public inbox for gcc-cvs@sourceware.org
help / color / mirror / Atom feed
* [gcc(refs/vendors/redhat/heads/gcc-8-branch)] fix _mm512_{, mask_}cmp*_p[ds]_mask at -O0 [PR96174]
@ 2020-09-17 17:23 Jakub Jelinek
0 siblings, 0 replies; only message in thread
From: Jakub Jelinek @ 2020-09-17 17:23 UTC (permalink / raw)
To: gcc-cvs
https://gcc.gnu.org/g:1a13132af60b40907e7f7057639199ddf8b5b970
commit 1a13132af60b40907e7f7057639199ddf8b5b970
Author: Jakub Jelinek <jakub@redhat.com>
Date: Wed Jul 15 11:34:44 2020 +0200
fix _mm512_{,mask_}cmp*_p[ds]_mask at -O0 [PR96174]
The _mm512_{,mask_}cmp_p[ds]_mask and also _mm_{,mask_}cmp_s[ds]_mask
intrinsics have an argument which must have a constant passed to it
and so use an inline version only for ifdef __OPTIMIZE__ and have
a #define for -O0. But the _mm512_{,mask_}cmp*_p[ds]_mask intrinsics
don't need a constant argument, they are essentially the first
set with the constant added to them implicitly based on the comparison
name, and so there is no #define version for them (correctly).
But their inline versions are defined in between the first and s[ds]
set and so inside of ifdef __OPTIMIZE__, which means that with -O0
they aren't defined at all.
This patch fixes that by moving those after the #ifdef __OPTIMIZE #else
use #define #endif block.
2020-07-15 Jakub Jelinek <jakub@redhat.com>
PR target/96174
* config/i386/avx512fintrin.h (_mm512_cmpeq_pd_mask,
_mm512_mask_cmpeq_pd_mask, _mm512_cmplt_pd_mask,
_mm512_mask_cmplt_pd_mask, _mm512_cmple_pd_mask,
_mm512_mask_cmple_pd_mask, _mm512_cmpunord_pd_mask,
_mm512_mask_cmpunord_pd_mask, _mm512_cmpneq_pd_mask,
_mm512_mask_cmpneq_pd_mask, _mm512_cmpnlt_pd_mask,
_mm512_mask_cmpnlt_pd_mask, _mm512_cmpnle_pd_mask,
_mm512_mask_cmpnle_pd_mask, _mm512_cmpord_pd_mask,
_mm512_mask_cmpord_pd_mask, _mm512_cmpeq_ps_mask,
_mm512_mask_cmpeq_ps_mask, _mm512_cmplt_ps_mask,
_mm512_mask_cmplt_ps_mask, _mm512_cmple_ps_mask,
_mm512_mask_cmple_ps_mask, _mm512_cmpunord_ps_mask,
_mm512_mask_cmpunord_ps_mask, _mm512_cmpneq_ps_mask,
_mm512_mask_cmpneq_ps_mask, _mm512_cmpnlt_ps_mask,
_mm512_mask_cmpnlt_ps_mask, _mm512_cmpnle_ps_mask,
_mm512_mask_cmpnle_ps_mask, _mm512_cmpord_ps_mask,
_mm512_mask_cmpord_ps_mask): Move outside of __OPTIMIZE__ guarded
section.
* gcc.target/i386/avx512f-vcmppd-3.c: New test.
* gcc.target/i386/avx512f-vcmpps-3.c: New test.
