05-12-2012, 01:08 PM
Multiplication Acceleration Through Twin Precision
Twin Precesion.ppt (Size: 624 KB / Downloads: 32)
Need for Project
Multiplication is a complex arithmetic operation, which is reflected in its relatively high signal propagation delay, high power dissipation, and large area requirement.
The bit-width of the multiplier is, therefore, often much larger than the data represented inside the operands, which leads to unnecessarily high power dissipation and unnecessary long delay.
We present the twin-precision technique for integer multipliers.
The twin-precision technique can reduce the power dissipation by adapting a multiplier to the bit-width of the operands being computed.
The technique also enables an increased computational throughput, by allowing several narrow-width operations to be computed in parallel.
The twin-precision technique is an efficient way of achieving double throughput in a multiplier with low area overhead and with only a small delay penalty.
Algorithm for Baugh–Wooley
The creation of the reorganized partial-product array comprises three steps:
the most significant partial product of the first (N-1)rows and the last row of partial products except the most significant have to be negated,
a constant one is added to the Nth column,
the most significant bit (MSB) of the final result is negated.