Toward a software transactional memory for heterogeneous CPU–GPU processors

A Villegas, A Navarro, R Asenjo, O Plata - The Journal of Supercomputing, 2019 - Springer
The heterogeneous accelerated processing units (APUs) integrate a multi-core CPU and a
GPU within the same chip. Modern APUs implement CPU–GPU platform atomics for simple …

Lerna: parallelizing dependent loops using speculation

MM Saad, R Palmieri, B Ravindran - ACM Transactions on Storage (TOS …, 2019 - dl.acm.org
We present Lerna, an end-to-end tool that automatically and transparently detects and
extracts parallelism from data-dependent sequential loops. Lerna uses speculation …

Extending TM primitives using low level semantics

MM Saad, R Palmieri, A Hassan… - Proceedings of the 28th …, 2016 - dl.acm.org
Transactional Memory (TM) has recently emerged as an optimistic concurrency control
technique that isolates concurrent executions at the level of memory reads and writes …

A comparative analysis of STM approaches to reduction operations in irregular applications

M Pedrero, E Gutierrez, S Romero, O Plata - Journal of Computational …, 2016 - Elsevier
As a recently consolidated paradigm for optimistic concurrency in modern multicore
architectures, Transactional Memory (TM) can help to the exploitation of parallelism in …

Encapsulated open nesting for STM: fine-grained higher-level conflict detection

M Bättig, TR Gross - Proceedings of the 24th Symposium on Principles …, 2019 - dl.acm.org
Open nesting allows replacing the automatic detection of conflicting memory accesses used
in transactional memory (TM) with programmer-specified higher-level conflict detection …

ReduxSTM: Optimizing STM designs for irregular applications

M Pedrero, E Gutierrez, S Romero, O Plata - Journal of Parallel and …, 2017 - Elsevier
The exploitation of optimistic concurrency in modern multicore architectures via
Transactional Memory (TM) is becoming a mainstream programming paradigm. TM features …

[PDF][PDF] Lerna: Transparent and effective speculative loop parallelization

MM Saad, R Palmieri, B Ravindran - Proceedings of the Eleventh ACM …, 2016 - hyflow.org
In this paper, we present Lerna, a system that automatically and transparently detects and
extracts parallelism from sequential code using speculation combined with a set of …

Transactions on mergeable objects

DD Akkoorath, A Bieniusa - … and Systems: 13th Asian Symposium, APLAS …, 2015 - Springer
Destructible updates on shared objects require careful handling of concurrent accesses in
multi-threaded programs. Paradigms such as Transactional Memory support the …

Scalable Consistency in the Multi-core Era

DD Akkoorath - 2020 - kluedo.ub.rptu.de
The advent of heterogeneous many-core systems has increased the spectrum of achievable
performance from multi-threaded programming. As the processor components become more …

[PDF][PDF] ReduxSTM: Optimizing STM designs for Irregular Applications

M Pedrero-Luque, ED Gutiérrez-Carrasco… - 2018 - riuma.uma.es
The exploitation of optimistic concurrency in modern multicore architectures via
Transactional Memory (TM) is becoming a mainstream programming paradigm. TM features …