BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20200129T163557Z
LOCATION:603
DTSTART;TZID=America/Denver:20191118T113000
DTEND;TZID=America/Denver:20191118T115000
UID:submissions.supercomputing.org_SC19_sess122_ws_pmbss102@linklings.com
SUMMARY:Comparing Managed Memory and UVM with and without Prefetching on N
 VIDIA Volta GPUs
DESCRIPTION:Workshop\n\nComparing Managed Memory and UVM with and without 
 Prefetching on NVIDIA Volta GPUs\n\nGayatri, Gott, Deslippe\n\nOne of the 
 major differences in many-core versus multicore architectures is the prese
 nce of two different memory spaces: a host space and a device space. In th
 e case of NVIDIA GPUs, the device is supplied with data from the host via 
 one of the multiple memory management API calls provided by the CUDA frame
 work, such as CudaMallocManaged and CudaMemCpy.  Modern systems, such as t
 he Summit supercomputer, have the capability to avoid the use of CUDA call
 s for memory management and access the same data on GPU and CPU. This is d
 one via the Address Translation Services (ATS) technology that gives a uni
 fied virtual address space for data allocated with malloc and new if there
  is an NVLink connection between the two memory spaces. In this paper, we 
 perform a deep analysis of the performance achieved when using two types o
 f unified virtual memory addressing: UVM and managed memory.\n\nTag: Works
 hop Reg Pass, Benchmarks, Performance, Scientific Computing, Simulation\n\
 nRegistration Category: Workshop Reg Pass, Benchmarks, Performance, Scient
 ific Computing, Simulation
URL:https://sc19.supercomputing.org/presentation/?id=ws_pmbss102&sess=sess
 122
END:VEVENT
END:VCALENDAR