Research
(76 intermediate revisions by one user not shown) | |||
Line 7: | Line 7: | ||
{| id=portal cellspacing="0" cellpadding="0" width=100% style="border:1px solid #B8C7D9; padding:0px;" | {| id=portal cellspacing="0" cellpadding="0" width=100% style="border:1px solid #B8C7D9; padding:0px;" | ||
|- | |- | ||
− | | colspan="2" style="background:# | + | | colspan="2" style="background:#8FBCBF; text-align:center; padding:1px; border-bottom:1px #8FBCBF solid;" | |
− | <h2 style="margin:.1em; border-bottom:1px; font-size:140%; font-weight:bold;"> Computing with | + | <h2 style="margin:.1em; border-bottom:1px; font-size:140%; font-weight:bold;"> Computing with Switching Lattices </h2> |
|- | |- | ||
| valign="top" style="padding:8px 8px 0px 8px; background:#f5fffa;" <!--H210 S4 V100--> | | | valign="top" style="padding:8px 8px 0px 8px; background:#f5fffa;" <!--H210 S4 V100--> | | ||
− | + | A switching lattice, formed as a two dimensional network of four-terminal switches, is introduced as a crossbar based, regular, dense, area-efficient, and CMOS-compatible structure for logic computing. A four-terminal switch, corresponding to a crossbar cross-point or a lattice site, has one control input and four terminals. The control input makes all of its terminals either all disconnected (OFF) or all connected (ON). | |
+ | [[Image:research_lattice_logic.png|center|none|800px|link=]] | ||
+ | |||
+ | <h3> | ||
+ | Technology Development</h3> | ||
− | [[Image: | + | We show that '''switching lattices are CMOS-compatible'''. For this purpose, we propose |
+ | different four-terminal switch structures, and construct them in three dimensional | ||
+ | technology computer-aided design (TCAD) environment as well as in Cadence environment satisfying the design rules of the TSMC 65nm CMOS process and perform | ||
+ | simulations. | ||
+ | Experimental results show that the realization of logic functions using switching lattices occupy '''much less layout area''' and have | ||
+ | competitive delay and power consumption values when compared to the conventional CMOS implementations. | ||
+ | |||
+ | [[Image:research_lattice_technology.png|center|none|800px|link=]] | ||
+ | |||
+ | <h3> | ||
+ | Performance Optimization</h3> | ||
+ | We propose a logic synthesis algorithm to optimize '''lattice sizes under a delay constraint'''. We also propose '''static and dynamic logic solutions for area-delay-power efficiency''' of the lattices. | ||
+ | <!-- [[Image:Research-2.png|center|none|800px|link=]] --> | ||
<h3> | <h3> | ||
Synthesis</h3> | Synthesis</h3> | ||
− | We | + | We propose '''optimal and heuristic''' algorithms to implement logic functions with minimum size switching lattices. |
− | + | ||
<!-- [[Image:Research-1.png|center|none|800px|link=]] --> | <!-- [[Image:Research-1.png|center|none|800px|link=]] --> | ||
− | |||
− | |||
− | |||
− | |||
− | |||
<!-- YAYIN --> | <!-- YAYIN --> | ||
{| id="mp-upper" style="width: 100%; margin:4px 0 0 0; background:none; border-spacing: 0px;" | {| id="mp-upper" style="width: 100%; margin:4px 0 0 0; background:none; border-spacing: 0px;" | ||
Line 43: | Line 53: | ||
{| style="border:1px solid #abd5f5; background:#f1f5fc;" | {| style="border:1px solid #abd5f5; background:#f1f5fc;" | ||
+ | |||
| | | | ||
{| | {| | ||
|- valign=top | |- valign=top | ||
| width="100" |'''title''': | | width="100" |'''title''': | ||
− | | width="450"|[[Media: | + | | width="450"|[[Media: Akkan_EtAl_H_and_Square_Lattice_Technology_Development.pdf | Technology Development and Modeling of Switching Lattices Using Square and H Shaped Four-Terminal Switches]] |
|- valign="top" | |- valign="top" | ||
| '''authors''': | | '''authors''': | ||
− | | | + | | width="450"| Nihat Akkan, Serzat Safaltin, Levent Aksoy, Ismail Cevik, Herman Sedef, Csaba Andras Moritz, and [[Mustafa Altun]] |
|- valign="top" | |- valign="top" | ||
| '''appeared in''': | | '''appeared in''': | ||
− | | width="450" | [http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber= | + | | width="450" | [http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6245516 IEEE Transactions on Emerging Topics in Computing], Vol. 10, Issue 1, pp. 351–360, 2022. |
− | |- valign= | + | |- valign=top |
| '''presented at''': | | '''presented at''': | ||
− | | width="450"| [http://www. | + | | width="450"| [http://www.date-conference.com/ Design, Automation and Test in Europe (DATE)], Grenoble, France, 2020. |
|} | |} | ||
+ | |||
| align=center width="70" | | | align=center width="70" | | ||
<span class="plainlinks"> | <span class="plainlinks"> | ||
− | [[File:PDF.png|65px|link=http://www.ecc.itu.edu.tr/images/ | + | [[File:PDF.png|65px|link=http://www.ecc.itu.edu.tr/images/6/69/Akkan_EtAl_H_and_Square_Lattice_Technology_Development.pdf]]</span> |
<br> | <br> | ||
− | [[Media: | + | [[Media:Akkan_EtAl_H_and_Square_Lattice_Technology_Development.pdf | Paper]] |
| align="center" width="70" | | | align="center" width="70" | | ||
<span class="plainlinks"> | <span class="plainlinks"> | ||
− | [[File:PPT.jpg|60px|link= | + | [[File:PPT.jpg|60px|link=https://www.ecc.itu.edu.tr/images/1/1c/Cevik_Aksoy_Altun_CMOS_Implementation_of_Switching_Lattices.pptx]] |
</span> | </span> | ||
− | <br> [ | + | <br> [https://www.ecc.itu.edu.tr/images/1/1c/Cevik_Aksoy_Altun_CMOS_Implementation_of_Switching_Lattices.pptx Slides] |
|} | |} | ||
{| style="border:1px solid #abd5f5; background:#f1f5fc;" | {| style="border:1px solid #abd5f5; background:#f1f5fc;" | ||
− | |||
| | | | ||
{| | {| | ||
|- valign=top | |- valign=top | ||
| width="100" |'''title''': | | width="100" |'''title''': | ||
− | | width="450"|[[Media: | + | | width="450"|[[Media:Aksoy_Altun_Realizations_with_Switching_Lattices.pdf | Novel Methods for Efficient Realization of Logic Functions Using Switching Lattices]] |
|- valign="top" | |- valign="top" | ||
| '''authors''': | | '''authors''': | ||
− | | width="450"| | + | | Levent Aksoy and [[Mustafa Altun]] |
− | |- valign=top | + | |- valign="top" |
+ | | '''appeared in''': | ||
+ | | width="450" | [http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=12 IEEE Transactions on Computers], Vol. 69, Issue 3, pp. 427–440, 2020. | ||
+ | |- valign="top" | ||
| '''presented at''': | | '''presented at''': | ||
− | | width="450"| [http:// | + | | width="450"| [http://www.date-conference.com/ Design, Automation and Test in Europe (DATE)], Florence, Italy, 2019. |
|} | |} | ||
− | |||
| align=center width="70" | | | align=center width="70" | | ||
<span class="plainlinks"> | <span class="plainlinks"> | ||
− | [[File:PDF.png|65px|link=http://www.ecc.itu.edu.tr/images/ | + | [[File:PDF.png|65px|link=http://www.ecc.itu.edu.tr/images/e/e0/Aksoy_Altun_Realizations_with_Switching_Lattices.pdf]]</span> |
<br> | <br> | ||
− | [[Media: | + | [[Media:Aksoy_Altun_Realizations_with_Switching_Lattices.pdf | Paper]] |
| align="center" width="70" | | | align="center" width="70" | | ||
<span class="plainlinks"> | <span class="plainlinks"> | ||
− | [[File: | + | [[File:PPT.jpg|60px|link=https://www.ecc.itu.edu.tr/images/5/54/Aksoy_Altun_SAT_based_Synthesis_of_Switching_Lattices.pptx]] |
</span> | </span> | ||
− | <br> [ | + | <br> [https://www.ecc.itu.edu.tr/images/5/54/Aksoy_Altun_SAT_based_Synthesis_of_Switching_Lattices.pptx Slides] |
|} | |} | ||
− | {| style="border:1px solid #abd5f5; background:#f1f5fc;" | + | |} |
+ | | style="border:1px solid transparent;" | | ||
+ | <!-- PROJE --> | ||
+ | | class="MainPageBG" style="width:50%; border:0px solid #A9A9A9; vertical-align:top;"| | ||
+ | {| id="mp-right" style="width:100%; vertical-align:top;" | ||
+ | | | ||
+ | |||
+ | {| style="margin-left: auto; margin-right: 0px; border:1px solid #abd5f5; background:#d0e5f5; padding:0.2em 0.5em; font-weight:bold;" | ||
+ | |||
+ | |- valign=top | ||
+ | | width="696" |'''Funding Projects''' | ||
+ | |} | ||
+ | {| style="margin-left: auto; margin-right: 0px; border:1px solid #abd5f5; background:#f1f5fc;" | ||
+ | | | ||
+ | {| | ||
+ | |- valign="top" | ||
+ | | width="140" |'''title''': | ||
+ | | width="558"| Implementation of 3D Nano Stuctures and Switching Lattices | ||
+ | |- valign="top" | ||
+ | | '''agency & program''': | ||
+ | | width="450"| [https://ufuk2020.org.tr/en/content/tubitak-nsf-joint-research-program TUBITAK-NSF Joint Research Program (2501)] | ||
+ | |- valign="top" | ||
+ | | '''budget''': | ||
+ | | 720.000 TL | ||
+ | |- valign="top" | ||
+ | | '''duration''': | ||
+ | | 2019-2023, ''completed'' | ||
+ | |} | ||
+ | {| style="margin-left: auto; margin-right: 0px; border:0.1px solid #abd5ff; background:#f1f5fc; padding:0.2em 0em;" | ||
