PARMA-DITAM '18Pub Date : 2018-01-23DOI: 10.1145/3183767.3183780
Hugo Miomandre, Julien Hascoët, K. Desnos, Kevin J. M. Martin, B. Dinechin, J. Nezan
{"title":"Embedded Runtime for Reconfigurable Dataflow Graphs on Manycore Architectures","authors":"Hugo Miomandre, Julien Hascoët, K. Desnos, Kevin J. M. Martin, B. Dinechin, J. Nezan","doi":"10.1145/3183767.3183780","DOIUrl":"https://doi.org/10.1145/3183767.3183780","url":null,"abstract":"Embedded manycore architectures offer energy-efficient super-computing capabilities but are notoriously difficult to program with traditional parallel Application Programming Interfaces (APIs). To address this challenge, dataflow Models of Computation (MoCs) are increasingly used as their high-level of abstraction eases the automation of computation mapping, memory allocation, and communication management. Reconfigurable dataflow is a class of dataflow MoC that fosters a unique trade-off between application dynamicity and predictability. This paper introduces the first embedded runtime manager enabling the execution of reconfigurable dataflow graphs on a Non-Uniform Memory Access (NUMA) architecture. The proposed runtime manager dynamically deploys reconfigurable dataflow graphs on clustered Processing Elements (PEs) through the Networks-on-Chips (NoCs) of the manycore architecture. An open-source implementation on the Kalray MPPA® processor demonstrates the feasibility and the great potential of such a runtime. The first results with an image processing application show a power efficiency 2.5 times better than on a multicore x86 architecture.","PeriodicalId":386343,"journal":{"name":"PARMA-DITAM '18","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115006443","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
PARMA-DITAM '18Pub Date : 2018-01-23DOI: 10.1145/3183767.3183782
V. Muttillo, G. Valente, L. Pomante
{"title":"Criticality-driven Design Space Exploration for Mixed-Criticality Heterogeneous Parallel Embedded Systems","authors":"V. Muttillo, G. Valente, L. Pomante","doi":"10.1145/3183767.3183782","DOIUrl":"https://doi.org/10.1145/3183767.3183782","url":null,"abstract":"Heterogeneous platforms are becoming widely diffused in the embedded system area, mainly because of the opportunities to increase application execution performance and, at the same time, to optimize other orthogonal metrics. In such a context, the introduction of mixed-criticality constraints, while considering heterogenous parallel architectures, creates new challenges to industrial and academic research. The main design issue is related to a Design Space Exploration (DSE) approach able to cope with mixed-criticality constraints that typically limits the number of feasible solutions. So, this work1 focuses on DSE for embedded systems based on heterogeneous parallel architectures and subjected to mixed-criticality constraints. In particular, it presents a criticality-driven evolutionary approach integrated into a reference Electronic System Level HW/SW Co-Design flow to support the designer of mixed-criticality embedded systems.","PeriodicalId":386343,"journal":{"name":"PARMA-DITAM '18","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133248099","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
PARMA-DITAM '18Pub Date : 2018-01-23DOI: 10.1145/3183767.3183781
Mingze Ma, R. Sakellariou
{"title":"Reducing Code Size in Scheduling Synchronous Dataflow Graphs on Multicore Systems","authors":"Mingze Ma, R. Sakellariou","doi":"10.1145/3183767.3183781","DOIUrl":"https://doi.org/10.1145/3183767.3183781","url":null,"abstract":"A Synchronous Dataflow Graph (SDFG) is a widely used abstraction to capture the characteristics of a number of applications often running on embedded systems. When scheduling/mapping an SDFG on a multicore embedded system, the code of tasks may have to be duplicated onto multiple cores to fully utilize the parallelism of the multicore system. However, such an approach may increase the overall code size in the system, which may not be desirable. This paper proposes a code-size-aware scheduling heuristic, which decreases code duplication of SDFGs on multicore systems, hence minimizing overall code size while not affecting throughput. In experiments, the proposed heuristic achieves significant code size reduction for all the tested SDFGs compared with a state-of-art recently proposed scheduling algorithm.","PeriodicalId":386343,"journal":{"name":"PARMA-DITAM '18","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126348852","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
PARMA-DITAM '18Pub Date : 2018-01-23DOI: 10.1145/3183767.3183776
Ricardo Nobre, Luís Reis, João Bispo, Tiago Carvalho, João MP Cardoso, Stefano Cherubin, G. Agosta
