Design Space Exploration of Memory Controller Placement in Throughput Processors with Deep Learning
نویسندگان
چکیده
منابع مشابه
Hypermedia processors: design space exploration
We present a framework for area optimal system design space exploration for hypermedia applications. We focus on a category of processors that are programmable yet optimized to a hypermedia application. The key components of the framework presented in this paper are a retargetable instruction-level parallelism compiler, instruction level simulators, a set of complete media applications written ...
متن کاملTradeoffs in the Design Space Exploration of Application-Specific Processors
An application-specific instruction set processor (ASIP) design methodology can exploit special characteristics of applications to meet the performance and time-to-market requirements. In this paper, tradeoffs encountered in the design of application-specific processors targeting embedded applications are discussed. The exploration of the architecture design space is a crucial step to effective...
متن کاملDeep Space Design Environments for Human Exploration
Mission scenarios outside the Earth’s protective magnetic shield are being studied. Included are high usage assets in the near-Earth environment for casual trips, for research, and for commercial/operational platforms, in which career exposures will be multi-mission determined over the astronaut’s lifetime. The operational platforms will serve as launching points for deep space exploration miss...
متن کاملDesign Space Exploration framework for memory exploration in heterogeneous architectures
The increasing amount of computation in heterogeneous architectures (including CPU and GPU cores) puts a big burden on memory subsystem. With the gap between compute units and the memory performance getting wider, designing a platform with a responsive memory system becomes more challenging. This issue is exacerbated when memory systems have to satisfy a high volume of traffic generated from he...
متن کاملScaling Deep Learning on Multiple In-Memory Processors
Deep learning methods are proven to be state-of-theart in addressing many challenges in machine learning domains. However, it comes at the cost of high computational requirements and energy consumption. The emergence of Processing In Memory (PIM) with diestacking technology presents an opportunity to speed up deep learning computation and reduce energy consumption by providing low-cost high-ban...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Computer Architecture Letters
سال: 2019
ISSN: 1556-6056,1556-6064,2473-2575
DOI: 10.1109/lca.2019.2905587