BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Women@CL Talklet Event - Coral Westoby and Alessia Angeli and Smit
 a Vijaya Kumar
DTSTART:20220203T130000Z
DTEND:20220203T140000Z
UID:TALK169514@talks.cam.ac.uk
CONTACT:Lorena Qendro
DESCRIPTION:*Zoom link*: https://cl-cam-ac-uk.zoom.us/j/91801402497?pwd=a2
 93N3dHcVhMcEJyVGlHa1gzWE5sZz09\n\n----------------------------------------
 -------\n\n*Speaker*: Coral Westoby\n\n*Title*: The POETS Project: Partial
 ly Ordered Event Triggered Systems for future HPC applications.\n\n*Abstra
 ct*: The physical sciences have been intrigued by event driven computing s
 ystems since the first analog integrators. The POETS project (Cambridge le
 ad S. Moore) provides a hardware platform to observe convincing weak scali
 ng for simulations running under a Partially Ordered Event Triggered Syste
 m\, with the aim of motivating future HPC architectural developments. Curr
 ent research activities include applications investigation in molecular me
 chanics\, neural biology\, and ML alongside the programming and architectu
 ral support required to use tens of thousands of threads where 4 instructi
 ons take longer than a message passing operation. Within the CL\, a cluste
 r of 72 Intel DE10 SX280 boards with 100Gb/s interconnect is currently und
 er construction\, providing a fabric an order of magnitude larger than cur
 rently available.\n\n-----------------------------------------------\n\n*S
 peaker*: Alessia Angeli\n\n*Title*: Kinematics of reaching movements to in
 hibit a prepotent response: A wearable 3-axis\naccelerometer analysis.\n\n
 *Abstract*: The aim of our research is to explore the distinctive contribu
 tion of motor planning and control to\nhuman reaching movements. In partic
 ular\, the movements were triggered by the selection of a\nprepotent respo
 nse (Dominant) or\, instead\, by the inhibition of the prepotent response\
 , which\nrequired the selection of an alternative one (Non-dominant). To t
 his end\, we adapted a Go/NoGo task to investigate both the dominant and n
 on-dominant movements of a cohort of 19 adults\,\nutilizing kinematic meas
 ures to discriminate between the planning and control components of the\nt
 wo actions. In this experiment\, a low-cost\, easy to use\, 3-axis wrist-w
 orn accelerometer was put\nto good use to obtain raw acceleration data and
  to compute and break down its velocity\ncomponents. The values obtained w
 ith this task indicate that with the inhibition of a prepotent\nresponse\,
  the selection and execution of the alternative one yields both a longer r
 eaction time and\nmovement duration. Moreover\, the peak velocity occurred
  later in time in the non-dominant\nresponse with respect to the dominant 
 response\, revealing that participants tended to indulge\nmore in motor pl
 anning than in adjusting their movement along the way. Finally\, comparing
  such\nresults to the findings obtained by other means in the literature\,
  we discuss the feasibility of an\naccelerometer-based analysis to disenta
 ngle distinctive cognitive mechanisms of human\nmovements. In addition\, t
 he development of motor skills is strictly connected to the optimisation\n
 of cognitive abilities and difficulties to inhibit motor behaviours are co
 mmon to\nneurodevelopmental disorders such as Attention Deficit and Hypera
 ctivity Disorder (ADHD).\nHowever\, the motor and cognitive processes bene
 ath the profound interindividual differences\nthat characterize this popul
 ation are still unclear. For these reasons\, we are working in this\ndirec
 tion\, considering the same experimental setting\, in order to investigate
  both the dominant\nand non-dominant movements of a cohort of ADHD childre
 n.\n\n-----------------------------------------------\n\n*Speaker*: Smita 
 Vijaya Kumar\n\n*Title*: How To Simulate Standard Workload Traces on Kuber
 netes Cluster.\n\n*Abstract*: Many companies have made available traces of
  workloads running on their compute clusters. The well-known ones include 
 workloads from Google\, Alibaba\, Microsoft\, and Yahoo. The workloads are
  a collection of requests\, and each request is described by parameters su
 ch as the arrival time\, number of tasks and task durations. How can one u
 se these workloads and simulate them on a Kubernetes cluster? This talk wi
 ll walk us through the steps involved in converting a large textual worklo
 ad file consisting of tens of thousands of such requests into actual jobs 
 that are consumed by Kubernetes.\n\n--------------------------------------
 ---------
LOCATION:Zoom
END:VEVENT
END:VCALENDAR