SlideShare uma empresa Scribd logo
1 de 6
CONTACT: PRAVEEN KUMAR. L (,+91 – 9791938249)
MAIL ID: sunsid1989@gmail.com, praveen@nexgenproject.com
Web: www.nexgenproject.com, www.finalyear-ieeeprojects.com
Fixed-Point Computing Element Design for
Transcendental Functions and Primary Operations in
Speech Processing
Abstract:
This brief presents a fixed-point architecture based on a reconfigurable scheme for integrating
several commonly used mathematical operations of speech signal processing. The proposed
design can perform two transcendental mathematical operations called logarithm and powering,
and three commonly used computations with similar operations named polynomial calculation,
filtering, and windowing. By analyzing the adopted algorithms of the above five operations, a
simplified computing unit is designed. This unit can combine six types of operations by
reconfiguring the data paths, and the same multiply– add architecture can be reused for reducing
the redundant usage of logic gates. The experimental results reveal that the proposed design can
work at a 200-MHz clock rate, and its gate count only has 11.9k. Compared with the results of
the floating-point function, the median errors of the proposed design for computing the powering
and logarithmic functions are 0.57% and 0.11%, respectively. Such results indicate that this
simple architecture can be effectively used in most speech processing applications. The proposed
architecture of this paper analysis the logic size, area and power consumption using Xilinx 14.2.
Enhancement of the project:
Existing System:
With respect to the related studies, Ramamoorthy et al. first noticed the suitable priorities of the
Newton–Raphson method (NRM) for computing the square-root operations. In this brief, a
finding was discovered that the division in the recursion of the NRM could be removed, when
the target function of the NRM changed to the inverse square root. Seth and Gan also presented a
hardware design based on the NRM. In this design, several lookup tables (LUTs) and polynomial
expansions (PEs) are used to approximate the value of the inverse square root, for reducing the
number of multiplications and additions. However, the memory requirement for the LUTs and
the PEs was still a drawback. Auger et al. developed a multiplier free algorithm based on a
dichotomous coordinate descent (DCD) technique for the solutions of division, square root, and
CONTACT: PRAVEEN KUMAR. L (,+91 – 9791938249)
MAIL ID: sunsid1989@gmail.com, praveen@nexgenproject.com
Web: www.nexgenproject.com, www.finalyear-ieeeprojects.com
logarithmic operations. The DCD-based algorithm included only additions, shift operations, and
logic conditions. Such an algorithm was very proper to design a relevant low-gate-count
architecture. Nam et al. developed a 3-D graphics rendering engine for a handheld system. The
design, respectively, used two LUTs for computing the reciprocal square root and the power
function. It might hugely increase the chip area. To solve this problem, Kim et al. proposed an
arithmetic architecture that can compute the most fixed-point transcendental functions using the
equivalent logarithmic functions. To reduce the usage of memory, the fractional part of the
logarithmic functions was approximated by an LUT with several adders and shift operations.
This brief provided a fast and area-efficient solution for various transcendental functions for a
fixed-point 3-D graphic application. However, the designed LUTs limited the range of the output
value, so it was hard to be used for other applications
Disadvantages:
 Gate count is high
 Power consumption
Proposed System:
Computation Analysis for Designing FSM
In the proposed design, the basic operations of the abovementioned algorithms are first analyzed.
We note that the required basic operations in the above algorithms are very similar. That is, the
designed hardware can use the same architecture to compute these operations, so the required
hardware area can be reduced. Table I lists the analyzed operations for calculating the operation
that is listed. The first and second columns list the function type and its included computation,
respectively. The rest of the columns show the necessary operations for these types of
