Hi!

These intrinsics are supposed to do an unaligned may_alias load
of a 16-bit or 32-bit value and store it as the first element of
a 128-bit integer vector, with all other elements cleared.

The current _mm_storeu_* implementation implements that correctly, uses
__*_u types to do the store and extracts the first element of a vector into
it.
But _mm_loadu_si{16,32} gets it all wrong.  It performs an aligned
non-may_alias load and because _mm_set_epi{16,32} has the args reversed,
it also inserts it into the last vector element instead of first.

The following patch fixes that, bootstrapped/regtested on x86_64-linux
and i686-linux, ok for trunk and affected release branches?

Note, while the Intrinsics guide for _mm_loadu_si32 says SSE2,
for _mm_loadu_si16 it says strangely SSE.  But the intrinsics
returns __m128i, which is only defined in emmintrin.h, and
_mm_set_epi16 is also only SSE2 and later in emmintrin.h.
Even clang defines it in emmintrin.h and ends up with inlining
failure when calling _mm_loadu_si16 from sse,no-sse2 function.
So, isn't that a bug in the intrinsic guide instead?

2022-03-12  Jakub Jelinek  <ja...@redhat.com>

        PR target/99754
        * config/i386/emmintrin.h (_mm_loadu_si32): Put loaded value into
        first   rather than last element of the vector, use __m32_u to do
        a really unaligned load, use just 0 instead of (int)0.
        (_mm_loadu_si16): Put loaded value into first rather than last
        element of the vector, use __m16_u to do a really unaligned load,
        use just 0 instead of (short)0.

        * gcc.target/i386/pr99754-1.c: New test.
        * gcc.target/i386/pr99754-2.c: New test.

--- gcc/config/i386/emmintrin.h.jj      2022-01-11 23:11:21.766298923 +0100
+++ gcc/config/i386/emmintrin.h 2022-03-11 16:47:24.789884825 +0100
@@ -718,14 +718,13 @@ _mm_loadu_si64 (void const *__P)
 extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, 
__artificial__))
 _mm_loadu_si32 (void const *__P)
 {
-  return _mm_set_epi32 (*(int *)__P, (int)0, (int)0, (int)0);
+  return _mm_set_epi32 (0, 0, 0, (*(__m32_u *)__P)[0]);
 }
 
 extern __inline __m128i __attribute__((__gnu_inline__, __always_inline__, 
__artificial__))
 _mm_loadu_si16 (void const *__P)
 {
-  return _mm_set_epi16 (*(short *)__P, (short)0, (short)0, (short)0,
-                       (short)0, (short)0, (short)0, (short)0);
+  return _mm_set_epi16 (0, 0, 0, 0, 0, 0, 0, (*(__m16_u *)__P)[0]);
 }
 
 extern __inline void __attribute__((__gnu_inline__, __always_inline__, 
__artificial__))
--- gcc/testsuite/gcc.target/i386/pr99754-1.c.jj        2022-03-11 
16:43:30.621120896 +0100
+++ gcc/testsuite/gcc.target/i386/pr99754-1.c   2022-03-11 16:43:18.250291856 
+0100
@@ -0,0 +1,20 @@
+/* PR target/99754 */
+/* { dg-do run } */
+/* { dg-options "-O2 -msse2" } */
+/* { dg-require-effective-target sse2 } */
+
+#include "sse2-check.h"
+#include <emmintrin.h>
+
+static void
+sse2_test (void)
+{
+  union { unsigned char buf[32]; long long ll; } u;
+  u.buf[1] = 0xfe;
+  u.buf[2] = 0xca;
+  u.buf[17] = 0xaa;
+  u.buf[18] = 0x55;
+  _mm_storeu_si16 (&u.buf[17], _mm_loadu_si16 (&u.buf[1]));
+  if (u.buf[17] != 0xfe || u.buf[18] != 0xca)
+    abort ();
+}
--- gcc/testsuite/gcc.target/i386/pr99754-2.c.jj        2022-03-11 
16:43:41.701967763 +0100
+++ gcc/testsuite/gcc.target/i386/pr99754-2.c   2022-03-11 16:45:16.391659211 
+0100
@@ -0,0 +1,24 @@
+/* PR target/99754 */
+/* { dg-do run } */
+/* { dg-options "-O2 -msse2" } */
+/* { dg-require-effective-target sse2 } */
+
+#include "sse2-check.h"
+#include <emmintrin.h>
+
+static void
+sse2_test (void)
+{
+  union { unsigned char buf[32]; long long ll; } u;
+  u.buf[1] = 0xbe;
+  u.buf[2] = 0xba;
+  u.buf[3] = 0xfe;
+  u.buf[4] = 0xca;
+  u.buf[17] = 0xaa;
+  u.buf[18] = 0x55;
+  u.buf[19] = 0xaa;
+  u.buf[20] = 0x55;
+  _mm_storeu_si32 (&u.buf[17], _mm_loadu_si32 (&u.buf[1]));
+  if (u.buf[17] != 0xbe || u.buf[18] != 0xba || u.buf[19] != 0xfe || u.buf[20] 
!= 0xca)
+    abort ();
+}

        Jakub

Reply via email to