Table of Contents
Advertisement
fmpy d4,d7,d3 fadd.s d3,d1 x:(r0)+,d4.s y:(r4)+n4,d7.s 1
fmpy d4,d7,d3 fadd.s d3,d1 x:(r0)+,d4.s y:(r4)+n4,d7.s 1
fmpy d4,d7,d3 fadd.s d3,d1 x:(r0)+,d4.s y:(r4)+n4,d7.s 1
fmpy d4,d7,d3 fadd.s d3,d1 x:(r0)+,d4.s y:(r4)+n4,d7.s 1
fmpy d4,d7,d3 fadd.s d3,d1 x:(r0)+,d4.s y:(r4)+n4,d7.s 1
fmpy d4,d7,d3 fadd.s d3,d1 x:(r0)+,d4.s y:(r4)+n4,d7.s 1
fmpy d4,d7,d3 fadd.s d3,d1 x:(r0)+,d4.s y:(r4)+n4,d7.s 1
fmpy d4,d7,d3 fadd.s d3,d1 x:(r0)+,d4.s y:(r4)+n4,d7.s 1
move d1.s,y:(r5)+n5 d5.s,d2.s
fmpy d4,d7,d3 fadd.s d3,d2 x:(r0)+,d4.s y:(r4)+n4,d7.s 1
fmpy d4,d7,d3 fadd.s d3,d2 x:(r0)+,d4.s y:(r4)+n4,d7.s 1
fmpy d4,d7,d3 fadd.s d3,d2 x:(r0)+,d4.s y:(r4)+n4,d7.s 1
fmpy d4,d7,d3 fadd.s d3,d2 x:(r0)+,d4.s y:(r4)+n4,d7.s 1
fmpy d4,d7,d3 fadd.s d3,d2 x:(r0)+,d4.s y:(r4)+n4,d7.s 1
fmpy d4,d7,d3 fadd.s d3,d2 x:(r0)+,d4.s y:(r4)+n4,d7.s 1
fmpy d4,d7,d3 fadd.s d3,d2 x:(r0)+,d4.s y:(r4)+,d1.s
move d2.s,y:(r5)+n5 d5.s,d1.s
move (r5)+
endall
B.1.57
[16x16] by [16x16] Matrix Multiplication (Modulo Aligned)
;This routine performs a [16x16] by [16x16] matrix multiplication
;for the 96000 floating-point DSP chip.
;for N=16.
;format.
For example, take the matrix A:
;
;
;
;
;
;
;Matrix A's elements are stored as such:
;amatrix
dc A(1,1),A(1,2),...,A(1,N),A(2,1),A(2,2),...,A(2,N), ...
;
;Matrix A is in X memory, while matrices B and C are in Y memory.
;Since modulo N**2 addressing is used for all matrices, the first
;k least significant bits of the address of the beginning of any
;matrix storage area must be equal to zero, where 2**k >= N**2.
;
MOTOROLA
fadd.s d3,d2
The data for all matrices is stored in row major
A(1,1) ... A(1,N)
.
.
.
.
A(N,1) ... A(N,N)
DSP96002 USER'S MANUAL
;junk to d1.s
y:(r4)+n4,d7.s 1
Sample data is given
.
.
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
---
---
Totals: 86
607
B-133
Advertisement
Table of Contents
