XtremeDSP 48 Slice
High performance XtremeDSP™ DSP48 slices allow designers to implement multiple slower operations using timemultiplexing methods. They provide:
 Improved flexibility and utilization
 Improved application efficiency
 Reduced overall power consumption
 Increased maximum frequency
 Reduced setup plus clocktoout time
 Support for many independent functions, including multiply, multiply accumulate (MACC), multiply add, threeinput add, barrel shift, widebus multiplexing, magnitude comparator, bitwise logic functions, pattern detect, and wide counter
 Support for cascading multiple DSP48s slices to form wide math functions, DSP filters, and complex arithmetic without the use of general FPGA fabric
XtremeDSP DSP48s Slice Comparison 
Function 
Spartan®3A DSP DSP48A 
Virtex®4 FPGA
DSP48 
Virtex5 FPGA DSP48E 
Multiplier 
18 x 18 
18 x 18 
25 x 18 
Preadder 
Yes 
No 
No 
Cascade inputs 
One 
One 
Two 
Cascade output 
Yes 
Yes 
Yes 
Dedicated C input 
Yes 
No 
Yes 
Adder 
2 input 48bit 
3 input 48bit 
3 input 48bit 
ALU logic functions 
No 
No 
Yes 
Pattern detect 
No 
No 
Yes 
SIMD ALU support 
No 
No 
Yes 
Carry signals 
Carry in 
Carry in 
Carry in and out 
RTL support 
Main functions + preadd 
Main functions 
Main functions 
XtremeDSP DSP48E Slices for the Virtex5 Family
DSP48E slices, available in all Virtex5 devices, accelerate algorithms and enable higher levels of DSP integration and lower power consumption than previousgeneration Virtex devices. They:
 Support over 40 dynamically controlled operating modes including: multiplier, multiplieraccumulator, multiplieradder/subtractor, three input adder, barrel shifter, wide bus multiplexers, wide counters, and comparators.
 Enable efficient adderchain architectures for implementing highperformance filters and complex math efficiently.
 Draw only 1.38 mW/100 MHz at a toggle rate of 38%  a 40% reduction from previousgeneration slices.
Virtex5 FPGA DSP48E Feature Benefits 
Feature 
Benefit 
25bit by 18bit, two's complement multiplier with full precision 48bit result 
Enable higher precision for greater dynamic range, singleprecision floatingpoint math, and wide filters with fewer slices. 
Enhanced second stage 
Enable three input, flexible 48bit adder/subtracter with optional registered accumulation feedback.
Implement pattern detector for convergent rounding, underflow/overflow detection for saturation arithmetic, and autoresetting counters/accumulators.
Support SIMD operations. 
Over 40 dynamic usercontroller operating modes 
Adapt DSPE slice functions from clock cycle to clock cycle. 
18bit B cascade routing 
Support input sample propagation. 
New 30bit A cascade routing 
Enable advanced filter implementations and reduce power. 
Independent, 48bit C input 
Multiply, add, use large threeoperand addition, or flexible rounding mode. Increase usability by eliminating sharing of C input across slices to simplify design and increase performance. 
Cascading, 48bit P bus 
Support output propagation of partial results. 
XtremeDSP DSP48 Slices for the Virtex4 Family
DSP48 slices are available in all Virtex4 family members to accelerate algorithms and solve complex DSP challenges. They provide:
 500 MHz performance independently or when combined within a column to implement DSP functions.
 2.3 mW/100 MHz power consumption per slice, at a typical toggle rate of 38%.
 Support for over 40 dynamically controlled operating modes including; multiplier, multiplieraccumulator, multiplieradder/subtracter, three input adder, barrel shifter, wide bus multiplexers, or wide counters.
 DSP48 slice cascading without using device fabric or routing resources to perform wide math functions, DSP filters, and complex arithmetic.
XtremeDSP DSP48 Slice Highlights
 18bit by 18bit, two's complement multiplier with full precision 36bit result, sign extended to 48 bits.
 Three input, flexible 48bit adder/subtracter with optional registered accumulation feedback.
 Over 40 dynamic usercontroller operating modes to adapt XtremeDSP Slice functions from clock cycle to clock cycle.
 Cascading, 18bit B bus, supporting input sample propagation.
 Cascading, 48bit P bus, supporting output propagation of partial results.
 Multiprecision multiplier and arithmetic support with 17bit operand right shift to align wide multiplier partial products (parallel or sequential multiplication).
 Symmetric intelligent rounding support for greater computational accuracy.
 Performanceenhancing pipeline options for control and data signals are selectable by configuration bits.
 Input port "C" typically used for multiply, add, large threeoperand addition or flexible rounding mode.
 Separate reset and clock enable for control and data registers.
XtremeDSP DSP48A Slices for the Spartan3A DSP Family
The 250 MHz DSP48A Slice provides an 18bit x 18bit multiplier, 18bit preadder, 48bit postadder/accumulator, and cascade capabilities for various DSP applications.
DSP48A Slice Highlights
 18bit by 18bit, two's complement multiplier with full precision 36bit result, sign extended to 48 bits.
 Preadder saves 9 logic slices per DSP48A used.
 Two input, flexible 48bit adder/subtracter with optional registered accumulation feedback.
 Cascading, 18bit B bus, supporting input sample propagation.
 Cascading, 48bit P bus, supporting output propagation of partial results.
 Multiprecision multiplier and arithmetic support with 17bit operand right shift to align wide multiplier partial products (parallel or sequential multiplication).
 Symmetric intelligent rounding support for greater computational accuracy.
 Performanceenhancing pipeline options for control and data signals are selectable by configuration bits.
 Input port "C" typically used for multiply, add, large threeoperand addition or flexible rounding mode.
 Separate reset and clock enable for control and data registers.
