Infineon TriCore TC1.6P - MSUBR.Q - Multiply-Subtract Q Format with Rounding; MSUBRS.Q - Multiply-Subtract Q Format with Rounding, Saturated

TriCore
®
TC1.6P & TC1.6E
32-bit Unified Processor Core
Instruction Set
V1.0 2013-07
User Manual (Volume 2) 3-269
MSUBR.Q
Multiply-Subtract Q Format with Rounding
MSUBRS.Q
Multiply-Subtract Q Format with Rounding, Saturated
Description
Multiply two signed 16-bit (half-word) values. Subtract the product (left justified if n == 1) from a 32-bit signed value,
and put the rounded result in a 32-bit register. The lower half-word is cleared. Overflow and advanced overflow
are calculated on the final results.
Note that n should only take the values 0 or 1, any other value returns an undefined result. If (n == 1) then 8000
H
* 8000
H
= 7FFFFFFF
H
(for signed 16-bit * 16-bit multiplications only).
MSUBR.QD[c], D[d], D[a] L, D[b] L, n (RRR1)
32 - (16L * 16L) rounded --> 32
sc = (D[a][15:0] == 8000
H
) AND (D[b][15:0] == 8000
H
) AND (n == 1);
mul_res = sc ? 7FFFFFFF
H
: ((D[a][15:0] * D[b][15:0]) << n);
result = D[d] - mul_res + 8000
H
;
D[c] = {result[31:16], 16’b0}; // Short fraction
MSUBR.QD[c], D[d], D[a] U, D[b] U, n (RRR1)
32 - (16U * 16U) rounded --> 32
sc = (D[a][31:16] == 8000
H
) AND (D[b][31:16] == 8000
H
) AND (n == 1);
mul_res = sc ? 7FFFFFFF
H
: ((D[a][31:16] * D[b][31:16]) << n);
result = D[d] - mul_res + 8000
H
;
D[c] = {result[31:16], 16’b0}; // Short fraction
MSUBRS.QD[c], D[d], D[a] L, D[b] L, n (RRR1)
32 - (16L * 16L) rounded -->32 saturated
sc = (D[a][15:0] == 8000
H
) AND (D[b][15:0] == 8000
H
) AND (n == 1);
mul_res = sc ? 7FFFFFFF
H
: ((D[a][15:0] * D[b][15:0]) << n);
result = D[d] - mul_res + 8000
H
;
D[c] = {ssov(result,32)[31:16]), 16’b0}; // Short fraction
MSUBRS.QD[c], D[d], D[a] U, D[b] U, n (RRR1)
32 - (16U * 16U) rounded --> 32 saturated
31
c
28 27
d
24 23
07
H
18 17
n
16 15
b
12 11
a
8 7
63
H
0
31
c
28 27
d
24 23
06
H
18 17
n
16 15
b
12 11
a
8 7
63
H
0
31
c
28 27
d
24 23
27
H
18 17
n
16 15
b
12 11
a
8 7
63
H
0