Hi,
As PR109082 shows, some uses of vec_sld in emmintrin.h don't
strictly guarantee the given shift count is in the range
0-15 (inclusive). This patch is to make the argument
range constraint honored for those uses.
Bootstrapped and regtested on powerpc64-linux-gnu P8 and
powerpc64le-linux-gnu P9 and P10.
I'm going to push this soon if no objections.
BR,
Kewen
-----
PR target/109082
gcc/ChangeLog:
* config/rs6000/emmintrin.h (_mm_bslli_si128): Check __N is not less
than zero when calling vec_sld.
(_mm_bsrli_si128): Return __A if __N is zero, check __N is bigger than
zero when calling vec_sld.
(_mm_slli_si128): Return __A if _imm5 is zero, check _imm5 is bigger
than zero when calling vec_sld.
gcc/testsuite/ChangeLog:
* gcc.target/powerpc/pr109082.c: New test.
---
gcc/config/rs6000/emmintrin.h | 10 +++++++---
gcc/testsuite/gcc.target/powerpc/pr109082.c | 14 ++++++++++++++
2 files changed, 21 insertions(+), 3 deletions(-)
create mode 100644 gcc/testsuite/gcc.target/powerpc/pr109082.c
diff --git a/gcc/config/rs6000/emmintrin.h b/gcc/config/rs6000/emmintrin.h
index f6a6dbf399a..bfff7ff6fea 100644
--- a/gcc/config/rs6000/emmintrin.h
+++ b/gcc/config/rs6000/emmintrin.h
@@ -1601,7 +1601,7 @@ _mm_bslli_si128 (__m128i __A, const int __N)
__v16qu __result;
const __v16qu __zeros = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 };
- if (__N < 16)
+ if (__N >= 0 && __N < 16)
__result = vec_sld ((__v16qu) __A, __zeros, __N);
else
__result = __zeros;
@@ -1615,7 +1615,9 @@ _mm_bsrli_si128 (__m128i __A, const int __N)
__v16qu __result;
const __v16qu __zeros = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 };
- if (__N < 16)
+ if (__N == 0)
+ return __A;
+ else if (__N > 0 && __N < 16)
#ifdef __LITTLE_ENDIAN__
if (__builtin_constant_p(__N))
/* Would like to use Vector Shift Left Double by Octet
@@ -1650,7 +1652,9 @@ _mm_slli_si128 (__m128i __A, const int _imm5)
__v16qu __result;
const __v16qu __zeros = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 };
- if (_imm5 < 16)
+ if (_imm5 == 0)
+ return __A;
+ else if (_imm5 > 0 && _imm5 < 16)
#ifdef __LITTLE_ENDIAN__
__result = vec_sld ((__v16qu) __A, __zeros, _imm5);
#else
diff --git a/gcc/testsuite/gcc.target/powerpc/pr109082.c
b/gcc/testsuite/gcc.target/powerpc/pr109082.c
new file mode 100644
index 00000000000..98da22c386b
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/pr109082.c
@@ -0,0 +1,14 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target powerpc_vsx_ok } */
+/* { dg-options "-O2 -mvsx" } */
+
+/* Verify there is no warning message. */
+
+#define NO_WARN_X86_INTRINSICS 1
+#include <emmintrin.h>
+
+__m128i
+foo (__m128i A)
+{
+ return _mm_bsrli_si128 (A, 0);
+}
--
2.31.1
