Player is loading...

Embed

Embed code

Transcriptions

Note: this content has been automatically generated.
00:00:01
and in good old days valuable by any so are the service
00:00:05
the new so every other year disorder was twice as fast
00:00:08
as the one that you had before today how was so some not getting as fast as they had been get and
00:00:14
the graph on this uh on the slide is showing good single third
00:00:18
performance as well as number of course course over over the
00:00:20
years as you can see all of them are flat and it means that the times a hard day was providing freely
00:00:27
the performance improvement the is all our hands a this means that's all
00:00:32
for now as more responsibility to sustain the data would performance
00:00:37
in my research i investigate opportunities and take needs to improve all
00:00:42
but improve performance of a particular software system database system
00:00:46
by using c. p. u. resources efficiently so now let's let's let's
00:00:50
first look at how database systems utilise the c. p. resource
00:00:54
a on the slide bigger off on the left hand side shoals c. p. u. position for
00:00:57
database systems as you can see they are only busy at ten percent of the time
00:01:02
the graph on the right hand side on the other hand zooms into
00:01:04
the business cycles and categorise them interested and useful cycles it
00:01:09
you get for three database systems d. b. m. s. a. e. d. b. m. s. b. d. b. m. s. c.
00:01:13
it you can see more than seventy percent of the time c. p. u. cycles are based the stories altogether show that
00:01:19
the system space more than ninety seven percent of the competition capacity in today's modern source
00:01:26
so there are two main reasons for this waste the first one is interference
00:01:31
it interferes happens due to fog reason multiple users sharing the same so resources
00:01:36
uh for different databases interfere with each other when they shapes all resources in
00:01:41
terms of they are resource demand eh computing resource demand kinds commercially
00:01:47
the resistance all located an entire so for a single user and therefore
00:01:50
and utilise the mushy the second reason is hard there's severe mismatch
00:01:55
into this more than processes their memories wireless them uh uh features that
00:01:59
software can exploit database systems however can mention are not beal
00:02:04
to explode all the available part isn't in the process of in today's modern processes
00:02:09
i used to all major hardware mechanism to improve c.
00:02:12
p. u. transition for database systems isolation and perfection
00:02:16
isolation aloe shaving so resources among different databases the
00:02:20
dots offering much from interference whisper fetching
00:02:23
laws part rising dataquest that would otherwise be see lies by the database system
00:02:29
by isolating and highlighting dataquest you can if you can improve c. v. c. p.
00:02:33
u. transition significantly enhance sustained the data would performance for database systems thanks

Share this talk: 


Conference program

Welcome address
Andreas Mortensen, Vice President for Research, EPFL
7 June 2018 · 9:49 a.m.
Introduction
Jim Larus, Dean of IC School, EPFL
7 June 2018 · 10 a.m.
The Young Software Engineer’s Guide to Using Formal Methods
K. Rustan M. Leino, Amazon
7 June 2018 · 10:16 a.m.
Safely Disrupting Computer Networks with Software
Katerina Argyraki, EPFL
7 June 2018 · 11:25 a.m.
Short IC Research Presentation 2: Gamified Rehabilitation with Tangible Robots
Arzu Guneysu Ozgur, EPFL (CHILI)
7 June 2018 · 12:15 p.m.
Short IC Research Presentation 3: kickoff.ai
Lucas Maystre, Victor Kristof, EPFL (LCA)
7 June 2018 · 12:19 p.m.
Short IC Research Presentation 5: CleanM
Stella Giannakopoulo, EPFL (DIAS)
7 June 2018 · 12:25 p.m.
Short IC Research Presentation 6: Understanding Cities through Data
Eleni Tzirita Zacharatou, EPFL (DIAS)
7 June 2018 · 12:27 p.m.
Short IC Research Presentation 7: Datagrowth and application trends
Matthias Olma, EPFL (DIAS)
7 June 2018 · 12:31 p.m.
Short IC Research Presentation 8: Point Cloud, a new source of knowledge
Mirjana Pavlovic, EPFL (DIAS)
7 June 2018 · 12:34 p.m.
Short IC Research Presentation 9: To Click or not to Click?
Eleni Tzirita Zacharatou, EPFL (DIAS)
7 June 2018 · 12:37 p.m.
Short IC Research Presentation 10: RaaSS Reliability as a Software Service
Maaz Mohiuddlin, LCA2, IC-EPFL
7 June 2018 · 12:40 p.m.
Short IC Research Presentation 11: Adversarial Machine Learning in Byzantium
El Mahdi El Mhamdi, EPFL (LPD)
7 June 2018 · 12:43 p.m.
20s pitch 1: Cost and Energy Efficient Data Management
Utku Sirin, (DIAS)
7 June 2018 · 2:20 p.m.
20s pitch 2: Gamification of Rehabilitation
Arzu Guneysu Ozgur, EPFL (CHILI)
7 June 2018 · 2:21 p.m.
20s pitch 4: Neural Network Guided Expression Transformation
Romain Edelmann, EPFL (LARA)
7 June 2018 · 2:21 p.m.
20s pitch 5: Unified, High Performance Data Cleaning
Stella Giannakopoulo, EPFL (DIAS)
7 June 2018 · 2:21 p.m.
20s pitch 6: Interactive Exploration of Urban Data with GPUs
Eleni Tzirita Zacharatou, EPFL (DIAS)
7 June 2018 · 2:22 p.m.
20s pitch 7: Interactive Data Exploration
Matthias Olma, EPFL (DIAS)
7 June 2018 · 2:22 p.m.
20s pitch 8: Efficient Point Cloud Processing
Mirjana Pavlovic, EPFL (DIAS)
7 June 2018 · 2:23 p.m.
20s pitch 9: To Click or not to Click?
Eleni Tzirita Zacharatou, EPFL (DIAS)
7 June 2018 · 2:24 p.m.
20s pitch 10: RaaSS Reliability as a Software Service
Maaz Mohiuddlin, LCA2, IC-EPFL
7 June 2018 · 2:24 p.m.
20s pitch 11: Adversarial Machine Learning in Byzantium
El Mahdi El Mhamdi, EPFL (LPD)
7 June 2018 · 2:24 p.m.
Machine Learning: Alchemy for the Modern Computer Scientist
Erik Meijer, Facebook
7 June 2018 · 2:29 p.m.