11.07.2015 Views

section 7 - Index of

section 7 - Index of

section 7 - Index of

SHOW MORE
SHOW LESS

You also want an ePaper? Increase the reach of your titles

YUMPU automatically turns print PDFs into web optimized ePapers that Google loves.

3.5 DATA ALU PROGRAMMING MODELThe Data ALU features 24-bit input/output data registers that can be concatenated to accommodate48-bit data and two 56-bit accumulators, which are segmented into three 24-bit pieces that can be transferred over the buses. Figure 3-14 illustrates how the registersin the programming model are grouped.XDATAALUINPUT REGISTERSy-47 0 47 0I X1 XO I I Y1 YO I23 023 0 23 023 0ADATAALUACCUMULATOR REGISTERS55 0 55 0IA21 A1 AO I 1 821 81 80 I23 8 7 0 23 o 23 0 23 8 7023 o 23 0*Read as sign extension bits, written as don't care.BFigure 3-14 DSP56K Programming Model3.6 DATA ALU SUMMARYThe Data ALU performs arithmetic operations involving multiply and accumulate operations.It executes all instructions in one machine cycle and is not pipelined. The two 24-bitnumbers being multiplied can come from the X registers (XO or X1) or Y registers (YO orY1). After multiplication, they are added (or subtracted) with one <strong>of</strong> the 56-bit accumulatorsand can be convergently rounded to 24 bits. The convergent-rounding forcingfunction detects the $800000 condition in the LSP and makes the correction as necessary.The final result is then stored in one <strong>of</strong> the accumulators as a valid 56-bit number.The condition code bits are set based on the rounded output <strong>of</strong> the logic unit.

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!