diff options
| author | Aaron Sawdey <acsawdey@linux.vnet.ibm.com> | 2016-05-09 16:56:30 +0000 |
|---|---|---|
| committer | Aaron Sawdey <acsawdey@gcc.gnu.org> | 2016-05-09 11:56:30 -0500 |
| commit | 8964ed82dbf9554c07ba02f060a0b4ab7d17765c (patch) | |
| tree | 48eb1f57289f4e995f069f38213ad5c8a16f0347 /gcc | |
| parent | fc97f8050225946f1f8ba00046ff0d068783c3b4 (diff) | |
| download | gcc-8964ed82dbf9554c07ba02f060a0b4ab7d17765c.zip gcc-8964ed82dbf9554c07ba02f060a0b4ab7d17765c.tar.gz gcc-8964ed82dbf9554c07ba02f060a0b4ab7d17765c.tar.bz2 | |
rs6000.c (rs6000_reassociation_width): Add function for TARGET_SCHED_REASSOCIATION_WIDTH to enable parallel...
* config/rs6000/rs6000.c (rs6000_reassociation_width): Add
function for TARGET_SCHED_REASSOCIATION_WIDTH to enable
parallel reassociation for power8 and forward.
From-SVN: r236043
Diffstat (limited to 'gcc')
| -rw-r--r-- | gcc/ChangeLog | 6 | ||||
| -rw-r--r-- | gcc/config/rs6000/rs6000.c | 37 |
2 files changed, 43 insertions, 0 deletions
diff --git a/gcc/ChangeLog b/gcc/ChangeLog index 007ae87..0cd9534 100644 --- a/gcc/ChangeLog +++ b/gcc/ChangeLog @@ -1,3 +1,9 @@ +2016-05-04 Aaron Sawdey <acsawdey@linux.vnet.ibm.com> + + * config/rs6000/rs6000.c (rs6000_reassociation_width): Add + function for TARGET_SCHED_REASSOCIATION_WIDTH to enable + parallel reassociation for power8 and forward. + 2016-05-09 Uros Bizjak <ubizjak@gmail.com> * config/i386/i386.md (absneg splitters with general regs): Use diff --git a/gcc/config/rs6000/rs6000.c b/gcc/config/rs6000/rs6000.c index 368fec2..34495f3 100644 --- a/gcc/config/rs6000/rs6000.c +++ b/gcc/config/rs6000/rs6000.c @@ -1755,6 +1755,9 @@ static const struct attribute_spec rs6000_attribute_table[] = #undef TARGET_CONDITIONAL_REGISTER_USAGE #define TARGET_CONDITIONAL_REGISTER_USAGE rs6000_conditional_register_usage +#undef TARGET_SCHED_REASSOCIATION_WIDTH +#define TARGET_SCHED_REASSOCIATION_WIDTH rs6000_reassociation_width + #undef TARGET_TRAMPOLINE_INIT #define TARGET_TRAMPOLINE_INIT rs6000_trampoline_init @@ -8633,6 +8636,40 @@ rs6000_offsettable_memref_p (rtx op, machine_mode reg_mode) true, worst_case); } +/* Determine the reassociation width to be used in reassociate_bb. + This takes into account how many parallel operations we + can actually do of a given type, and also the latency. + P8: + int add/sub 6/cycle + mul 2/cycle + vect add/sub/mul 2/cycle + fp add/sub/mul 2/cycle + dfp 1/cycle +*/ + +static int +rs6000_reassociation_width (unsigned int opc ATTRIBUTE_UNUSED, + enum machine_mode mode) +{ + switch (rs6000_cpu) + { + case PROCESSOR_POWER8: + case PROCESSOR_POWER9: + if (DECIMAL_FLOAT_MODE_P (mode)) + return 1; + if (VECTOR_MODE_P (mode)) + return 4; + if (INTEGRAL_MODE_P (mode)) + return opc == MULT_EXPR ? 4 : 6; + if (FLOAT_MODE_P (mode)) + return 4; + break; + default: + break; + } + return 1; +} + /* Change register usage conditional on target flags. */ static void rs6000_conditional_register_usage (void) |