+ | |- valign="top" | ||
+ | | width="140" |'''project goal''': | ||
+ | | width="558"| Design, fabrication, and test of switching lattices and nano-crossbars within 3D interconnect architectures. | ||
+ | |||
+ | |} | ||
+ | |} | ||
+ | |||
+ | |} | ||
+ | |} | ||
+ | |} | ||
+ | |||
+ | |||
+ | {| id=portal cellspacing="0" cellpadding="0" width=100% style="border:1px solid #B8C7D9; padding:0px;" | ||
+ | |- | ||
+ | | colspan="2" style="background:#8FBCAF; text-align:center; padding:1px; border-bottom:1px #8FBCAF solid;" | | ||
+ | <h2 style="margin:.1em; border-bottom:1px; font-size:140%; font-weight:bold;"> Energy Efficient ANN Hardware Implementation </h2> | ||
+ | |- | ||
+ | | valign="top" style="padding:8px 8px 0px 8px; background:#f5fffa;" <!--H210 S4 V100--> | | ||
+ | |||
+ | We aim to use '''hardware aware training''' techniques, new '''hybrid bit parallel-serial''' number representations, and constant multiplication based '''sharing''' techniques to reduce energy consumption of feed-forward artificial neural networks (ANNs). | ||
+ | |||
+ | [[Image:research_ANN.png|center|none|800px|link=]] | ||
+ | |||
+ | |||
+ | <!-- YAYIN --> | ||
+ | {| id="mp-upper" style="width: 100%; margin:4px 0 0 0; background:none; border-spacing: 0px;" | ||
+ | | class="MainPageBG" style="width:50%; border:0px solid #D8BFD8; vertical-align:top; color:#000;" | | ||
+ | {| id="mp-left" style="width:100%; vertical-align:top;" | ||
+ | |||
+ | | | ||
+ | |||
+ | {| style="border:1px solid #abd5f5; background:#d0e5f5; padding:0.2em 0.5em; font-weight:bold;" | ||
+ | |||
+ | |- valign=top | ||
+ | | width="696" |'''Selected Publications''' | ||
+ | |} | ||
+ | {| style="border:1px solid #abd5f5; background:#f1f5fc;" | ||
| | | | ||
{| | {| | ||
|- valign=top | |- valign=top | ||
| width="100" |'''title''': | | width="100" |'''title''': | ||
− | | width="450"|[[Media: | + | | width="450"| [[Media:Aksoy_Parvin_Nojehdeh_Altun_Time_Multiplexed_ANN_Implementation.pdf | Efficient Time-Multiplexed Realization of Feedforward Artificial Neural Networks]] |
|- valign="top" | |- valign="top" | ||
| '''authors''': | | '''authors''': | ||
− | | [[Mustafa Altun]] | + | | Levent Aksoy, Sajjad Parvin, Mohammadreza Nojehdeh, and [[Mustafa Altun]] |
− | + | ||
− | + | ||
− | + | ||
|- valign="top" | |- valign="top" | ||
| '''presented at''': | | '''presented at''': | ||
− | | [http:// | + | | width="450"| [http://iscas2020.org/ IEEE International Symposium on Circuits and Systems (ISCAS)], Seville, Spain, 2020. |
|} | |} | ||
| align=center width="70" | | | align=center width="70" | | ||
<span class="plainlinks"> | <span class="plainlinks"> | ||
− | [[File:PDF.png|65px|link=http://www.ecc.itu.edu.tr/images/ | + | [[File:PDF.png|65px|link=http://www.ecc.itu.edu.tr/images/e/eb/Aksoy_Parvin_Nojehdeh_Altun_Time_Multiplexed_ANN_Implementation.pdf]]</span> |
<br> | <br> | ||
− | [[Media: | + | [[Media:Aksoy_Parvin_Nojehdeh_Altun_Time_Multiplexed_ANN_Implementation.pdf | Paper]] |
| align="center" width="70" | | | align="center" width="70" | | ||
<span class="plainlinks"> | <span class="plainlinks"> | ||
− | [[File:PPT.jpg|60px|link= | + | [[File:PPT.jpg|60px|link=https://www.ecc.itu.edu.tr/images/3/3a/Aksoy_Parvin_Nojehdeh_Altun_Time_Multiplexed_ANN_Implementation.pptx]] |
</span> | </span> | ||
− | <br> [ | + | <br> [https://www.ecc.itu.edu.tr/images/3/3a/Aksoy_Parvin_Nojehdeh_Altun_Time_Multiplexed_ANN_Implementation.pptx Slides] |
|} | |} | ||
− | |||
|} | |} | ||
+ | |||
| style="border:1px solid transparent;" | | | style="border:1px solid transparent;" | | ||
<!-- PROJE --> | <!-- PROJE --> | ||
| class="MainPageBG" style="width:50%; border:0px solid #A9A9A9; vertical-align:top;"| | | class="MainPageBG" style="width:50%; border:0px solid #A9A9A9; vertical-align:top;"| | ||
{| id="mp-right" style="width:100%; vertical-align:top;" | {| id="mp-right" style="width:100%; vertical-align:top;" | ||
+ | |||
| | | | ||
Line 141: | Line 217: | ||
| width="696" |'''Funding Projects''' | | width="696" |'''Funding Projects''' | ||
|} | |} | ||
+ | |||
{| style="margin-left: auto; margin-right: 0px; border:1px solid #abd5f5; background:#f1f5fc;" | {| style="margin-left: auto; margin-right: 0px; border:1px solid #abd5f5; background:#f1f5fc;" | ||
Line 147: | Line 224: | ||
|- valign="top" | |- valign="top" | ||
| width="140" |'''title''': | | width="140" |'''title''': | ||
− | | width="558"| | + | | width="558"|Energy-Efficient Hardware Design of Artificial Neural Networks (ANNs) for Mobile Platforms |
|- valign="top" | |- valign="top" | ||
| '''agency & program''': | | '''agency & program''': | ||
− | + | | [http://www.tubitak.gov.tr/tr/destekler/akademik/ulusal-destek-programlari/icerik-1001-bilimsel-ve-teknolojik-arastirma-projelerini-destekleme-pr TUBITAK Scientific and Technological Research Projects Funding Program (1001)] | |
|- valign="top" | |- valign="top" | ||
| '''budget''': | | '''budget''': | ||
− | | | + | | 400.000 TL |
|- valign="top" | |- valign="top" | ||
| '''duration''': | | '''duration''': | ||
− | | | + | | 2020-2023, ''completed'' |
|} | |} | ||
− | + | {| style="margin-left: auto; margin-right: 0px; border:0.1px solid #abd5ff; background:#f1f5fc; padding:0.2em 0em;" | |
+ | |- valign="top" | ||
+ | | width="140" |'''project goal''': | ||
+ | | width="558"| Implementing energy-efficient ANNs by changing the rules of computing from the level of number representations to the level of circuit and system design. | ||
+ | |||
+ | |} | ||
|} | |} | ||
− | {| style="margin-left: auto; margin-right: 0px; border:1px solid #abd5f5; background:#f1f5fc;" | + | <!-- {| style="margin-left: auto; margin-right: 0px; border:1px solid #abd5f5; background:#f1f5fc;" |
| | | | ||
Line 166: | Line 248: | ||
|- valign=top | |- valign=top | ||
| width="140" |'''title''': | | width="140" |'''title''': | ||
− | | width="558"| | + | | width="558"| Gate and Transistor Implementations of Accurate Arithmetic Operation Blocks with Stochastic Logic |
|- valign="top" | |- valign="top" | ||
| '''agency & program''': | | '''agency & program''': | ||
− | | [http:// | + | | [http://bap.itu.edu.tr/ Istanbul Technical University Research Support Program (ITU-BAP)] |
− | + | ||
− | + | ||
− | + | ||
|- valign="top" | |- valign="top" | ||
| '''duration''': | | '''duration''': | ||
− | | | + | | 2017-2019, ''completed'' |
|} | |} | ||
− | |} | + | |
− | + | |} --> | |
|} | |} | ||
|} | |} | ||
|} | |} | ||
− | |||
− | |||
{| id=portal cellspacing="0" cellpadding="0" width=100% style="border:1px solid #B8C7D9; padding:0px;" | {| id=portal cellspacing="0" cellpadding="0" width=100% style="border:1px solid #B8C7D9; padding:0px;" | ||
|- | |- | ||
− | | colspan="2" style="background:# | + | | colspan="2" style="background:#8FBC9F; text-align:center; padding:1px; border-bottom:1px #8FBC9F solid;" | |
− | <h2 style="margin:.1em; border-bottom:1px; font-size:140%; font-weight:bold;"> | + | <h2 style="margin:.1em; border-bottom:1px; font-size:140%; font-weight:bold;"> Computing with Nano-Crossbar Arrays </h2> |
+ | |||
|- | |- | ||
| valign="top" style="padding:8px 8px 0px 8px; background:#f5fffa;" <!--H210 S4 V100--> | | | valign="top" style="padding:8px 8px 0px 8px; background:#f5fffa;" <!--H210 S4 V100--> | | ||
− | + | Nano-crossbar arrays have emerged as a strong candidate technology to replace CMOS in near future. They are regular and dense structures. Computing with crossbar arrays is achieved by its crosspoints behaving as switches, either two-terminal or four-terminal. Depending on the technology used, a two-terminal switch behaves as a diode, a resistive/memristive switch, or a field effect transistor (FET). On the other hand, a four-terminal switch has a unique behavior. While there have been many different technologies proposed for two-terminal switch based arrays, technology development for four-terminal switch based arrays, called switching lattices, has recently started. | |
− | + | ||
+ | For both two-terminal and four-terminal switch based arrays, we aim to develop a complete synthesis and performance optimization methodology for switching nano-crossbar arrays that leads to the design and construction of an emerging nanocomputer. We also aim to develeop CMOS-compatible technologies for crossbar arrays, specifically for switching lattices. | ||
− | [[Image: | + | [[Image:Research_nano-2019.png|center|none|800px|link=]] |
<h3> | <h3> | ||
+ | Technology Development</h3> | ||
− | + | Although a four-terminal switch based array offers a '''significant area advantage''', in terms of the number of switches, compared to the ones having two-terminal switches, its realization at the technology level needs | |
