Subordinate Kernels: Application Offloading in Asymmetric Multi-Processor Systems
نویسندگان
چکیده
Modern computing systems incorporate a plethora of auxiliary processing cores located on devices such as graphics cards, network devices and raid controllers. These processors are becoming increasingly sophisticated and could provide application offloading if exploitable by third party code. However, to provide an environment for practical general purpose application offloading, the operating system must present a homogeneous programming interface across the heterogeneous processors and provide a safe execution environment. In this paper we present a subordinate kernel operating system structure as a means of practical and safe execution of third party application code on auxiluary processing cores. We expand this concept of subordinate kernels by describing a proof of concept design of application offloading in the Singularity research
منابع مشابه
Design Methodology for Offloading Software Executions to FPGA
Field programmable gate array (FPGA) is a flexible solution for offloading part of the computations from a processor. In particular, it can be used to accelerate an execution of a computationally heavy part of the software application, e.g., in DSP, where small kernels are repeated often. Since an application code for a processor is a software, a design methodology is needed to convert the code...
متن کاملOperating Systems and Asymmetric Single-ISA CMPs: The Potential for Saving Energy
CPUs consume too much power. Modern complex cores sometimes waste power on functions that are not useful for the code they run. In particular, operating system kernels do not benefit from many power-consuming features that were intended to improve application performance. We propose using asymmetric single-ISA CMPs (ASISA-CMPs), multicore CPUs where all cores execute the same instruction set ar...
متن کاملTcp Servers: a Tcp/ip Offloading Architecture for Internet Servers, Using Memory-mapped Communication
OF THE THESIS TCP Servers: A TCP/IP Offloading Architecture for Internet Servers, using Memory-Mapped Communication by Kalpana S Banerjee Thesis Director: Liviu Iftode TCP Server is a system architecture aiming to offload network processing from the host(s) running an Internet server. The TCP Server can be executed on a dedicated processor, node or intelligent network interface using low-overhe...
متن کاملDesign and Program Multi-processor Platform for High-performance Embedded Processing
Modern embedded markets call for high density computing ability, making it is difficult to use just one microprocessor to meet function requirements of highperformance embedded systems. Multiple processors, including general-purpose embedded microprocessors, digital signal processors (DSPs), ASICs and FPGA hardware accelerators, are often used in these embedded systems. Not all processors in an...
متن کاملNetwork interfaces for programmable NICs and multicore platforms
1389-1286/$ see front matter 2009 Elsevier B.V doi:10.1016/j.comnet.2009.09.011 * Corresponding author. Tel.: +34 952134166; fax E-mail address: [email protected] (A. Ortiz). The availability of multicore processors and programmable NICs, such as TOEs (TCP/IP Offloading Engines), provides new opportunities for designing efficient network interfaces to cope with the gap between the improvement ra...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2007