Computing with memory: Difference between revisions

Revision as of 03:57, 19 September 2016

Latest revision as of 04:22, 3 January 2025

(5 intermediate revisions by 4 users not shown)

Line 3:

{{technical|date=August 2012}}

}}

{{short description|Type of computing platform}}

'''Computing with Memorymemory''' refers to computing platforms where function response is stored in memory array, either one or two-dimensional, in the form of [[lookup table]]s (LUTs) and functions are evaluated by retrieving the values from the LUTs. These computing platforms can follow either a purely spatial computing model, as in [[Fieldfield-programmable gate array]] (FPGA), or a temporal computing model, where a function is evaluated across multiple clock cycles. The latter approach aims at reducing the overhead of programmable interconnect in FPGA by folding interconnect resources inside a computing element. It uses dense two-dimensional memory arrays to store large multiple-input multiple-output LUTs. Computing with Memorymemory differs from Computingcomputing in Memorymemory or [[Processorprocessor-in-memory]] (PIM) concepts, widely investigated in the context of integrating a processor and memory on the same chip to reduce memory latency and increase bandwidth. These architectures seek to reduce the distance the data travels between the processor and the memory. The [[Berkeley IRAM project]] is one notable contribution in the area of PIM architectures.

==Details==

<!-- Deleted image removed: [[Image:Memory Logic Block.png|thumb|right|alt=Time-multiplexed execution of mapped application using embedded memory blocks .|Functional block diagram of Memorymemory-based Based Computation.computation]] -->

Computing with memory platforms are typically used to provide the benefit of hardware reconfigurability. Reconfigurable computing platforms offer advantages in terms of reduced design cost, early time-to-market, rapid prototyping and easily customizable hardware systems. FPGAs present a popular reconfigurable computing platform for implementing digital circuits. They follow a purely spatial computing model. Since their inception in 1985, the basic structure of the FPGAs has continued to consist of two-dimensional array of Configurableconfigurable Logiclogic blocks (CLBs) and a programmable interconnect matrix.<ref name="Ref 1">K.Compton and S. Hauck, "Computing: A Survey of systems and software", ''ACM Surveys'', Vol. 34, No. 2, June, 2002.</ref> FPGA performance and power dissipation is largely dominated by the elaborate programmable interconnect (PI) architecture.<ref name="Ref 2">S. M. Trimberger, "''Field Programmable Gate Array Technology"'', Norwell, MA: Kluwer, 1994.</ref><ref name="Ref 3">A. Rahman, S. Das, A. P. Chandrakasan, R. Reif, "Wiring Requirement and Three-Dimensional Integration Technology for Field Programmable Gate Arrays", ''IEEE Trans. on Very Large Scale Integration Systems'', Vol. 11, No. 1, February, 2003.</ref> An effective way of reducing the impact of the PI architecture in FPGA is to place small LUTs in close proximity (referred as clusters) and to allow intra-cluster communication using local interconnects. Due to the benefits of a clustered FPGA architecture, major FPGA vendors have incorporated it in their commercial products.<ref name="Ref 4">[http://www.xilinx.com Xilinx Corporation]</ref><ref name="Ref 5">[http://www.altera.com Altera Corporation]</ref> Investigations have also been made to reduce the overhead due to PI in fine-grained FPGAs by mapping larger multi-input multi-output LUTs to embedded memory blocks. Although it follows a similar spatial computing model, part of the logic functions are implemented using embedded memory blocks while the remaining part is realized using smaller LUTs.<ref name="Ref 6">J. Cong and S. Xu, "Technology Mapping for FPGAs with Embedded Memory Blocks", Symposium on Field Programmable Gate Array, 1998.</ref> Such a heterogeneous mapping can improve the area and performance by reducing the contribution of programmable interconnects.