+ | further justifications and raises a number of questions about its | ||
+ | feasibility. We answer these questions. By using | ||
+ | three dimensional technology computer-aided design (TCAD) | ||
+ | simulations, we show that '''four-terminal switches can be directly implemented with the CMOS technology'''. Then, by fitting the TCAD simulation data | ||
+ | to the standard CMOS current-voltage equations, we develop a | ||
+ | Spice model of a four-terminal switch. | ||
− | We propose a | + | <h3> |
+ | Performance Optimization</h3> | ||
+ | |||
+ | We study crossbar arrays including the memristive ones. We | ||
+ | propose a '''defect-tolerant logic synthesis algorithms by considering area, delay, and power costs''' of the arrays. | ||
+ | <!-- [[Image:Research-2.png|center|none|800px|link=]] --> | ||
<h3> | <h3> | ||
+ | Fault Tolerance</h3> | ||
− | + | We examine reconfigurable crossbar arrays by considering randomly occurred '''stuck-open and stuck-closed crosspoint faults'''. In the presence of '''permanent''' faults, a fast and accurate heuristic algorithm is proposed that uses the techniques of index sorting, backtracking, and row matching. In the presence of '''transient''' faults, tolerance analysis is performed by formally and recursively determining tolerable fault positions. | |
+ | <!-- [[Image:Research-2.png|center|none|800px|link=]] --> | ||
− | We | + | <h3> |
+ | Synthesis</h3> | ||
+ | We study '''implementation of Boolean functions''' with nano-crossbar arrays where each crosspoint behaves as a diode, a FET, and a four-terminal switch. For these three types, we give array size formulations for a given Boolean function. Additionally, we focus on four-terminal switch based implementations and propose an algorithm that implements Boolean functions with '''optimal array sizes'''. | ||
+ | <!-- [[Image:Research-1.png|center|none|800px|link=]] --> | ||
− | |||
<!-- YAYIN --> | <!-- YAYIN --> | ||
{| id="mp-upper" style="width: 100%; margin:4px 0 0 0; background:none; border-spacing: 0px;" | {| id="mp-upper" style="width: 100%; margin:4px 0 0 0; background:none; border-spacing: 0px;" | ||
Line 224: | Line 318: | ||
| width="696" |'''Selected Publications''' | | width="696" |'''Selected Publications''' | ||
|} | |} | ||
+ | |||
{| style="border:1px solid #abd5f5; background:#f1f5fc;" | {| style="border:1px solid #abd5f5; background:#f1f5fc;" | ||
+ | |||
| | | | ||
− | {| | + | {| |
|- valign=top | |- valign=top | ||
| width="100" |'''title''': | | width="100" |'''title''': | ||
− | | width=" | + | | width="450"|[[Media: Safaltin_EtAl_Technology_Development_for_Switching_Lattices.pdf| Realization of Four-Terminal Switching Lattices: Technology Development and Circuit Modeling]] |
− | ]] | + | |
|- valign="top" | |- valign="top" | ||
| '''authors''': | | '''authors''': | ||
− | | [[Mustafa Altun]], | + | | width="450"| Serzat Safaltin, Oguz Gencer, Ceylan Morgul, Levent Aksoy, Sebahattin Gurmen, Csaba Andras Moritz, and [[Mustafa Altun]] |
+ | |- valign=top | ||
+ | | '''presented at''': | ||
+ | | width="450"| [http://www.date-conference.com/ Design, Automation and Test in Europe (DATE)], Florence, Italy, 2019. | ||
+ | |} | ||
+ | |||
+ | | align=center width="70" | | ||
+ | <span class="plainlinks"> | ||
+ | [[File:PDF.png|65px|link=http://www.ecc.itu.edu.tr/images/2/2c/Safaltin_EtAl_Technology_Development_for_Switching_Lattices.pdf]]</span> | ||
+ | <br> | ||
+ | [[Media:Safaltin_EtAl_Technology_Development_for_Switching_Lattices.pdf | Paper]] | ||
+ | | align="center" width="70" | | ||
+ | <span class="plainlinks"> | ||
+ | |||
+ | [[File:PPT.jpg|60px|link=https://www.ecc.itu.edu.tr/images/7/71/Safaltin_EtAl_Technology_Development_for_Switching_Lattices.pptx]] | ||
+ | </span> | ||
+ | <br> [https://www.ecc.itu.edu.tr/images/7/71/Safaltin_EtAl_Technology_Development_for_Switching_Lattices.pptx Slides] | ||
+ | |} | ||
+ | |||
+ | {| style="border:1px solid #abd5f5; background:#f1f5fc;" | ||
+ | | | ||
+ | {| | ||
+ | |- valign=top | ||
+ | | width="100" |'''title''': | ||
+ | | width="450"|[[Media:Tunali_Morgul_Altun_Defect_Tolerant_Memristor_Crossbars.pdf | Defect Tolerant Logic Synthesis for Memristor Crossbars with Performance Evaluation]] | ||
+ | |- valign="top" | ||
+ | | '''authors''': | ||
+ | | Onur Tunali and [[Mustafa Altun]] | ||
|- valign="top" | |- valign="top" | ||
| '''appeared in''': | | '''appeared in''': | ||
− | | [http:// | + | | width="450" | [http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=40 IEEE Micro], Vol. 38, Issue 5, pp. 22–31, 2018. |
+ | |- valign="top" | ||
+ | | '''presented at''': | ||
+ | | width="450"| [http://www.date-conference.com/ Design, Automation and Test in Europe (DATE)], Dresden, Germany, 2018. | ||
|} | |} | ||
− | | align=center width="70" | | + | | align=center width="70" | |
<span class="plainlinks"> | <span class="plainlinks"> | ||
− | [[File:PDF.png|65px|link=http://www.ecc.itu.edu.tr/images/ | + | [[File:PDF.png|65px|link=http://www.ecc.itu.edu.tr/images/d/db/Tunali_Morgul_Altun_Defect_Tolerant_Memristor_Crossbars.pdf]]</span> |
<br> | <br> | ||
− | [[Media: | + | [[Media:Tunali_Morgul_Altun_Defect_Tolerant_Memristor_Crossbars.pdf | Paper]] |
+ | | align="center" width="70" | | ||
+ | <span class="plainlinks"> | ||
+ | |||
+ | [[File:PPT.jpg|60px|link=https://www.ecc.itu.edu.tr/images/b/b8/Tunali_Altun_Logic_Synthesis_and_Defect_Tolerance_for_Memristive_Crossbars.pptx]] | ||
+ | </span> | ||
+ | <br> [https://www.ecc.itu.edu.tr/images/b/b8/Tunali_Altun_Logic_Synthesis_and_Defect_Tolerance_for_Memristive_Crossbars.pptx Slides] | ||
|} | |} | ||
+ | |||
{| style="border:1px solid #abd5f5; background:#f1f5fc;" | {| style="border:1px solid #abd5f5; background:#f1f5fc;" | ||
Line 250: | Line 382: | ||
|- valign=top | |- valign=top | ||
| width="100" |'''title''': | | width="100" |'''title''': | ||
− | | width="450"|[[Media: | + | | width="450"|[[Media:Altun_EtAl_Synthesis_and_Testing_for_Switching_Nano_Crossbar_Arrays.pdf | Logic Synthesis and Testing Techniques for Switching Nano-Crossbar Arrays]] |
|- valign="top" | |- valign="top" | ||
| '''authors''': | | '''authors''': | ||
− | | | + | | width="450"| Dan Alexandrescu, [[Mustafa Altun]], Lorena Anghel, Anna Bernasconi, Valentina Ciriani, Luca Frontini, and Mehdi Tahoori |
+ | |- valign=top | ||
+ | | '''appeared in''': | ||
+ | | width="450" | [http://www.journals.elsevier.com/microprocessors-and-microsystems/ Microprocessors and Microsystems], Vol. 54, pp. 14–25, 2017. | ||
+ | |- valign="top" | ||
+ | | '''presented at''': | ||
+ | | width="450"| [http://dsd-seaa2016.cs.ucy.ac.cy/index.php Euromicro Conference on Digital System Design (DSD)], Limassol, Cyprus, 2016. | ||
+ | |} | ||
+ | |||
+ | | align=center width="70" | | ||
+ | <span class="plainlinks"> | ||
+ | [[File:PDF.png|65px|link=http://www.ecc.itu.edu.tr/images/0/0a/Altun_EtAl_Synthesis_and_Testing_for_Switching_Nano_Crossbar_Arrays.pdf]]</span> | ||
+ | <br> | ||
+ | [[Media:Altun_EtAl_Synthesis_and_Testing_for_Switching_Nano_Crossbar_Arrays.pdf | Paper]] | ||
+ | | align="center" width="70" | | ||
+ | <span class="plainlinks"> | ||
+ | |||
+ | [[File:PDF.png|65px|link=https://www.ecc.itu.edu.tr/images/7/7f/Altun_EtAl_Synthesis_and_Performance_Optimization_of_a_Switching_Nano-crossbar_Computer_SLIDES.pdf]] | ||
+ | </span> | ||
+ | <br> [[Media:Altun_EtAl_Synthesis_and_Performance_Optimization_of_a_Switching_Nano-crossbar_Computer_SLIDES.pdf | Slides]] | ||
+ | |} | ||
+ | |||
+ | {| style="border:1px solid #abd5f5; background:#f1f5fc;" | ||
+ | | | ||
+ | {| | ||
+ | |- valign=top | ||
+ | | width="100" |'''title''': | ||
+ | | width="450"|[[Media:Tunali_Altun_Permanent_and_Transient_Fault_Tolerance_for_Reconfigurable_Nano-Crossbar_Arrays.pdf | Permanent and Transient Fault Tolerance for Reconfigurable Nano-Crossbar Arrays]] | ||
+ | |- valign="top" | ||
+ | | '''authors''': | ||
+ | | Onur Tunali and [[Mustafa Altun]] | ||
|- valign="top" | |- valign="top" | ||
| '''appeared in''': | | '''appeared in''': | ||
− | | width="450"| [http:// | + | | width="450" | [http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=43 IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems], Vol. 36, Issue 5, pp. 747–760, 2017. |
|- valign="top" | |- valign="top" | ||
| '''presented at''': | | '''presented at''': | ||
− | | width="450"| [http://www. | + | | width="450"| [http://www.nanoarch.org/ IEEE/ACM International Symposium on Nanoscale Architectures<br> (NANOARCH)], Boston, USA, 2015. |
