https://gcc.gnu.org/g:e98175b635a332f28ba1dd8e5da67bcec92efcc5
commit e98175b635a332f28ba1dd8e5da67bcec92efcc5 Author: Michael Meissner <meiss...@linux.ibm.com> Date: Fri Nov 22 17:49:32 2024 -0500 Use vector pair load/store for memcpy with -mcpu=future In the development for the power10 processor, GCC did not enable using the load vector pair and store vector pair instructions when optimizing things like memory copy. This patch enables using those instructions if -mcpu=future is used. 2024-11-22 Michael Meissner <meiss...@linux.ibm.com> gcc/ * config/rs6000/rs6000-cpus.def (ISA_FUTURE_MASKS_SERVER): Enable using load vector pair and store vector pair instructions for memory copy operations. (POWERPC_MASKS): Make the bit for enabling using load vector pair and store vector pair operations set and reset when the PowerPC processor is changed. * gcc/config/rs6000/rs6000.cc (rs6000_machine_from_flags): Disable -mblock-ops-vector-pair from influcing .machine selection. gcc/testsuite/ * gcc.target/powerpc/future-3.c: New test. Diff: --- gcc/config/rs6000/rs6000-cpus.def | 4 +++- gcc/config/rs6000/rs6000.cc | 2 +- gcc/testsuite/gcc.target/powerpc/future-3.c | 21 +++++++++++++++++++++ 3 files changed, 25 insertions(+), 2 deletions(-) diff --git a/gcc/config/rs6000/rs6000-cpus.def b/gcc/config/rs6000/rs6000-cpus.def index 354c1d8de4f0..2f189dd416ca 100644 --- a/gcc/config/rs6000/rs6000-cpus.def +++ b/gcc/config/rs6000/rs6000-cpus.def @@ -84,7 +84,8 @@ | OPTION_MASK_POWER11) #define FUTURE_MASKS_SERVER (POWER11_MASKS_SERVER \ - | OPTION_MASK_FUTURE) + | OPTION_MASK_FUTURE \ + | OPTION_MASK_BLOCK_OPS_VECTOR_PAIR) /* Flags that need to be turned off if -mno-vsx. */ #define OTHER_VSX_VECTOR_MASKS (OPTION_MASK_EFFICIENT_UNALIGNED_VSX \ @@ -114,6 +115,7 @@ /* Mask of all options to set the default isa flags based on -mcpu=<xxx>. */ #define POWERPC_MASKS (OPTION_MASK_ALTIVEC \ + | OPTION_MASK_BLOCK_OPS_VECTOR_PAIR \ | OPTION_MASK_CMPB \ | OPTION_MASK_CRYPTO \ | OPTION_MASK_DFP \ diff --git a/gcc/config/rs6000/rs6000.cc b/gcc/config/rs6000/rs6000.cc index ab26192b687d..35e42a80ac5c 100644 --- a/gcc/config/rs6000/rs6000.cc +++ b/gcc/config/rs6000/rs6000.cc @@ -5906,7 +5906,7 @@ rs6000_machine_from_flags (void) /* Disable the flags that should never influence the .machine selection. */ flags &= ~(OPTION_MASK_PPC_GFXOPT | OPTION_MASK_PPC_GPOPT | OPTION_MASK_ISEL - | OPTION_MASK_ALTIVEC); + | OPTION_MASK_ALTIVEC | OPTION_MASK_BLOCK_OPS_VECTOR_PAIR); if ((flags & (FUTURE_MASKS_SERVER & ~ISA_3_1_MASKS_SERVER)) != 0) return "future"; diff --git a/gcc/testsuite/gcc.target/powerpc/future-3.c b/gcc/testsuite/gcc.target/powerpc/future-3.c new file mode 100644 index 000000000000..1cbe9170f121 --- /dev/null +++ b/gcc/testsuite/gcc.target/powerpc/future-3.c @@ -0,0 +1,21 @@ +/* { dg-do compile } */ +/* { dg-options "-mdejagnu-cpu=future -O2" } */ + +/* Test to see that memcpy will use load/store vector pair with + -mcpu=future. */ + +#ifndef SIZE +#define SIZE 4 +#endif + +extern vector double to[SIZE], from[SIZE]; + +void +copy (void) +{ + __builtin_memcpy (to, from, sizeof (to)); + return; +} + +/* { dg-final { scan-assembler {\mlxvpx?\M} } } */ +/* { dg-final { scan-assembler {\mstxvpx?\M} } } */