Optimizing 32 bits integer manipulation on 8 bit AVR target

[Sylvain Leroux]

As a complement to my previous message,

It appears the following C source leads to much better code:

---------8<-----------------------------------
void f(uint32_t i) {
     union __attribute__((__packed__)) {
	uint32_t i;
	struct S { uint8_t a,b,c,d; } s;
     } u;

     u.i = i | ((uint32_t)(0xFF) << 16);

     DDRA = (uint32_t)(u.s.d);
     DDRA = (uint32_t)(u.s.c);
     DDRA = (uint32_t)(u.s.b);
     DDRA = (uint32_t)(u.s.a);
}
---------8<-----------------------------------

avr-objdump:
---------8<-----------------------------------
     union __attribute__((__packed__)) {
         uint32_t i;
         struct S { uint8_t a,b,c,d; } s;
     } u;

     u.i = i | ((uint32_t)(0xFF) << 16);
   58:   af 6f           ori     r26, 0xFF       ; 255

     DDRA = (uint32_t)(u.s.d);
   5a:   ba bb           out     0x1a, r27       ; 26
     DDRA = (uint32_t)(u.s.c);
   5c:   aa bb           out     0x1a, r26       ; 26
     DDRA = (uint32_t)(u.s.b);
   5e:   9a bb           out     0x1a, r25       ; 26
     DDRA = (uint32_t)(u.s.a);
   60:   8a bb           out     0x1a, r24       ; 26
---------8<-----------------------------------

*But*, the C code is no longer portable since I'm using 
"__attribute__((__packed__))". Moreover it requires endianness 
knowledge/assumption.


That's why I was hoping for a command line option allowing gcc to 
perform the same optimization.

- Sylvain


On 08/30/2012 02:54 PM, Sylvain Leroux wrote:
> Hi,
>
> It seems to me that avr-gcc/avr-g++ is producing sub-optimal code for
> the 'f' function in the following source code:
>
> ---------8<-----------------------------------
> #include <avr/io.h>
>
> void f(uint32_t i) {
> i |= ((uint32_t)(0xFF) << 16);
>
> /* DDRA is an 8 bit register */
> DDRA = (uint32_t)(i);
> DDRA = (uint32_t)(i>>8);
> DDRA = (uint32_t)(i>>16);
> DDRA = (uint32_t)(i>>24);
> }
>
> int main() {
> volatile uint32_t n = 0x01020304;
>
> f(n);
> }
> ---------8<-----------------------------------
> Having compiled with the following options:
> avr-gcc c.c -mmcu=attiny2313
> -Os -ffunction-sections -fdata-sections
> -g -Wl,--gc-sections -Wl,--print-gc-sections
> -fipa-cp -fcprop-registers -fweb
>
> ... here is the relevant fragment as displayed by avr-objdump. I marked
> with a star (*) all the instruction that appears to be useless:
> ---------8<-----------------------------------
> void f(uint32_t i) {
> i |= ((uint32_t)(0xFF) << 16);
> 34: 8f 6f ori r24, 0xFF ; 255
>
> DDRA = (uint32_t)(i);
> 36: 6a bb out 0x1a, r22 ; 26
> DDRA = (uint32_t)(i>>8);
> 38: 27 2f mov r18, r23
> * 3a: 38 2f mov r19, r24
> * 3c: 49 2f mov r20, r25
> * 3e: 55 27 eor r21, r21
> 40: 2a bb out 0x1a, r18 ; 26
> DDRA = (uint32_t)(i>>16);
> 42: 9c 01 movw r18, r24
> * 44: 44 27 eor r20, r20
> * 46: 55 27 eor r21, r21
> 48: 2a bb out 0x1a, r18 ; 26
> DDRA = (uint32_t)(i>>24);
> 4a: 69 2f mov r22, r25
> * 4c: 77 27 eor r23, r23
> * 4e: 88 27 eor r24, r24
> * 50: 99 27 eor r25, r25
> 52: 6a bb out 0x1a, r22 ; 26
> }
> 54: 08 95 ret
> ---------8<-----------------------------------
>
> Both gcc and g++ produce the same code. And I get the same results both
> with 4.3.5 and 4.7.1
>
> Here is my question:
> Is there any option(s) that will help gcc to not produce those extra
> instructions in such case?
>
>
> Regards,
> - Sylvain
>
>
>


-- 
-- Sylvain Leroux
-- sylvain@chicoree.fr
-- http://www.chicoree.fr