|} | |} | ||
| align=center width="70" | | | align=center width="70" | | ||
<span class="plainlinks"> | <span class="plainlinks"> | ||
− | [[File:PDF.png|65px|link=http://www.ecc.itu.edu.tr/images/c/ | + | [[File:PDF.png|65px|link=http://www.ecc.itu.edu.tr/images/c/cc/Tunali_Altun_Permanent_and_Transient_Fault_Tolerance_for_Reconfigurable_Nano-Crossbar_Arrays.pdf]]</span> |
<br> | <br> | ||
− | [[Media: | + | [[Media:Tunali_Altun_Permanent_and_Transient_Fault_Tolerance_for_Reconfigurable_Nano-Crossbar_Arrays.pdf | Paper]] |
| align="center" width="70" | | | align="center" width="70" | | ||
<span class="plainlinks"> | <span class="plainlinks"> | ||
− | [[File:PPT.jpg|60px|link= | + | [[File:PPT.jpg|60px|link=https://www.ecc.itu.edu.tr/images/f/f9/Tunali_Altun_Defect_Tolerance_in_Diode_FET_and_Four-Terminal_Switch_based_Nano-Crossbar_Arrays.pptx]] |
</span> | </span> | ||
− | <br> [ | + | <br> [https://www.ecc.itu.edu.tr/images/f/f9/Tunali_Altun_Defect_Tolerance_in_Diode_FET_and_Four-Terminal_Switch_based_Nano-Crossbar_Arrays.pptx Slides] |
|} | |} | ||
+ | <!-- | ||
+ | {| style="border:1px solid #abd5f5; background:#f1f5fc;" | ||
+ | | | ||
+ | {| | ||
+ | |- valign=top | ||
+ | | width="100" |'''title''': | ||
+ | | width="450"|[[Media:Altun_Riedel_Logic_Synthesis_for_Switching_Lattices.pdf | Logic Synthesis for Switching Lattices]] | ||
+ | |- valign="top" | ||
+ | | '''authors''': | ||
+ | | [[Mustafa Altun]] and Marc Riedel | ||
+ | |- valign="top" | ||
+ | | '''appeared in''': | ||
+ | | width="450"| [http://www.computer.org/portal/web/tc IEEE Transactions on Computers], Vol. 61, Issue 11, pp. 1588–1600, 2012. | ||
+ | |- valign="top" | ||
+ | | '''presented at''': | ||
+ | | [http://www.dac.com Design Automation Conference (DAC)], Anaheim, USA, 2010. | ||
|} | |} | ||
+ | | align=center width="70" | | ||
+ | <span class="plainlinks"> | ||
+ | [[File:PDF.png|65px|link=http://www.ecc.itu.edu.tr/images/c/ca/Altun_Riedel_Logic_Synthesis_for_Switching_Lattices.pdf]]</span> | ||
+ | <br> | ||
+ | [[Media:Altun_Riedel_Logic_Synthesis_for_Switching_Lattices.pdf | Paper]] | ||
+ | | align="center" width="70" | | ||
+ | <span class="plainlinks"> | ||
+ | [[File:PPT.jpg|60px|link=https://www.ecc.itu.edu.tr/images/2/28/Altun_Riedel_Lattice-Based_Computation_of_Boolean_Functions.ppt]] | ||
+ | </span> | ||
+ | <br> [https://www.ecc.itu.edu.tr/images/2/28/Altun_Riedel_Lattice-Based_Computation_of_Boolean_Functions.ppt Slides] | ||
+ | |} | ||
+ | --> | ||
+ | |} | ||
| style="border:1px solid transparent;" | | | style="border:1px solid transparent;" | | ||
<!-- PROJE --> | <!-- PROJE --> | ||
| class="MainPageBG" style="width:50%; border:0px solid #A9A9A9; vertical-align:top;"| | | class="MainPageBG" style="width:50%; border:0px solid #A9A9A9; vertical-align:top;"| | ||
{| id="mp-right" style="width:100%; vertical-align:top;" | {| id="mp-right" style="width:100%; vertical-align:top;" | ||
− | |||
| | | | ||
Line 294: | Line 484: | ||
|- valign="top" | |- valign="top" | ||
| width="140" |'''title''': | | width="140" |'''title''': | ||
− | | width="558"| | + | | width="558"|Synthesis and Performance Optimization of a Switching Nano-Crossbar Computer |
|- valign="top" | |- valign="top" | ||
| '''agency & program''': | | '''agency & program''': | ||
− | | [http:// | + | | width="558"| [http://ec.europa.eu/research/mariecurieactions/about-msca/actions/rise/index_en.htm European Union/European Commission H2020 MSCA Research and Innovation Staff Exchange Program (RISE)] |
|- valign="top" | |- valign="top" | ||
| '''budget''': | | '''budget''': | ||
− | | | + | | 724.500 EURO |
|- valign="top" | |- valign="top" | ||
| '''duration''': | | '''duration''': | ||
− | | | + | | 2015-2019, ''completed'' |
|} | |} | ||
− | + | {| style="margin-left: auto; margin-right: 0px; border:0.1px solid #abd5ff; background:#f1f5fc; padding:0.2em 0em;" | |
+ | |- valign="top" | ||
+ | | width="140" |'''project goal''': | ||
+ | | width="558"| Developing a complete synthesis methodology for nano-crossbar arrays, and implementing technology-dependent state machines that leads to the design and construction of an emerging computer. | ||
+ | |||
+ | |} | ||
+ | |||
|} | |} | ||
{| style="margin-left: auto; margin-right: 0px; border:1px solid #abd5f5; background:#f1f5fc;" | {| style="margin-left: auto; margin-right: 0px; border:1px solid #abd5f5; background:#f1f5fc;" | ||
Line 313: | Line 509: | ||
|- valign=top | |- valign=top | ||
| width="140" |'''title''': | | width="140" |'''title''': | ||
− | | width="558"| | + | | width="558"|Synthesis and Reliability Analysis of Nano Switching Arrays |
|- valign="top" | |- valign="top" | ||
| '''agency & program''': | | '''agency & program''': | ||
− | | [http:// | + | | [http://www.tubitak.gov.tr/tr/destekler/akademik/ulusal-destek-programlari/icerik-3501-kariyer-gelistirme-programi TUBITAK Career Program (3501)] |
+ | |- valign="top" | ||
+ | | '''budget''': | ||
+ | | 190.000 TL | ||
|- valign="top" | |- valign="top" | ||
| '''duration''': | | '''duration''': | ||
− | | 2014- | + | | 2014-2017, ''completed'' |
+ | |} | ||
+ | {| style="margin-left: auto; margin-right: 0px; border:0.1px solid #abd5ff; background:#f1f5fc; padding:0.2em 0em;" | ||
+ | |- valign="top" | ||
+ | | width="140" |'''project goal''': | ||
+ | | width="558"| Performing logic synthesis, fault tolerance, and performance optimization for nano-crossbar arrays. | ||
+ | |||
|} | |} | ||
− | |||
|} | |} | ||
Line 333: | Line 537: | ||
{| id=portal cellspacing="0" cellpadding="0" width=100% style="border:1px solid #B8C7D9; padding:0px;" | {| id=portal cellspacing="0" cellpadding="0" width=100% style="border:1px solid #B8C7D9; padding:0px;" | ||
|- | |- | ||
− | | colspan="2" style="background:# | + | | colspan="2" style="background:#8FBC8F; text-align:center; padding:1px; border-bottom:1px #8FBC8F solid;" | |
− | <h2 style="margin:.1em; border-bottom:1px; font-size:140%; font-weight:bold;"> Stochastic | + | <h2 style="margin:.1em; border-bottom:1px; font-size:140%; font-weight:bold;"> Stochastic and Bit Stream Computing </h2> |
|- | |- | ||
| valign="top" style="padding:8px 8px 0px 8px; background:#f5fffa;" <!--H210 S4 V100--> | | | valign="top" style="padding:8px 8px 0px 8px; background:#f5fffa;" <!--H210 S4 V100--> | | ||
− | <h3> | + | We propose a novel computing paradigm “Bit Stream Computing (BSC)” that does not necessarily employ randomly or Binomially distributed bit streams as stochastic |
+ | computing does. '''Any type of streams can be used either stochastic | ||
+ | or deterministic'''. The proposed paradigm benefits from the area | ||
+ | advantage of stochastic logic and the accuracy advantage of | ||
+ | conventional binary logic. We implement '''accurate arithmetic | ||
+ | multiplier and adder circuits''', classified as asynchronous or | ||
+ | synchronous. We believe that this study '''opens | ||
+ | up new horizons for computing that enables us to implement | ||
+ | much smaller yet accurate arithmetic circuits''' compared to the | ||
+ | conventional binary and stochastic ones. | ||
+ | |||
+ | <!-- <h3> | ||
Accurate Arithmetic Implementations</h3> | Accurate Arithmetic Implementations</h3> | ||
− | We propose a method to overcome the main drawback in stochastic computing, '''low accuracy''' or related '''long computing times'''. Our method manipulates stochastic bit streams with the aid of feedback mechanisms. We implement error-free arithmetic multiplier and adder circuits by considering performance parameters area, delay, and accuracy. | + | We propose a method to overcome the main drawback in stochastic computing, '''low accuracy''' or related '''long computing times'''. Our method manipulates stochastic bit streams with the aid of feedback mechanisms. We implement error-free arithmetic multiplier and adder circuits by considering performance parameters area, delay, and accuracy. --> |
− | + | [[Image:Research_Bit_Stream.png|center|none|800px|link=]] | |
− | [[Image: | + | |
<!-- YAYIN --> | <!-- YAYIN --> | ||
Line 362: | Line 576: | ||
|- valign=top | |- valign=top | ||
| width="100" |'''title''': | | width="100" |'''title''': | ||
− | | width="450"|[[Media: | + | | width="450"|[[Media:Vahapoglu_Altun_From_Stochastic_To_Bit_Stream_Computing.pdf | From Stochastic to Bit Stream Computing: Accurate Implementation of Arithmetic Circuits and Applications in Neural Networks]] |
|- valign="top" | |- valign="top" | ||
| '''authors''': | | '''authors''': | ||
| Ensar Vahapoglu and [[Mustafa Altun]] | | Ensar Vahapoglu and [[Mustafa Altun]] | ||
