithms for Accuracy Enhancement in a Hardware Logic Simulator (PA, RT, WJD), pp. 645–648.
- PLDI-1989-HorwatCD #experience #implementation #programming
- Experience with CST: Programming and Implementation (WH, AAC, WJD), pp. 101–109.
- DAC-1987-AgrawalDEFJK #architecture #design #hardware
- Architecture and Design of the MARS Hardware Accelerator (PA, WJD, AKE, WCF, HVJ, ASK), pp. 101–107.
- ASPLOS-2018-TurakhiaBD #assembly #named
- Darwin: A Genomics Co-processor Provides up to 15, 000X Acceleration on Long Read Assembly (YT, GB, WJD), pp. 199–213.