The massive parallelism present in GPUs comes at the cost of reduced L1 and L2 cache
sizes per thread, leading to serious cache contention problems such as thrashing. Hence …

Authors' addresses: Devashree Tripathy, University of California, Riverside, 900 University
Ave, Riverside, CA, 92521, USA, devashree. tripathy@ email. ucr. edu; AmirAli Abdolrashidi …

Authors' addresses: Devashree Tripathy, University of California, Riverside, 900 University
Ave, Riverside, CA, 92521, USA, devashree. tripathy@ email. ucr. edu; AmirAli Abdolrashidi …

This work is partly supported by NSF Grants CCF-1815643 and CCF-1907401. Authors'
addresses: D. Tripathy, A. Abdolrashidi, LN Bhuyan, L. Zhou, and D. Wong, University of …

Authors' addresses: Devashree Tripathy, University of California, Riverside, 900 University
Ave, Riverside, CA, 92521, USA, devashree. tripathy@ email. ucr. edu; AmirAli Abdolrashidi …

Authors' addresses: Devashree Tripathy, University of California, Riverside, 900 University
Ave, Riverside, CA, 92521, USA, devashree. tripathy@ email. ucr. edu; AmirAli Abdolrashidi …