Contrary to the purely spatial computing model of FPGA, a reconfigurable computing platform that employs a temporal computing model (or a combination of both temporal and spatial) has also been investigated <ref name="Ref 7">S. Paul and S. Bhunia, "Reconfigurable Computing Using Content Addressable Memory for Improved Performance and Resource Usage", Design Automation Conference, 2008.</ref><ref name="Ref 8">S. Paul, S. Chatterjee, S. Mukhopadhyay and S. Bhunia, "Nanoscale Reconfigurable Computing Using Non-Volatile 2-D STTRAM Array", International Conference on Nanotechnology, 2009.</ref> in the context of improving performance and energy over conventional FPGA. These platforms, referred as "memory-based computing" (MBC), use dense two-dimensional memory array to store the LUTs. Such frameworks rely on breaking a complex function (''f'') into small sub-functions; representing the sub-functions as multi-input, multi-output LUTs in the memory array; and evaluating the function ''f'' over multiple cycles. MBC can leverage on the high density, low power and high performance advantages of nanoscale memory.<ref name="Ref 8"/>

<ref name="Ref 8">S. Paul, S. Chatterjee, S. Mukhopadhyay and S. Bhunia, "Nanoscale Reconfigurable Computing Using Non-Volatile 2-D STTRAM Array", International Conference on Nanotechnology, 2009.</ref> in the context of improving performance and energy over conventional FPGA. These platforms, referred as Memory Based Computing (MBC), use dense two-dimensional memory array to store the LUTs. Such frameworks rely on breaking a complex function (''f'') into small sub-functions; representing the sub-functions as multi-input, multi-output LUTs in the memory array; and evaluating the function ''f'' over multiple cycles. MBC can leverage on the high density, low power and high performance advantages of nanoscale memory.<ref name="Ref 8"/> [[:Image:Memory Logic Block.png]] shows the high-level block diagram of MBC. Each computing element incorporates a two-dimensional memory array for storing LUTs, a small controller for sequencing evaluation of sub-functions and a set of temporary registers to hold the intermediate outputs from individual partitions. A fast, local routing framework inside each computing block generates the address for LUT access. Multiple such computing elements can be spatially connected using FPGA-like programmable interconnect architecture to enable mapping of large functions. The local time-multiplexed execution inside the computing elements can drastically reduce the requirement of programmable interconnects leading to large improvement in energy-delay product and better scalability of performance across technology generations. The memory array inside each computing element can be realized by [[Content-addressable memory]] (CAM) to drastically reduce the memory requirement for certain applications.<ref name="Ref 7"/>

<!-- Deleted image removed: [[:Image:Memory Logic Block.png]] shows the high-level block diagram of MBC. -->

<ref name="Ref 8">S. Paul, S. Chatterjee, S. Mukhopadhyay and S. Bhunia, "Nanoscale Reconfigurable Computing Using Non-Volatile 2-D STTRAM Array", International Conference on Nanotechnology, 2009.</ref> in the context of improving performance and energy over conventional FPGA. These platforms, referred as Memory Based Computing (MBC), use dense two-dimensional memory array to store the LUTs. Such frameworks rely on breaking a complex function (''f'') into small sub-functions; representing the sub-functions as multi-input, multi-output LUTs in the memory array; and evaluating the function ''f'' over multiple cycles. MBC can leverage on the high density, low power and high performance advantages of nanoscale memory.<ref name="Ref 8"/> [[:Image:Memory Logic Block.png]] shows the high-level block diagram of MBC. Each computing element incorporates a two-dimensional memory array for storing LUTs, a small controller for sequencing evaluation of sub-functions and a set of temporary registers to hold the intermediate outputs from individual partitions. A fast, local routing framework inside each computing block generates the address for LUT access. Multiple such computing elements can be spatially connected using FPGA-like programmable interconnect architecture to enable mapping of large functions. The local time-multiplexed execution inside the computing elements can drastically reduce the requirement of programmable interconnects leading to large improvement in energy-delay product and better scalability of performance across technology generations. The memory array inside each computing element can be realized by [[Contentcontent-addressable memory]] (CAM) to drastically reduce the memory requirement for certain applications.<ref name="Ref 7"/>

==See also==

* [[Reconfigurable Computing]]

* [[Field-programmable gate array]] (FPGA)

* [[Computational RAM]]

* [[Field-programmable gate array]] (FPGA)

* [[Memoization]]

* [[Reconfigurable Computingcomputing]]

==References==