| Message ID | eaf7c82e-edea-4b54-8be3-7c725e3d719a@linux.ibm.com |
|---|---|
| State | New |
| Headers | show |
| Series | rs6000, remove redundant built-ins and add more test cases | expand |
Hi Carl, on 2024/8/8 01:15, Carl Love wrote: > > GCC maintainers: > > The following patch adds missing test cases for the overloaded vec_perm built-in. It also fixes and issue with printing the 128-bit values in the DEBUG section that was noticed when adding the additional test cases. > > The patch has been tested on Power 10 LE and BE with no regressions. > > Please let me know if it is acceptable for mainline. Thanks. > > Carl > > ------------------------------------------------------------- > > rs6000, add testcases to the overloaded vec_perm built-in > > The overloaded vec_perm built-in supports permuting signed and unsigned > vectors of char, bool char, short int, short bool, int, bool, > long long int, long long bool, int128, float and double. However, not all > of the supported arguments are included in the test cases. This patch adds > the missing test cases. > > Additionally, in the 128-bit debug print statements the expected result and > the result need to be cast to unsigned long long to print correctly. The > patch makes this additional change to the print statements. > > gcc/ChangeLog: > * doc/extend.texi: Fix spelling mistake in description of the > vec_sel built-in. > Add documentation of the 128-bit vec_perm instance. > > gcc/testsuite/ChangeLog: > * gcc.target/powerpc/vsx-builtin-3.c: Add vec_perm test cases for > arguments of type vector signed long long int, long long bool, > bool, bool short, bool char and pixel, > vector unsigned long long int, unsigned int, unsigned short int, > unsigned char. > Cast arguments for debug prints to unsigned long long. > * gcc.target/powerpc/builtins-4-int128-runnable.c: Add vec_perm > test cases for signed and unsigned int128 arguments. Nit: Some changelog lines have unnecessary newlines and spaces. > --- > gcc/doc/extend.texi | 12 +- > .../powerpc/builtins-4-int128-runnable.c | 108 +++++++++++++++--- > .../gcc.target/powerpc/vsx-builtin-3.c | 18 +++ > 3 files changed, 121 insertions(+), 17 deletions(-) > > diff --git a/gcc/doc/extend.texi b/gcc/doc/extend.texi > index 48b27ff9f39..bf6f4094040 100644 > --- a/gcc/doc/extend.texi > +++ b/gcc/doc/extend.texi > @@ -21553,9 +21553,19 @@ vector bool __int128 vec_sel (vector bool __int128, > vector bool __int128, vector unsigned __int128); > @end smallexample > > -The instance is an extension of the exiting overloaded built-in @code{vec_sel} > +The instance is an extension of the existing overloaded built-in @code{vec_sel} > that is documented in the PVIPR. Good catch! > > +@smallexample > +vector signed __int128 vec_perm (vector signed __int128, > + vector signed __int128); > +vector unsigned __int128 vec_perm (vector unsigned __int128, > + vector unsigned __int128); > +@end smallexample > + > +The 128-bit integer arguments for the @code{vec_perm} built-in are in addition > +to the instances that are documented in the PVIPR. Nit: Maybe just copy the above wording for @code{vec_sel} but replaced with @code{vec_perm} to keep them