Latency-hiding work stealing: Scheduling interacting parallel computations with work stealing
With the rise of multicore computers, parallel applications no longer consist solely of
computational, batch workloads, but also include applications that may, for example, take …
computational, batch workloads, but also include applications that may, for example, take …
TAPAS: Generating parallel accelerators from parallel programs
S Margerm, A Sharifian, A Guha… - 2018 51st Annual …, 2018 - ieeexplore.ieee.org
High-level-synthesis (HLS) tools generate accelerators from software programs to ease the
task of building hardware. Unfortunately, current HLS tools have limited support for …
task of building hardware. Unfortunately, current HLS tools have limited support for …
Task parallel assembly language for uncompromising parallelism
Achieving parallel performance and scalability involves making compromises between
parallel and sequential computation. If not contained, the overheads of parallelism can …
parallel and sequential computation. If not contained, the overheads of parallelism can …
Scheduling I/O latency-hiding futures in task-parallel platforms
Task parallelism research has traditionally focused on optimizing computation-intensive
applications. Due to the proliferation of commodity parallel processors, there has been …
applications. Due to the proliferation of commodity parallel processors, there has been …
Processor-oblivious record and replay
Record-and-replay systems are useful tools for debugging non-deterministic parallel
programs by first recording an execution and then replaying that execution to produce the …
programs by first recording an execution and then replaying that execution to produce the …
Lightweight preemptive user-level threads
Many-to-many mapping models for user-to kernel-level threads (or" M: N threads") have
been extensively studied for decades as a lightweight substitute for current Pthreads …
been extensively studied for decades as a lightweight substitute for current Pthreads …
Analyzing the performance trade-off in implementing user-level threads
User-level threads have been widely adopted as a means of achieving lightweight
concurrent execution without the costs of OS-level threads. Nevertheless, the costs of …
concurrent execution without the costs of OS-level threads. Nevertheless, the costs of …
Lessons learned from analyzing dynamic promotion for user-level threading
A performance vs. practicality trade-off exists between user-level threading techniques. The
community has settled mostly on a black-and-white perspective; fully fledged threads …
community has settled mostly on a black-and-white perspective; fully fledged threads …
Exploring trade-offs in parallel beam-ACO
J Hajewski, S Oliveira, DE Stewart… - 2021 IEEE 11th Annual …, 2021 - ieeexplore.ieee.org
The Traveling Salesman Problem is a conceptually simple problem that is computationally
difficult due to the size of the search space, which grows factorially with the number of cities …
difficult due to the size of the search space, which grows factorially with the number of cities …
Access control policy combination from similarity analysis for secure privacy-preserved ehr systems
F Rezaeibagha, Y Mu - 2017 IEEE Trustcom/BigDataSE/ICESS, 2017 - ieeexplore.ieee.org
In distributed systems, there is often a need to combine the heterogeneous access control
policies to offer more comprehensive services to users in the local or national level. A large …
policies to offer more comprehensive services to users in the local or national level. A large …