computation.
TABLE I NECESSARY BASIC OPERATIONS FOR THE COMPUTATION
CONTACT: PRAVEEN KUMAR. L (,+91 – 9791938249)
MAIL ID: sunsid1989@gmail.com, praveen@nexgenproject.com
Web: www.nexgenproject.com, www.finalyear-ieeeprojects.com
Fig. 1 totally consists of seven states, in which six states are used to compute different kinds of
computations, as listed in Table I. These states include:
1) idle (IDLE);
2) BLA phase one (BLA P1);
3) BLA phase two (BLA P2);
4) the NRM for computing the power function (NRM);
5) EBS;
6) polynomial computation/ convolution (POL/CON);
7) windowing (WIN).
Notably, each state implies several behaviors, and the different behaviors are decided by the
values of the corresponding counter and state register.
Fig. 1. Example of state diagram for computing (a) logarithmic function (Mode = 0) and (b) power function (Mode
= 1). Dashed lines: controller will not go in these states with the different mode.
Fig. 2 shows the architecture of the proposed system, including a 4-to-2 multiplexer, a 16-word
dual-port SRAM, a parallelin-serial-out (PISO) register, a mathematical computing unit, and a
CONTACT: PRAVEEN KUMAR. L (,+91 – 9791938249)
MAIL ID: sunsid1989@gmail.com, praveen@nexgenproject.com
Web: www.nexgenproject.com, www.finalyear-ieeeprojects.com
corresponding controller. As shown in Fig. 3, the input Mode determines which operation is
performed by the proposed system when the Act signal rises up. Then, the input Order means the
order of polynomial, a filter, or a window function. The dual-port SRAM has 16-word space and
32-bit word length, which can temporally store the coefficients. In addition, the PISO register
determines the behavior for the calculation of the EBS state. Finally, the multiplexer array can
decide which coefficients need to be stored in the SRAM, or to be computed.
Fig. 2. Architecture of the proposed system.
Fig. 3 represents the architecture of the proposed mathematical computing unit. This architecture
includes only a multiplier, an adder, a barrel shifter, a comparator, two registers, and seven
multiplexers. In this design, the same arithmetic logics can be reused for different kinds of
computations, as listed in Table IV. As shown in Fig. 3, the left multiplexer selects the
coefficients for different kinds of computations. The middle multiplier, adder, and shifter can
reorganize the computing flow to achieve distinct functionalities.
CONTACT: PRAVEEN KUMAR. L (,+91 – 9791938249)
MAIL ID: sunsid1989@gmail.com, praveen@nexgenproject.com
Web: www.nexgenproject.com, www.finalyear-ieeeprojects.com
Fig. 3. Architecture of a mathematical computing unit.
1) The following content briefly describes how the proposed hardware works with these six
states. 1) IDLE: This state keeps waiting until the signal Act rises up, and then, the input
Mode decides the next states for computing the corresponding function.
2) BLA P1: This state responses for computing BLA P1. The signal Sig_C is sent from the
comparator in the mathematical computing unit, and is used to conform whether the next
state is BLA P1 or BLA P2.
3) BLA P2: This state is used to compute the second phase of the BLA. The computation of
the second phase will be kept until the Count value reaches M. Afterward, the next state
is decided by the value that is saved in the stage register. If the value is one, the system
will go back to BLA P1 to calculate the value of log2(B). Otherwise, the next state will be
set to the NRM for computing (log2(B))−1.
4) NRM: This state executes the iterations of Newton’s method for computing the power
function. Cnt records the computation cycle. The value of xk
2M will be first computed by
the EBS when PCount is zero.
5) EBS: This state is to compute εI , εF , and xk
2M . In each cycle, the PISO shifts a bit to the
controller for determining the behavior of the EBS.
6) POL and WIN: These two states response for the computation of the polynomial and the
convolution, respectively.
Advantages:
 Improve the reusable efficiency.
 Gate count is reduced
CONTACT: PRAVEEN KUMAR. L (,+91 – 9791938249)
MAIL ID: sunsid1989@gmail.com, praveen@nexgenproject.com
Web: www.nexgenproject.com, www.finalyear-ieeeprojects.com
 Power reduced
Software implementation:
 Modelsim
 Xilinx ISE

