{"title":"Balanced Modular Addition for the Moduli Set $ \\{2^{q},2^{q}\\mp 1,2^{2q}+1\\}${2q,2q∓1,22q+1} via Moduli-($ 2^{q}\\mp \\sqrt{-1}$2q∓-1) Adders","authors":"Ghassem Jaberipur;Elham Rahman;Jeong-A Lee","doi":"10.1109/TC.2024.3461235","DOIUrl":null,"url":null,"abstract":"Moduli-set \n<inline-formula><tex-math>$ \\mathbf{\\tau}=\\{2^{\\boldsymbol{q}},2^{\\boldsymbol{q}}\\pm 1\\}$</tex-math></inline-formula>\n is often the base of choice for realization of digital computations via residue number systems. The optimum arithmetic performance in parallel residue channels, is generally achieved via equal bit-width residues (e.g., \n<inline-formula><tex-math>$ \\boldsymbol{q}~ \\mathbf{i}\\mathbf{n}~ \\mathbf{\\tau}$</tex-math></inline-formula>\n) that usually leads to equal computation speed within all the residue channels. However, the commonly difficult and costly task of reverse conversion (RC) is often eased in the existence of conjugate moduli. For example, \n<inline-formula><tex-math>$ 2^{\\boldsymbol{q}}\\mp 1\\in \\mathbf{\\tau}$</tex-math></inline-formula>\n, lead to the efficient modulo-(\n<inline-formula><tex-math>$ 2^{2\\boldsymbol{q}}-1$</tex-math></inline-formula>\n) addition, as the bulk of \n<inline-formula><tex-math>$ \\mathbf{\\tau}$</tex-math></inline-formula>\n-RC, via the New-CRT reverse conversion method. Nevertheless, for additional dynamic range, \n<inline-formula><tex-math>$ \\mathbf{\\tau}$</tex-math></inline-formula>\n is augmented with other moduli. In particular, \n<inline-formula><tex-math>$ \\mathbf{\\phi}=\\mathbf{\\tau}\\cup \\{2^{2\\boldsymbol{q}}+1\\}$</tex-math></inline-formula>\n, leads to efficient RC, where the added modulo is conjugate with the product \n<inline-formula><tex-math>$ 2^{2\\boldsymbol{q}}-1$</tex-math></inline-formula>\n of \n<inline-formula><tex-math>$ 2^{\\boldsymbol{q}}\\mp 1\\in \\mathbf{\\tau}$</tex-math></inline-formula>\n. Therefore, the final step of \n<inline-formula><tex-math>$ \\mathbf{\\phi}$</tex-math></inline-formula>\n-RC would be fast and low cost/power modulo-(\n<inline-formula><tex-math>$ 2^{4\\boldsymbol{q}}-1$</tex-math></inline-formula>\n) addition. However, the \n<inline-formula><tex-math>$ 2\\boldsymbol{q}$</tex-math></inline-formula>\n-bit channel-width jeopardizes the existing delay-balance in \n<inline-formula><tex-math>$ \\mathbf{\\tau}$</tex-math></inline-formula>\n. As a remedial solution, given that \n<inline-formula><tex-math>$ 2^{2\\boldsymbol{q}}+1=\\left(2^{\\boldsymbol{q}}-\\boldsymbol{j}\\right)\\left(2^{\\boldsymbol{q}}+\\boldsymbol{j}\\right)$</tex-math></inline-formula>\n, with \n<inline-formula><tex-math>$ \\boldsymbol{j}=\\sqrt{-1}$</tex-math></inline-formula>\n, we design and implement modulo-(\n<inline-formula><tex-math>$ 2^{2\\boldsymbol{q}}+1$</tex-math></inline-formula>\n) adders via two parallel \n<inline-formula><tex-math>$ \\boldsymbol{q}$</tex-math></inline-formula>\n-bit moduli-(\n<inline-formula><tex-math>$ 2^{\\boldsymbol{q}}\\mp \\boldsymbol{j}$</tex-math></inline-formula>\n) adders. The analytical and synthesis based evaluations of the proposed modulo-(\n<inline-formula><tex-math>$ 2^{\\boldsymbol{q}}\\mp \\boldsymbol{j}$</tex-math></inline-formula>\n) adders show that the delay-balance of \n<inline-formula><tex-math>$ \\mathbf{\\tau}$</tex-math></inline-formula>\n is preserved with no cost overhead vs. \n<inline-formula><tex-math>$ \\mathbf{\\phi}$</tex-math></inline-formula>\n. In particular, the binary-to-complex and complex-to-binary convertors are merely cost-free and immediate.","PeriodicalId":13087,"journal":{"name":"IEEE Transactions on Computers","volume":"74 1","pages":"316-324"},"PeriodicalIF":3.6000,"publicationDate":"2024-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Computers","FirstCategoryId":"94","ListUrlMain":"https://ieeexplore.ieee.org/document/10680467/","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, HARDWARE & ARCHITECTURE","Score":null,"Total":0}
引用次数: 0
Abstract
Moduli-set
$ \mathbf{\tau}=\{2^{\boldsymbol{q}},2^{\boldsymbol{q}}\pm 1\}$
is often the base of choice for realization of digital computations via residue number systems. The optimum arithmetic performance in parallel residue channels, is generally achieved via equal bit-width residues (e.g.,
$ \boldsymbol{q}~ \mathbf{i}\mathbf{n}~ \mathbf{\tau}$
) that usually leads to equal computation speed within all the residue channels. However, the commonly difficult and costly task of reverse conversion (RC) is often eased in the existence of conjugate moduli. For example,
$ 2^{\boldsymbol{q}}\mp 1\in \mathbf{\tau}$
, lead to the efficient modulo-(
$ 2^{2\boldsymbol{q}}-1$
) addition, as the bulk of
$ \mathbf{\tau}$
-RC, via the New-CRT reverse conversion method. Nevertheless, for additional dynamic range,
$ \mathbf{\tau}$
is augmented with other moduli. In particular,
$ \mathbf{\phi}=\mathbf{\tau}\cup \{2^{2\boldsymbol{q}}+1\}$
, leads to efficient RC, where the added modulo is conjugate with the product
$ 2^{2\boldsymbol{q}}-1$
of
$ 2^{\boldsymbol{q}}\mp 1\in \mathbf{\tau}$
. Therefore, the final step of
$ \mathbf{\phi}$
-RC would be fast and low cost/power modulo-(
$ 2^{4\boldsymbol{q}}-1$
) addition. However, the
$ 2\boldsymbol{q}$
-bit channel-width jeopardizes the existing delay-balance in
$ \mathbf{\tau}$
. As a remedial solution, given that
$ 2^{2\boldsymbol{q}}+1=\left(2^{\boldsymbol{q}}-\boldsymbol{j}\right)\left(2^{\boldsymbol{q}}+\boldsymbol{j}\right)$
, with
$ \boldsymbol{j}=\sqrt{-1}$
, we design and implement modulo-(
$ 2^{2\boldsymbol{q}}+1$
) adders via two parallel
$ \boldsymbol{q}$
-bit moduli-(
$ 2^{\boldsymbol{q}}\mp \boldsymbol{j}$
) adders. The analytical and synthesis based evaluations of the proposed modulo-(
$ 2^{\boldsymbol{q}}\mp \boldsymbol{j}$
) adders show that the delay-balance of
$ \mathbf{\tau}$
is preserved with no cost overhead vs.
$ \mathbf{\phi}$
. In particular, the binary-to-complex and complex-to-binary convertors are merely cost-free and immediate.
期刊介绍:
The IEEE Transactions on Computers is a monthly publication with a wide distribution to researchers, developers, technical managers, and educators in the computer field. It publishes papers on research in areas of current interest to the readers. These areas include, but are not limited to, the following: a) computer organizations and architectures; b) operating systems, software systems, and communication protocols; c) real-time systems and embedded systems; d) digital devices, computer components, and interconnection networks; e) specification, design, prototyping, and testing methods and tools; f) performance, fault tolerance, reliability, security, and testability; g) case studies and experimental and theoretical evaluations; and h) new and important applications and trends.