|
The group runs a weekly seminar series, covering papers,
projects, and events related with our research. These seminars
are open to anyone on Chalmers or GU who wishes to attend.
Seminars 2011
Current seminar series coordinator: Daniel Cederman.
| 
iCalendar |
RSS Feed |
| Date | Time | Location | Speaker | Refreshment Organizer | Title + Abstract |
| Thu, Dec 15 | 13:30 | 8103 | Mohamed Mustafa | - |
A demonstration of self-* pulse synchronization algorithms for autonomous TDMA MAC in VANETs.
|
| Thu, Dec 8 | 13:30 | 8103 | Negin | - |
The Consensus Problem in Fault-Tolerant Computing
|
| Thu, Nov 24 | 13:30 | 8103 | Vincenzo Gulisano | - |
Elasticity, Load Balancing and High Availability solutions in Data Streaming
|
| Thu, Nov 17 | 13:30 | 8103 | Vincenzo Gulisano | - |
StreamCloud Stream Processing Engine Overview
|
| Thu, Nov 10 | 13:30 | 8103 | Vincenzo Gulisano | - |
From DBs to Data Streaming
|
| Thu, Oct 27 | 13:30 | 8103 | Simon Claviere and Devan Sohier | - |
Local Clustering of Dynamical Distributed Systems with Inter-cluster Routing
|
| Thu, Oct 20 | 13:30 | 8103 | Mohamed Mustafa | - |
Self-* Pulse Synchronization for Autonomous
TDMA MAC in VANETs
|
| Thu, Oct 13 | 13:30 | 8103 | Frederic Gruau | - |
Rekindling parallelism
Computing in parallel means performing computation simultaneously, this
generates two distinct views:
-Performance view A mean to accelerate computation using coarse
grain parallelism.
-Decentralization view A new way of programming by decentralizing
massive fine grain parallelism.
Researchers on massive parallel models study the programming
expressiveness, i.e. new bio-inspired ways of computing such as
artificial neural network or multi agent systems solving new kinds of
problems, but are usually not directly concerned about high performance.
In contrast, researchers on high performance tend to narrow the scope of
parallel expressiveness by preserving the sequential model of computation
and defining specific language constructs that can lead to parallel
run-time performance for more classical parallel algorithms.
We argue that parallelism will really fully blossom only when both views
get unified through the achievement of a new generic computing model that,
while enabling decentralized computation, also supports classical way of
programming and incorporates the hardware constraints to provide parallel
performance. We are working on such a generic model called self
developing self mapping network. This paper first justifies the motivation
for such a model, and then sketches the fundamental principles of this
model.
|
| Thu, Oct 6 | 13:30 | 8103 | Negin | - |
Consensus
|
| Thu, Sep 29 | 13:30 | 8103 | Cristofer Englund | - |
The CoAct project and the Chalmers team in GCDC
|
| Thu, Sep 22 | 13:30 | 8103 | Georgios | - |
MDS Summer School on Discrete Optimization and Network
Flows
|
| Thu, Sep 15 | 13:30 | 5128 | Zhang | - |
SAC travel report
|
| Thu, Sep 8 | 13:00 | 5128 | Nhan | - |
Euro-Par travel report
|
| Thu, Sep 1 | 13:30 | 5128 | Zhang | - |
Collaborative Detection of DDoS Attacks over Multiple Network Domains
|
| Thu, Aug 25 | 13:30 | 5128 | Nhan | - |
Progress Guarantees when Composing Lock-free Objects
*Abstract*
Highly concurrent and reliable data objects are vital for parallel
programming.
Lock-free shared data objects are highly concurrent and guarantee that at
least
one operation, from a set of concurrently executed operations, finishes
after a
finite number of steps regardless of the state of the other operations.
Lock-free
data objects provide progress guarantees on the object level. In this paper,
we
first examine the progress guarantees provided by lock-free shared data
objects that have been constructed by composing other lock-free data
objects.
We observe that although lock-free data objects are composable when it comes
to linearizability, when it comes to progress guarantees they are not. More
specifically
we show that when a lock-free data object is used as a component (is shared)
by two
or more lock-free data objects concurrently, these objects can no longer
guarantee
lock-free progress. This makes it impossible for programmers to directly
compose
lock-free data objects and guarantee lock-freedom. To help programmability
in
concurrent settings, this paper presents a new synchronization mechanism for
composing lock-free data objects. The proposed synchronization mechanism
provides an interface to be used when calling a lock-free object from other
lock-free
objects, and guarantees lock-free progress for every object constructed. An
experimental
evaluation of the performance cost that the new mechanism introduces, as
expected,
for providing progress guarantees is also presented.
|
| Tue, Jul 5 | 13:30 | 5128 | Nhan | - |
An Approach to Eventual Consistency with Commutative Replicated Data Types
Eventual consistency is the weakest consistency level that guarantees convergence.
