diff options
author | Pat Haugen <pthaugen@linux.ibm.com> | 2021-05-10 13:49:06 -0500 |
---|---|---|
committer | Pat Haugen <pthaugen@linux.ibm.com> | 2021-05-10 13:49:06 -0500 |
commit | 51d89e61f7ebfe75ca752e62bd29b58cb957235c (patch) | |
tree | 03c652519f171317f9b62d2249ba6da35d7f33b5 /gcc/go | |
parent | e85f3aeddbdba27ec883bb85a58f96615726da32 (diff) | |
download | gcc-51d89e61f7ebfe75ca752e62bd29b58cb957235c.zip gcc-51d89e61f7ebfe75ca752e62bd29b58cb957235c.tar.gz gcc-51d89e61f7ebfe75ca752e62bd29b58cb957235c.tar.bz2 |
Add ALTIVEC_REGS as pressure class.
Code that has heavy register pressure on Altivec registers can suffer from
over-aggressive scheduling during sched1, which then leads to increased
register spill. This is due to the fact that registers that prefer
ALTIVEC_REGS are currently assigned an allocno class of VSX_REGS. This then
misleads the scheduler to think there are 64 regs available, when in reality
there are only 32 Altivec regs. This patch fixes the problem by assigning an
allocno class of ALTIVEC_REGS and adding ALTIVEC_REGS as a pressure class.
2021-05-10 Pat Haugen <pthaugen@linux.ibm.com>
gcc/ChangeLog:
* config/rs6000/rs6000.c (rs6000_ira_change_pseudo_allocno_class):
Return ALTIVEC_REGS if that is best_class.
(rs6000_compute_pressure_classes): Add ALTIVEC_REGS.
gcc/testsuite/ChangeLog:
* gcc.target/powerpc/fold-vec-insert-float-p9.c: Adjust counts.
* gcc.target/powerpc/vec-rlmi-rlnm.c: Likewise.
Diffstat (limited to 'gcc/go')
0 files changed, 0 insertions, 0 deletions