Mais conteúdo relacionado

Destaque (7)

2 matriz 8º e, f
2 matriz 8º e, f2 matriz 8º e, f
2 matriz 8º e, f
 
NAU-transcript-3
NAU-transcript-3NAU-transcript-3
NAU-transcript-3
 
M2 Conflict
M2 ConflictM2 Conflict
M2 Conflict
 
Matriz 8º e, f 1º teste 16 17
Matriz  8º  e, f 1º teste 16 17Matriz  8º  e, f 1º teste 16 17
Matriz 8º e, f 1º teste 16 17
 
A crise do século xiv parte 1
A crise do século xiv parte 1A crise do século xiv parte 1
A crise do século xiv parte 1
 
Revolução francesa parte 3
Revolução francesa parte 3Revolução francesa parte 3
Revolução francesa parte 3
 
Ficha 1 cultura da catedral- sociedade e cruzadas
Ficha 1  cultura da catedral- sociedade e cruzadasFicha 1  cultura da catedral- sociedade e cruzadas
Ficha 1 cultura da catedral- sociedade e cruzadas
 

Mais de Nexgen Technology

Mais de Nexgen Technology (20)

MECHANICAL PROJECTS IN PONDICHERRY, 2020-21 MECHANICAL PROJECTS IN CHE...
    MECHANICAL PROJECTS IN PONDICHERRY,   2020-21  MECHANICAL PROJECTS IN CHE...    MECHANICAL PROJECTS IN PONDICHERRY,   2020-21  MECHANICAL PROJECTS IN CHE...
MECHANICAL PROJECTS IN PONDICHERRY, 2020-21 MECHANICAL PROJECTS IN CHE...
 
MECHANICAL PROJECTS IN PONDICHERRY, 2020-21 MECHANICAL PROJECTS IN CHE...
    MECHANICAL PROJECTS IN PONDICHERRY,   2020-21  MECHANICAL PROJECTS IN CHE...    MECHANICAL PROJECTS IN PONDICHERRY,   2020-21  MECHANICAL PROJECTS IN CHE...
MECHANICAL PROJECTS IN PONDICHERRY, 2020-21 MECHANICAL PROJECTS IN CHE...
 
MECHANICAL PROJECTS IN PONDICHERRY, 2020-21 MECHANICAL PROJECTS IN CHE...
    MECHANICAL PROJECTS IN PONDICHERRY,   2020-21  MECHANICAL PROJECTS IN CHE...    MECHANICAL PROJECTS IN PONDICHERRY,   2020-21  MECHANICAL PROJECTS IN CHE...
MECHANICAL PROJECTS IN PONDICHERRY, 2020-21 MECHANICAL PROJECTS IN CHE...
 
MECHANICAL PROJECTS IN PONDICHERRY, 2020-21 MECHANICAL PROJECTS IN CHE...
    MECHANICAL PROJECTS IN PONDICHERRY,   2020-21  MECHANICAL PROJECTS IN CHE...    MECHANICAL PROJECTS IN PONDICHERRY,   2020-21  MECHANICAL PROJECTS IN CHE...
MECHANICAL PROJECTS IN PONDICHERRY, 2020-21 MECHANICAL PROJECTS IN CHE...
 
MECHANICAL PROJECTS IN PONDICHERRY, 2020-21 MECHANICAL PROJECTS IN CHE...
    MECHANICAL PROJECTS IN PONDICHERRY,   2020-21  MECHANICAL PROJECTS IN CHE...    MECHANICAL PROJECTS IN PONDICHERRY,   2020-21  MECHANICAL PROJECTS IN CHE...
MECHANICAL PROJECTS IN PONDICHERRY, 2020-21 MECHANICAL PROJECTS IN CHE...
 
MECHANICAL PROJECTS IN PONDICHERRY, 2020-21 MECHANICAL PROJECTS IN CHE...
    MECHANICAL PROJECTS IN PONDICHERRY,   2020-21  MECHANICAL PROJECTS IN CHE...    MECHANICAL PROJECTS IN PONDICHERRY,   2020-21  MECHANICAL PROJECTS IN CHE...
MECHANICAL PROJECTS IN PONDICHERRY, 2020-21 MECHANICAL PROJECTS IN CHE...
 
MECHANICAL PROJECTS IN PONDICHERRY, 2020-21 MECHANICAL PROJECTS IN CH...
     MECHANICAL PROJECTS IN PONDICHERRY,   2020-21  MECHANICAL PROJECTS IN CH...     MECHANICAL PROJECTS IN PONDICHERRY,   2020-21  MECHANICAL PROJECTS IN CH...
MECHANICAL PROJECTS IN PONDICHERRY, 2020-21 MECHANICAL PROJECTS IN CH...
 
MECHANICAL PROJECTS IN PONDICHERRY, 2020-21 MECHANICAL PROJECTS IN CHENN...
  MECHANICAL PROJECTS IN PONDICHERRY,   2020-21  MECHANICAL PROJECTS IN CHENN...  MECHANICAL PROJECTS IN PONDICHERRY,   2020-21  MECHANICAL PROJECTS IN CHENN...
MECHANICAL PROJECTS IN PONDICHERRY, 2020-21 MECHANICAL PROJECTS IN CHENN...
 
MECHANICAL PROJECTS IN PONDICHERRY, 2020-21 MECHANICAL PROJECTS IN CHE...
    MECHANICAL PROJECTS IN PONDICHERRY,   2020-21  MECHANICAL PROJECTS IN CHE...    MECHANICAL PROJECTS IN PONDICHERRY,   2020-21  MECHANICAL PROJECTS IN CHE...
MECHANICAL PROJECTS IN PONDICHERRY, 2020-21 MECHANICAL PROJECTS IN CHE...
 
MECHANICAL PROJECTS IN PONDICHERRY, 2020-21 MECHANICAL PROJECTS IN CHE...
    MECHANICAL PROJECTS IN PONDICHERRY,   2020-21  MECHANICAL PROJECTS IN CHE...    MECHANICAL PROJECTS IN PONDICHERRY,   2020-21  MECHANICAL PROJECTS IN CHE...
MECHANICAL PROJECTS IN PONDICHERRY, 2020-21 MECHANICAL PROJECTS IN CHE...
 
MECHANICAL PROJECTS IN PONDICHERRY, 2020-21 MECHANICAL PROJECTS IN CHENNA...
 MECHANICAL PROJECTS IN PONDICHERRY,   2020-21  MECHANICAL PROJECTS IN CHENNA... MECHANICAL PROJECTS IN PONDICHERRY,   2020-21  MECHANICAL PROJECTS IN CHENNA...
MECHANICAL PROJECTS IN PONDICHERRY, 2020-21 MECHANICAL PROJECTS IN CHENNA...
 
Ieee 2020 21 vlsi projects in pondicherry,ieee vlsi projects in chennai
Ieee 2020 21 vlsi projects in pondicherry,ieee  vlsi projects  in chennaiIeee 2020 21 vlsi projects in pondicherry,ieee  vlsi projects  in chennai
Ieee 2020 21 vlsi projects in pondicherry,ieee vlsi projects in chennai
 
Ieee 2020 21 power electronics in pondicherry,Ieee 2020 21 power electronics
Ieee 2020 21 power electronics in pondicherry,Ieee 2020 21 power electronics Ieee 2020 21 power electronics in pondicherry,Ieee 2020 21 power electronics
Ieee 2020 21 power electronics in pondicherry,Ieee 2020 21 power electronics
 
Ieee 2020 -21 ns2 in pondicherry, Ieee 2020 -21 ns2 projects,best project cen...
Ieee 2020 -21 ns2 in pondicherry, Ieee 2020 -21 ns2 projects,best project cen...Ieee 2020 -21 ns2 in pondicherry, Ieee 2020 -21 ns2 projects,best project cen...
Ieee 2020 -21 ns2 in pondicherry, Ieee 2020 -21 ns2 projects,best project cen...
 
Ieee 2020 21 ns2 in pondicherry,best project center in pondicherry,final year...
Ieee 2020 21 ns2 in pondicherry,best project center in pondicherry,final year...Ieee 2020 21 ns2 in pondicherry,best project center in pondicherry,final year...
Ieee 2020 21 ns2 in pondicherry,best project center in pondicherry,final year...
 
Ieee 2020 21 java dotnet in pondicherry,final year projects in pondicherry,pr...
Ieee 2020 21 java dotnet in pondicherry,final year projects in pondicherry,pr...Ieee 2020 21 java dotnet in pondicherry,final year projects in pondicherry,pr...
Ieee 2020 21 java dotnet in pondicherry,final year projects in pondicherry,pr...
 
Ieee 2020 21 iot in pondicherry,final year projects in pondicherry,project ce...
Ieee 2020 21 iot in pondicherry,final year projects in pondicherry,project ce...Ieee 2020 21 iot in pondicherry,final year projects in pondicherry,project ce...
Ieee 2020 21 iot in pondicherry,final year projects in pondicherry,project ce...
 
Ieee 2020 21 blockchain in pondicherry,final year projects in pondicherry,bes...
Ieee 2020 21 blockchain in pondicherry,final year projects in pondicherry,bes...Ieee 2020 21 blockchain in pondicherry,final year projects in pondicherry,bes...
Ieee 2020 21 blockchain in pondicherry,final year projects in pondicherry,bes...
 
