FreeChainXenon/gcc
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

[RS6000] cost SLOW_UNALIGNED_ACCESS

Browse source 
* config/rs6000/rs6000.c (rs6000_rtx_costs): Make unaligned mem
	cost more.

From-SVN: r239012
This commit is contained in:
Alan Modra 2016-08-03 10:05:14 +09:30 • committed by Alan Modra
parent d1f0a70a12
commit cef58349a0
2 changed files with 10 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
gcc/ChangeLog
View file

@ -1,3 +1,8 @@
2016-08-03 Alan Modra <amodra@gmail.com>
* config/rs6000/rs6000.c (rs6000_rtx_costs): Make unaligned mem
cost more.
2016-08-03 Alan Modra <amodra@gmail.com>
* config/rs6000/rs6000.md (fix_trunc<mode>si2): Force source operand

5
gcc/config/rs6000/rs6000.c
View file

@ -34336,11 +34336,16 @@ rs6000_rtx_costs (rtx x, machine_mode mode, int outer_code,
case CONST:
case HIGH:
case SYMBOL_REF:
*total = !speed ? COSTS_N_INSNS (1) + 1 : COSTS_N_INSNS (2);
return true;
case MEM:
/* When optimizing for size, MEM should be slightly more expensive
than generating address, e.g., (plus (reg) (const)).
L1 cache latency is about two instructions. */
*total = !speed ? COSTS_N_INSNS (1) + 1 : COSTS_N_INSNS (2);
if (SLOW_UNALIGNED_ACCESS (mode, MEM_ALIGN (x)))
*total += COSTS_N_INSNS (100);
return true;
case LABEL_REF: