AVR-Chat

And there is Duff's device (Google is your friend here) for the more 
general case where the count is neither 8 bits nor a multiple of 8:

    count = 256;
    uint8_t *to = mydata;
    register int n = (count + 7) / 8;      /* count > 0 assumed */

    switch (count % 8)
    {
    case 0:        do {  *to++ = PIND;
    case 7:              *to++ = PIND;
    case 6:              *to++ = PIND;
    case 5:              *to++ = PIND;
    case 4:              *to++ = PIND;
    case 3:              *to++ = PIND;
    case 2:              *to++ = PIND;
    case 1:              *to++ = PIND;
                       } while (--n > 0);
    }

Which compiles, with GCC3.4.5 and -Os, to give:

    count = 256;
    uint8_t *to = mydata;
  136:	e2 e6       	ldi	r30, 0x62	; 98
  138:	f0 e0       	ldi	r31, 0x00	; 0
    register int n = (count + 7) / 8;      /* count > 0 assumed */
  13a:	20 e2       	ldi	r18, 0x20	; 32
  13c:	30 e0       	ldi	r19, 0x00	; 0

    switch (count % 8)
    {
    case 0:        do {  *to++ = PIND;
  13e:	80 b3       	in	r24, 0x10	; 16
  140:	81 93       	st	Z+, r24
    case 7:              *to++ = PIND;
  142:	80 b3       	in	r24, 0x10	; 16
  144:	81 93       	st	Z+, r24
    case 6:              *to++ = PIND;
  146:	80 b3       	in	r24, 0x10	; 16
  148:	81 93       	st	Z+, r24
    case 5:              *to++ = PIND;
  14a:	80 b3       	in	r24, 0x10	; 16
  14c:	81 93       	st	Z+, r24
    case 4:              *to++ = PIND;
  14e:	80 b3       	in	r24, 0x10	; 16
  150:	81 93       	st	Z+, r24
    case 3:              *to++ = PIND;
  152:	80 b3       	in	r24, 0x10	; 16
  154:	81 93       	st	Z+, r24
    case 2:              *to++ = PIND;
  156:	80 b3       	in	r24, 0x10	; 16
  158:	81 93       	st	Z+, r24
    case 1:              *to++ = PIND;
  15a:	80 b3       	in	r24, 0x10	; 16
  15c:	81 93       	st	Z+, r24
                       } while (--n > 0);
  15e:	21 50       	subi	r18, 0x01	; 1
  160:	30 40       	sbci	r19, 0x00	; 0
  162:	12 16       	cp	r1, r18
  164:	13 06       	cpc	r1, r19
  166:	5c f3       	brlt	.-42     	; 0x13e <myloop+0x6c>
  168:	08 95       	ret

I have to dash to work so I have not checked the cycle count and such 
but it looks pretty good to me.

Pete Harrison