Ieee 2020 -21 bigdata in pondicherry,project center in pondicherry,best proje...
Ieee 2020 -21 bigdata in pondicherry,project center in pondicherry,best proje...Ieee 2020 -21 bigdata in pondicherry,project center in pondicherry,best proje...
Ieee 2020 -21 bigdata in pondicherry,project center in pondicherry,best proje...
 
Ieee 2020 21 embedded in pondicherry,final year projects in pondicherry,best...
Ieee 2020 21  embedded in pondicherry,final year projects in pondicherry,best...Ieee 2020 21  embedded in pondicherry,final year projects in pondicherry,best...
Ieee 2020 21 embedded in pondicherry,final year projects in pondicherry,best...
 

Último

Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
Christo Ananth
 

Último (20)

Call Girls in Nagpur Suman Call 7001035870 Meet With Nagpur Escorts
Call Girls in Nagpur Suman Call 7001035870 Meet With Nagpur EscortsCall Girls in Nagpur Suman Call 7001035870 Meet With Nagpur Escorts
Call Girls in Nagpur Suman Call 7001035870 Meet With Nagpur Escorts
 
KubeKraft presentation @CloudNativeHooghly
KubeKraft presentation @CloudNativeHooghlyKubeKraft presentation @CloudNativeHooghly
KubeKraft presentation @CloudNativeHooghly
 
Booking open Available Pune Call Girls Pargaon 6297143586 Call Hot Indian Gi...
Booking open Available Pune Call Girls Pargaon  6297143586 Call Hot Indian Gi...Booking open Available Pune Call Girls Pargaon  6297143586 Call Hot Indian Gi...
Booking open Available Pune Call Girls Pargaon 6297143586 Call Hot Indian Gi...
 
University management System project report..pdf
University management System project report..pdfUniversity management System project report..pdf
University management System project report..pdf
 
High Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur EscortsHigh Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Isha Call 7001035870 Meet With Nagpur Escorts
 
Roadmap to Membership of RICS - Pathways and Routes
Roadmap to Membership of RICS - Pathways and RoutesRoadmap to Membership of RICS - Pathways and Routes
Roadmap to Membership of RICS - Pathways and Routes
 
UNIT-II FMM-Flow Through Circular Conduits
UNIT-II FMM-Flow Through Circular ConduitsUNIT-II FMM-Flow Through Circular Conduits
UNIT-II FMM-Flow Through Circular Conduits
 
Glass Ceramics: Processing and Properties
Glass Ceramics: Processing and PropertiesGlass Ceramics: Processing and Properties
Glass Ceramics: Processing and Properties
 
(SHREYA) Chakan Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Esc...
(SHREYA) Chakan Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Esc...(SHREYA) Chakan Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Esc...
(SHREYA) Chakan Call Girls Just Call 7001035870 [ Cash on Delivery ] Pune Esc...
 
Booking open Available Pune Call Girls Koregaon Park 6297143586 Call Hot Ind...
Booking open Available Pune Call Girls Koregaon Park  6297143586 Call Hot Ind...Booking open Available Pune Call Girls Koregaon Park  6297143586 Call Hot Ind...
Booking open Available Pune Call Girls Koregaon Park 6297143586 Call Hot Ind...
 
CCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete Record
CCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete RecordCCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete Record
CCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete Record
 
Extrusion Processes and Their Limitations
Extrusion Processes and Their LimitationsExtrusion Processes and Their Limitations
Extrusion Processes and Their Limitations
 
MANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLS
MANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLSMANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLS
MANUFACTURING PROCESS-II UNIT-5 NC MACHINE TOOLS
 
(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANJALI) Dange Chowk Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
 
MANUFACTURING PROCESS-II UNIT-1 THEORY OF METAL CUTTING
MANUFACTURING PROCESS-II UNIT-1 THEORY OF METAL CUTTINGMANUFACTURING PROCESS-II UNIT-1 THEORY OF METAL CUTTING
MANUFACTURING PROCESS-II UNIT-1 THEORY OF METAL CUTTING
 