+ | |- valign="top" | ||
+ | | '''appeared in''': | ||
+ | | arXiv, 1805.06262, 2018. | ||
|- valign=top | |- valign=top | ||
| '''presented at''': | | '''presented at''': | ||
− | | width="450"| [http://www. | + | | width="450"| [http://www.eng.ucy.ac.cy/theocharides/isvlsi16/ IEEE Computer Society Annual Symposium on VLSI (ISVLSI)], Pittsburgh, USA, 2016. |
|} | |} | ||
| align=center width="70" | | | align=center width="70" | | ||
<span class="plainlinks"> | <span class="plainlinks"> | ||
− | [[File:PDF.png|65px|link=http://www.ecc.itu.edu.tr/images/ | + | [[File:PDF.png|65px|link=http://www.ecc.itu.edu.tr/images/7/73/Vahapoglu_Altun_From_Stochastic_To_Bit_Stream_Computing.pdf]]</span> |
<br> | <br> | ||
− | [[Media: | + | [[Media:Vahapoglu_Altun_From_Stochastic_To_Bit_Stream_Computing.pdf | Paper]] |
| align="center" width="70" | | | align="center" width="70" | | ||
<span class="plainlinks"> | <span class="plainlinks"> | ||
− | [[File:PPT.jpg|60px|link= | + | [[File:PPT.jpg|60px|link=https://www.ecc.itu.edu.tr/images/d/d6/Vahapoglu_Altun_Accurate_Synthesis_of_Arithmetic_Operations_with_Stochastic_Logic.pptx]] |
</span> | </span> | ||
− | <br> [ | + | <br> [https://www.ecc.itu.edu.tr/images/d/d6/Vahapoglu_Altun_Accurate_Synthesis_of_Arithmetic_Operations_with_Stochastic_Logic.pptx Poster] |
|} | |} | ||
|} | |} | ||
Line 412: | Line 629: | ||
|- valign="top" | |- valign="top" | ||
| '''duration''': | | '''duration''': | ||
− | | 2017-2020 | + | | 2017-2020, ''completed'' |
− | + | ||
|} | |} | ||
+ | {| style="margin-left: auto; margin-right: 0px; border:0.1px solid #abd5ff; background:#f1f5fc; padding:0.2em 0em;" | ||
+ | |- valign="top" | ||
+ | | width="140" |'''project goal''': | ||
+ | | width="558"| Improving accuracy in stochastic computing with implementing error–free aritmetic blocks, and using them in large-area electronics. | ||
− | {| style="margin-left: auto; margin-right: 0px; border:1px solid #abd5f5; background:#f1f5fc;" | + | |} |
+ | |} | ||
+ | <!-- {| style="margin-left: auto; margin-right: 0px; border:1px solid #abd5f5; background:#f1f5fc;" | ||
| | | | ||
Line 431: | Line 653: | ||
|} | |} | ||
− | |} | + | |} --> |
− | + | ||
|} | |} | ||
|} | |} | ||
Line 442: | Line 663: | ||
{| id=portal cellspacing="0" cellpadding="0" width=100% style="border:1px solid #B8C7D9; padding:0px;" | {| id=portal cellspacing="0" cellpadding="0" width=100% style="border:1px solid #B8C7D9; padding:0px;" | ||
|- | |- | ||
− | | colspan="2" style="background:# | + | | colspan="2" style="background:#8FBC7F; text-align:center; padding:1px; border-bottom:1px #8FBC7F solid;" | |
<h2 style="margin:.1em; border-bottom:1px; font-size:140%; font-weight:bold;"> Approximate Circuit and System Design </h2> | <h2 style="margin:.1em; border-bottom:1px; font-size:140%; font-weight:bold;"> Approximate Circuit and System Design </h2> | ||
|- | |- | ||
| valign="top" style="padding:8px 8px 0px 8px; background:#f5fffa;" <!--H210 S4 V100--> | | | valign="top" style="padding:8px 8px 0px 8px; background:#f5fffa;" <!--H210 S4 V100--> | | ||
+ | <!-- <h3> | ||
+ | Power/Area Efficient Approximate System Design Methodology</h3> --> | ||
− | + | This work provides '''power/area efficiency of circuit-level design with accuracy supervision of system-level design'''. First, approximate computational units, mostly adders and multipliers, are synthesized in circuit level. Then, in system level, the appropriate approximate computational units are selected to minimize the total computation cost, yet maintaining | |
− | + | the ultimate performance. The method investigates the overall system from the highest level down to the arithmetic units to determine the sufficient output quality at each block. | |
− | + | ||
− | This work | + | |
− | + | ||
[[Image:Research-approximate.png|center|none|800px|link=]] | [[Image:Research-approximate.png|center|none|800px|link=]] | ||
Line 472: | Line 692: | ||
|- valign=top | |- valign=top | ||
| width="100" |'''title''': | | width="100" |'''title''': | ||
− | | width="450"|[[Media: | + | | width="450"|[[Media:Nojehdeh_Altun_Approximate_Adders_Multipliers.pdf | Systematic Synthesis of Approximate Adders and Multipliers with Accurate Error Calculations]] |
|- valign="top" | |- valign="top" | ||
| '''authors''': | | '''authors''': | ||
− | | | + | | Mohammadreza Nojehdeh and [[Mustafa Altun]] |
+ | |- valign="top" | ||
+ | | '''appeared in''': | ||
+ | | width="450" | [http://www.journals.elsevier.com/integration Integration, the VLSI Journal], Vol. 70, pp. 99–107, 2020. | ||
|- valign=top | |- valign=top | ||
| '''presented at''': | | '''presented at''': | ||
− | | width="450"| [http://www. | + | | width="450"| [http://www.eng.ucy.ac.cy/theocharides/isvlsi20/ IEEE Computer Society Annual Symposium on VLSI (ISVLSI)], Limassol, Cyprus, 2020. |
+ | |} | ||
+ | | align=center width="70" | | ||
+ | <span class="plainlinks"> | ||
+ | [[File:PDF.png|65px|link=http://www.ecc.itu.edu.tr/images/c/c8/Nojehdeh_Altun_Approximate_Adders_Multipliers.pdf]]</span> | ||
+ | <br> | ||
+ | [[Media:Nojehdeh_Altun_Approximate_Adders_Multipliers.pdf | Paper]] | ||
+ | | align="center" width="70" | | ||
+ | <span class="plainlinks"> | ||
+ | |||
+ | [[File:PPT.jpg|60px|link=https://www.ecc.itu.edu.tr/images/7/7f/Nojehdeh_Aksoy_Altun_Approximate_ANN.pptx]] | ||
+ | </span> | ||
+ | <br> [https://www.ecc.itu.edu.tr/images/7/7f/Nojehdeh_Aksoy_Altun_Approximate_ANN.pptx Slides] | ||
+ | |} | ||
+ | {| style="border:1px solid #abd5f5; background:#f1f5fc;" | ||
+ | | | ||
+ | {| | ||
+ | |- valign=top | ||
+ | | width="100" |'''title''': | ||
+ | | width="450"|[[Media:Ayhan_Altun_Circuit_Aware_Approximate_System_Design.pdf| Circuit Aware Approximate System Design with Case Studies in Image Processing and Neural Networks]] | ||
+ | |- valign="top" | ||
+ | | '''authors''': | ||
+ | | Tuba Ayhan and [[Mustafa Altun]] | ||
+ | |- valign="top" | ||
+ | | '''appeared in''': | ||
+ | | [http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6287639 IEEE Access], Vol. 7, pp. 4726–4734, 2019. | ||
+ | |- valign=top | ||
+ | | '''presented at''': | ||
+ | | width="450"| [http://www.eng.ucy.ac.cy/theocharides/isvlsi17/ IEEE Computer Society Annual Symposium on VLSI (ISVLSI)], Bochum, Germany, 2017. | ||
|} | |} | ||
| align=center width="70" | | | align=center width="70" | | ||
<span class="plainlinks"> | <span class="plainlinks"> | ||
− | [[File:PDF.png|65px|link=http://www.ecc.itu.edu.tr/images/ | + | [[File:PDF.png|65px|link=http://www.ecc.itu.edu.tr/images/9/90/Ayhan_Altun_Circuit_Aware_Approximate_System_Design.pdf]]</span> |
<br> | <br> | ||
− | [[Media: | + | [[Media:Ayhan_Altun_Circuit_Aware_Approximate_System_Design.pdf | Paper]] |
| align="center" width="70" | | | align="center" width="70" | | ||
<span class="plainlinks"> | <span class="plainlinks"> | ||
− | [[File:PPT.jpg|60px|link= | + | [[File:PPT.jpg|60px|link=https://www.ecc.itu.edu.tr/images/8/86/Ayhan_Kula_Altun_Approximate_System_Design_Methodology.pptx]] |
</span> | </span> | ||
− | <br> [ | + | <br> [https://www.ecc.itu.edu.tr/images/8/86/Ayhan_Kula_Altun_Approximate_System_Design_Methodology.pptx Slides] |
|} | |} | ||
Line 524: | Line 775: | ||
|- valign="top" | |- valign="top" | ||
| '''duration''': | | '''duration''': | ||
− | | 2017-2020 | + | | 2017-2020, ''completed'' |
|} | |} | ||
+ | {| style="margin-left: auto; margin-right: 0px; border:0.1px solid #abd5ff; background:#f1f5fc; padding:0.2em 0em;" | ||
+ | |- valign="top" | ||
+ | | width="140" |'''project goal''': | ||
+ | | width="558"| Developing a hierarchical circuit/system design approach that can find solutions close to optimal solutions for power/energy consumption by determining the required accuracy performance of each circuit block, depending on the level of accuracy or quality desired from the system. | ||
|} | |} | ||
+ | |} | ||
+ | |} | ||
+ | |} | ||
+ | |} | ||
+ | |||
+ | <!-- QUANTUM --> | ||
+ | |||
+ | {| id=portal cellspacing="0" cellpadding="0" width=100% style="border:1px solid #B8C7D9; padding:0px;" | ||
+ | |- | ||
+ | | colspan="2" style="background:#8FBC6F; text-align:center; padding:1px; border-bottom:1px #8FBC6F solid;" | | ||
+ | <h2 style="margin:.1em; border-bottom:1px; font-size:140%; font-weight:bold;"> Reversible Computing </h2> | ||
+ | |- | ||
+ | | valign="top" style="padding:8px 8px 0px 8px; background:#f5fffa;" <!--H210 S4 V100--> | | ||
+ | |||
+ | Unlike conventional CMOS circuits, reversible circuits do not have latent faults, so faults occurring in internal circuit nodes | ||
