[PATCH 7/13 ver 3] rs6000, add overloaded vec_sel with int128 arguments

Kewen.Lin linkw@linux.ibm.com
Tue Jun 4 05:58:20 GMT 2024


Hi,

on 2024/5/30 00:03, Carl Love wrote:
> This was patch 6 in the previous series.  Updated the documentation file per the comments.  No functional changes to the patch.
> 
>                           Carl 
> ------------------------------------------------------------
> 
> rs6000, add overloaded vec_sel with int128 arguments
> 
> Extend the vec_sel built-in to take three signed/unsigned int128 arguments
> and return a signed/unsigned int128 result.
> 
> Extending the vec_sel built-in makes the existing buit-ins
> __builtin_vsx_xxsel_1ti and __builtin_vsx_xxsel_1ti_uns obsolete.  The
> patch removes these built-ins.
> 
> The patch adds documentation and test cases for the new overloaded vec_sel
> built-ins.
> 
> gcc/ChangeLog:
> 	* config/rs6000/rs6000-builtins.def (__builtin_vsx_xxsel_1ti,
> 	__builtin_vsx_xxsel_1ti_uns): Remove built-in definitions.
> 	* config/rs6000/rs6000-overload.def (vec_sel): Add new overloaded
> 	definitions.
> 	* doc/extend.texi: Add documentation for new vec_sel instances.
> 
> gcc/testsuite/ChangeLog:
> 	* gcc.target/powerpc/vec-sel-runnable-i128.c: New test file.
> ---
>  gcc/config/rs6000/rs6000-builtins.def         |   6 -
>  gcc/config/rs6000/rs6000-overload.def         |   4 +
>  gcc/doc/extend.texi                           |  12 ++
>  .../powerpc/vec-sel-runnable-i128.c           | 129 ++++++++++++++++++
>  4 files changed, 145 insertions(+), 6 deletions(-)
>  create mode 100644 gcc/testsuite/gcc.target/powerpc/vec-sel-runnable-i128.c
> 
> diff --git a/gcc/config/rs6000/rs6000-builtins.def b/gcc/config/rs6000/rs6000-builtins.def
> index 13e36df008d..ea0da77f13e 100644
> --- a/gcc/config/rs6000/rs6000-builtins.def
> +++ b/gcc/config/rs6000/rs6000-builtins.def
> @@ -1904,12 +1904,6 @@
>    const vuc __builtin_vsx_xxsel_16qi_uns (vuc, vuc, vuc);
>      XXSEL_16QI_UNS vector_select_v16qi_uns {}
>  
> -  const vsq __builtin_vsx_xxsel_1ti (vsq, vsq, vsq);
> -    XXSEL_1TI vector_select_v1ti {}
> -
> -  const vsq __builtin_vsx_xxsel_1ti_uns (vsq, vsq, vsq);
> -    XXSEL_1TI_UNS vector_select_v1ti_uns {}
> -
>    const vd __builtin_vsx_xxsel_2df (vd, vd, vd);
>      XXSEL_2DF vector_select_v2df {}
>  
> diff --git a/gcc/config/rs6000/rs6000-overload.def b/gcc/config/rs6000/rs6000-overload.def
> index 4d857bb1af3..a210c5ad10d 100644
> --- a/gcc/config/rs6000/rs6000-overload.def
> +++ b/gcc/config/rs6000/rs6000-overload.def
> @@ -3274,6 +3274,10 @@
>      VSEL_2DF  VSEL_2DF_B
>    vd __builtin_vec_sel (vd, vd, vull);
>      VSEL_2DF  VSEL_2DF_U
> +  vsq __builtin_vec_sel (vsq, vsq, vsq);
> +    VSEL_1TI  VSEL_1TI_S
> +  vuq __builtin_vec_sel (vuq, vuq, vuq);
> +    VSEL_1TI_UNS  VSEL_1TI_U