consistent. > + > @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/builtins-4-int128-runnable.c b/gcc/testsuite/gcc.target/powerpc/builtins-4-int128-runnable.c > index 62c11132cf3..c61b0ecb854 100644 > --- a/gcc/testsuite/gcc.target/powerpc/builtins-4-int128-runnable.c > +++ b/gcc/testsuite/gcc.target/powerpc/builtins-4-int128-runnable.c > @@ -18,6 +18,16 @@ int main() { > __uint128_t data_u128[100]; > __int128_t data_128[100]; > > +#ifdef __BIG_ENDIAN__ > + vector unsigned char vuc = {0xC, 0xD, 0xE, 0xF, 0x8, 0x9, 0xA, 0xB, > + 0x1C, 0x1D, 0x1E, 0x1F, 0x18, 0x19, 0x1A, 0x1B}; > +#else > + vector unsigned char vuc = {0x4, 0x5, 0x6, 0x7, 0x0, 0x1, 0x2, 0x3, > + 0x14, 0x15, 0x16, 0x17, 0x10, 0x11, 0x12, 0x13}; > +#endif > + > + vector __int128_t vec_128_arg1, vec_128_arg2; > + vector __uint128_t vec_u128_arg1, vec_u128_arg2; > vector __int128_t vec_128_expected1, vec_128_result1; > vector __uint128_t vec_u128_expected1, vec_u128_result1; > signed long long zero = (signed long long) 0; > @@ -37,11 +47,13 @@ int main() { > { > #ifdef DEBUG > printf("Error: vec_xl(), vec_128_result1[0] = %lld %llu; ", > - vec_128_result1[0] >> 64, > - vec_128_result1[0] & (__int128_t)0xFFFFFFFFFFFFFFFF); > + (unsigned long long)(vec_128_result1[0] >> 64), > + (unsigned long long)(vec_128_result1[0] > + & (__int128_t)0xFFFFFFFFFFFFFFFF)); > printf("vec_128_expected1[0] = %lld %llu\n", > - vec_128_expected1[0] >> 64, > - vec_128_expected1[0] & (__int128_t)0xFFFFFFFFFFFFFFFF); > + (unsigned long long)(vec_128_expected1[0] >> 64), > + (unsigned long long)(vec_128_expected1[0] > + & (__int128_t)0xFFFFFFFFFFFFFFFF)); > #else > abort (); > #endif > @@ -53,11 +65,13 @@ int main() { > { > #ifdef DEBUG > printf("Error: vec_xl(), vec_u128_result1[0] = %lld; ", > - vec_u128_result1[0] >> 64, > - vec_u128_result1[0] & (__int128_t)0xFFFFFFFFFFFFFFFF); > + (unsigned long long)(vec_u128_result1[0] >> 64), > + (unsigned long long)(vec_u128_result1[0] > + & (__int128_t)0xFFFFFFFFFFFFFFFF)); > printf("vec_u128_expected1[0] = %lld\n", > - vec_u128_expected1[0] >> 64, > - vec_u128_expected1[0] & (__int128_t)0xFFFFFFFFFFFFFFFF); > + (unsigned long long)(vec_u128_expected1[0] >> 64), > + (unsigned long long)(vec_u128_expected1[0] > + & (__int128_t)0xFFFFFFFFFFFFFFFF)); > #else > abort (); > #endif > @@ -76,11 +90,12 @@ int main() { > { > #ifdef DEBUG > printf("Error: vec_xl_be(), vec_128_result1[0] = %llu %llu;", > - vec_128_result1[0] >> 64, > - vec_128_result1[0] & 0xFFFFFFFFFFFFFFFF); > + (unsigned long long)(vec_128_result1[0] >> 64), > + (unsigned long long)(vec_128_result1[0] & 0xFFFFFFFFFFFFFFFF)); > printf(" vec_128_expected1[0] = %llu %llu\n", > - vec_128_expected1[0] >> 64, > - vec_128_expected1[0] & 0xFFFFFFFFFFFFFFFF); > + (unsigned long long)(vec_128_expected1[0] >> 64), > + (unsigned long long)(vec_128_expected1[0] > + & 0xFFFFFFFFFFFFFFFF)); > #else > abort (); > #endif > @@ -98,11 +113,72 @@ int main() { > { > #ifdef DEBUG > printf("Error: vec_xl_be(), vec_u128_result1[0] = %llu %llu;", > - vec_u128_result1[0] >> 64, > - vec_u128_result1[0] & 0xFFFFFFFFFFFFFFFF); > + (unsigned long long)(vec_u128_result1[0] >> 64), > + (unsigned long long)(vec_u128_result1[0] & 