Signal and Data Processing
پردازش علائم و دادهها
JSDP
Engineering & Technology
http://jsdp.rcisp.ac.ir
1
admin
2538-4201
2538-421X
10.52547/jsdp
1
8888
fa
jalali
1397
3
1
gregorian
2018
6
1
15
1
online
1
fulltext
fa
ضربکننده و ضربجمعکننده پیمانه 2n+1 برای پردازنده سیگنال دیجیتال
Modulo 2n+1 Multiply and MAC Units Specified for DSPs
مقالات پردازش تصویر
Paper
كاربردي
Applicable
<p style="text-align: justify;"><strong><span style="font-family:b nazanin;">یکی از مهم­ترین عملیات پردازنده­های سیگنال دیجیتال فیلترکردن است که معادل عملیات جمع و ضرب متوالی است. ادغام دو واحد ضرب­کننده و جمع­کننده موجود در ساختار این پردازنده­­ها منجر به ایجاد یک واحد جدید به نام ضربجمع­کننده می­شود. جهت بهبود کارایی واحد ضربجمع­کننده، از سامانههای اعداد مانده­ای می­توان بهره گرفت. این سامانه بهدلیل انجام عملیات بهصورت موازی روی پیمانه­ها و محدودکردن انتشار رقم نقلی به داخل هر پیمانه، سرعت و توان مصرفی مدارهای محاسباتی مانند ضرب­کننده و ضربجمع­کننده را بهبود می­بخشند. از میان مجموعه پیمانه </span></strong><strong><span dir="LTR"><span style="font-size:8.0pt;">{2<em><sup>n</sup></em>+1,2<em><sup>n</sup></em>,2<em><sup>n</sup></em>-1}</span></span></strong><strong><span style="font-family:b nazanin;">، مدارهای پیمانه </span></strong><strong><span dir="LTR"><span style="font-size:8.0pt;">2<em><sup>n</sup></em>+1</span></span></strong><strong><span style="font-family:b nazanin;"> بهدلیل نیاز به مسیر داده </span></strong><span style="font-family:b nazanin;">(</span><strong><em><span dir="LTR"><span style="font-size:8.0pt;">n</span></span></em></strong><strong><span dir="LTR"><span style="font-size:8.0pt;">+1</span></span></strong><span style="font-family:b nazanin;">)</span><strong><span style="font-family:b nazanin;"> بیتی، مسیر بحرانی خواهند بود. در این مقاله، ابتدا یک واحد ضربجمع­کننده برای پیمانه </span></strong><strong><span dir="LTR"><span style="font-size:8.0pt;">2<em><sup>n</sup></em>+1</span></span></strong><strong><span style="font-family:b nazanin;"> ارائه شده و سپس، برای بهبود بیشتر کارایی از روش خط لوله و چندولتاژی استفاده می­شود. نتایج شبیه­سازی بیانگر بهبود تأخیر، توان مصرفی و </span></strong><strong><span dir="LTR"><span style="font-size:8.0pt;">PDP</span></span></strong><strong><span style="font-family:b nazanin;"> مدارهای پیشنهادی بدون کاهش کارایی نسبت به مدارهای موجود است.</span></strong><strong><span style="font-family:b nazanin;"></span></strong><br>
</p>
<p style="text-align: justify;"><strong>Nowadays, digital signal processors (DSPs) are appropriate choices for real-time image and video processing in embedded multimedia applications not only due to their superior signal processing performance, but also of the high levels of integration and very low-power consumption. Filtering which consists of multiple addition and multiplication operations, is one of the most fundamental operations of DSPs. Therefore, there is a need for an additional unit just after the multiplication unit in DSPs. </strong><strong>By combining multiply and add units, new structure named MAC (Multiply and ACcumulate) unit is provided. </strong><strong>Residue Number System (RNS) can improve speed and power consumption of arithmetic circuits as it offers </strong><strong>parallel arithmetic operations on each moduli and confines carry propagation to each moduli. In order to improve the efficiency of the MAC unit, RNS could be utilized</strong><strong>.</strong><br>
<strong>RNS divides large numbers to smaller numbers, called residues, according to a moduli set and enables performing arithmetic operations on each moduli independently. The moduli set {2<em><sup>n</sup></em>-1,2<em><sup>n</sup></em>,2<em><sup>n</sup></em>+1} is the most famous among others because of its simple and efficient implementation. Among this moduli set, modulo 2<em><sup>n</sup></em>+1 circuits are the critical path due to (<em>n</em>+1)-bit wide data path</strong> <strong>despite other two modules which all have <em>n</em>-bit wide operands.</strong> <strong>In order to overcome the problem of (<em>n</em>+1) bits operands, three representations has been suggested: diminished-1, Signed-LSB and Stored-Unibit.</strong> <strong>Although different multipliers have been proposed for diminished-1 representation, no multiplication structure has been proposed for the last two ones. </strong><strong>Modulo 2<em><sup>n</sup></em>+1 multipliers are divided into 3 categories depending on their inputs and outputs types:</strong> <strong>both operands use standard (weighted) representation; one input uses standard representation, while the other one utilizes diminished-1 representation; both inputs use diminished-1 representation. Although several multiply and add units have been proposed for the first 2 categories, no MAC unit is proposed for the multipliers of a third category which outperform multipliers of other categories. </strong><strong>In this article at first, one modulo 2<em><sup>n</sup></em>+1 MAC unit for the third category is proposed and then for further improvement, pipeline and multi-voltage techniques are utilized. Pipeline structure enables a trade-off between power consumption and delay. Whenever high-performance with least delay is desirable, nominal supply voltage can be chosen (high performance mode) otherwise by reducing supply voltage to the amount at which pipeline circuit and normal circuit without pipeline would have the same performance, power consumption decreases significantly (low power mode).</strong><br>
<strong>Simulations are performed in two phases. At first phase, proposed MAC unit without pipeline structure is described via VHDL code and synthesized with synopsys design vision tool. Results indicate that the proposed structure outperforms PDP (Power-Delay-Product) up to 39% compared to the state of the art MAC units. At second phase, CMOS transistor level implementation in two modes i.e. low power and high performance modes with Cadence Design Systems tool is provided. Simulation results indicate that at low power condition, proposed pipeline MAC unit yields to 71% power savings compared to existing circuits without declining efficiency. Furthermore, at high performance condition, however power consumption has increased, reducing delay up to 54% yields to 39% PDP savings for proposed pipeline MAC unit.</strong><br>
</p>
پردازنده سیگنال دیجیتال, ضربجمعکننده, سامانه اعداد ماندهای, نمایش diminished-1, ضربکننده
Digital signal processor, MAC, Residue number system, diminished-1 representation, multiplier
127
138
http://jsdp.rcisp.ac.ir/browse.php?a_code=A-10-1023-1&slc_lang=fa&sid=1
Negar
Akbarzadeh
نگار
اکبرزاده
ne.akbarzadeh@mail.sbu.ac.ir
10031947532846005979
10031947532846005979
No
Sharif University of Technology
دانشگاه صنعتی شریف
Somayeh
Timarchi
سمیه
تیمارچی
s_timarchi@sbu.ac.ir
10031947532846005980
10031947532846005980
Yes
Shahid Beheshti University
دانشگاه شهید بهشتی