Kewen:
On 6/3/24 22:58, Kewen.Lin wrote:
> Hi,
>
> on 2024/5/30 00:10, Carl Love wrote:
>> This was patch 10 from the previous series. The patch was updated to
>> address feedback comments.
>>
>> Carl
>> ---------------------------------------------------
>>
>> rs6000, extend vec_xxpermdi built-in for __int128 args
>>
>> Add a new signed and unsigned overloaded instances for vec_xxpermdi
>>
>> __int128 vec_xxpermdi (__int128, __int128, const int);
>> __uint128 vec_xxpermdi (__uint128, __uint128, const int);
>>
>> Update the documentation to include a reference to the new built-in
>> instances.
>>
>> Add test cases for the new overloaded instances.
>>
>> gcc/ChangeLog:
>> * config/rs6000/rs6000-overload.def (vec_xxpermdi): Add new
>> overloaded built-in instances.
>> * doc/extend.texi: Add documentation for new overloaded built-in
>> instances.
>>
>> gcc/testsuite/ChangeLog:gcc/testsuite/ChangeLog:
>> * gcc.target/powerpc/vec_perm-runnable-i128.c: New test file.
>> ---
>> gcc/config/rs6000/rs6000-overload.def | 4 +
>> gcc/doc/extend.texi | 2 +
>> .../powerpc/vec_perm-runnable-i128.c | 229 ++++++++++++++++++
>> 3 files changed, 235 insertions(+)
>> create mode 100644 gcc/testsuite/gcc.target/powerpc/vec_perm-runnable-i128.c
>>
>> diff --git a/gcc/config/rs6000/rs6000-overload.def
>> b/gcc/config/rs6000/rs6000-overload.def
>> index a210c5ad10d..45000f161e4 100644
>> --- a/gcc/config/rs6000/rs6000-overload.def
>> +++ b/gcc/config/rs6000/rs6000-overload.def
>> @@ -4932,6 +4932,10 @@
>> XXPERMDI_4SF XXPERMDI_VF
>> vd __builtin_vsx_xxpermdi (vd, vd, const int);
>> XXPERMDI_2DF XXPERMDI_VD
>> + vsq __builtin_vsx_xxpermdi (vsq, vsq, const int);
>> + XXPERMDI_1TI XXPERMDI_1TI
>> + vuq __builtin_vsx_xxpermdi (vuq, vuq, const int);
>> + XXPERMDI_1TI XXPERMDI_1TUI
>
> Nits:
> - Move them before "vf __builtin_vsx_xxpermdi (vf, vf, const int);" so
> they are close to instances for other integral types.
> - As the existing name convention, _{SQ,UQ} are better.
>
> vsq __builtin_vsx_xxpermdi (vsq, vsq, const int);
> XXPERMDI_1TI XXPERMDI_1SQ
> vuq __builtin_vsx_xxpermdi (vuq, vuq, const int);
> XXPERMDI_1TI XXPERMDI_1UQ
>
OK, moved the definitions up and changed the names.
>>
>> [VEC_XXSLDWI, vec_xxsldwi, __builtin_vsx_xxsldwi]
>> vsc __builtin_vsx_xxsldwi (vsc, vsc, const int);
>> diff --git a/gcc/doc/extend.texi b/gcc/doc/extend.texi
>> index 0756230b19e..edfef1bdab7 100644
>> --- a/gcc/doc/extend.texi
>> +++ b/gcc/doc/extend.texi
>> @@ -22555,6 +22555,8 @@ void vec_vsx_st (vector bool char, int, signed char
>> *);
>> vector double vec_xxpermdi (vector double, vector double, const int);
>> vector float vec_xxpermdi (vector float, vector float, const int);
>> vector long long vec_xxpermdi (vector long long, vector long long, const
>> int);
>
>> +vector __int128 vec_xxpermdi (vector __int128, vector __int128, const int);
>> +vector __int128 vec_xxpermdi (vector __uint128, vector __uint128, const
>> int);
>
> Nit: These two lines break the long long and unsigned long long lines, can
> you move
> them one line upward? Also using the explicit "signed" and "unsigned" would
> be
> better than "__{u,}int128".