0xFFFFFFFFFFFFFFFF)); > + printf(" vec_u128_expected1[0] = %llu %llu\n", > + (unsigned long long)(vec_u128_expected1[0] >> 64), > + (unsigned long long)(vec_u128_expected1[0] > + & 0xFFFFFFFFFFFFFFFF)); > +#else > + abort (); > +#endif > + } > + > + /* vec_perm() tests */ > + vec_128_arg1 = (vector __int128_t){ (__uint128_t)0x1122334455667788ULL }; > + vec_128_arg2 = (vector __int128_t){ (__uint128_t)0xAAABBBCCCDDDEEEF }; > + > +#ifdef __BIG_ENDIAN__ > + vec_128_expected1[0] = 0x5566778811223344ULL; > + vec_128_expected1[0] = (vec_128_expected1[0] << 64) | > + 0xcdddeeefaaabbbccULL; > +#else > + vec_128_expected1[0] = 0xcdddeeefaaabbbccULL; > + vec_128_expected1[0] = (vec_128_expected1[0] << 64) | > + 0x5566778811223344ULL; > +#endif > + > + vec_128_result1 = vec_perm (vec_128_arg1, vec_128_arg2, vuc); > + > + if (vec_128_expected1[0] != vec_128_result1[0]) > + { > +#ifdef DEBUG > + printf("Error: vec_perm(), vec_128_result1[0] = %llu %llu;", > + (unsigned long long)(vec_128_result1[0] >> 64), > + (unsigned long long)(vec_128_result1[0] & 0xFFFFFFFFFFFFFFFF)); > + printf(" vec_128_expected1[0] = %llu %llu\n", > + (unsigned long long)(vec_128_expected1[0] >> 64), > + (unsigned long long)(vec_128_expected1[0] > + & 0xFFFFFFFFFFFFFFFF)); > +#else > + abort (); > +#endif > + } > + vec_u128_arg1 = (vector __uint128_t){ (__uint128_t)0x1122334455667788ULL }; > + vec_u128_arg2 = (vector __uint128_t){ (__uint128_t)0xAAABBBCCCDDDEEEF }; > + > +#ifdef __BIG_ENDIAN__ > + vec_u128_expected1[0] = 0x5566778811223344ULL; > + vec_u128_expected1[0] = (vec_u128_expected1[0] << 64) | > + 0xcdddeeefaaabbbccULL; > +#else > + vec_u128_expected1[0] = 0xcdddeeefaaabbbccULL; > + vec_u128_expected1[0] = (vec_u128_expected1[0] << 64) | > + 0x5566778811223344ULL; > +#endif > + > + vec_u128_result1 = vec_perm (vec_u128_arg1, vec_u128_arg2, vuc); > + > + if (vec_u128_expected1[0] != vec_u128_result1[0]) > + { > +#ifdef DEBUG > + printf("Error: vec_perm(), vec_u128_result1[0] = %llu %llu;", > + (unsigned long long)(vec_u128_result1[0] >> 64), > + (unsigned long long)(vec_u128_result1[0] & 0xFFFFFFFFFFFFFFFF)); > printf(" vec_u128_expected1[0] = %llu %llu\n", > - vec_u128_expected1[0] >> 64, > - vec_u128_expected1[0] & 0xFFFFFFFFFFFFFFFF); > + (unsigned long long)(vec_u128_expected1[0] >> 64), > + (unsigned long long)(vec_u128_expected1[0] > + & 0xFFFFFFFFFFFFFFFF)); > #else > abort (); > #endif > diff --git a/gcc/testsuite/gcc.target/powerpc/vsx-builtin-3.c b/gcc/testsuite/gcc.target/powerpc/vsx-builtin-3.c > index 67c93be1469..b3b76be34b9 100644 > --- a/gcc/testsuite/gcc.target/powerpc/vsx-builtin-3.c > +++ b/gcc/testsuite/gcc.target/powerpc/vsx-builtin-3.c > @@ -39,10 +39,17 @@ > > #include <altivec.h> > > +extern __vector long long int sll[][4]; There is a "extern __vector long long sll[][4]" below. > +extern __vector long long bool bll[][4]; > extern __vector int si[][4]; > +extern __vector bool int bi[][4]; Similar, having "... __vector __bool int bi[][4]" below. > extern __vector short ss[][4]; > +extern __vector bool short bs[][4]; Similar, having "... __vector __bool short bs[][4]" below. > extern __vector signed char sc[][4]; > +extern __vector bool char bc[][4]; Ditto. > +extern __vector pixel p[][4]; Similar, having "... __vector __pixel p[][4]" below. > extern __vector float f[][4]; > +extern __vector unsigned long long int ull[][4]; As above, I think we only need "bll" and "ull" here. BR, Kewen > extern __vector unsigned int ui[][4]; > extern __vector unsigned short us[][4]; > extern __vector unsigned char uc[][4]; > @@ -88,12 +95,23 @@ int do_perm(void) > { > int i = 0; > > + sll[i][0] = vec_perm (sll[i][1], sll[i][2], uc[i][3]); i++; > + bll[i][0] = vec_perm (bll[i][1], bll[i][2], uc[i][3]); i++; > si[i][0] = vec_perm (si[i][1], si[i][2], uc[i][3]); i++; > + bi[i][0] = vec_perm (bi[i][1], bi[i][2], uc[i][3]); i++; > ss[i][0] = vec_perm (ss[i][1], ss[i][2], uc[i][3]); i++; > + bs[i][0] = vec_perm (bs[i][1], bs[i][2], uc[i][3]); i++; > sc[i][0] = vec_perm (sc[i][1], sc[i][2], uc[i][3]); i++; > + bc[i][0] = vec_perm (bc[i][1], bc[i][2], uc[i][3]); i++; > + p[i][0] = vec_perm (p[i][1], p[i][2], uc[i][3]); i++; > f[i][0] = vec_perm (f[i][1], f[i][2], uc[i][3]); i++; > d[i][0] = vec_perm (d[i][1], d[i][2], uc[i][3]); i++; > > + ull[i][0] = vec_perm (ull[i][1], ull[i][2], uc[i][3]); i++; > + ui[i][0] = vec_perm (ui[i][1], ui[i][2], uc[i][3]); i++; > + us[i][0] = vec_perm (us[i][1], us[i][2], uc[i][3]); i++; > + uc[i][0] = vec_perm (uc[i][1], uc[i][2], uc[i][3]); i++; > + > si[i][0] = vec_perm (si[i][1], si[i][2], uc[i][3]); i++; > ss[i][0] = vec_perm (ss[i][1], ss[i][2], uc[i][3]); i++; > sc[i][0] = vec_perm (sc[i][1], sc[i][2], uc[i][3]); i++;
diff --git a/gcc/doc/extend.texi b/gcc/doc/extend.texi index 48b27ff9f39..bf6f4094040 100644 --- a/gcc/doc/extend.texi +++ b/gcc/doc/extend.texi @@ -21553,9 +21553,19 @@ vector bool __int128 vec_sel (vector bool __int128, vector bool __int128, vector unsigned __int128); @end smallexample -The instance is an extension of the exiting overloaded built-in @code{vec_sel} +The instance is an extension of the existing overloaded built-in @code{vec_sel} that is documented in the PVIPR. +@smallexample +vector signed __int128 vec_perm (vector signed __int128, + vector signed __int128); +vector unsigned __int128 vec_perm (vector unsigned __int128, + vector unsigned __int128); +@end smallexample + +The 128-bit integer arguments for the @code{vec_perm} built-in are in addition +to the instances that are 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/builtins-4-int128-runnable.c b/gcc/testsuite/gcc.target/powerpc/builtins-4-int128-runnable.c index 62c11132cf3..c61b0ecb854 100644 --- a/gcc/testsuite/gcc.target/powerpc/builtins-4-int128-runnable.c +++ b/gcc/testsuite/gcc.target/powerpc/builtins-4-int128-runnable.c @@ -18,6 +18,16 @@ int main() { __uint128_t data_u128[100]; __int128_t data_128[100]; +#ifdef __BIG_ENDIAN__ + vector unsigned char vuc = {0xC, 0xD, 0xE, 0xF, 0x8, 0x9, 0xA, 0xB, + 0x1C, 0x1D, 0x1E, 0x1F, 0x18, 0x19, 0x1A, 0x1B}; +#else + vector unsigned char vuc = {0x4, 0x5, 0x6, 0x7, 0x0, 0x1, 0x2, 0x3, + 0x14, 0x15, 0x16, 0x17, 0x10, 0x11, 0x12, 0x13}; +#endif + + vector __int128_t vec_128_arg1, vec_128_arg2; + vector __uint128_t vec_u128_arg1, vec_u128_arg2; vector __int128_t vec_128_expected1, vec_128_result1; vector __uint128_t vec_u128_expected1, vec_u128_result1; signed long long zero = (signed long long) 0; @@ -37,11 +47,13 @@ int main() { { #ifdef DEBUG printf("Error: vec_xl(), vec_128_result1[0] = %lld %llu; ", - vec_128_result1[0] >> 64, - vec_128_result1[0] & (__int128_t)0xFFFFFFFFFFFFFFFF); + (unsigned long long)(vec_128_result1[0] >> 64), + (unsigned long long)(vec_128_result1[0] + & (__int128_t)0xFFFFFFFFFFFFFFFF)); printf("vec_128_expected1[0] = %lld %llu\n", - vec_128_expected1[0] >> 64, - vec_128_expected1[0] & (__int128_t)0xFFFFFFFFFFFFFFFF); + (unsigned long long)(vec_128_expected1[0] >> 64), + (unsigned long long)(vec_128_expected1[0] + & (__int128_t)0xFFFFFFFFFFFFFFFF)); #else abort (); #endif @@ -53,11 +65,13 @@ int main() { { #ifdef DEBUG printf("Error: vec_xl(), vec_u128_result1[0] = %lld; ", - vec_u128_result1[0] >> 64, - vec_u128_result1[0] & (__int128_t)0xFFFFFFFFFFFFFFFF); + (unsigned long long)(vec_u128_result1[0] >> 64), + (unsigned long long)(vec_u128_result1[0] + & (__int128_t)0xFFFFFFFFFFFFFFFF)); printf("vec_u128_expected1[0] = %lld\n", - vec_u128_expected1[0] >> 64, - vec_u128_expected1[0] & (__int128_t)0xFFFFFFFFFFFFFFFF); + (unsigned long long)(vec_u128_expected1[0] >> 64), + (unsigned long long)(vec_u128_expected1[0] + & (__int128_t)0xFFFFFFFFFFFFFFFF)); #else abort (); #endif @@ -76,11 +90,12 @@ int main() { { #ifdef DEBUG printf("Error: vec_xl_be(), vec_128_result1[0] = %llu %llu;", - vec_128_result1[0] >> 64, - vec_128_result1[0] & 0xFFFFFFFFFFFFFFFF); + (unsigned long long)(vec_128_result1[0] >> 64), + (unsigned long long)(vec_128_result1[0] & 0xFFFFFFFFFFFFFFFF)); printf(" vec_128_expected1[0] = %llu %llu\n", - vec_128_expected1[0] >> 64, - vec_128_expected1[0] & 0xFFFFFFFFFFFFFFFF); + (unsigned long long)(vec_128_expected1[0] >> 64), + (unsigned long long)(vec_128_expected1[0] + & 0xFFFFFFFFFFFFFFFF)); #else abort (); #endif @@ -98,11 +113,72 @@ int main() { { #ifdef DEBUG printf("Error: vec_xl_be(), vec_u128_result1[0] = %llu %llu;", - vec_u128_result1[0] >> 64, - vec_u128_result1[0] & 0xFFFFFFFFFFFFFFFF); + (unsigned long long)(vec_u128_result1[0] >> 64), + (unsigned long long)(vec_u128_result1[0] & 0xFFFFFFFFFFFFFFFF)); + printf(" vec_u128_expected1[0] = %llu %llu\n", + (unsigned long long)(vec_u128_expected1[0] >> 64), + (unsigned long long)(vec_u128_expected1[0] + & 0xFFFFFFFFFFFFFFFF)); +#else + abort (); +#endif + } + + /* vec_perm() tests */ + vec_128_arg1 = (vector __int128_t){ (__uint128_t)0x1122334455667788ULL }; + vec_128_arg2 = (vector __int128_t){ (__uint128_t)0xAAABBBCCCDDDEEEF }; + +#ifdef __BIG_ENDIAN__ + vec_128_expected1[0] = 0x5566778811223344ULL; + vec_128_expected1[0] = (vec_128_expected1[0] << 64) | + 0xcdddeeefaaabbbccULL; +#else + vec_128_expected1[0] = 0xcdddeeefaaabbbccULL; + vec_128_expected1[0] = (vec_128_expected1[0] << 64) | + 0x5566778811223344ULL; +#endif + + vec_128_result1 = vec_perm (vec_128_arg1, vec_128_arg2, vuc); + + if (vec_128_expected1[0] != vec_128_result1[0]) + { +#ifdef DEBUG + printf("Error: vec_perm(), vec_128_result1[0] = %llu %llu;", + (unsigned long long)(vec_128_result1[0] >> 64), + (unsigned long long)(vec_128_result1[0] & 