Travelled to:2 × USA
Collaborated with:Hongyuan Liu 0002 S.Pai A.K.Mishra R.Iyer C.R.Das O.Mutlu C.Xu Y.Xie V.Narayanan O.Kayiran N.C.Nachiappan M.T.Kandemir R.Ausavarungnirun Vance Miller Joshua Landgraf S.Ghose Jayneel Gandhi C.J.Rossbach
Talks about:perform (2) cach (2) hierarchi (1) architect (1) techniqu (1) redesign (1) volatil (1) support (1) schedul (1) concurr (1)
Person: Adwait Jog
DBLP: Jog:Adwait
Contributed to:
2013
201220182020Wrote 4 papers:
- ASPLOS-2013-JogKNMKMID #array #concurrent #named #owl #performance #scheduling #thread
- OWL: cooperative thread array aware scheduling techniques for improving GPGPU performance (AJ, OK, NCN, AKM, MTK, OM, RI, CRD), pp. 395–406.
- DAC-2012-JogMXXNID #architecture #performance
- Cache revive: architecting volatile STT-RAM caches for enhanced performance in CMPs (AJ, AKM, CX, YX, VN, RI, CRD), pp. 243–252.
- ASPLOS-2018-Ausavarungnirun #concurrent #gpu #memory management #multi #named
- MASK: Redesigning the GPU Memory Hierarchy to Support Multi-Application Concurrency (RA, VM, JL, SG, JG, AJ, CJR, OM), pp. 503–518.
- ASPLOS-2020-0002PJ #how #performance #why
- Why GPUs are Slow at Executing NFAs and How to Make them Faster (HL0, SP, AJ), pp. 251–265.