ISEP – CISTER – Relatórios
Permanent URI for this collection
Browse
Browsing ISEP – CISTER – Relatórios by Author "Andersson, Björn"
Now showing 1 - 10 of 29
Results Per Page
Sort Options
- A 12*(1+|R|/(4m))-speed algorithm for scheduling constrained-deadline sporadic real-time tasks on a multiprocessor comprising m processors where a task may request one of |R| sequentially-reusable shared resourcesPublication . Andersson, Björn; Easwaran, ArvindWe present a 12*(1+|R|/(4m))-speed algorithm for scheduling constrained-deadline sporadic real-time tasks on a multiprocessor comprising m processors where a task may request one of |R| sequentially-reusable shared resources.
- Analysing TDMA with slot skippingPublication . Andersson, Björn; Tovar, Eduardo; Pereira, NunoWe propose a schedulability analysis for a particular class of time division multiple access (TDMA) networks, which we label as TDMA/SS. SS stands for slot skipping, reflecting the fact that a slot is skipped whenever it is not used. Hence, the next slot can start earlier in benefit of hard real-time traffic. In the proposed schedulability analysis, we assume knowledge of all message streams in the system, and that each node schedules messages in its output queue according to a rate monotonic policy (as an example). We present the analysis in two steps. Firstly, we address the case where a node is only permitted to transmit a maximum of one message per TDMA cycle. Secondly, we generalise the analysis to the case where a node is assigned a budget of messages per TDMA cycle it may transmit. A simple algorithm to assign budgets to nodes is also presented.
- Assigning real-time tasks on heterogeneous multiprocessors with two types of processorsPublication . Andersson, Björn; Bletsas, KonstantinosConsider the problem of scheduling a set of implicitdeadline sporadic tasks on a heterogeneous multiprocessor so as to meet all deadlines. Tasks cannot migrate and the platform is restricted in that each processor is either of type-1 or type-2 (with each task characterized by a different speed of execution upon each type of processor). We present an algorithm for this problem with a timecomplexity of O(n·m), where n is the number of tasks and m is the number of processors. It offers the guarantee that if a task set can be scheduled by any non-migrative algorithm to meet deadlines then our algorithm meets deadlines as well if given processors twice as fast. Although this result is proven for only a restricted heterogeneous multiprocessor, we consider it significant for being the first realtime scheduling algorithm to use a low-complexity binpacking approach to schedule tasks on a heterogeneous multiprocessor with provably good performance.
- Calculating an upper bound on the finishing time of a group of threads executing on a GPU: a preliminary case studyPublication . Raravi, Gurulingesh; Andersson, BjörnGraphics processor units (GPUs) today can be used for computations that go beyond graphics and such use can attain a performance that is orders of magnitude greater than a normal processor. The software executing on a graphics processor is composed of a set of (often thousands of) threads which operate on different parts of the data and thereby jointly compute a result which is delivered to another thread executing on the main processor. Hence the response time of a thread executing on the main processor is dependent on the finishing time of the execution of threads executing on the GPU. Therefore, we present a simple method for calculating an upper bound on the finishing time of threads executing on a GPU, in particular NVIDIA Fermi. Developing such a method is nontrivial because threads executing on a GPU share hardware resources at very fine granularity.
- Collision-free prioritized medium access control in wireless networks with hidden nodesPublication . Andersson, Björn; Pereira, Nuno; Tovar, EduardoWe propose a collision-free medium access control (MAC) protocol, which implements static-priority scheduling and works in the presence of hidden nodes. The MAC protocol allows multiple masters and is fully distributed; it is an adaptation to a wireless channel of the dominance protocol used in the CAN bus. But unlike that protocol, our protocol does not require a node having the ability to sense the channel while transmitting to the channel. Our protocol is collision-free even in the presence of hidden nodes and it achieves this without synchronized clocks or out-of-band busy tones. In addition, the protocol is designed to ensure that many non-interfering nodes can transmit in parallel and it functions for both broadcast and unicast transmissions.
- Collision-free prioritized medium access in the presence of hidden nodes without relying on out-of-band signalingPublication . Andersson, Björn; Pereira, Nuno; Tovar, EduardoConsider the problem of sharing a wireless channel between a set of computer nodes. Hidden nodes exist and there is no base station. Each computer node hosts a set of sporadic message streams where a message stream releases messages with real-time deadlines. We propose a collision-free wireless medium access control (MAC) protocol which implements staticpriority scheduling. The MAC protocol allows multiple masters and is fully distributed. It neither relies on synchronized clocks nor out-of-band signaling; it is an adaptation to a wireless channel of the dominance protocol used in the CAN bus. But unlike that protocol, our protocol does not require a node having the ability to receive an incoming bit from the channel while transmitting to the channel. Our protocol has the key feature of not only being prioritized and collision-free but also dealing successfully with hidden nodes. This key feature enables schedulability analysis of sporadic message streams in multihop networks.
- Conjecture about global fixed-priority preemptive multiprocessor scheduling of implicit-deadline sporadic tasks: the utilization bound of SM-US(sqrt(2)-1) is sqrt(2)-1Publication . Andersson, BjörnConsider global fixed-priority preemptive multiprocessor scheduling of implicit-deadline sporadic tasks. I conjecture that the utilization bound of SM-US(√2−1) is √2-1.
- A conjecture about provably good task assignment on heterogeneous multiprocessor platforms but with a stronger adversaryPublication . Raravi, Gurulingesh; Andersson, Björn; Bletsas, KonstantinosConsider the problem of scheduling a set of implicit-deadline sporadic tasks to meet all deadlines on a heterogeneous multiprocessor platform. We use an algorithm proposed in [1] (we refer to it as LP-EE) from state-of-the-art for assigning tasks to heterogeneous multiprocessor platform and (re-)prove its performance guarantee but for a stronger adversary.We conjecture that if a task set can be scheduled to meet deadlines on a heterogeneous multiprocessor platform by an optimal task assignment scheme that allows task migrations then LP-EE meets deadlines as well with no migrations if given processors twice as fast. We illustrate this with an example.
- Delay-bounded medium access for unidirectional wireless linksPublication . Andersson, Björn; Pereira, Nuno; Tovar, EduardoConsider a wireless network where links may be unidirectional, that is, a computer node A can broadcast a message and computer node B will receive this message but if B broadcasts then A will not receive it. Assume that messages have deadlines. We propose a medium access control (MAC) protocol which replicates a message in time with carefully selected pauses between replicas, and in this way it guarantees that for every message at least one replica of that message is transmitted without collision. The protocol ensures this with no knowledge of the network topology and it requires neither synchronized clocks nor carrier sensing capabilities. We believe this result is significant because it is the only MAC protocol that offers an upper bound on the message queuing delay for unidirectional links without relying on synchronized clocks.
- Disseminating data using broadcast when topology is unknownPublication . Andersson, Björn; Pereira, Nuno; Tovar, EduardoConsider the problem of disseminating data from an arbitrary source node to all other nodes in a distributed computer system, like Wireless Sensor Networks (WSNs). We assume that wireless broadcast is used and nodes do not know the topology. We propose new protocols which disseminate data faster and use fewer broadcasts than the simple broadcast protocol.
- «
- 1 (current)
- 2
- 3
- »