+ | always result in an error at the output. This is a unique feature for online or concurrent fault tolerance. Motivated by this, we implement error tolerant CMOS circuit blocks by exploiting reversible computing. We first synthesize reversible circuits with reversible gates; then we make them fault-tolerant; and finally we perform conversion from reversible gates to CMOS gates. | ||
+ | |||
+ | |||
+ | [[Image:Research-reversible-2.png|center|none|800px|link=]] | ||
+ | |||
+ | <h3> | ||
+ | |||
+ | Perfect Online Error Detection </h3> | ||
+ | |||
+ | In order to achieve a CMOS circuit having '''100% online or concurrent error detection''', we exploit reversible computing by proposing a new, fault preservative, and reversible gate library. We ensure that the parity, even or odd, is preserved at all levels including the output level unless there is a faulty node. | ||
+ | <!--<h3> | ||
+ | |||
+ | Synthesis </h3> | ||
+ | |||
+ | We propose a fast synthesis algorithm that implements any given reversible Boolean function with reversible gates. Instead of an exhaustive search on every given function, our algorithm creates a library of '''essential functions''' and performs '''sorting'''. As an example, to implement 4 bit circuits we only use 120 essential functions out of all 20922789888000 functions. We also perform optimization for both '''reversible and quantum circuit costs''' by considering adjacent gate pairs. | ||
+ | --> | ||
+ | <h3> | ||
+ | |||
+ | Online Error Detection and Correction </h3> | ||
+ | |||
+ | We develop two techniques to make a reversible circuit fault-tolerant by using multiple-control Toffoli gates. The first technique is based on '''single parity preserving''', and offers error detection for odd number of errors at the output. The second technique is constructed on '''Hamming codes for error correction'''. We also claim that perfect error detection is possible with conservative reversible gates such as a Fredkin gate. As the next step, we '''utilize the proposed reversible circuits with conventional CMOS gates'''. | ||
+ | |||
+ | <!-- [[Image:Research-4.png|center|none|800px|link=]] --> | ||
+ | <!-- YAYIN --> | ||
+ | {| id="mp-upper" style="width: 100%; margin:4px 0 0 0; background:none; border-spacing: 0px;" | ||
+ | | class="MainPageBG" style="width:50%; border:0px solid #D8BFD8; vertical-align:top; color:#000;" | | ||
+ | {| id="mp-left" style="width:100%; vertical-align:top;" | ||
+ | |||
+ | | | ||
+ | |||
+ | {| style="border:1px solid #abd5f5; background:#d0e5f5; padding:0.2em 0.5em; font-weight:bold;" | ||
+ | |||
+ | |- valign=top | ||
+ | | width="696" |'''Selected Publications''' | ||
+ | |} | ||
+ | |||
+ | {| style="border:1px solid #abd5f5; background:#f1f5fc;" | ||
+ | |||
+ | | | ||
+ | {| | ||
+ | |- valign=top | ||
+ | | width="100" |'''title''': | ||
+ | | width="450"|[[Media:Parvin_Altun_Perfect_Concurrent_Fault_Detection.pdf| Perfect Concurrent Fault Detection in CMOS Logic Circuits Using Parity Preservative Reversible Gates | ||
+ | ]] | ||
+ | |- valign="top" | ||
+ | | '''authors''': | ||
+ | | Sajjad Parvin and [[Mustafa Altun]] | ||
+ | |- valign="top" | ||
+ | | '''appeared in''': | ||
+ | | [http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6287639 IEEE Access], Vol. 7, pp. 163939–163947, 2019. | ||
+ | |- valign=top | ||
+ | | '''presented at''': | ||
+ | | width="450"| [http://tima.univ-grenoble-alpes.fr/conferences/iolts/iolts19/ IEEE International Symposium on On-Line Testing and Robust System Design (IOLTS)], Rhodes Island, Greece, 2019. | ||
+ | |} | ||
+ | |||
+ | | align=center width="70" | | ||
+ | <span class="plainlinks"> | ||
+ | [[File:PDF.png|65px|link=http://www.ecc.itu.edu.tr/images/3/3c/Parvin_Altun_Perfect_Concurrent_Fault_Detection.pdf]]</span> | ||
+ | <br> | ||
+ | [[Media:Parvin_Altun_Perfect_Concurrent_Fault_Detection.pdf | Paper]] | ||
+ | | align="center" width="70" | | ||
+ | <span class="plainlinks"> | ||
+ | |||
+ | [[File:PPT.jpg|60px|link=http://www.ecc.itu.edu.tr/images/f/f4/Parvin_Altun_CMOS_Fault_Tolerance_with_Preservative_Reversible_Gates.pptx]] | ||
+ | </span> | ||
+ | <br> [http://www.ecc.itu.edu.tr/images/f/f4/Parvin_Altun_CMOS_Fault_Tolerance_with_Preservative_Reversible_Gates.pptx Poster] | ||
+ | |} | ||
+ | |||
+ | {| style="border:1px solid #abd5f5; background:#f1f5fc;" | ||
+ | | | ||
+ | {| | ||
+ | |- valign=top | ||
+ | | width="100" |'''title''': | ||
+ | | width="524"|[[Media:Altun_Parvin_Cilasun_Exploiting_Reversible_Computing_for_CMOS_Fault_Tolerance.pdf| Exploiting Reversible Computing for Latent-Fault-Free Error Detecting/Correcting CMOS Circuits | ||
+ | ]] | ||
+ | |- valign="top" | ||
+ | | '''authors''': | ||
+ | | [[Mustafa Altun]], Sajjad Parvin, and Husrev Cilasun | ||
+ | |- valign="top" | ||
+ | | '''appeared in''': | ||
+ | | [http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6287639 IEEE Access], Vol. 6, pp. 74475–74484, 2018. | ||
+ | |} | ||
+ | | align=center width="70" | | ||
+ | <span class="plainlinks"> | ||
+ | [[File:PDF.png|65px|link=http://www.ecc.itu.edu.tr/images/7/7d/Altun_Parvin_Cilasun_Exploiting_Reversible_Computing_for_CMOS_Fault_Tolerance.pdf]]</span> | ||
+ | <br> | ||
+ | [[Media:Altun_Parvin_Cilasun_Exploiting_Reversible_Computing_for_CMOS_Fault_Tolerance.pdf | Paper]] | ||
+ | |} | ||
+ | |||
+ | <!-- {| style="border:1px solid #abd5f5; background:#f1f5fc;" | ||
+ | |||
+ | | | ||
+ | {| | ||
+ | |- valign=top | ||
+ | | width="100" |'''title''': | ||
+ | | width="450"|[[Media:Susam_Altun_Fast_Synthesis_of_Reversible_Circuits_using_a_Sorting_Algorithm_and_Optimization.pdf| Fast Synthesis of Reversible Circuits using a Sorting Algorithm and Optimization]] | ||
+ | |- valign="top" | ||
+ | | '''authors''': | ||
+ | | Omercan Susam and [[Mustafa Altun]] | ||
+ | |- valign="top" | ||
+ | | '''appeared in''': | ||
+ | | width="450"| [http://www.oldcitypublishing.com/journals/mvlsc-home/ Journal of Multiple-Valued Logic and Soft Computing], Vol. 29, Issue 1-2, pp. 1–23, 2017. | ||
+ | |- valign="top" | ||
+ | | '''presented at''': | ||
+ | | width="450"| [http://www.ieee-icecs2014.org/ IEEE International Conference on Electronics Circuits and Systems (ICECS)], Marseille, France, 2014. | ||
+ | |} | ||
+ | | align=center width="70" | | ||
+ | <span class="plainlinks"> | ||
+ | [[File:PDF.png|65px|link=http://www.ecc.itu.edu.tr/images/c/cd/Susam_Altun_Fast_Synthesis_of_Reversible_Circuits_using_a_Sorting_Algorithm_and_Optimization.pdf]]</span> | ||
+ | <br> | ||
+ | [[Media:Susam_Altun_Fast_Synthesis_of_Reversible_Circuits_using_a_Sorting_Algorithm_and_Optimization.pdf | Paper]] | ||
+ | | align="center" width="70" | | ||
+ | <span class="plainlinks"> | ||
+ | |||
+ | [[File:PPT.jpg|60px|link=https://www.ecc.itu.edu.tr/images/d/d0/Susam_Altun_An_Efficient_Algorithm_to_Synthesize_Quantum_Circuits_and_Optimization.pptx]] | ||
+ | </span> | ||
+ | <br> [https://www.ecc.itu.edu.tr/images/d/d0/Susam_Altun_An_Efficient_Algorithm_to_Synthesize_Quantum_Circuits_and_Optimization.pptx Slides] | ||
+ | |} | ||
+ | --> | ||
+ | |} | ||
+ | |||
+ | | style="border:1px solid transparent;" | | ||
+ | <!-- PROJE --> | ||
+ | | class="MainPageBG" style="width:50%; border:0px solid #A9A9A9; vertical-align:top;"| | ||
+ | {| id="mp-right" style="width:100%; vertical-align:top;" | ||
+ | |||
+ | | | ||
+ | |||
+ | {| style="margin-left: auto; margin-right: 0px; border:1px solid #abd5f5; background:#d0e5f5; padding:0.2em 0.5em; font-weight:bold;" | ||
+ | |||
+ | |- valign=top | ||
+ | | width="696" |'''Funding Projects''' | ||
+ | |} | ||
+ | {| style="margin-left: auto; margin-right: 0px; border:1px solid #abd5f5; background:#f1f5fc;" | ||
+ | |||
+ | | | ||
+ | {| | ||
+ | |- valign="top" | ||
+ | | width="140" |'''title''': | ||
+ | | width="558"|Implementation of a Fault-Aware 8-Bit Reversible Microprocessor | ||
+ | |- valign="top" | ||
+ | | '''agency & program''': | ||
+ | | [http://www.tubitak.gov.tr/tr/destekler/akademik/ulusal-destek-programlari/icerik-1002-hizli-destek-programi TUBITAK Short Term R&D Funding Program (1002)] | ||
+ | |- valign="top" | ||
+ | | '''budget''': | ||
+ | | 30.000 TL | ||
+ | |- valign="top" | ||
+ | | '''duration''': | ||
+ | | 2016-2017, ''completed'' | ||
+ | |} | ||
+ | {| style="margin-left: auto; margin-right: 0px; border:0.1px solid #abd5ff; background:#f1f5fc; padding:0.2em 0em;" | ||
+ | |- valign="top" | ||
+ | | width="140" |'''project goal''': | ||
+ | | width="558"| Developing a synthesis methodology for online fault aware reversible circuits and implementing their CMOS counterparts. | ||
+ | |||
+ | |} | ||
+ | |} | ||
+ | |||
