Search

Heterogeneous-ISA computing platforms have become ubiquitous, and will be used for diverse workloads which render static mappings of computation to processors inadequate. Dynamic mappings which adjust an application's usage in consideration of platform workload can reduce application latency and increase throughput for heterogeneous platforms. We introduce AIRA, a compiler and runtime for flexible execution of applications in CPU-GPU platforms. Using AIRA, we demonstrate up to a 3.78x speedup in benchmarks from Rodinia and Parboil, run with various workloads on a server-class platform. Additionally, AIRA is able to extract up to an 87 percent increase in platform throughput over a static mapping.

Energy efficiency is one of the most important design considerations in running modern datacenters. Datacenter operating systems rely on software techniques such as execution migration to achieve energy efficiency across pools of machines. Execution migration is possible in datacenters today because they consist mainly of homogeneous-ISA machines. However, recent market trends indicate that alternate ISAs such as ARM and PowerPC are pushing into the datacenter, meaning current execution migration techniques are no longer applicable. How can execution migration be applied in future heterogeneous-ISA datacenters?In this work we present a compiler, runtime, and an operating system extension for enabling execution migration between heterogeneous-ISA servers. We present a new multi-ISA binary architecture and heterogeneous-OS containers for facilitating efficient migration of natively-compiled applications. We build and evaluate a prototype of our design and demonstrate energy savings of up to 66% for a workload running on an ARM and an x86 server interconnected by a high-speed network.

With the advances in network speeds a single processor cannot cope anymore with the growing number of data streams from a single network card. Multicore processors come at a rescue but traditional SMP OSes, which integrate the software network stack, scale only to a certain extent,limiting an application's ability to serve more connections while increasing the number of cores. On the other hand, kernel bypass solutions seem to scale better, but limit resource flexibility and control. We propose attacking these problems with a distributed OS design, using multiple network stacks (one per kernel) and relying on multi-queue hardware and hardware flow steering. This creates a single-socket abstraction among kernels while minimizing inter-core communication. We introduce our design, consisting of a distributed network stack, a distributed device driver, and a load-balancing algorithm. We compare our prototype, NetPopcorn, with Linux, Affinity Accept, FastSocket. NetPopcorn accepts between 5 to 8 times more connections and reduces the tail latency compared to these competitors. We also compare NetPopcorn with mTCP and observe that for high core counts, mTCP accepts only 18% more connections yet with higher tail latency than NetPopcorn.

The ITER Heating Neutral Beam injectors will be implemented in three steps: development of the ion source prototype, development of the full injector prototype, and, finally, construction of up to three ITER injectors. The first two steps will be carried out in the ITER neutral beam test facility under construction in Italy. The ion source prototype, referred to as SPIDER, which is currently in the development phase, is a complex experiment involving more than 20 plant units and operating with beam-on pulses lasting up to 1 h. As for control and data acquisition it requires fast and slow control (cycle time around 0.1 ms and 10 ms, respectively), synchronization (10 ns resolution), and data acquisition for about 1000 channels (analogue and images) with sampling frequencies up to tens of MS/s, data throughput up to 200 MB/s, and data storage volume of up to tens of TB/year. The paper describes the architecture of the SPIDER control and data acquisition system, discussing the SPIDER requirements and the ITER CODAC interfaces and specifications for plant system instrumentation and control.

The real-time control system of RFX-mod, in operation since 2005, has been successful and has allowed several important achievements in the RFX physics research program. As a consequence of this fact, new control algorithms are under investigation, which are more demanding in terms of both enhanced computing power and reduced system latency, currently around 1.5 ms. For this reason, a major upgrade of the system is being considered, and a new architecture has been proposed, taking advantage of the rapid evolution of computer technology in the last years. The central component of the new architecture is a Linux-based multicore server, where individual cores replace the VME computers. The server is connected to the I/O via PCI-e based bus extenders, and every PCI-e connection is managed by a separate core. The system is supervised by MARTe, a software framework for real-time applications written in C++ and developed at JET and currently used for the JET vertical stabilization and in other fusion devices.

We adopt a model of a real-time distributed network where the synchronization is done by an external timing network that triggers the acquisitions. A Switched Ethernet is used to send the synchronously sampled data from nodes to nodes to perform the distributed control algorithm. In order to guarantee low latencies and jitter, the traffic on the Switched Ethernet must be carefully analyzed to be able to correctly model closed-loop systems and potentially identify events that might lead to large delays or even packet losses. In this paper we discuss the most relevant results from a testbed control network with synchronous data acquisition nodes. A switched Gigabit Ethernet is adopted and each node uses RTnet running in a RTAI/Linux Operating System. To resolve the problem of timing uncertainties at the data link layer, we propose a new custom solution based on a TDMA discipline.