(cherry picked from commit 12d69dbfff9dd5ad4a30b20d1636f5cab6425e8c)
Diff:
---
gcc/config/i386/avx512fintrin.h | 164 +++++++++++------------
gcc/testsuite/gcc.target/i386/avx512f-vcmppd-3.c | 4 +
gcc/testsuite/gcc.target/i386/avx512f-vcmpps-3.c | 4 +
3 files changed, 90 insertions(+), 82 deletions(-)
diff --git a/gcc/config/i386/avx512fintrin.h b/gcc/config/i386/avx512fintrin.h
index 142c0ee2350..88771a39126 100644
--- a/gcc/config/i386/avx512fintrin.h
+++ b/gcc/config/i386/avx512fintrin.h
@@ -14134,6 +14134,88 @@ _mm512_mask_cmp_pd_mask (__mmask8 __U, __m512d __X, __m512d __Y, const int __P)
_MM_FROUND_CUR_DIRECTION);
}
+extern __inline __mmask8
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cmp_sd_mask (__m128d __X, __m128d __Y, const int __P)
+{
+ return (__mmask8) __builtin_ia32_cmpsd_mask ((__v2df) __X,
+ (__v2df) __Y, __P,
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __mmask8
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_cmp_sd_mask (__mmask8 __M, __m128d __X, __m128d __Y, const int __P)
+{
+ return (__mmask8) __builtin_ia32_cmpsd_mask ((__v2df) __X,
+ (__v2df) __Y, __P,
+ (__mmask8) __M,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __mmask8
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_cmp_ss_mask (__m128 __X, __m128 __Y, const int __P)
+{
+ return (__mmask8) __builtin_ia32_cmpss_mask ((__v4sf) __X,
+ (__v4sf) __Y, __P,
+ (__mmask8) -1,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+extern __inline __mmask8
+__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
+_mm_mask_cmp_ss_mask (__mmask8 __M, __m128 __X, __m128 __Y, const int __P)
+{
+ return (__mmask8) __builtin_ia32_cmpss_mask ((__v4sf) __X,
+ (__v4sf) __Y, __P,
+ (__mmask8) __M,
+ _MM_FROUND_CUR_DIRECTION);
+}
+
+#else
+#define _mm512_cmp_pd_mask(X, Y, P) \
+ ((__mmask8) __builtin_ia32_cmppd512_mask ((__v8df)(__m512d)(X), \
+ (__v8df)(__m512d)(Y), (int)(P),\
+ (__mmask8)-1,_MM_FROUND_CUR_DIRECTION))
+
+#define _mm512_cmp_ps_mask(X, Y, P) \
+ ((__mmask16) __builtin_ia32_cmpps512_mask ((__v16sf)(__m512)(X), \
+ (__v16sf)(__m512)(Y), (int)(P),\
+ (__mmask16)-1,_MM_FROUND_CUR_DIRECTION))
+
+#define _mm512_mask_cmp_pd_mask(M, X, Y, P) \
+ ((__mmask8) __builtin_ia32_cmppd512_mask ((__v8df)(__m512d)(X), \
+ (__v8df)(__m512d)(Y), (int)(P),\
+ (__mmask8)(M), _MM_FROUND_CUR_DIRECTION))
+
+#define _mm512_mask_cmp_ps_mask(M, X, Y, P) \
+ ((__mmask16) __builtin_ia32_cmpps512_mask ((__v16sf)(__m512)(X), \
+ (__v16sf)(__m512)(Y), (int)(P),\
+ (__mmask16)(M),_MM_FROUND_CUR_DIRECTION))
+
+#define _mm_cmp_sd_mask(X, Y, P) \
+ ((__mmask8) __builtin_ia32_cmpsd_mask ((__v2df)(__m128d)(X), \
+ (__v2df)(__m128d)(Y), (int)(P),\
+ (__mmask8)-1,_MM_FROUND_CUR_DIRECTION))
+
+#define _mm_mask_cmp_sd_mask(M, X, Y, P) \
+ ((__mmask8) __builtin_ia32_cmpsd_mask ((__v2df)(__m128d)(X), \
+ (__v2df)(__m128d)(Y), (int)(P),\
+ M,_MM_FROUND_CUR_DIRECTION))
+
+#define _mm_cmp_ss_mask(X, Y, P) \
+ ((__mmask8) __builtin_ia32_cmpss_mask ((__v4sf)(__m128)(X), \
+ (__v4sf)(__m128)(Y), (int)(P), \
+ (__mmask8)-1,_MM_FROUND_CUR_DIRECTION))
+
+#define _mm_mask_cmp_ss_mask(M, X, Y, P) \
+ ((__mmask8) __builtin_ia32_cmpss_mask ((__v4sf)(__m128)(X), \
+ (__v4sf)(__m128)(Y), (int)(P), \
+ M,_MM_FROUND_CUR_DIRECTION))
+#endif
+
extern __inline __mmask8
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_cmpeq_pd_mask (__m512d __X, __m512d __Y)
@@ -14454,88 +14536,6 @@ _mm512_mask_cmpord_ps_mask (__mmask16 __U, __m512 __X, __m512 __Y)
_MM_FROUND_CUR_DIRECTION);