+ | <!-- {| style="margin-left: auto; margin-right: 0px; border:1px solid #abd5f5; background:#f1f5fc;" | ||
+ | |||
+ | | | ||
+ | {| | ||
+ | |- valign=top | ||
+ | | width="140" |'''title''': | ||
+ | | width="558"|Quantum Circuit Design and Computation | ||
+ | |- valign="top" | ||
+ | | '''agency & program''': | ||
+ | | [http://bap.itu.edu.tr/ Istanbul Technical University Research Support Program (ITU-BAP)] | ||
+ | |- valign="top" | ||
+ | | '''duration''': | ||
+ | | 2014-2015, ''completed'' | ||
+ | |} | ||
+ | |||
+ | |} --> | ||
+ | |||
|} | |} | ||
|} | |} | ||
Line 535: | Line 980: | ||
{| id=portal cellspacing="0" cellpadding="0" width=100% style="border:1px solid #B8C7D9; padding:0px;" | {| id=portal cellspacing="0" cellpadding="0" width=100% style="border:1px solid #B8C7D9; padding:0px;" | ||
|- | |- | ||
− | | colspan="2" style="background:# | + | | colspan="2" style="background:#8FBC5F; text-align:center; padding:1px; border-bottom:1px #8FBC5F solid;" | |
<h2 style="margin:.1em; border-bottom:1px; font-size:140%; font-weight:bold;"> Reliability of Electronic Products </h2> | <h2 style="margin:.1em; border-bottom:1px; font-size:140%; font-weight:bold;"> Reliability of Electronic Products </h2> | ||
|- | |- | ||
Line 553: | Line 998: | ||
We investigate different degradation mechanisms of ZnO varistors. We propose a model showing how the varistor voltage Vv changes by time for different stress levels. For this purpose, accelerated degradation tests are applied for different AC current levels; then voltage values are measured. Different from the common practice in the literature that considers a degradation with only decreasing Vv values, we demonstrate '''either an increasing or a decreasing trend in the Vv parameter'''. | We investigate different degradation mechanisms of ZnO varistors. We propose a model showing how the varistor voltage Vv changes by time for different stress levels. For this purpose, accelerated degradation tests are applied for different AC current levels; then voltage values are measured. Different from the common practice in the literature that considers a degradation with only decreasing Vv values, we demonstrate '''either an increasing or a decreasing trend in the Vv parameter'''. | ||
− | + | <!-- | |
<h3> | <h3> | ||
Calibrated Accelerated Life Testing</h3> | Calibrated Accelerated Life Testing</h3> | ||
− | Dramatic decrease in failure rates for electronic products makes conventional accelerated life tests ('''ALT''') extremely time consuming and costly. Recently proposed calibrated accelerated life tests ('''CALT''') aim to use fewer samples than those used in ALT. We thoroughly compare ALT and CALT by considering the effects of failure rate, acceleration factor, and stress level on the required test time. | + | Dramatic decrease in failure rates for electronic products makes conventional accelerated life tests ('''ALT''') extremely time consuming and costly. Recently proposed calibrated accelerated life tests ('''CALT''') aim to use fewer samples than those used in ALT. We thoroughly compare ALT and CALT by considering the effects of failure rate, acceleration factor, and stress level on the required test time.--> |
<!-- YAYIN --> | <!-- YAYIN --> | ||
Line 598: | Line 1,043: | ||
<span class="plainlinks"> | <span class="plainlinks"> | ||
− | [[File:PPT.jpg|60px|link= | + | [[File:PPT.jpg|60px|link=https://www.ecc.itu.edu.tr/images/a/a7/Comert_Altun_Nadar_Erturk_Warranty_Forecasting_of_Electronic_Boards_using_Short-term_Field_Data.pptx]] |
</span> | </span> | ||
− | <br> [ | + | <br> [https://www.ecc.itu.edu.tr/images/a/a7/Comert_Altun_Nadar_Erturk_Warranty_Forecasting_of_Electronic_Boards_using_Short-term_Field_Data.pptx Slides] |
|} | |} | ||
Line 627: | Line 1,072: | ||
| align="center" width="70" | | | align="center" width="70" | | ||
<span class="plainlinks"> | <span class="plainlinks"> | ||
− | + | [[File:PPT.jpg|60px|link=https://www.ecc.itu.edu.tr/images/d/de/Yadavari_EtAl_Effects_of_ZnO_Varistor_Degradation_on_the_Overvoltage_Protection_Mechanism_of_Electronic_Boards.pptx]] | |
− | [[File:PPT.jpg|60px|link= | + | |
</span> | </span> | ||
− | <br> [ | + | <br> [https://www.ecc.itu.edu.tr/images/d/de/Yadavari_EtAl_Effects_of_ZnO_Varistor_Degradation_on_the_Overvoltage_Protection_Mechanism_of_Electronic_Boards.pptx Slides] |
|} | |} | ||
− | + | <!-- | |
{| style="border:1px solid #abd5f5; background:#f1f5fc;" | {| style="border:1px solid #abd5f5; background:#f1f5fc;" | ||
Line 655: | Line 1,099: | ||
<span class="plainlinks"> | <span class="plainlinks"> | ||
− | [[File:PPT.jpg|60px|link= | + | [[File:PPT.jpg|60px|link=https://www.ecc.itu.edu.tr/images/a/a8/Sal_Altun_Extensive_Investigation_of_CALT_in_Comparison_with_ALT.pptx]] |
</span> | </span> | ||
− | <br> [ | + | <br> [https://www.ecc.itu.edu.tr/images/a/a8/Sal_Altun_Extensive_Investigation_of_CALT_in_Comparison_with_ALT.pptx Slides] |
− | |} | + | |} --> |
− | |} | + | |} |
| style="border:1px solid transparent;" | | | style="border:1px solid transparent;" | | ||
<!-- PROJE --> | <!-- PROJE --> | ||
Line 688: | Line 1,132: | ||
| 2013-2015, ''completed'' | | 2013-2015, ''completed'' | ||
|} | |} | ||
− | + | {| style="margin-left: auto; margin-right: 0px; border:0.1px solid #abd5ff; background:#f1f5fc; padding:0.2em 0em;" | |
+ | |- valign="top" | ||
+ | | width="140" |'''project goal''': | ||
+ | | width="558"| Developing reliability prediction techniques for electronic cards of household appliances by using field return data, new accelerated test methodologies, and physics of failure based simulations. | ||
+ | |} | ||
|} | |} | ||
− | {| style="margin-left: auto; margin-right: 0px; border:1px solid #abd5f5; background:#f1f5fc;" | + | <!-- {| style="margin-left: auto; margin-right: 0px; border:1px solid #abd5f5; background:#f1f5fc;" |
| | | | ||
Line 705: | Line 1,153: | ||
|} | |} | ||
− | |} | + | |} --> |
|} | |} | ||
Line 716: | Line 1,164: | ||
{| id=portal cellspacing="0" cellpadding="0" width=100% style="border:1px solid #B8C7D9; padding:0px;" | {| id=portal cellspacing="0" cellpadding="0" width=100% style="border:1px solid #B8C7D9; padding:0px;" | ||
|- | |- | ||
− | | colspan="2" style="background:# | + | | colspan="2" style="background:#8FBC4F; text-align:center; padding:1px; border-bottom:1px #8FBC4F solid;" | |
<h2 style="margin:.1em; border-bottom:1px; font-size:140%; font-weight:bold;"> Analog Circuit Design </h2> | <h2 style="margin:.1em; border-bottom:1px; font-size:140%; font-weight:bold;"> Analog Circuit Design </h2> | ||
|- | |- | ||
Line 762: | Line 1,210: | ||
<span class="plainlinks"> | <span class="plainlinks"> | ||
− | [[File:PPT.jpg|60px|link= | + | [[File:PPT.jpg|60px|link=https://www.ecc.itu.edu.tr/images/7/77/Altun_Kuntman_A_Wideband_CMOS_Current-Mode_Operational_Amplifier_and_Its_Use_for_Band-Pass_Filter_Realization.ppt]] |
</span> | </span> | ||
− | <br> [ | + | <br> [https://www.ecc.itu.edu.tr/images/7/77/Altun_Kuntman_A_Wideband_CMOS_Current-Mode_Operational_Amplifier_and_Its_Use_for_Band-Pass_Filter_Realization.ppt Slides] |
|} | |} | ||
Line 779: | Line 1,227: | ||
{| id=portal cellspacing="0" cellpadding="0" width=100% style="border:1px solid #B8C7D9; padding:0px;" | {| id=portal cellspacing="0" cellpadding="0" width=100% style="border:1px solid #B8C7D9; padding:0px;" | ||
|- | |- | ||
− | | colspan="2" style="background:# | + | | colspan="2" style="background:#8FBC3F; text-align:center; padding:1px; border-bottom:1px #8FBC3F solid;" | |
<h2 style="margin:.1em; border-bottom:1px; font-size:140%; font-weight:bold;"> Discrete Mathematics </h2> | <h2 style="margin:.1em; border-bottom:1px; font-size:140%; font-weight:bold;"> Discrete Mathematics </h2> | ||
|- | |- | ||
Line 822: | Line 1,270: | ||
<span class="plainlinks"> | <span class="plainlinks"> | ||
− | [[File:PPT.jpg|60px|link= | + | [[File:PPT.jpg|60px|link=https://www.ecc.itu.edu.tr/images/1/18/Altun_Riedel_A_Study_on_Monotone_Self_Dual_Boolean_Functions.ppt]] |
</span> | </span> | ||
− | <br> [ | + | <br> [https://www.ecc.itu.edu.tr/images/1/18/Altun_Riedel_A_Study_on_Monotone_Self_Dual_Boolean_Functions.ppt Slides] |
|} | |} | ||
Latest revision as of 22:18, 17 April 2023
Our research aims to develop novel ways of computing, circuit design, and reliability for electronic circuits and systems. Our research mainly targets emerging technologies and new computing paradigms. Listed below are the research topics, ordered from newest to oldest as well as by considering their importance. Each topic is explained briefly in support with related papers and projects.
