Implemetasi Komputasi Akar Kuadrat Resolusi Tinggi pada Field Programmable Gate Array (FPGA)

Penulis

  • Muhammad Irfan Universitas Islam Indonesia, Daerah Istimewa Yogyakarta
  • Hendra Setiawan Universitas Islam Indonesia, Daerah Istimewa Yogyakarta

DOI:

https://doi.org/10.25126/jtiik.2022976756

Abstrak

Komputasi akar kuadrat diperlukan pada beberapa proses pengendalian, diantaranya untuk Direct Torque Control (DTC) pada sistem penggerak motor yang membutuhkan proses perhitungan yang sangat cepat. Field Programmable Gate Array (FPGA) merupakan salah satu perangkat yang dapat digunakan untuk implementasi komputasi yang memerlukan kecepatan dan presisi tinggi. Penerapan komputasi akar kuadrat pada FPGA menggunakan metode digit by digit non-restoring dengan beberapa modifikasi agar memiliki hasil perhitungan dengan nilai error yang kecil. Sistem tersebut diimplementasikan menggunakan 32-bit input dan 16-bit output. Proses perhitungan melibatkan Finite State machine (FSM) untuk menghemat resource yang diperlukan. Proses verifikasi sistem dilakukan dalam dua tahap, yaitu verifikasi fungsional dengan aplikasi ModelSim-Altera dan verifikasi hardware menggunakan modul FPGA Cylcone IV EP4CE6E228N. Hasil verifikasi menunjukkan bahwa hasil perhitungan akar kuadrat memiliki resolusi sampai dengan 0,0039. Selain itu, sistem ini membutuhkan 157 Logic Elements dan 120 register dengan kecepatan clock tertinggi yang dicapainya adalah 205 MHz untuk input 32 bit

 

Abstract

Square root computing is required in several control processes, such as for Direct Torque Control (DTC) on motor drive systems that require a very fast calculation process. Field Programmable Gate Array (FPGA) is one of the devices that recommended for high speed and precision computation. The implementation of the square root on the FPGA uses the digit-by-digit non-restoring method with some modifications to get a high precision of computation result. The system is implemented using 32-bit input and 16-bit output. The calculation process involves a Finite State machine (FSM) to minimize computation resources. The system verification process is carried out in two stages, i.e. functional verification using the ModelSim-Altera and hardware verification using the FPGA Cylcone IV EP4CE6E228N. The verification shows that the result of the square root calculation has a resolution of up to 0.0039. In addition, the system requires 157 Logic Elements and 120 registers with the highest clock speed can achieves 205 MHz for 32-bit input.



Downloads

Download data is not yet available.

Referensi

ANANTHALAKSHMI, A.V. & SUDHA, G.F., 2017. Design of a reversible floating-point square root using modified non-restoring algorithm. Microprocessors and Microsystems, 50, pp.39-53.

CHEN, Y.L., ZHAN, C.Z., JHENG, T.J. & WU, A.Y., 2012. Reconfigurable adaptive singular value decomposition engine design for high-throughput MIMO-OFDM systems. IEEE transactions on very large scale integration (VLSI) systems, 21(4), pp.747-760.

FRANCES-VILLORA, J.V., ROSADO-MUÑOZ, A., MARTÍNEZ-VILLENA, J. M., BATALLER-MOMPEAN, M., GUERRERO, J.F. and WEGRZYN, M., 2016. Hardware implementation of real-time Extreme Learning Machine in FPGA: analysis of precision, resource occupation and performance. Computers & Electrical Engineering, 51, pp.139-156.

JIDIN, A.Z., MOHAMAD, S.H., AHMAD, S., YAKUB, M.F., AZLAN, N.A.N. & JIDIN, A., 2016, November. Optimizing the flux and torque estimator of DTC in FPGA by using low-area square root calculator. In 2016 IEEE International Conference on Power and Energy (PECon) (pp. 517-521). IEEE.

MAHAPATRA, C., MAHBOOB, S., LEUNG, V.C. & STOURAITIS, T., 2012, December. Fast inverse square root-based matrix inverse for MIMO-LTE systems. In 2012 International Conference on Control Engineering and Communication Technology (pp. 321-324). IEEE.

MARKOVIC, D., NIKOLIC, B. & BRODERSEN, R.W., 2007. Power and area minimization for multidimensional signal processing. IEEE Journal of Solid-State Circuits, 42(4), pp.922-934.

REYES, F., CID, J., LIMON, M.A. & CERVANTES, M., 2013. Square root-type control for robot manipulators. International Journal of Advanced Robotic Systems, 10(1), p.39.

SAJID, I., AHMED, M.M. & ZIAVRAS, S.G., 2012. Novel pipelined architecture for efficient evaluation of the square root using a modified non-restoring algorithm. Journal of Signal Processing Systems, 67(2), pp.157-166.

SALMELA, P., HAPPONEN, A., JARVINEN, T., BURIAN, A. & TAKALA, J., 2006, June. DSP implementation of Cholesky decomposition. In Joint IST Workshop on Mobile Future, 2006 and the Symposium on Trends in Communications. SympoTIC'06. (pp. 6-9). IEEE.

SALMELA, P., BURIAN, A., JÄRVINEN, T., HAPPONEN, A. & TAKALA, J.H., 2011. Low-complexity inverse square root approximation for baseband matrix operations. International Scholarly Research Notices, 2011.

SAMAVI, S., SADRABADI, A. & KAKLAR, R.Z., 2003. Improving the Array Structure of a Non-Restoring Square Root Circuit. International Journal Of Engineering Science (English), 14(1), pp.1-15.

SAMAVI, S., SADRABADI, A. & FANIAN, A., 2008. Modular array structure for non-restoring square root circuit. Journal of Systems Architecture, 54(10), pp.957-966.

SUTIKNO, T., 2010. An optimized square root algorithm for implementation in FPGA hardware. TELKOMNIKA (Telecommunication Computing Electronics and Control), 8(1), pp.1-8.

SUTIKNO, T., IDRIS, N.R.N., JIDIN, A.Z. & DAUD, M.Z., 2011a, April. FPGA based high precision torque and flux estimator of direct torque control drives. In 2011 IEEE Applied Power Electronics Colloquium (IAPEC) (pp. 122-127). IEEE.

SUTIKNO, T., 2011b. An efficient implementation of the non-restoring square root algorithm in gate level. International journal of computer theory and engineering, 3(1), p.46.

SUTIKNO, T., IDRIS, N.R.N., JIDIN, A. & CIRSTEA, M.N., 2012. An improved FPGA implementation of direct torque control for induction machines. IEEE Transactions on Industrial Informatics, 9(3), pp.1280-1290.

XUAN-MUNG, N. & HONG, S.K., 2019. Improved altitude control algorithm for quadcopter unmanned aerial vehicles. Applied sciences, 9(10), p.2122.

Diterbitkan

29-12-2022

Cara Mengutip

Implemetasi Komputasi Akar Kuadrat Resolusi Tinggi pada Field Programmable Gate Array (FPGA). (2022). Jurnal Teknologi Informasi Dan Ilmu Komputer, 9(7), 1617-1622. https://doi.org/10.25126/jtiik.2022976756