scispace - formally typeset
Proceedings ArticleDOI

Multiplexer based adder for media signal processing

TLDR
The design of a highly re-configurable adder, which has been optimized for speed and area, is presented, which is the hybrid of binary carry lookahead adder of Brent, and carry select adder.
Abstract
This paper presents the design of a highly re-configurable adder, which has been optimized for speed and area. Since pass transistor based multiplexer is the fastest element in standard CMOS logic, we designed the adder using only multiplexers and 2-input inverted logic gates. This adder is the hybrid of binary carry lookahead adder of Brent, and carry select adder. By using the hybrid approach, the area and wiring of the adder is reduced by 1/2, keeping the adder delay proportional to O(log n). The critical path of the 68-bit partitioned adder consists of 7 two-to-one multiplexers and 1 XOR gate. The adder can be partitioned to support a variety of data formats, it can add two 64-bit-operands, four 32-bit operands, eight 16-bit operands, or sixteen and bit operands. The adder can be used for multi-media applications, and is well suited for VLIW processors. The adder is described in Verilog, and synthesized using Synopsys tool. The critical path delay of the 64-bit adder is 0.9 ns at typical conditions in standard cell 0.25 um technology.

read more

Citations
More filters
Journal ArticleDOI

Comparison of high-performance VLSI adders in the energy-delay space

TL;DR: The estimation is quick, not requiring extensive simulation or use of computer-aided design tools, yet sufficiently accurate to provide guidance through various choices in the design process.
Proceedings ArticleDOI

Energy-delay estimation technique for high-performance microprocessor VLSI adders

TL;DR: In this article, the authors compare the energy-delay trade-offs of high-performance 32-bit and 64-bit processor adders in 0.13/spl µ/m and 0.10/spl mu/m CMOS technologies, with an accuracy of 8% in delay estimates and 20% in energy estimates, compared with simulated data.
Journal ArticleDOI

A mux -based High-Performance Single-Cycle CMOS Comparator

TL;DR: A new architecture for high-fan-in CMOS comparator is proposed, based on a hierarchical two-stage comparator structure and a dynamic MUX is used instead of a comparator in the second stage of the structure to significantly improve the overall delay of the high- fan-in comparators.
Patent

High performance universal multiplier circuit

TL;DR: In this article, the authors present a partitioned multiplier circuit which is designed for high speed operations, which can perform one 32×32 bit multiplication, two 16×16 bit multiplications (simultaneously) or four 8×8 bits multiplications depending on input partitioning signals.
Journal ArticleDOI

Architecture and implementation of a vector/SIMD multiply-accumulate unit

TL;DR: The "shared segmentation" method is compared to an alternative method, referred to as the "shared subtree" method, by implementing vector MAC designs using two different technologies and three different vector widths.
References
More filters
Journal ArticleDOI

A Regular Layout for Parallel Adders

TL;DR: It is shown that addition of n-bit binary numbers can be performed on a chip with a regular layout in time proportional to log n and with area proportional to n.
Journal ArticleDOI

High-speed addition in CMOS

TL;DR: A fully static complementary metal-oxide semiconductor (CMOS) implementation of a Ling-type 32-bit adder that saves up to one gate delay and always reduces the number of serial transistors in the worst-case critical path over the conventional carry look-ahead (CLA) approach with a negligible increaser in hardware.
Journal ArticleDOI

On the Addition of Binary Numbers

TL;DR: An upper bound is derived for the time required to add numbers modulo 2n, using circuit elements with a limited fan-in and unit delay, and assuming that all numbers have the usual binary encoding.
Proceedings ArticleDOI

A low-power, high-speed implementation of a PowerPC/sup TM/ microprocessor vector extension

TL;DR: The microarchitecture and design of the vector arithmetic unit of this implementation of the AltiVec/sup TM/ technology is described, which provides new computational and storage operations for handling vectors of various data lengths and data types.