diff options
| author | Bin Cheng <bin.cheng@arm.com> | 2014-12-03 05:25:40 +0000 |
|---|---|---|
| committer | Bin Cheng <amker@gcc.gnu.org> | 2014-12-03 05:25:40 +0000 |
| commit | 51be49774041c9d2b588bb2fd139b5de7454c4f2 (patch) | |
| tree | 3c382659e0834db1d511d369dd51eb84d07e6f83 /gcc/doc/tm.texi | |
| parent | 28fe2ab37c2990882795560f8bc345518f9aeb98 (diff) | |
| download | gcc-51be49774041c9d2b588bb2fd139b5de7454c4f2.zip gcc-51be49774041c9d2b588bb2fd139b5de7454c4f2.tar.gz gcc-51be49774041c9d2b588bb2fd139b5de7454c4f2.tar.bz2 | |
target.def (fusion_priority): Wrap code with @smallexample.
* target.def (fusion_priority): Wrap code with @smallexample.
* doc/tm.texi: Regenerated.
From-SVN: r218301
Diffstat (limited to 'gcc/doc/tm.texi')
| -rw-r--r-- | gcc/doc/tm.texi | 22 |
1 files changed, 14 insertions, 8 deletions
diff --git a/gcc/doc/tm.texi b/gcc/doc/tm.texi index c54fc71..b9a7251 100644 --- a/gcc/doc/tm.texi +++ b/gcc/doc/tm.texi @@ -6797,6 +6797,7 @@ instructions. Given below example: +@smallexample ldr r10, [r1, 4] add r4, r4, r10 ldr r15, [r2, 8] @@ -6805,6 +6806,7 @@ Given below example: add r4, r4, r11 ldr r16, [r2, 12] sub r5, r5, r16 +@end smallexample On targets like ARM/AArch64, the two pairs of consecutive loads should be merged. Since peephole2 pass can't help in this case unless consecutive @@ -6812,19 +6814,22 @@ loads are actually next to each other in instruction flow. That's where this scheduling fusion pass works. This hook calculates priority for each instruction based on its fustion type, like: - ldr r10, [r1, 4] ; fusion_pri=99, pri=96 - add r4, r4, r10 ; fusion_pri=100, pri=100 - ldr r15, [r2, 8] ; fusion_pri=98, pri=92 - sub r5, r5, r15 ; fusion_pri=100, pri=100 - ldr r11, [r1, 0] ; fusion_pri=99, pri=100 - add r4, r4, r11 ; fusion_pri=100, pri=100 - ldr r16, [r2, 12] ; fusion_pri=98, pri=88 - sub r5, r5, r16 ; fusion_pri=100, pri=100 +@smallexample + ldr r10, [r1, 4] ; fusion_pri=99, pri=96 + add r4, r4, r10 ; fusion_pri=100, pri=100 + ldr r15, [r2, 8] ; fusion_pri=98, pri=92 + sub r5, r5, r15 ; fusion_pri=100, pri=100 + ldr r11, [r1, 0] ; fusion_pri=99, pri=100 + add r4, r4, r11 ; fusion_pri=100, pri=100 + ldr r16, [r2, 12] ; fusion_pri=98, pri=88 + sub r5, r5, r16 ; fusion_pri=100, pri=100 +@end smallexample Scheduling fusion pass then sorts all ready to issue instructions according to the priorities. As a result, instructions of same fusion type will be pushed together in instruction flow, like: +@smallexample ldr r11, [r1, 0] ldr r10, [r1, 4] ldr r15, [r2, 8] @@ -6833,6 +6838,7 @@ pushed together in instruction flow, like: sub r5, r5, r15 add r4, r4, r11 sub r5, r5, r16 +@end smallexample Now peephole2 pass can simply merge the two pairs of loads. |