I just noticed that for integral types, such as: signed/unsigned int, we have six instances:

  vsi __builtin_vec_sel (vsi, vsi, vbi);
    VSEL_4SI  VSEL_4SI_B
  vsi __builtin_vec_sel (vsi, vsi, vui);
    VSEL_4SI  VSEL_4SI_U
  vui __builtin_vec_sel (vui, vui, vbi);
    VSEL_4SI_UNS  VSEL_4SI_UB
  vui __builtin_vec_sel (vui, vui, vui);
    VSEL_4SI_UNS  VSEL_4SI_UU
  vbi __builtin_vec_sel (vbi, vbi, vbi);
    VSEL_4SI_UNS  VSEL_4SI_BB
  vbi __builtin_vec_sel (vbi, vbi, vui);

It considers the control vector can only have unsigned and bool types, also consider the
return type can be bool.  It aligns with what PVIPR defines, so here we should have:

vsq __builtin_vec_sel (vsq, vsq, vbq);
vsq __builtin_vec_sel (vsq, vsq, vuq);
vuq __builtin_vec_sel (vuq, vuq, vbq);
vuq __builtin_vec_sel (vuq, vuq, vuq);
vbq __builtin_vec_sel (vbq, vbq, vbq);
vbq __builtin_vec_sel (vbq, vbq, vuq);

Sorry that I didn't find this in the previous review.


>  ; The following variants are deprecated.
>    vsll __builtin_vec_sel (vsll, vsll, vsll);
>      VSEL_2DI_B  VSEL_2DI_S
> diff --git a/gcc/doc/extend.texi b/gcc/doc/extend.texi
> index b88e61641a2..0756230b19e 100644
> --- a/gcc/doc/extend.texi
> +++ b/gcc/doc/extend.texi
> @@ -21372,6 +21372,18 @@ Additional built-in functions are available for the 64-bit PowerPC
>  family of processors, for efficient use of 128-bit floating point
>  (@code{__float128}) values.
>  
> +Vector select
> +
> +@smallexample
> +vector signed __int128 vec_sel (vector signed __int128,
> +               vector signed __int128, vector signed __int128);
> +vector unsigned __int128 vec_sel (vector unsigned __int128,
> +               vector unsigned __int128, vector unsigned __int128);
> +@end smallexample

As above, the documentation here has to consider vector bool __int128 and note that
the control vector are of type either vector unsigned __int128 or vector bool __int128.

> +
> +The instance is an extension of the exiting overloaded built-in @code{vec_sel}
> +that is documented in the PVIPR.
> +
>  @node Basic PowerPC Built-in Functions Available on ISA 2.06
>  @subsubsection Basic PowerPC Built-in Functions Available on ISA 2.06
>  
> diff --git a/gcc/testsuite/gcc.target/powerpc/vec-sel-runnable-i128.c b/gcc/testsuite/gcc.target/powerpc/vec-sel-runnable-i128.c
> new file mode 100644
> index 00000000000..d82225cc847
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/powerpc/vec-sel-runnable-i128.c
> @@ -0,0 +1,129 @@
> +/* { dg-do run } */
> +/* { dg-require-effective-target vmx_hw } */
> +/* { dg-options "-save-temps" } */
> +/* { dg-final { scan-assembler-times "xxsel" 2 } } */

Nit: Can we rename this case to builtins-10.c and separate it into
one dg-do compile and the other dg-do "run" (like some builtins-*.c
which have *-x.c and *-x-runnable.c)?

It needs some more adjustments as the overloaded instances change.

