Hi! I observed recently that a couple of Power10 instructions and built-in functions were somehow not implemented. This patch adds one of them (vmsumcud). Although this isn't normally stage-4 material, this is really simple and carries no discernible risk, so I hope it can be considered.
Bootstrapped and tested on powerpc64le-linux-gnu with no regressions. Is this okay for trunk? Thanks! Bill 2022-02-07 Bill Schmidt <wschm...@linux.ibm.com> gcc/ * config/rs6000/rs6000-builtins.def (VMSUMCUD): New. * config/rs6000/rs6000-overload.def (VEC_MSUMC): New. * config/rs6000/vsx.md (UNSPEC_VMSUMCUD): New constant. (vmsumcud): New define_insn. gcc/testsuite/ * gcc.target/powerpc/vec-msumc.c: New test. --- gcc/config/rs6000/rs6000-builtins.def | 3 ++ gcc/config/rs6000/rs6000-overload.def | 4 ++ gcc/config/rs6000/vsx.md | 13 +++++++ gcc/testsuite/gcc.target/powerpc/vec-msumc.c | 39 ++++++++++++++++++++ 4 files changed, 59 insertions(+) create mode 100644 gcc/testsuite/gcc.target/powerpc/vec-msumc.c diff --git a/gcc/config/rs6000/rs6000-builtins.def b/gcc/config/rs6000/rs6000-builtins.def index d0ea54d77e4..846c0bafd45 100644 --- a/gcc/config/rs6000/rs6000-builtins.def +++ b/gcc/config/rs6000/rs6000-builtins.def @@ -3497,6 +3497,9 @@ const signed int __builtin_altivec_vstrihr_p (vss); VSTRIHR_P vstrir_p_v8hi {} + const vuq __builtin_vsx_vmsumcud (vull, vull, vuq); + VMSUMCUD vmsumcud {} + const signed int __builtin_vsx_xvtlsbb_all_ones (vsc); XVTLSBB_ONES xvtlsbbo {} diff --git a/gcc/config/rs6000/rs6000-overload.def b/gcc/config/rs6000/rs6000-overload.def index 5e38d597722..44e2945aaa0 100644 --- a/gcc/config/rs6000/rs6000-overload.def +++ b/gcc/config/rs6000/rs6000-overload.def @@ -2456,6 +2456,10 @@ vuq __builtin_vec_msum (vull, vull, vuq); VMSUMUDM VMSUMUDM_U +[VEC_MSUMC, vec_msumc, __builtin_vec_msumc] + vuq __builtin_vec_msumc (vull, vull, vuq); + VMSUMCUD + [VEC_MSUMS, vec_msums, __builtin_vec_msums] vui __builtin_vec_msums (vus, vus, vui); VMSUMUHS diff --git a/gcc/config/rs6000/vsx.md b/gcc/config/rs6000/vsx.md index 88053f11e29..e4904102526 100644 --- a/gcc/config/rs6000/vsx.md +++ b/gcc/config/rs6000/vsx.md @@ -372,6 +372,7 @@ (define_c_enum "unspec" UNSPEC_REPLACE_UN UNSPEC_VDIVES UNSPEC_VDIVEU + UNSPEC_VMSUMCUD UNSPEC_XXEVAL UNSPEC_XXSPLTIW UNSPEC_XXSPLTIDP @@ -6615,3 +6616,15 @@ (define_split emit_move_insn (operands[0], tmp4); DONE; }) + +;; vmsumcud +(define_insn "vmsumcud" +[(set (match_operand:V1TI 0 "register_operand" "+v") + (unspec:V1TI [(match_operand:V2DI 1 "register_operand" "v") + (match_operand:V2DI 2 "register_operand" "v") + (match_operand:V1TI 3 "register_operand" "v")] + UNSPEC_VMSUMCUD))] + "TARGET_POWER10" + "vmsumcud %0,%1,%2,%3" + [(set_attr "type" "vecsimple")] +) diff --git a/gcc/testsuite/gcc.target/powerpc/vec-msumc.c b/gcc/testsuite/gcc.target/powerpc/vec-msumc.c new file mode 100644 index 00000000000..524a2225c6c --- /dev/null +++ b/gcc/testsuite/gcc.target/powerpc/vec-msumc.c @@ -0,0 +1,39 @@ +/* { dg-do run { target { power10_hw } } } */ +/* { dg-require-effective-target power10_ok } */ +/* { dg-options "-mdejagnu-cpu=power10 -O2" } */ +#include <altivec.h> + +#define DEBUG 0 + +#if DEBUG +#include <stdio.h> +#endif + +extern void abort (void); + +int +main () +{ + vector unsigned long long arg1, arg2; + vector unsigned __int128 arg3, result, expected; + unsigned __int128 c = (unsigned __int128) (-1); /* 2^128 - 1 */ + + arg1 = (vector unsigned long long) { 111ULL, 300ULL }; + arg2 = (vector unsigned long long) { 700ULL, 222ULL }; + arg3 = (vector unsigned __int128) { c }; + expected = (vector unsigned __int128) { 1 }; + + result = vec_msumc (arg1, arg2, arg3); + if (result[0] != expected[0]) + { +#if DEBUG + printf ("ERROR, expected %d, result %d\n", + (unsigned int) expected[0], + (unsigned int) result[0]); +#else + abort (); +#endif + } + + return 0; +} -- 2.27.0