Hi,
on 2024/4/20 05:18, Carl Love wrote:
> rs6000, remove __builtin_vsx_vperm_* built-ins
>
> The undocumented built-ins:
> __builtin_vsx_vperm_16qi_uns,
> __builtin_vsx_vperm_1ti,
> __builtin_vsx_vperm_1ti_uns,
> __builtin_vsx_vperm_2df,
> __builtin_vsx_vperm_2di,
> __builtin_vsx_vperm_2di_uns,
> __builtin_vsx_vperm_4sf,
> __builtin_vsx_vperm_4si,
> __builtin_vsx_vperm_4si_uns
>
> are duplicats of the __builtin_altivec_* builtins that are used by
> the overloaded vec_perm built-in that is documented in the PVIPR.
>
> gcc/ChangeLog:
> * config/rs6000/rs6000-builtins.def (__builtin_vsx_vperm_16qi_uns,
> __builtin_vsx_vperm_1ti, __builtin_vsx_vperm_1ti_uns,
> __builtin_vsx_vperm_2df, __builtin_vsx_vperm_2di,
> __builtin_vsx_vperm_2di_uns, __builtin_vsx_vperm_4sf,
> __builtin_vsx_vperm_4si, __builtin_vsx_vperm_4si_uns): Remove
> built-in definitions and comments.
>
> gcc/testsuite/ChangeLog:
> * gcc.target/powerpc/vsx-builtin-3.c (__builtin_vsx_vperm_16qi_uns,
>__builtin_vsx_vperm_1ti, __builtin_vsx_vperm_1ti_uns,
> __builtin_vsx_vperm_2df, __builtin_vsx_vperm_2di,
> __builtin_vsx_vperm_2di_uns, __builtin_vsx_vperm_4sf,
> __builtin_vsx_vperm_4si, __builtin_vsx_vperm_4si_uns): Remove
> test cases.
> ---
> gcc/config/rs6000/rs6000-builtins.def | 33 ---
> .../gcc.target/powerpc/vsx-builtin-3.c| 20 ---
> 2 files changed, 53 deletions(-)
>
> diff --git a/gcc/config/rs6000/rs6000-builtins.def
> b/gcc/config/rs6000/rs6000-builtins.def
> index 3c409d729ea..f33564d3d9c 100644
> --- a/gcc/config/rs6000/rs6000-builtins.def
> +++ b/gcc/config/rs6000/rs6000-builtins.def
> @@ -1529,39 +1529,6 @@
>const vf __builtin_vsx_uns_floato_v2di (vsll);
> UNS_FLOATO_V2DI unsfloatov2di {}
>
> -; These are duplicates of __builtin_altivec_* counterparts, and are being
> -; kept for backwards compatibility. The reason for their existence is
> -; unclear. TODO: Consider deprecation/removal at some point.
> - const vsc __builtin_vsx_vperm_16qi (vsc, vsc, vuc);
> -VPERM_16QI_X altivec_vperm_v16qi {}
> -
> - const vuc __builtin_vsx_vperm_16qi_uns (vuc, vuc, vuc);
> -VPERM_16QI_UNS_X altivec_vperm_v16qi_uns {}
> -
> - const vsq __builtin_vsx_vperm_1ti (vsq, vsq, vsc);
> -VPERM_1TI_X altivec_vperm_v1ti {}
> -
> - const vsq __builtin_vsx_vperm_1ti_uns (vsq, vsq, vsc);
> -VPERM_1TI_UNS_X altivec_vperm_v1ti_uns {}
> -
> - const vd __builtin_vsx_vperm_2df (vd, vd, vuc);
> -VPERM_2DF_X altivec_vperm_v2df {}
> -
> - const vsll __builtin_vsx_vperm_2di (vsll, vsll, vuc);
> -VPERM_2DI_X altivec_vperm_v2di {}
> -
> - const vull __builtin_vsx_vperm_2di_uns (vull, vull, vuc);
> -VPERM_2DI_UNS_X altivec_vperm_v2di_uns {}
> -
> - const vf __builtin_vsx_vperm_4sf (vf, vf, vuc);
> -VPERM_4SF_X altivec_vperm_v4sf {}
> -
> - const vsi __builtin_vsx_vperm_4si (vsi, vsi, vuc);
> -VPERM_4SI_X altivec_vperm_v4si {}
> -
> - const vui __builtin_vsx_vperm_4si_uns (vui, vui, vuc);
> -VPERM_4SI_UNS_X altivec_vperm_v4si_uns {}
> -
>const vss __builtin_vsx_vperm_8hi (vss, vss, vuc);
> VPERM_8HI_X altivec_vperm_v8hi {}
>
> diff --git a/gcc/testsuite/gcc.target/powerpc/vsx-builtin-3.c
> b/gcc/testsuite/gcc.target/powerpc/vsx-builtin-3.c
> index 01f35dad713..35ea31b2616 100644
> --- a/gcc/testsuite/gcc.target/powerpc/vsx-builtin-3.c
> +++ b/gcc/testsuite/gcc.target/powerpc/vsx-builtin-3.c
> @@ -2,7 +2,6 @@
> /* { dg-skip-if "" { powerpc*-*-darwin* } } */
> /* { dg-require-effective-target powerpc_vsx_ok } */
> /* { dg-options "-O2 -mdejagnu-cpu=power7" } */
> -/* { dg-final { scan-assembler "vperm" } } */
> /* { dg-final { scan-assembler "xvrdpi" } } */
> /* { dg-final { scan-assembler "xvrdpic" } } */
> /* { dg-final { scan-assembler "xvrdpim" } } */
> @@ -56,25 +55,6 @@ extern __vector unsigned long long ull[][4];
> extern __vector __bool long bl[][4];
> #endif
>
> -int do_perm(void)
> -{
> - int i = 0;
> -
> - si[i][0] = __builtin_vsx_vperm_4si (si[i][1], si[i][2], uc[i][3]); i++;
> - ss[i][0] = __builtin_vsx_vperm_8hi (ss[i][1], ss[i][2], uc[i][3]); i++;
> - sc[i][0] = __builtin_vsx_vperm_16qi (sc[i][1], sc[i][2], uc[i][3]); i++;
> - f[i][0] = __builtin_vsx_vperm_4sf (f[i][1], f[i][2], uc[i][3]); i++;
> - d[i][0] = __builtin_vsx_vperm_2df (d[i][1], d[i][2], uc[i][3]); i++;
> -
> - si[i][0] = __builtin_vsx_vperm (si[i][1], si[i][2], uc[i][3]); i++;
> - ss[i][0] = __builtin_vsx_vperm (ss[i][1], ss[i][2], uc[i][3]); i++;
> - sc[i][0] = __builtin_vsx_vperm (sc[i][1], sc[i][2], uc[i][3]); i++;
> - f[i][0] = __builtin_vsx_vperm (f[i][1], f[i][2], uc[i][3]); i++;
> - d[i][0] = __builtin_vsx_vperm (d[i][1], d[i][2], uc[i][3]); i++;
> -
> - return i;
> -}
> -
I prefer to just relace these __builtin_vsx_vperm with vec_perm,
OK with this tweaked (also keep the above removed vperm scan), thanks!
BR,
Kewen
> int do_xxperm (void)
> {
>int i