The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Demand for low-power data processing hardware continues to rise inexorably. Existing programmable and “general purpose” solutions (eg. SIMD, GPGPUs) are insufficient, as evidenced by the order-of-magnitude improvements and industry adoption of application and domain-specific accelerators in important areas like machine learning, computer vision and big data. The stark tradeoffs between efficiency...
Domain-specific accelerators (DSAs), which sacrifice programmability for efficiency, are a reaction to the waning benefits of device scaling. This article demonstrates that there are commonalities between DSAs that can be exploited with programmable mechanisms. The goals are to create a programmable architecture that can match the benefits of a DSA and to create a platform for future accelerator investigations.
Hardware innovation is slowing, yet software innovation is flourishing, in large part because of a thriving open source ecosystem. Open source can similarly boost hardware development, but the way forward will require industry, academia, and hardware enthusiasts to address five significant issues.
Decades-old explicit dataflow architectures eliminate many of the overheads of general-purpose processors but have not been successful because of their lack of sufficient control speculation and the latency overhead of explicit communication. This article observes a synergy between out-of-order (OoO) and explicit dataflow processors, in which dynamically switching between them according to program...
This article consists of a collection of slides from the authors' conference presentation. MIAOW is a credible GPGPU implementation. Compatible with AMD Southern Islands ISA. Runs OpenCL programs and prototyped on FPGA. Similar design to industry state-of-art. Similar performance to industry state-of-art. Flexible and Extendable. MIOAW's hardware design is Open Source. Contributes to changing hardware...
Graphic Processing Unit (GPU) based general purpose computing is developing as a viable alternative to CPU based computing in many domains. In this paper, we introduce MIAOW (Many-core Integrated Accelerator Of Wisconsin), an open source RTL implementation of the AMD Southern Islands GPGPU ISA, capable of running unmodified OpenCL-based applications. We present our design motivated by our goals to...
General purpose processors (GPPs), from small inorder designs to many-issue out-of-order, incur large power overheads which must be addressed for future technology generations. Major sources of overhead include structures which dynamically extract the data-dependence graph or maintain precise state. Considering irregular workloads, current specialization approaches either heavily curtail performance,...
This paper presents C-CLOUD, a democratic cloud infrastructure for renting computing resources includingnon-cloud resources (i.e. computing equipment not part of any cloud infrastructure, such as, PCs, laptops, enterprise servers and clusters). C-CLOUD enables enormous amount of surplus computing resources, in the range of hundreds of millions, to be rented out to cloud users. Such a sharing of resources...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.