>
Yup, I didn't get them in the right place. Fixed.
>> vector unsigned long long vec_xxpermdi (vector unsigned long long,
>> vector unsigned long long, const
>> int);
>> vector int vec_xxpermdi (vector int, vector int, const int);
>> diff --git a/gcc/testsuite/gcc.target/powerpc/vec_perm-runnable-i128.c
>> b/gcc/testsuite/gcc.target/powerpc/vec_perm-runnable-i128.c
>> new file mode 100644
>> index 00000000000..2d5dce09404
>> --- /dev/null
>> +++ b/gcc/testsuite/gcc.target/powerpc/vec_perm-runnable-i128.c
>> @@ -0,0 +1,229 @@
>> +/* { dg-do run } */
>> +/* { dg-require-effective-target vmx_hw } */
>> +/* { dg-options "-save-temps" } */
>
> Nit: dg-options line isn't needed as it doesn't check assembly.
Removed the save-temps.
>
> 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 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_va_s128 = src_va_s128 << 64;
>> + src_va_s128 |= (vector signed __int128) {0x22446688AACCEE00};
>> + src_vb_s128 = (vector signed __int128) {0xFEDCBA9876543210};
>> + src_vb_s128 = src_vb_s128 << 64;
>> + src_vb_s128 |= (vector signed __int128) {0x3333333333333333};
>> +
>> + src_va_u128 = (vector unsigned __int128) {0x13579ACE02468BDF};
>> + src_va_u128 = src_va_u128 << 64;
>> + src_va_u128 |= (vector unsigned __int128) {0x1133557799BBDD00};
>> + src_vb_u128 = (vector unsigned __int128) {0xA987654FEDCB3210};
>> + src_vb_u128 = src_vb_u128 << 64;
>> + src_vb_u128 |= (vector unsigned __int128) {0x5555555555555555};
>> +
>> +
>> + /* Signed 128-bit arguments. */
>> + vresult_s128 = vec_xxpermdi (src_va_s128, src_vb_s128, 0x1);
>> +
>> +#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
>> + /* BE expected results */
>> + expected_vresult_s128 = (vector signed __int128) {0x123456789ABCDEF0};
>> + expected_vresult_s128 = expected_vresult_s128 << 64;
>> + expected_vresult_s128 |= (vector signed __int128) {0x3333333333333333};
>> +#else
>> + /* LE expected results */
>> + expected_vresult_s128 = (vector signed __int128) {0xFEDCBA9876543210};
>> + expected_vresult_s128 = expected_vresult_s128 << 64;
>> + expected_vresult_s128 |= (vector signed __int128) {0x22446688AACCEE00};
>> +#endif
>> +
>> + if (!check_s128_result (vresult_s128, expected_vresult_s128))
>> +#if DEBUG
>> + {
>> + printf ("ERROR, vec_xxpermdi (src_va_s128, src_vb_s128, 0x1) result
>> does not match expected output.\n");
>> + printf (" src_va_s128: ");
>> + print_i128 ((unsigned __int128) src_va_s128);
>> + printf ("\n src_vb_s128: ");
>> + print_i128 ((unsigned __int128) src_vb_s128);
>> + printf ("\n Result: ");
>> + print_i128 ((unsigned __int128) vresult_s128);
>> + printf ("\n Expected result: ");
>> + print_i128 ((unsigned __int128) expected_vresult_s128);
>> + printf ("\n");
>> + }
>> +#else
>> + abort ();
>> +#endif
>> +
>> + vresult_s128 = vec_xxpermdi (src_va_s128, src_vb_s128, 0x2);
>> +
>> +#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
>> + /* BE expected results */
>> + expected_vresult_s128 = (vector signed __int128) {0x22446688AACCEE00};
>> + expected_vresult_s128 = expected_vresult_s128 << 64;
>> + expected_vresult_s128 |= (vector signed __int128) {0xFEDCBA9876543210};
>> +#else
>> + /* LE expected results */
>> + expected_vresult_s128 = (vector signed __int128) {0x3333333333333333};