{"title":"Aspect-Driven Mixed-Precision Tuning Targeting GPUs","authors":"Ricardo Nobre, Luís Reis, João Bispo, Tiago Carvalho, João MP Cardoso, Stefano Cherubin, G. Agosta","doi":"10.1145/3183767.3183776","DOIUrl":"https://doi.org/10.1145/3183767.3183776","url":null,"abstract":"Writing mixed-precision kernels allows to achieve higher throughput together with outputs whose precision remain within given limits. The recent introduction of native half-precision arithmetic capabilities in several GPUs, such as NVIDIA P100 and AMD Vega 10, contributes to make precision-tuning even more relevant as of late. However, it is not trivial to manually find which variables are to be represented as half-precision instead of single- or double-precision. Although the use of half-precision arithmetic can speed up kernel execution considerably, it can also result in providing non-usable kernel outputs, whenever the wrong variables are declared using the half-precision data-type. In this paper we present an automatic approach for precision tuning. Given an OpenCL kernel with a set of inputs declared by a user (i.e., the person responsible for programming and/or tuning the kernel), our approach is capable of deriving the mixed-precision versions of the kernel that are better improve upon the original with respect to a given metric (e.g., time-to-solution, energy-to-solution). We allow the user to declare and/or select a metric to measure and to filter solutions based on the quality of the output. We implement a proof-of-concept of our approach using an aspect-oriented programming language called LARA. It is capable of generating mixed-precision kernels that result in considerably higher performance when compared with the original single-precision floating-point versions, while generating outputs that can be acceptable in some scenarios.","PeriodicalId":386343,"journal":{"name":"PARMA-DITAM '18","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130837337","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
PARMA-DITAM '18Pub Date : 2018-01-23DOI: 10.1145/3183767.3183778
M. Zanella, G. Massari, W. Fornaciari
{"title":"Enabling Run-Time Managed Distributed Mobile Computing","authors":"M. Zanella, G. Massari, W. Fornaciari","doi":"10.1145/3183767.3183778","DOIUrl":"https://doi.org/10.1145/3183767.3183778","url":null,"abstract":"The increasing pervasiveness of mobile devices combined with their replacement rate, led us to deal with the disposal of an increasing amount of still working electronic devices. This work proposes an approach to mitigate this problem by extending the mobile devices' lifetime, by integrating them as part of a distributed mobile computing system. Thanks also to the growing computational power of such devices, this paradigm opens up the opportunity to deploy mobile applications in a distributed manner. This, without forgetting the energy budget management as a paramount objective. In this work, we built a proof-of-concept, based on the extension of a run-time resource manager to support Android applications. We introduced a energy-aware device selection policy to dispatch the application workload according to both device capabilities and run-time status. Experimental results show that, as well as increasing the utilization of multiple mobile devices available to the single user, using an energy-efficiency and distributed approach can increase the battery duration between 12% and 36%.","PeriodicalId":386343,"journal":{"name":"PARMA-DITAM '18","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132775060","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
PARMA-DITAM '18Pub Date : 2018-01-23DOI: 10.1145/3183767.3183779
Lester Kalms, Tim Hebbeler, D. Göhringer
{"title":"Automatic OpenCL Code Generation from LLVM-IR using Polyhedral Optimization","authors":"Lester Kalms, Tim Hebbeler, D. Göhringer","doi":"10.1145/3183767.3183779","DOIUrl":"https://doi.org/10.1145/3183767.3183779","url":null,"abstract":"Nowadays, developers can implement applications using OpenCL for all kinds of architectures, like CPUs, GPUs and FPGAs. In this work, we propose a source-to-source compiler that can transform C/C++ source code to optimized OpenCL kernel and host code. This eases the programmability of heterogeneous architectures, to apply different optimization techniques and let the programmer have access during the optimization process. We use polyhedral modeling, which is based on the Polly tool from the LLVM framework, to analysis the code. The information is transferred to the Polyhedral Parallel Code Generator (PPCG), which is a source-to-source compiler that generates OpenCL or CUDA code, since Polly is designed for CPUs. PPCG uses the Abstract Syntax Tree of the Clang for transformation and can thus only process C-code as input. Our approach opens up many new possibilities, like processing other input languages or applying different optimizations, since it works on the intermediate language of the LLVM framework. A main part of the work was the creation of valid C-code from LLVM-IR basic blocks and regions. In addition, a module for recognizing and transforming local variables was created.","PeriodicalId":386343,"journal":{"name":"PARMA-DITAM '18","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132844432","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
PARMA-DITAM '18Pub Date : 2018-01-23DOI: 10.1145/3183767.3183790
R. Khasanov, Andrés Goens, J. Castrillón