0xFFFFFFFFFFFFFFFF)); + printf(" vec_128_expected1[0] = %llu %llu\n", + (unsigned long long)(vec_128_expected1[0] >> 64), + (unsigned long long)(vec_128_expected1[0] + & 0xFFFFFFFFFFFFFFFF)); +#else + abort (); +#endif + } + vec_u128_arg1 = (vector __uint128_t){ (__uint128_t)0x1122334455667788ULL }; + vec_u128_arg2 = (vector __uint128_t){ (__uint128_t)0xAAABBBCCCDDDEEEF }; + +#ifdef __BIG_ENDIAN__ + vec_u128_expected1[0] = 0x5566778811223344ULL; + vec_u128_expected1[0] = (vec_u128_expected1[0] << 64) | + 0xcdddeeefaaabbbccULL; +#else + vec_u128_expected1[0] = 0xcdddeeefaaabbbccULL; + vec_u128_expected1[0] = (vec_u128_expected1[0] << 64) | + 0x5566778811223344ULL; +#endif + + vec_u128_result1 = vec_perm (vec_u128_arg1, vec_u128_arg2, vuc); + + if (vec_u128_expected1[0] != vec_u128_result1[0]) + { +#ifdef DEBUG + printf("Error: vec_perm(), vec_u128_result1[0] = %llu %llu;", + (unsigned long long)(vec_u128_result1[0] >> 64), + (unsigned long long)(vec_u128_result1[0] & 0xFFFFFFFFFFFFFFFF)); printf(" vec_u128_expected1[0] = %llu %llu\n", - vec_u128_expected1[0] >> 64, - vec_u128_expected1[0] & 0xFFFFFFFFFFFFFFFF); + (unsigned long long)(vec_u128_expected1[0] >> 64), + (unsigned long long)(vec_u128_expected1[0] + & 0xFFFFFFFFFFFFFFFF)); #else abort (); #endif diff --git a/gcc/testsuite/gcc.target/powerpc/vsx-builtin-3.c b/gcc/testsuite/gcc.target/powerpc/vsx-builtin-3.c index 67c93be1469..b3b76be34b9 100644 --- a/gcc/testsuite/gcc.target/powerpc/vsx-builtin-3.c +++ b/gcc/testsuite/gcc.target/powerpc/vsx-builtin-3.c @@ -39,10 +39,17 @@ #include <altivec.h> +extern __vector long long int sll[][4]; +extern __vector long long bool bll[][4]; extern __vector int si[][4]; +extern __vector bool int bi[][4]; extern __vector short ss[][4]; +extern __vector bool short bs[][4]; extern __vector signed char sc[][4]; +extern __vector bool char bc[][4]; +extern __vector pixel p[][4]; extern __vector float f[][4]; +extern __vector unsigned long long int ull[][4]; extern __vector unsigned int ui[][4]; extern __vector unsigned short us[][4]; extern __vector unsigned char uc[][4]; @@ -88,12 +95,23 @@ int do_perm(void) { int i = 0; + sll[i][0] = vec_perm (sll[i][1], sll[i][2], uc[i][3]); i++; + bll[i][0] = vec_perm (bll[i][1], bll[i][2], uc[i][3]); i++; si[i][0] = vec_perm (si[i][1], si[i][2], uc[i][3]); i++; + bi[i][0] = vec_perm (bi[i][1], bi[i][2], uc[i][3]); i++; ss[i][0] = vec_perm (ss[i][1], ss[i][2], uc[i][3]); i++; + bs[i][0] = vec_perm (bs[i][1], bs[i][2], uc[i][3]); i++; sc[i][0] = vec_perm (sc[i][1], sc[i][2], uc[i][3]); i++; + bc[i][0] = vec_perm (bc[i][1], bc[i][2], uc[i][3]); i++; + p[i][0] = vec_perm (p[i][1], p[i][2], uc[i][3]); i++; f[i][0] = vec_perm (f[i][1], f[i][2], uc[i][3]); i++; d[i][0] = vec_perm (d[i][1], d[i][2], uc[i][3]); i++; + ull[i][0] = vec_perm (ull[i][1], ull[i][2], uc[i][3]); i++; + ui[i][0] = vec_perm (ui[i][1], ui[i][2], uc[i][3]); i++; + us[i][0] = vec_perm (us[i][1], us[i][2], uc[i][3]); i++; + uc[i][0] = vec_perm (uc[i][1], uc[i][2], uc[i][3]); i++; + si[i][0] = vec_perm (si[i][1], si[i][2], uc[i][3]); i++; ss[i][0] = vec_perm (ss[i][1], ss[i][2], uc[i][3]); i++; sc[i][0] = vec_perm (sc[i][1], sc[i][2], uc[i][3]); i++;