College Call Girls Nashik Nehal 7001305949 Independent Escort Service Nashik
College Call Girls Nashik Nehal 7001305949 Independent Escort Service NashikCollege Call Girls Nashik Nehal 7001305949 Independent Escort Service Nashik
College Call Girls Nashik Nehal 7001305949 Independent Escort Service Nashik
 
Introduction to Multiple Access Protocol.pptx
Introduction to Multiple Access Protocol.pptxIntroduction to Multiple Access Protocol.pptx
Introduction to Multiple Access Protocol.pptx
 
UNIT - IV - Air Compressors and its Performance
UNIT - IV - Air Compressors and its PerformanceUNIT - IV - Air Compressors and its Performance
UNIT - IV - Air Compressors and its Performance
 
Water Industry Process Automation & Control Monthly - April 2024
Water Industry Process Automation & Control Monthly - April 2024Water Industry Process Automation & Control Monthly - April 2024
Water Industry Process Automation & Control Monthly - April 2024
 
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
Call for Papers - Educational Administration: Theory and Practice, E-ISSN: 21...
 

Fixed point computing element design for transcendental functions and primary operations in speech processing

  • 1. CONTACT: PRAVEEN KUMAR. L (,+91 – 9791938249) MAIL ID: sunsid1989@gmail.com, praveen@nexgenproject.com Web: www.nexgenproject.com, www.finalyear-ieeeprojects.com Fixed-Point Computing Element Design for Transcendental Functions and Primary Operations in Speech Processing Abstract: This brief presents a fixed-point architecture based on a reconfigurable scheme for integrating several commonly used mathematical operations of speech signal processing. The proposed design can perform two transcendental mathematical operations called logarithm and powering, and three commonly used computations with similar operations named polynomial calculation, filtering, and windowing. By analyzing the adopted algorithms of the above five operations, a simplified computing unit is designed. This unit can combine six types of operations by reconfiguring the data paths, and the same multiply– add architecture can be reused for reducing the redundant usage of logic gates. The experimental results reveal that the proposed design can work at a 200-MHz clock rate, and its gate count only has 11.9k. Compared with the results of the floating-point function, the median errors of the proposed design for computing the powering and logarithmic functions are 0.57% and 0.11%, respectively. Such results indicate that this simple architecture can be effectively used in most speech processing applications. The proposed architecture of this paper analysis the logic size, area and power consumption using Xilinx 14.2. Enhancement of the project: Existing System: With respect to the related studies, Ramamoorthy et al. first noticed the suitable priorities of the Newton–Raphson method (NRM) for computing the square-root operations. In this brief, a finding was discovered that the division in the recursion of the NRM could be removed, when the target function of the NRM changed to the inverse square root. Seth and Gan also presented a hardware design based on the NRM. In this design, several lookup tables (LUTs) and polynomial expansions (PEs) are used to approximate the value of the inverse square root, for reducing the number of multiplications and additions. However, the memory requirement for the LUTs and the PEs was still a drawback. Auger et al. developed a multiplier free algorithm based on a dichotomous coordinate descent (DCD) technique for the solutions of division, square root, and
  • 2. CONTACT: PRAVEEN KUMAR. L (,+91 – 9791938249) MAIL ID: sunsid1989@gmail.com, praveen@nexgenproject.com Web: www.nexgenproject.com, www.finalyear-ieeeprojects.com logarithmic operations. The DCD-based algorithm included only additions, shift operations, and logic conditions. Such an algorithm was very proper to design a relevant low-gate-count architecture. Nam et al. developed a 3-D graphics rendering engine for a handheld system. The design, respectively, used two LUTs for computing the reciprocal square root and the power function. It might hugely increase the chip area. To solve this problem, Kim et al. proposed an arithmetic architecture that can compute the most fixed-point transcendental functions using the equivalent logarithmic functions. To reduce the usage of memory, the fractional part of the logarithmic functions was approximated by an LUT with several adders and shift operations. This brief provided a fast and area-efficient solution for various transcendental functions for a fixed-point 3-D graphic application. However, the designed LUTs limited the range of the output value, so it was hard to be used for other applications Disadvantages:  Gate count is high  Power consumption Proposed System: Computation Analysis for Designing FSM In the proposed design, the basic operations of the abovementioned algorithms are first analyzed. We note that the required basic operations in the above algorithms are very similar. That is, the designed hardware can use the same architecture to compute these operations, so the required hardware area can be reduced. Table I lists the analyzed operations for calculating the operation that is listed. The first and second columns list the function type and its included computation, respectively. The rest of the columns show the necessary operations for these types of computation. TABLE I NECESSARY BASIC OPERATIONS FOR THE COMPUTATION
