http://gcc.gnu.org/bugzilla/show_bug.cgi?id=52543
Georg-Johann Lay <gjl at gcc dot gnu.org> changed:
What |Removed |Added
----------------------------------------------------------------------------
Status|RESOLVED |REOPENED
Resolution|FIXED |
--- Comment #10 from Georg-Johann Lay <gjl at gcc dot gnu.org> 2012-08-02
18:29:41 UTC ---
(In reply to comment #9)
> Fixed.
NACK. I cannot confirm that anything changed:
If I revert the Hack from comment #4 that represents a memory access as UNSPEC
instead of as MEM (so that lower-subreg won't split), the code bloat returns.
Just suppose the examples given in comment #0
long readx (const __memx long *p)
{
return *p;
}
long read0 (const __flash long *p)
{
return *p;
}
with "GCC: (GNU) 4.8.0 20120802 (experimental)"
and -S -Os -dp -mmcu=avr5 -fno-split-wide-types
the result is fine and there are 32-bit accesses:
readx:
movw r30,r22 ; 17 *movhi/1 [length = 1]
mov r21,r24 ; 18 movqi_insn/1 [length = 1]
call __xload_4 ; 19 xload_si_libgcc [length = 2]
ret ; 24 return [length = 1]
read0:
movw r30,r24 ; 19 *movhi/1 [length = 1]
lpm r22,Z+ ; 20 *movsi/3 [length = 4]
lpm r23,Z+
lpm r24,Z+
lpm r25,Z+
ret ; 24 return [length = 1]
Without -fno-split-wide-types the bloat is still there:
readx:
push r12 ; 54 pushqi1/1 [length = 1]
push r13 ; 55 pushqi1/1 [length = 1]
push r14 ; 56 pushqi1/1 [length = 1]
mov r26,r24 ; 2 *movpsi/1 [length = 2]
movw r24,r22
movw r30,r24 ; 35 *movhi/1 [length = 1]
sbrc r26,7 ; 37 xload_8/1 [length = 4]
ld r22,Z
sbrs r26,7
lpm r22,Z
ldi r18,lo8(1) ; 49 *movpsi/5 [length = 3]
ldi r19,0
ldi r20,0
add r18,r24 ; 19 addpsi3/1 [length = 3]
adc r19,r25
adc r20,r26
movw r30,r18 ; 38 *movhi/1 [length = 1]
sbrc r20,7 ; 40 xload_8/1 [length = 4]
ld r23,Z
sbrs r20,7
lpm r23,Z
ldi r18,lo8(2) ; 64 *reload_inpsi [length = 4]
mov r12,r18
mov r13,__zero_reg__
mov r14,__zero_reg__
add r12,r24 ; 22 addpsi3/1 [length = 3]
adc r13,r25
adc r14,r26
ldi r18,lo8(3) ; 51 *movpsi/5 [length = 3]
ldi r19,0
ldi r20,0
add r18,r24 ; 25 addpsi3/1 [length = 3]
adc r19,r25
adc r20,r26
movw r30,r12 ; 41 *movhi/1 [length = 1]
sbrc r14,7 ; 43 xload_8/1 [length = 4]
ld r24,Z
sbrs r14,7
lpm r24,Z
movw r30,r18 ; 44 *movhi/1 [length = 1]
sbrc r20,7 ; 46 xload_8/1 [length = 4]
ld r25,Z
sbrs r20,7
lpm r25,Z
pop r14 ; 59 popqi [length = 1]
pop r13 ; 60 popqi [length = 1]
pop r12 ; 61 popqi [length = 1]
ret ; 62 return_from_epilogue [length = 1]
read0:
movw r30,r24 ; 35 *movhi/1 [length = 1]
lpm r22,Z+ ; 17 movqi_insn/4 [length = 1]
lpm r23,Z ; 20 movqi_insn/4 [length = 1]
movw r18,r24 ; 38 *movhi/1 [length = 1]
subi r18,-2 ; 22 addhi3_clobber/2 [length = 2]
sbci r19,-1
movw r20,r24 ; 39 *movhi/1 [length = 1]
subi r20,-3 ; 25 addhi3_clobber/2 [length = 2]
sbci r21,-1
movw r30,r18 ; 40 *movhi/1 [length = 1]
lpm r24,Z ; 33 movqi_insn/4 [length = 1]
movw r30,r20 ; 41 *movhi/1 [length = 1]
lpm r25,Z ; 34 movqi_insn/4 [length = 1]
ret ; 44 return [length = 1]
Each 32-bit move is still split into 4 8-bit moves even though that is
extremely expensive. This happens both for PSImode and for HImode addresses.