The Ion Source experiment, called SPIDER, is the first experiment to be realized in the ITER Neutral Beam Test Facility under construction at Consorzio RFX, Padova, Italy. Its data acquisition system will provide the collection of around one thousand signals at a sampling rate ranging from a few S/s to 10 MS/s and of diagnostics and inspection images produced at a frame frequency from 10 to 150 frame per second, for beam durations of up to one hour. As the final product of the Test Facility will be the ITER Heating Neutral Beam Injector, we decided to follow the ITER CODAC guidelines. Therefore, the EPICS system provided in the CODAC Core System has been assessed and adopted in plant control. In addition to EPICS, the MDSplus system will be adopted for the overall data management. MDSplus can handle a rich set of data types and offers support for both local and remote data access in a variety of languages, a feature not fully supported by EPICS. All experiment data in SPIDER will be maintained in a single MDSplus database containing both experiment configuration and acquired data. The seamless integration of EPICS and MDSplus in a single system requires the development of some new tools, namely: A Channel Archiver which provides storage into MDSplus pulse files of data produced by EPICS Input Output Controllers (IOC) and exported as Process Variables via Channel Access; A set of IOC records providing direct access from IOC into MDSPlus files; A Channel Access Server to export MDSplus data as EPICS Process Variables, making them directly accessible by IOCs. We expect that the integration of the two frameworks will result in a system that combines the best features from each one, i.e., the management of distributed Process Variables and the IOC concept for EPICS, the sophisticated data management and remote access for MDSplus.

The PCU-Project [1] launched for the enhancement of the vertical stabilisation system at JET required the design of a new real-time control system with the challenging specifications of 2 Gops and a cycle time of 50 μ s. The RTAI based architecture running on an x86 multi-core processor technology demonstrated to be the best platform for meeting the high requirements. Moreover, on this architecture thanks to the smart allocation of the interrupts it was possible to demonstrate simultaneous data streaming at 50 MBs on Ethernet while handling a real-time 100 kHz interrupt source with a maximum jitter of just 3 μ s. Because of the memory limitation imposed by 32 bit version Linux running in kernel mode, the RTAI-based new controller allows a maximum practical data storage of 800 MB per pulse. While this amount of data can be accepted for JET normal operation it posed some limitations in the debugging and commissioning of the system. In order to increase the capability of the data acquisition of the system we have designed a mechanism that allows continuous full bandwidth ( 56 MB/s) data streaming from the real-time task (running in kernel mode) to either a data collector (running in user mode) or an external data acquisition server. The exploited architecture involves a peer to peer mechanisms where the sender running in RTAI kernel mode broadcasts large chunks of data using UDP packets, implemented using the ‘fcomm’ RTAI extension [2] , to a receiver that will store the data. The paper will present the results of the initial RTAI operating system tests, the design of the streaming architecture and the first experimental results.

The Plasma Control Upgrade (PCU) enhancement project was setup with the aim of effectively increasing the JET operating space by both improving the Vertical Stabilization System Controller and by procuring a more powerful Radial Field Amplifier. The hardware and software technological advancements that have been used allowed to implement a 200 channel, 20 kHz control system with less than 2 μ s jitter and over 2 G o p s of processing capability. The software design, driven by an object oriented analysis, enabled a good compromise between real-time performances and reliability–maintainability objectives. The first operational experience of the system will be presented.

A new framework for the development and execution of real-time codes is currently being developed and commissioned at JET. The foundations of the system are Linux, the Real Time Application Interface (RTAI) and a wise exploitation of the new i386 multi-core processors technology. The driving motivation was the need to find a real-time operating system for the i386 platform able to satisfy JET Vertical Stabilisation Enhancement project requirements: 50 μs cycle time. Even if the initial choice was the VxWorks operating system, it was decided to explore an open source alternative, mostly because of the costs involved in the commercial product. The work started with the definition of a precise set of requirements and milestones to achieve: Linux distribution and kernel versions to be used for the real-time operating system; complete characterization of the Linux/RTAI real-time capabilities; exploitation of the multi-core technology; implementation of all the required and missing features; commissioning of the system. Latency and jitter measurements were compared for Linux and RTAI in both user and kernel-space. The best results were attained using the RTAI kernel solution where the time to reschedule a real-time task after an external interrupt is of 2.35 ± 0.35 μs. In order to run the real-time codes in the kernel-space, a solution to provide user-space functionalities to the kernel modules had to be designed. This novel work provided the most common functions from the standard C library and transparent interaction with files and sockets to the kernel real-time modules. Kernel C++ support was also tested, further developed and integrated in the framework. The work has produced very convincing results so far: complete isolation of the processors assigned to real-time from the Linux non real-time activities, high level of stability over several days of benchmarking operations and values well below 3 μs for task rescheduling after external interrupt. From being the alternative option, RTAI has been finally chosen as the platform for the project. A first stable version of the framework has been integrated on the JET system and is already being commissioned. It will be soon be used on the Vertical Stabilisation Enhancement for the Plasma Control Upgrade (PCU) project at JET.

