OpenE2K
/
gcc
2
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

rs6000: Fix up *intrin.h for C89 [PR104239] 

When writing testcases for the previously posted patch, I have noticed
that 3 of the headers aren't valid C89 (I didn't have any dg-options
so -ansi -pedantic-errors was implied and these errors were reported).

The following patch fixes those, ok for trunk?

Note, as can be seen even in this patch, seems older rs6000/*intrin.h
headers uglify not just argument names (__A instead of A etc.), but also
automatic variable names and other local identifiers, while e.g. emmintrin.h
or bmi2intrin.h clearly uglify only the argument names and not local
variables.  I think that should be fixed but don't have time for that myself
(libstdc++ or e.g. the x86 headers uglify everything; this is so that one
can
 #define result a + b
 #include <x86intrin.h>
etc.).

2022-01-26  Jakub Jelinek  <jakub@redhat.com>

	PR target/104239
	* config/rs6000/emmintrin.h (_mm_sad_epu8): Use __asm__ instead of
	asm.
	* config/rs6000/smmintrin.h (_mm_minpos_epu16): Declare iterator
	before for loop instead of for init clause.
	* config/rs6000/bmi2intrin.h (_pext_u64): Likewise.

	* gcc.target/powerpc/pr104239-3.c: New test.
This commit is contained in:
Jakub Jelinek 2022-01-26 22:55:11 +01:00
parent 2bf8da684b
commit fd5b0488ad
4 changed files with 13 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
gcc/config/rs6000/bmi2intrin.h
View File

@ -118,7 +118,8 @@ _pext_u64 (unsigned long long __X, unsigned long long __M)
/* Also if the pext mask is constant, then the popcount is /* Also if the pext mask is constant, then the popcount is
constant, we can evaluate the following loop at compile constant, we can evaluate the following loop at compile
time and use a constant bit permute vector. */ time and use a constant bit permute vector. */
for (long i = 0; i < __builtin_popcountl (__M); i++) long i;
for (i = 0; i < __builtin_popcountl (__M); i++)
{ {
c = __builtin_clzl (m); c = __builtin_clzl (m);
p = (p << 8) | c; p = (p << 8) | c;

2
gcc/config/rs6000/emmintrin.h
View File

@ -2215,7 +2215,7 @@ _mm_sad_epu8 (__m128i __A, __m128i __B)
vsum = (__vector signed int) vec_sum4s (vabsdiff, zero); vsum = (__vector signed int) vec_sum4s (vabsdiff, zero);
#ifdef __LITTLE_ENDIAN__ #ifdef __LITTLE_ENDIAN__
/* Sum across four integers with two integer results. */ /* Sum across four integers with two integer results. */
asm ("vsum2sws %0,%1,%2" : "=v" (result) : "v" (vsum), "v" (zero)); __asm__ ("vsum2sws %0,%1,%2" : "=v" (result) : "v" (vsum), "v" (zero));
/* Note: vec_sum2s could be used here, but on little-endian, vector /* Note: vec_sum2s could be used here, but on little-endian, vector
shifts are added that are not needed for this use-case. shifts are added that are not needed for this use-case.
A vector shift to correctly position the 32-bit integer results A vector shift to correctly position the 32-bit integer results

3
gcc/config/rs6000/smmintrin.h
View File

@ -687,7 +687,8 @@ _mm_minpos_epu16 (__m128i __A)
union __u __u = { .__m = __A }, __r = { .__m = {0} }; union __u __u = { .__m = __A }, __r = { .__m = {0} };
unsigned short __ridx = 0; unsigned short __ridx = 0;
unsigned short __rmin = __u.__uh[__ridx]; unsigned short __rmin = __u.__uh[__ridx];
for (unsigned long __i = 1; __i < 8; __i++) unsigned long __i;
for (__i = 1; __i < 8; __i++)
{ {
if (__u.__uh[__i] < __rmin) if (__u.__uh[__i] < __rmin)
{ {

8
gcc/testsuite/gcc.target/powerpc/pr104239-3.c Normal file
View File

@ -0,0 +1,8 @@
/* PR target/104239 */
/* { dg-do compile } */
/* { dg-options "-O2 -mdejagnu-cpu=power8 -DNO_WARN_X86_INTRINSICS -std=c89" } */
/* { dg-require-effective-target powerpc_p8vector_ok } */
#include <x86intrin.h>
int i;