Computing with Switching Lattices | ||||||||||||||||||||||||||||||||||||||||
A switching lattice, formed as a two dimensional network of four-terminal switches, is introduced as a crossbar based, regular, dense, area-efficient, and CMOS-compatible structure for logic computing. A four-terminal switch, corresponding to a crossbar cross-point or a lattice site, has one control input and four terminals. The control input makes all of its terminals either all disconnected (OFF) or all connected (ON). ![]() Technology DevelopmentWe show that switching lattices are CMOS-compatible. For this purpose, we propose different four-terminal switch structures, and construct them in three dimensional technology computer-aided design (TCAD) environment as well as in Cadence environment satisfying the design rules of the TSMC 65nm CMOS process and perform simulations. Experimental results show that the realization of logic functions using switching lattices occupy much less layout area and have competitive delay and power consumption values when compared to the conventional CMOS implementations. ![]() Performance OptimizationWe propose a logic synthesis algorithm to optimize lattice sizes under a delay constraint. We also propose static and dynamic logic solutions for area-delay-power efficiency of the lattices. SynthesisWe propose optimal and heuristic algorithms to implement logic functions with minimum size switching lattices.
|
Energy Efficient ANN Hardware Implementation | |||||||||||||||||||||||||||
We aim to use hardware aware training techniques, new hybrid bit parallel-serial number representations, and constant multiplication based sharing techniques to reduce energy consumption of feed-forward artificial neural networks (ANNs). ![]()
|
Computing with Nano-Crossbar Arrays | |||||||||||||||||||||||||||
Nano-crossbar arrays have emerged as a strong candidate technology to replace CMOS in near future. They are regular and dense structures. Computing with crossbar arrays is achieved by its crosspoints behaving as switches, either two-terminal or four-terminal. Depending on the technology used, a two-terminal switch behaves as a diode, a resistive/memristive switch, or a field effect transistor (FET). On the other hand, a four-terminal switch has a unique behavior. While there have been many different technologies proposed for two-terminal switch based arrays, technology development for four-terminal switch based arrays, called switching lattices, has recently started. For both two-terminal and four-terminal switch based arrays, we aim to develop a complete synthesis and performance optimization methodology for switching nano-crossbar arrays that leads to the design and construction of an emerging nanocomputer. We also aim to develeop CMOS-compatible technologies for crossbar arrays, specifically for switching lattices. ![]() Technology DevelopmentAlthough a four-terminal switch based array offers a significant area advantage, in terms of the number of switches, compared to the ones having two-terminal switches, its realization at the technology level needs further justifications and raises a number of questions about its feasibility. We answer these questions. By using three dimensional technology computer-aided design (TCAD) simulations, we show that four-terminal switches can be directly implemented with the CMOS technology. Then, by fitting the TCAD simulation data to the standard CMOS current-voltage equations, we develop a Spice model of a four-terminal switch. Performance OptimizationWe study crossbar arrays including the memristive ones. We propose a defect-tolerant logic synthesis algorithms by considering area, delay, and power costs of the arrays. Fault ToleranceWe examine reconfigurable crossbar arrays by considering randomly occurred stuck-open and stuck-closed crosspoint faults. In the presence of permanent faults, a fast and accurate heuristic algorithm is proposed that uses the techniques of index sorting, backtracking, and row matching. In the presence of transient faults, tolerance analysis is performed by formally and recursively determining tolerable fault positions. SynthesisWe study implementation of Boolean functions with nano-crossbar arrays where each crosspoint behaves as a diode, a FET, and a four-terminal switch. For these three types, we give array size formulations for a given Boolean function. Additionally, we focus on four-terminal switch based implementations and propose an algorithm that implements Boolean functions with optimal array sizes.
|
Stochastic and Bit Stream Computing | |||||||||||||||||||||||||||||
We propose a novel computing paradigm “Bit Stream Computing (BSC)” that does not necessarily employ randomly or Binomially distributed bit streams as stochastic computing does. Any type of streams can be used either stochastic or deterministic. The proposed paradigm benefits from the area advantage of stochastic logic and the accuracy advantage of conventional binary logic. We implement accurate arithmetic multiplier and adder circuits, classified as asynchronous or synchronous. We believe that this study opens up new horizons for computing that enables us to implement much smaller yet accurate arithmetic circuits compared to the conventional binary and stochastic ones. ![]()
|
Approximate Circuit and System Design | ||||||||||||||||||||||||||||||||||||||||
This work provides power/area efficiency of circuit-level design with accuracy supervision of system-level design. First, approximate computational units, mostly adders and multipliers, are synthesized in circuit level. Then, in system level, the appropriate approximate computational units are selected to minimize the total computation cost, yet maintaining the ultimate performance. The method investigates the overall system from the highest level down to the arithmetic units to determine the sufficient output quality at each block. ![]()
|
Reversible Computing | |||||||||||||||||||||||||||||||||||||
Unlike conventional CMOS circuits, reversible circuits do not have latent faults, so faults occurring in internal circuit nodes always result in an error at the output. This is a unique feature for online or concurrent fault tolerance. Motivated by this, we implement error tolerant CMOS circuit blocks by exploiting reversible computing. We first synthesize reversible circuits with reversible gates; then we make them fault-tolerant; and finally we perform conversion from reversible gates to CMOS gates.
![]() Perfect Online Error DetectionIn order to achieve a CMOS circuit having 100% online or concurrent error detection, we exploit reversible computing by proposing a new, fault preservative, and reversible gate library. We ensure that the parity, even or odd, is preserved at all levels including the output level unless there is a faulty node. Online Error Detection and CorrectionWe develop two techniques to make a reversible circuit fault-tolerant by using multiple-control Toffoli gates. The first technique is based on single parity preserving, and offers error detection for odd number of errors at the output. The second technique is constructed on Hamming codes for error correction. We also claim that perfect error detection is possible with conservative reversible gates such as a Fredkin gate. As the next step, we utilize the proposed reversible circuits with conventional CMOS gates.
|
Reliability of Electronic Products | ||||||||||||||||||||||||||||||||||||||||
The rapid developments in electronics, especially in the last decade, have elevated the importance of electronics reliability. Conventionally used accelerated reliability tests have lost their significance; time consuming and expensive feature of these tests is against the demands of today's very rapid electronic product cycles. In this study, we propose less costly, yet accurate, reliability prediction techniques using field return data, new accelerated test methodologies, and physics of failure based simulations. We cooperate with one of the Europe’s largest household appliance companies Arçelik A.Ş.. ![]() Reliability Analysis and Prediction with Field DataWe propose an accurate reliability prediction model for high-volume electronic products throughout their warranty periods by using field return data. Our model is constructed on a Weibull-exponential hazard rate scheme by using the proposed change point detection method based on backward and forward data analysis. Our prediction model can make a 36-month (full warranty) reliability prediction of an electronic board with using its field data as short as 3 months. Degradation Processes in VaristorsWe investigate different degradation mechanisms of ZnO varistors. We propose a model showing how the varistor voltage Vv changes by time for different stress levels. For this purpose, accelerated degradation tests are applied for different AC current levels; then voltage values are measured. Different from the common practice in the literature that considers a degradation with only decreasing Vv values, we demonstrate either an increasing or a decreasing trend in the Vv parameter.
|
Analog Circuit Design | |||||||||||||||
Positive FeedbackThe conventional wisdom is that analog circuits should not include positive feedback loops. As controversial as it seems, we have successfully used positive feedback for impedance improvement in a current amplifier. With adding few transistors we have achieved very low input resistance values. Additionally, we have proposed a new fully-differential current amplifier and tested it in a filter application.
|
Discrete Mathematics | |||||||||||||
Self Duality ProblemThe problem of testing whether a monotone Boolean function in irredundant disjuntive normal form (IDNF) is self-dual is one of few problems in circuit/time complexity whose precise tractability status is unknown. We have focused on this famous problem. We have shown that monotone self-dual Boolean functions in IDNF do not have more variables than disjuncts. We have proposed an algorithm to test whether a monotone Boolean function in IDNF with n variables and n disjuncts is self-dual. The algorithm runs in O(n^3) time.
|