>> + expected_vresult_s128 = expected_vresult_s128 << 64;
>> + expected_vresult_s128 |= (vector signed __int128) {0x123456789ABCDEF0};
>> +#endif
>> +
>> + if (!check_s128_result (vresult_s128, expected_vresult_s128))
>> +#if DEBUG
>> + {
>> + printf ("ERROR, vec_xxpermdi (src_va_s128, src_vb_s128, 0x2) result
>> does not match expected output.\n");
>> + printf (" src_va_s128: ");
>> + print_i128 ((unsigned __int128) src_va_s128);
>> + printf ("\n src_vb_s128: ");
>> + print_i128 ((unsigned __int128) src_vb_s128);
>> + printf ("\n Result: ");
>> + print_i128 ((unsigned __int128) vresult_s128);
>> + printf ("\n Expected result: ");
>> + print_i128 ((unsigned __int128) expected_vresult_s128);
>> + printf ("\n");
>> + }
>> +#else
>> + abort ();
>> +#endif
>> +
>> + /* Unigned arguments. */
>> + vresult_u128 = vec_xxpermdi (src_va_u128, src_vb_u128, 0x1);
>> +
>> + #if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
>> + /* BE expected results */
>> + expected_vresult_u128 = (vector unsigned __int128) {0x13579ACE02468BDF};
>> + expected_vresult_u128 = expected_vresult_u128 << 64;
>> + expected_vresult_u128 |= (vector unsigned __int128) {0x5555555555555555};
>> +#else
>> + /* LE expected results */
>> + expected_vresult_u128 = (vector unsigned __int128) {0xA987654FEDCB3210};
>> + expected_vresult_u128 = expected_vresult_u128 << 64;
>> + expected_vresult_u128 |= (vector unsigned __int128) {0x1133557799BBDD00};
>> +#endif
>> +
>> + if (!check_u128_result (vresult_u128, expected_vresult_u128))
>> +#if DEBUG
>> + {
>> + printf ("ERROR, vec_xxpermdi (src_va_u128, src_vb_u128, 0x1) result
>> does not match expected output.\n");
>> + printf (" src_va_s128: ");
>> + print_i128 ((unsigned __int128) src_va_s128);
>> + printf ("\n src_vb_s128: ");
>> + print_i128 ((unsigned __int128) src_vb_s128);
>> + printf ("\n Result: ");
>> + print_i128 ((unsigned __int128) vresult_u128);
>> + printf ("\n Expected result: ");
>> + print_i128 ((unsigned __int128) expected_vresult_u128);
>> + printf ("\n");
>> + }
>> +#else
>> + abort ();
>> +#endif
>> +
>> + /* Unigned arguments. */
>> + vresult_u128 = vec_xxpermdi (src_va_u128, src_vb_u128, 0x2);
>> +
>> +#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
>> + /* BE expected results */
>> + expected_vresult_u128 = (vector unsigned __int128) {0x1133557799BBDD00};
>> + expected_vresult_u128 = expected_vresult_u128 << 64;
>> + expected_vresult_u128 |= (vector unsigned __int128) {0xA987654FEDCB3210};
>> +#else
>> + /* LE expected results */
>> + expected_vresult_u128 = (vector unsigned __int128) {0x5555555555555555};
>> + expected_vresult_u128 = expected_vresult_u128 << 64;
>> + expected_vresult_u128 |= (vector unsigned __int128) {0x13579ACE02468BDF};
>> +#endif
>> +
>> + if (!check_u128_result (vresult_u128, expected_vresult_u128))
>> +#if DEBUG
>> + {
>> + printf ("ERROR, vec_xxpermdi (src_va_u128, src_vb_u128, 0x2) result
>> does not match expected output.\n");
>> + printf (" src_va_s128: ");
>> + print_i128 ((unsigned __int128) src_va_s128);
>> + printf ("\n src_vb_s128: ");
>> + print_i128 ((unsigned __int128) src_vb_s128);
>> + printf ("\n 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;
>> +}
>