{"title":"Implicit Data-Parallelism in Kahn Process Networks: Bridging the MacQueen Gap","authors":"R. Khasanov, Andrés Goens, J. Castrillón","doi":"10.1145/3183767.3183790","DOIUrl":"https://doi.org/10.1145/3183767.3183790","url":null,"abstract":"Modern embedded systems are rapidly increasing their complexity, both in terms of numbers of cores, as well as heterogeneity. To generate efficient code for these systems, it is common to leverage formal models of computation. Among these, the dataflow model of Kahn Process Networks (KPN) is widespread because it is expressive but guarantees a deterministic execution. However, the KPN model is ill-suited to expose data-level parallelism, since this has to be made explicit in the process network. This is aggravated by the fact that its most common execution model, Kahn-MacQueen, poses restrictive conditions on the scheduling of data-parallel processes, leading to an inefficient execution. In this paper we present a novel extension to the KPN model and a relaxed execution strategy that addresses this problem, while keeping the deterministic KPN semantics. It improves run-time adaptivity in malleable way and provides implicit parallelism. We evaluate our approach on two architectures, improving the performance of a benchmark by up to 25.6% on an Intel chip with hyper-threading, and by up to 78.0 % on a heterogeneous embedded ARM big.LITTLE architecture.","PeriodicalId":386343,"journal":{"name":"PARMA-DITAM '18","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131920124","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
PARMA-DITAM '18Pub Date : 2018-01-23DOI: 10.1145/3183767.3183768
Vojtech Cima, Stanislav Böhm, J. Martinovič, J. Dvorský, K. Janurová, T. Aa, T. Ashby, V. Chupakhin
{"title":"HyperLoom: A Platform for Defining and Executing Scientific Pipelines in Distributed Environments","authors":"Vojtech Cima, Stanislav Böhm, J. Martinovič, J. Dvorský, K. Janurová, T. Aa, T. Ashby, V. Chupakhin","doi":"10.1145/3183767.3183768","DOIUrl":"https://doi.org/10.1145/3183767.3183768","url":null,"abstract":"Real-world scientific applications often encompass end-to-end data processing pipelines composed of a large number of interconnected computational tasks of various granularity. We introduce HyperLoom, an open source platform for defining and executing such pipelines in distributed environments and providing a Python interface for defining tasks. HyperLoom is a self-contained system that does not use an external scheduler for the actual execution of the task. We have successfully employed HyperLoom for executing chemogenomics pipelines used in pharmaceutic industry for novel drug discovery.","PeriodicalId":386343,"journal":{"name":"PARMA-DITAM '18","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128727359","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
PARMA-DITAM '18Pub Date : 2018-01-23DOI: 10.1145/3183767.3183769
G. Agosta, W. Fornaciari, G. Massari, A. Pupykina, F. Reghenzani, M. Zanella
{"title":"Managing Heterogeneous Resources in HPC Systems","authors":"G. Agosta, W. Fornaciari, G. Massari, A. Pupykina, F. Reghenzani, M. Zanella","doi":"10.1145/3183767.3183769","DOIUrl":"https://doi.org/10.1145/3183767.3183769","url":null,"abstract":"To sustain performance while facing always tighter power and energy envelopes, High Performance Computing (HPC) is increasingly leveraging heterogeneous architectures. This poses new challenges: to efficiently exploit the available resources, both in terms of hardware and energy, resource management must support a wide range of different heterogeneous devices and programming models that target different application domains. We present a strategy for resource management and programming model support for heterogeneous accelerators for HPC systems with requirements targeting performance, power and predictability. We show how resource management can, in addition to allowing multiple applications to share a set of resources, reduce the burden on the application developer and improve the efficiency of resource allocation.","PeriodicalId":386343,"journal":{"name":"PARMA-DITAM '18","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131082317","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
PARMA-DITAM '18Pub Date : 2018-01-23DOI: 10.1145/3183767.3183770
H. Arabnejad, João Bispo, Jorge G. Barbosa, João MP Cardoso
{"title":"AutoPar-Clava: An Automatic Parallelization source-to-source tool for C code applications","authors":"H. Arabnejad, João Bispo, Jorge G. Barbosa, João MP Cardoso","doi":"10.1145/3183767.3183770","DOIUrl":"https://doi.org/10.1145/3183767.3183770","url":null,"abstract":"Automatic parallelization of sequential code has become increasingly relevant in multicore programming. In particular, loop parallelization continues to be a promising optimization technique for scientific applications, and can provide considerable speedups for program execution. Furthermore, if we can verify that there are no true data dependencies between loop iterations, they can be easily parallelized.\u0000 This paper describes Clava AutoPar, a library for the Clava weaver that performs automatic and symbolic parallelization of C code. The library is composed of two main parts, parallel loop detection and source-to-source code parallelization. The system is entirely automatic and attempts to statically detect parallel loops for a given input program, without any user intervention or profiling information. We obtained a geometric mean speedup of 1.5 for a set of programs from the C version of the NAS benchmark, and experimental results suggest that the performance obtained with Clava AutoPar is comparable or better than other similar research and commercial tools.","PeriodicalId":386343,"journal":{"name":"PARMA-DITAM '18","volume":"461 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131345320","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}