BR,
Kewen

> +
> +#include <altivec.h>
> +
> +#define DEBUG 0
> +
> +#if DEBUG
> +#include <stdio.h>
> +void print_i128 (unsigned __int128 val)
> +{
> +  printf(" 0x%016llx%016llx",
> +         (unsigned long long)(val >> 64),
> +         (unsigned long long)(val & 0xFFFFFFFFFFFFFFFF));
> +}
> +#endif
> +
> +extern void abort (void);
> +
> +union convert_union {
> +  vector signed __int128    s128;
> +  vector unsigned __int128  u128;
> +  char  val[16];
> +} convert;
> +
> +int check_u128_result(vector unsigned __int128 vresult_u128,
> +		      vector unsigned __int128 expected_vresult_u128)
> +{
> +  /* Use a for loop to check each byte manually so the test case will run
> +     with ISA 2.06.
> +
> +     Return 1 if they match, 0 otherwise.  */
> +
> +  int i;
> +
> +  union convert_union result;
> +  union convert_union expected;
> +
> +  result.u128 = vresult_u128;
> +  expected.u128 = expected_vresult_u128;
> +
> +  /* Check if each byte of the result and expected match. */
> +  for (i = 0; i < 16; i++)
> +    {
> +      if (result.val[i] != expected.val[i])
> +	return 0;
> +    }
> +  return 1;
> +}
> +
> +int check_s128_result(vector signed __int128 vresult_s128,
> +		      vector signed __int128 expected_vresult_s128)
> +{
> +  /* Convert the arguments to unsigned, then check equality.  */
> +  union convert_union result;
> +  union convert_union expected;
> +
> +  result.s128 = vresult_s128;
> +  expected.s128 = expected_vresult_s128;
> +
> +  return check_u128_result (result.u128, expected.u128);
> +}
> +
> +
> +int
> +main (int argc, char *argv [])
> +{
> +  int i;
> +  
> +  vector signed __int128 src_va_s128;
> +  vector signed __int128 src_vb_s128;
> +  vector signed __int128 src_vc_s128;
> +  vector signed __int128 vresult_s128;
> +  vector signed __int128 expected_vresult_s128;
> +
> +  vector unsigned __int128 src_va_u128;
> +  vector unsigned __int128 src_vb_u128;
> +  vector unsigned __int128 src_vc_u128;
> +  vector unsigned __int128 vresult_u128;
> +  vector unsigned __int128 expected_vresult_u128;
> +
> +  src_va_s128 = (vector signed __int128) {0x123456789ABCDEF0};
> +  src_vb_s128 = (vector signed __int128) {0xFEDCBA9876543210};
> +  src_vc_s128 = (vector signed __int128) {0x3333333333333333};
> +  expected_vresult_s128 = (vector signed __int128) {0x32147658ba9cfed0};
> +
> +  /* Signed arguments.  */
> +  vresult_s128 = vec_sel (src_va_s128, src_vb_s128, src_vc_s128);
> +
> +  if (!check_s128_result (vresult_s128, expected_vresult_s128))
> +#if DEBUG
> +    {
> +      printf ("ERROR, vec_sel (src_va_s128, src_vb_s128, src_vc_s128) result does not match expected output.\n");
> +      printf ("  Result:          ");
> +      print_i128 ((unsigned __int128) vresult_s128);
> +      printf ("\n  Expected result: ");
> +      print_i128 ((unsigned __int128) expected_vresult_s128);
> +      printf ("\n");
> +    }
> +#else
> +    abort ();
> +#endif
> +
> +  src_va_u128 = (vector unsigned __int128) {0x13579ACE02468BDF};
> +  src_vb_u128 = (vector unsigned __int128) {0xA987654FEDCB3210};
> +  src_vc_u128 = (vector unsigned __int128) {0x5555555555555555};
> +  expected_vresult_u128 = (vector unsigned __int128) {0x0307CFCF47439A9A};
> +
> +  /* Unigned arguments.  */
> +  vresult_u128 = vec_sel (src_va_u128, src_vb_u128, src_vc_u128);
> +
> +  if (!check_u128_result (vresult_u128, expected_vresult_u128))
> +#if DEBUG
> +    {
> +      printf ("ERROR, vec_sel (src_va_u128, src_vb_u128, src_vc_u128) result does not match expected output.\n");
> +      printf ("  Result:          ");
> +      print_i128 ((unsigned __int128) vresult_u128);
> +      printf ("\n  Expected result: ");
> +      print_i128 ((unsigned __int128) expected_vresult_u128);
> +      printf ("\n");
> +    }
> +#else
> +    abort ();
> +#endif
> +
> +    return 0;
> +}



More information about the Gcc-patches mailing list