Gaudi components for concurrency: Concurrency for existing and future experiments

16th International workshop on Advanced Computing and Analysis Techniques in physics research

物理学;计算机科学

Clemencic, M.^1 ; Funke, D.^1 ; Hegner, B.^1 ; Mato, P.^1 ; Piparo, D.^1 ; Shapoval, I.^1

CERN, Geneva 23

CH-1211, Switzerland^1

关键词: Directed acyclic graph (DAG);    Dynamic priority;    Fine-grained parallelism;    Large Hadron Collider;    Parallel processing;    Resource management;    Sequence optimization;    Sequential processing;   

Others  :  https://iopscience.iop.org/article/10.1088/1742-6596/608/1/012021/pdf
DOI  :  10.1088/1742-6596/608/1/012021

学科分类：计算机科学（综合）

来源: IOP

【 摘 要 】

HEP experiments produce enormous data sets at an ever-growing rate. To cope with the challenge posed by these data sets, experiments' software needs to embrace all capabilities modern CPUs offer. With decreasingmemory/coreratio, the one-process-per-core approach of recent years becomes less feasible. Instead, multi-threading with fine-grained parallelism needs to be exploited to benefit from memory sharing among threads. Gaudi is an experiment-independent data processing framework, used for instance by the ATLAS and LHCbexperiments at CERN's Large Hadron Collider. It has originally been designed with only sequential processing in mind. In a recent effort, the frame work has been extended to allow for multi-threaded processing. This includes components for concurrent scheduling of several algorithms - either processingthe same or multiple events, thread-safe data store access and resource management. In the sequential case, the relationships between algorithms are encoded implicitly in their pre-determined execution order. For parallel processing, these relationships need to be expressed explicitly, in order for the scheduler to be able to exploit maximum parallelism while respecting dependencies between algorithms. Therefore, means to express and automatically track these dependencies need to be provided by the framework. In this paper, we present components introduced to express and track dependencies of algorithms to deduce a precedence-constrained directed acyclic graph, which serves as basis for our algorithmically sophisticated scheduling approach for tasks with dynamic priorities. We introduce an incremental migration path for existing experiments towards parallel processing and highlight the benefits of explicit dependencies even in the sequential case, such as sanity checks and sequence optimization by graph analysis.