Consolidation and isolation are key technologies that promoted the undisputed popularity of virtualization in most of the computer industry. This popularity has recently led to a growing interest in real-time virtualization, making this technology enter the real-time system market. However, it has several issues due to the strict timing guarantees contracted. Moreover supporting legacy software stacks adds another level of complexity when the software is a black box. We present KairosVM, a latency-bounded, real-time extension to Linux's KVM module. It aims to bridge the lack of communication of the real-time requirements between the guest scheduler and the host scheduler, exploiting virtual machine introspection. The hypervisor captures the real-time requirements of the guest by catching previously added undefined instructions, without the need to do any modification to the guests. Our evaluations show that KairosVM's overhead is negligible when compared to existing introspection solutions thus can be used in real-time.

EPICS is used worldwide to build distributed control systems for scientific experiments. The EPICS software suite is based around the Channel Access (CA) network protocol that allows the communication of different EPICS clients and servers in a distributed architecture. Servers are called Input/Output Controllers (IOCs) and perform real-world I/O or local control tasks. EPICS IOCs were originally designed for VxWorks to meet the demanding real-time requirements of control algorithms and have lately been ported to different operating systems. The MARTe framework has recently been adopted to develop an increasing number of hard real-time systems in different fusion experiments. MARTe is a software library that allows the rapid and modular development of stand-alone hard real-time control applications on different operating systems. MARTe has been created to be portable and during the last years it has evolved to follow the multi-core evolution.In this paper we review several implementation differences between EPICS IOC and MARTe. We dissect their internal data structures and synchronization mechanisms to understand what happens behind the scenes. Differences in the component based approach and in the concurrent model of computation in EPICS IOC and MARTe are explained. Such differences lead to distinct time models in the computational blocks and distinct real-time capabilities of the two frameworks that a developer must be aware of.

SPIDER, the ITER-size ion-source test bed in the ITER Neutral Beam Test Facility, is a fusion device requiring a complex central system to provide control and data acquisition, referred to as CODAS. The CODAS software architecture will rely on EPICS and MDSplus, two open-source, collaborative software frameworks, targeted at control and data acquisition, respectively. EPICS has been selected as ITER CODAC middleware and, as the final deliverable of the Neutral Beam Test Facility is the procurement of the ITER Heating Neutral Beam Injector, we decided to adopt this ITER technology. MDSplus is a software package for data management, supporting advanced concepts, such as platform and underlying hardware independence, self description data, and data driven model. The combined use of EPICS and MDSplus is not new in fusion, but their level of integration will be new in SPIDER, achieved by a more refined data access layer. The paper presents the integration software to use effectively EPICS and MDSplus, including the definition of appropriate EPICS records to interact with MDSplus. The MDSplus and EPICS archive concepts are also compared on the basis of performance tests and data streaming is investigated by ad-hoc measurements.

The Multithreaded Application Real-Time executor (MARTe) is a data driven framework environment for the development and deployment of real-time control algorithms. The main ideas which led to the present version of the framework were to standardise the development of real-time control systems, while providing a set of strictly bounded standard interfaces to the outside world and also accommodating a collection of facilities which promote the speed and ease of development, commissioning and deployment of such systems. At the core of every MARTe based application, is a set of independent inter-communicating software blocks, named Generic Application Modules (GAM), orchestrated by a real-time scheduler. The platform independence of its core library provides MARTe the necessary robustness and flexibility for conveniently testing applications in different environments including non-real-time operating systems. MARTe is already being used in several machines, each with its own peculiarities regarding hardware interfacing, supervisory control configuration, operating system and target control application. This paper presents and compares the most recent results of systems using MARTe: the JET Vertical Stabilisation system, which uses the Real Time Application Interface (RTAI) operating system on Intel multi-core processors; the COMPASS plasma control system, driven by Linux RT also on Intel multi-core processors; ISTTOK real-time tomography equilibrium reconstruction which shares the same support configuration of COMPASS; JET error field correction coils based on VME, PowerPC and VxWorks; FTU LH reflected power system running on VME, Intel with RTAI.