Texas Instruments TMS320C67X/C67X+ DSP manual Mpyspdp

MPYSPDP Multiply Single-Precision Value x Double-Precision Value (C67x+ CPU)

MPYSPDP				Multiply Single-Precision Floating-Point Value y Double-Precision
				Floating-Point Value
Syntax					MPYSPDP (.unit) src1, src2, dst
					.unit = .M1 or .M2
Compatibility					C67x+ CPU only
Opcode
31	29	28	27	23		22	18	17	13	12	11	7	6	5	4	3	2	1	0

creg

z

dst

src2

src1

x

0 1 0 1 1 0 1

1 0 0 s p

3 155511 1

Opcode map field used...	For operand type...	Unit
src1	sp	.M1, .M2
src2	xsp
dst	sp

Description	The single-precision src1 operand is multiplied by the double-precision src2
	operand to produce a double-precision result. The result is placed in dst.
Execution	if (cond)	src1 ￿ src2 → dst
	else	nop

Notes:

1)If one source is SNaN or QNaN, the result is a signed NaN_out. If either source is SNaN, the INVAL bit is set also. The sign of NaN_out is the exclusive-OR of the input signs.

2)Signed infinity multiplied by signed infinity or a normalized number (other than signed 0) returns signed infinity. Signed infinity multiplied by signed 0 returns a signed NaN_out and sets the INVAL bit.

3)If one or both sources are signed 0, the result is signed 0 unless the other source is NaN or signed infinity, in which case the result is signed NaN_out.

4)A denormalized source is treated as signed 0 and the DENn bit is set. The INEX bit is set except when the other source is signed infinity, signed NaN, or signed 0. Therefore, a signed infinity multiplied by a denormal- ized number gives a signed NaN_out and sets the INVAL bit.

5)If rounding is performed, the INEX bit is set.

3-168 Instruction Set SPRU733