Hello all,
A frequent need in my code is to combine two 8 bit variables into a 16 bit
variable. I am trying to determine the optimal way to do this. The naïve way
and a more clever way both generate extra instructions that could be optimized
away. I include a test case and comments which explain the setup and issue in
more detail. It seems this is a missed opportunity for optimization in the
compiler.
Thomas
#include <avr/io.h>
#include <inttypes.h>
#include <avr/interrupt.h>
/*
$ avr-gcc -v
Using built-in specs.
COLLECT_GCC=avr-gcc
COLLECT_LTO_WRAPPER=/usr/local/Cellar/avr-gcc/4.9.2/libexec/gcc/avr/4.9.2/lto-wrapper
Target: avr
Configured with: ../configure --enable-languages=c,c++ --target=avr
--disable-libssp --disable-nls --with-dwarf2
--prefix=/usr/local/Cellar/avr-gcc/4.9.2
--with-gmp=/usr/local/Cellar/gmp/6.0.0a
--with-mpfr=/usr/local/Cellar/mpfr/3.1.2-p10
--with-mpc=/usr/local/Cellar/libmpc/1.0.2
--datarootdir=/usr/local/Cellar/avr-gcc/4.9.2/share
--bindir=/usr/local/Cellar/avr-gcc/4.9.2/bin --with-as=/usr/local/bin/avr-as
--with-ld=/usr/local/bin/avr-ld
Thread model: single
gcc version 4.9.2 (GCC)
*/
// compile like:
// avr-gcc -mmcu=atmega328p -std=gnu99 -Os -Wall -DF_CPU=16000000
-Wa,-ahlmsd=sixteenbit_test.lst -o sixteenbit_test.elf sixteenbit_test.c
// data storage memory (might be used in ISR for example)
volatile uint16_t data;
// read and return a byte from the serial port
uint8_t read_byte() {
while (!(UCSR0A & _BV(RXC0)));
return (uint8_t)UDR0;
}
int main() {
cli();
// init serial port
// etc
sei();
uint8_t temp_hi, temp_lo;
// receive a word with |
temp_hi = read_byte();
temp_lo = read_byte();
cli(); // not okay to get interrupted while assigning
// in case an ISR comes and tries to read 'data'
/* compiles to
47 0012 282F mov r18,r24
48 0014 30E0 ldi r19,0
49 0016 C901 movw r24,r18
50 0018 9C2B or r25,r28
51 001a 9093 0000 sts data+1,r25
52 001e 8093 0000 sts data,r24
where r28 is temp_hi and r24 is temp_lo
8 bytes and 4 cycles worse than the good solution
*/
data = (temp_hi<<8) | temp_lo;
sei(); // can get interrupted again
// receive a word with pointer assignment
// ugly and still does not compile how I want
temp_hi = read_byte();
temp_lo = read_byte();
cli(); // not okay to get interrupted while assigning
// in case an ISR comes and tries to read 'data'
/* compiles to
66 0030 E0E0 ldi r30,lo8(data)
67 0032 F0E0 ldi r31,hi8(data)
68 0034 8083 st Z,r24
69 0036 C183 std Z+1,r28
2 cycles worse than the good solution
*/
*((uint8_t*)&data) = temp_lo;
*((uint8_t*)&data+1) = temp_hi;
sei(); // can get interrupted again
/*
Why won't the compiler compile it as
sts data, r24
sts data+1, r28
It will, in the second case, if it feels Z and Y are otherwise occupied.
But I couldn't get to think that for a reasonably short sample.
It also will work correctly in this case for -O2.
*/
}_______________________________________________
AVR-GCC-list mailing list
AVR-GCC-list@nongnu.org
https://lists.nongnu.org/mailman/listinfo/avr-gcc-list