Informally, it requires that all replicas of an object will eventually reach
the same, correct, final value, assuming that no new updates are submitted to
the object. Eventual consistency is an important correctness criteria in systems with a
lazy, update-anywhere strategy. This seminar will give an introduction to eventual
consistency and previous works on Conflicted-free Replicated Data Types - an approach to
achieve eventual consistency.
|
| Thu, Jun 9 | 10:00 | 6128 | Andreas | - |
ICDCS rehearsal
|
| Thu, Jun 7 | 11:00 | 3364 | Gunnar Bj�rkman | - |
An introduction to SCADA systems and security issues within such systems
|
| Tue, May 31 | 10:00 | 5128 | William Johansson,
Gustaf Dalemar, Oskar Ingemarsson and Linus Hermansson | - |
A virtual traffic light
Traffic safety is something that is very hard to guarantee and causes
many deaths and injuries each year. This does not only cause emotional
suffering but also costs society great amounts of money. A big reason
for traffic accidents are intersections where the traditional approach
has been to build stationary traffic lights. It is not however
economically feasible to build traffic lights everywhere, which means
that safety can not be guaranteed in every intersection.
This report proposes a traffic light that uses wireless communication
between neighboring vehicles without the need of any stationary
device: a virtual traffic light. The design of the virtual traffic
light has through proof sketches and computer simulations been shown
to fulfill three criteria: safety, robustness and liveness. The
criteria states that two conflicting directions never should have
green at the same time, that the traffic light should be fault
tolerant and should guarantee that every vehicle arriving at the
intersection is able to cross in a finite time.
Compared to ordinary traffic lights, the virtual traffic light does
not use a stationary device and can therefore easily be created at
every intersection. This can create a considerable effect on traffic
safety and holds great value for any society. Because of this, the
project is something that is greatly demanded. The design that is
presented in this report also has large possibilities for future works
and may inspire many new projects.
|
| Thu, May 19 | 13:30 | 5128 | Giorgos | - |
The Price of Being Near-Sighted
|
| Thu, May 12 | 13:30 | 5128 | Zhang | - |
Distributed Data Classification
|
| Thu, May 5 | 13:30 | 5128 | Daniel | - |
Introduction to SCC
|
| Thu, Apr 21 | 13:30 | 5128 | Farnaz | - |
BADGERS11 travel report
|
| Thu, Apr 14 | 13:30 | 5128 | Nhan | - |
Wait-free Queue With Multiple Enqueuers and Dequeuers
|
| Wed, Apr 6 | 13:30 | 4128 | Farnaz | - |
On Collection of Large-Scale Multi-Purpose Datasets on Internet Backbone Links
|
| Thu, Mar 31 | 13:30 | 5128 | Mitra and Linus | - |
VTL progress report
|
| Tue, Mar 15 | 13:30 | 4128 | Zhang | - |
CluB: A Cluster Based Framework for Mitigating Distributed Denial of Service Attacks
Distributed Denial of Service (DDoS) attacks are threats not only for the
direct targets but also for the core of the network. They are also hard to
detect in advance, hence methods to deal with them need to be proactive.
By building on earlier work and improving on distribution of control aspects,
we propose a Cluster Based framework, which is called CluB, to mitigate DDoS attacks;
the method
balances the effectiveness-overhead trade-off by addressing the issue of
granularity of control in the network.
CluB, can collaborate with different routing policies in the network,
including contemporary datagram options.
We estimate the effectiveness of the framework and also study a set of
factors for tuning the granularity of control.
|
| Tue, Mar 8 | 13:15 | EE | Maged M. Michael | - |
Conditions for Strong Synchronization in Concurrent Algorithms
Concurrent algorithm designers often find it difficult to avoid expensive synchronization,
in particular store-load ordering and atomic operations. This talk presents conditions
under which, it is impossible to design algorithms that avoid such strong synchronization
patterns. The identified conditions impact operations on many common data types and
problems, such as FIFO queues, LIFO stacks, counters, sets, work queues, mutual exclusion.
The identification of conditions for strong synchronization open the door for tradeoffs between
synchronization overheads and the strength of specification of abstract data types. Strong
synchronization may be avoided by specification relaxations such as limiting concurrency,
limiting the API, and relaxing determinism.
Bio
Dr. Maged M. Michael is a research staff member at the IBM Thomas J. Watson Research
Center. He received a PhD. degree in computer science from the University of Rochester. His
research interests are primarily in concurrent algorithms, concurrent programming, and
concurrent memory management. He is the designer of well-known concurrent algorithms,
including lock-free malloc, hazard pointers, and non-blocking algorithms for common data
structures. His algorithms are used in commercial standard libraries, runtime systems,
middleware, and real-time systems.
|
| Fri, Mar 4 | 13:15 | 5128 | Andreas | - |
Rehearsal Licentiate Presentation
|
| Thu, Mar 3 | 13:30 | 5128 | Daniel | - |
Rehearsal PhD Defence
|
| Thu, Feb 17 | 13:30 | 5128 | Zhang | - |
Path authentication
|
| Thu, Feb 10 | 13:30 | 5128 | Mitra Pahlavan | - |
Master thesis proposal
|
| Thu, Jan 20 | 14:00 | 5128 | Daniel | - |
Data Structures in Work-Stealing
|
 Top of Page
Archived Seminars
Use the following links to get access to the seminar schedules
of previous years:
2011,
2010,
2009,
2008,
2007,
2006,
2005,
2004,
2003,
2002,
2001,
2000.
Top of Page
|