  • 3. CONTACT: PRAVEEN KUMAR. L (,+91 – 9791938249) MAIL ID: sunsid1989@gmail.com, praveen@nexgenproject.com Web: www.nexgenproject.com, www.finalyear-ieeeprojects.com Fig. 1 totally consists of seven states, in which six states are used to compute different kinds of computations, as listed in Table I. These states include: 1) idle (IDLE); 2) BLA phase one (BLA P1); 3) BLA phase two (BLA P2); 4) the NRM for computing the power function (NRM); 5) EBS; 6) polynomial computation/ convolution (POL/CON); 7) windowing (WIN). Notably, each state implies several behaviors, and the different behaviors are decided by the values of the corresponding counter and state register. Fig. 1. Example of state diagram for computing (a) logarithmic function (Mode = 0) and (b) power function (Mode = 1). Dashed lines: controller will not go in these states with the different mode. Fig. 2 shows the architecture of the proposed system, including a 4-to-2 multiplexer, a 16-word dual-port SRAM, a parallelin-serial-out (PISO) register, a mathematical computing unit, and a
  • 4. CONTACT: PRAVEEN KUMAR. L (,+91 – 9791938249) MAIL ID: sunsid1989@gmail.com, praveen@nexgenproject.com Web: www.nexgenproject.com, www.finalyear-ieeeprojects.com corresponding controller. As shown in Fig. 3, the input Mode determines which operation is performed by the proposed system when the Act signal rises up. Then, the input Order means the order of polynomial, a filter, or a window function. The dual-port SRAM has 16-word space and 32-bit word length, which can temporally store the coefficients. In addition, the PISO register determines the behavior for the calculation of the EBS state. Finally, the multiplexer array can decide which coefficients need to be stored in the SRAM, or to be computed. Fig. 2. Architecture of the proposed system. Fig. 3 represents the architecture of the proposed mathematical computing unit. This architecture includes only a multiplier, an adder, a barrel shifter, a comparator, two registers, and seven multiplexers. In this design, the same arithmetic logics can be reused for different kinds of computations, as listed in Table IV. As shown in Fig. 3, the left multiplexer selects the coefficients for different kinds of computations. The middle multiplier, adder, and shifter can reorganize the computing flow to achieve distinct functionalities.
  • 5. CONTACT: PRAVEEN KUMAR. L (,+91 – 9791938249) MAIL ID: sunsid1989@gmail.com, praveen@nexgenproject.com Web: www.nexgenproject.com, www.finalyear-ieeeprojects.com Fig. 3. Architecture of a mathematical computing unit. 1) The following content briefly describes how the proposed hardware works with these six states. 1) IDLE: This state keeps waiting until the signal Act rises up, and then, the input Mode decides the next states for computing the corresponding function. 2) BLA P1: This state responses for computing BLA P1. The signal Sig_C is sent from the comparator in the mathematical computing unit, and is used to conform whether the next state is BLA P1 or BLA P2. 3) BLA P2: This state is used to compute the second phase of the BLA. The computation of the second phase will be kept until the Count value reaches M. Afterward, the next state is decided by the value that is saved in the stage register. If the value is one, the system will go back to BLA P1 to calculate the value of log2(B). Otherwise, the next state will be set to the NRM for computing (log2(B))−1. 4) NRM: This state executes the iterations of Newton’s method for computing the power function. Cnt records the computation cycle. The value of xk 2M will be first computed by the EBS when PCount is zero. 5) EBS: This state is to compute εI , εF , and xk 2M . In each cycle, the PISO shifts a bit to the controller for determining the behavior of the EBS. 6) POL and WIN: These two states response for the computation of the polynomial and the convolution, respectively. Advantages:  Improve the reusable efficiency.  Gate count is reduced
  • 6. CONTACT: PRAVEEN KUMAR. L (,+91 – 9791938249) MAIL ID: sunsid1989@gmail.com, praveen@nexgenproject.com Web: www.nexgenproject.com, www.finalyear-ieeeprojects.com  Power reduced Software implementation:  Modelsim  Xilinx ISE