}
-extern __inline __mmask8
-__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm_cmp_sd_mask (__m128d __X, __m128d __Y, const int __P)
-{
- return (__mmask8) __builtin_ia32_cmpsd_mask ((__v2df) __X,
- (__v2df) __Y, __P,
- (__mmask8) -1,
- _MM_FROUND_CUR_DIRECTION);
-}
-
-extern __inline __mmask8
-__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm_mask_cmp_sd_mask (__mmask8 __M, __m128d __X, __m128d __Y, const int __P)
-{
- return (__mmask8) __builtin_ia32_cmpsd_mask ((__v2df) __X,
- (__v2df) __Y, __P,
- (__mmask8) __M,
- _MM_FROUND_CUR_DIRECTION);
-}
-
-extern __inline __mmask8
-__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm_cmp_ss_mask (__m128 __X, __m128 __Y, const int __P)
-{
- return (__mmask8) __builtin_ia32_cmpss_mask ((__v4sf) __X,
- (__v4sf) __Y, __P,
- (__mmask8) -1,
- _MM_FROUND_CUR_DIRECTION);
-}
-
-extern __inline __mmask8
-__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
-_mm_mask_cmp_ss_mask (__mmask8 __M, __m128 __X, __m128 __Y, const int __P)
-{
- return (__mmask8) __builtin_ia32_cmpss_mask ((__v4sf) __X,
- (__v4sf) __Y, __P,
- (__mmask8) __M,
- _MM_FROUND_CUR_DIRECTION);
-}
-
-#else
-#define _mm512_cmp_pd_mask(X, Y, P) \
- ((__mmask8) __builtin_ia32_cmppd512_mask ((__v8df)(__m512d)(X), \
- (__v8df)(__m512d)(Y), (int)(P),\
- (__mmask8)-1,_MM_FROUND_CUR_DIRECTION))
-
-#define _mm512_cmp_ps_mask(X, Y, P) \
- ((__mmask16) __builtin_ia32_cmpps512_mask ((__v16sf)(__m512)(X), \
- (__v16sf)(__m512)(Y), (int)(P),\
- (__mmask16)-1,_MM_FROUND_CUR_DIRECTION))
-
-#define _mm512_mask_cmp_pd_mask(M, X, Y, P) \
- ((__mmask8) __builtin_ia32_cmppd512_mask ((__v8df)(__m512d)(X), \
- (__v8df)(__m512d)(Y), (int)(P),\
- (__mmask8)(M), _MM_FROUND_CUR_DIRECTION))
-
-#define _mm512_mask_cmp_ps_mask(M, X, Y, P) \
- ((__mmask16) __builtin_ia32_cmpps512_mask ((__v16sf)(__m512)(X), \
- (__v16sf)(__m512)(Y), (int)(P),\
- (__mmask16)(M),_MM_FROUND_CUR_DIRECTION))
-
-#define _mm_cmp_sd_mask(X, Y, P) \
- ((__mmask8) __builtin_ia32_cmpsd_mask ((__v2df)(__m128d)(X), \
- (__v2df)(__m128d)(Y), (int)(P),\
- (__mmask8)-1,_MM_FROUND_CUR_DIRECTION))
-
-#define _mm_mask_cmp_sd_mask(M, X, Y, P) \
- ((__mmask8) __builtin_ia32_cmpsd_mask ((__v2df)(__m128d)(X), \
- (__v2df)(__m128d)(Y), (int)(P),\
- M,_MM_FROUND_CUR_DIRECTION))
-
-#define _mm_cmp_ss_mask(X, Y, P) \
- ((__mmask8) __builtin_ia32_cmpss_mask ((__v4sf)(__m128)(X), \
- (__v4sf)(__m128)(Y), (int)(P), \
- (__mmask8)-1,_MM_FROUND_CUR_DIRECTION))
-
-#define _mm_mask_cmp_ss_mask(M, X, Y, P) \
- ((__mmask8) __builtin_ia32_cmpss_mask ((__v4sf)(__m128)(X), \
- (__v4sf)(__m128)(Y), (int)(P), \
- M,_MM_FROUND_CUR_DIRECTION))
-#endif
-
extern __inline __mmask16
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm512_kmov (__mmask16 __A)
diff --git a/gcc/testsuite/gcc.target/i386/avx512f-vcmppd-3.c b/gcc/testsuite/gcc.target/i386/avx512f-vcmppd-3.c
new file mode 100644
index 00000000000..3d36eca78fa
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512f-vcmppd-3.c
@@ -0,0 +1,4 @@
+/* { dg-do compile } */
+/* { dg-options "-O0 -mavx512f" } */
+
+#include "avx512f-vcmppd-1.c"
diff --git a/gcc/testsuite/gcc.target/i386/avx512f-vcmpps-3.c b/gcc/testsuite/gcc.target/i386/avx512f-vcmpps-3.c
new file mode 100644
index 00000000000..af797aad2de
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512f-vcmpps-3.c
@@ -0,0 +1,4 @@
+/* { dg-do compile } */
+/* { dg-options "-O0 -mavx512f" } */
+
+#include "avx512f-vcmpps-1.c"
^ permalink raw reply [flat|nested] only message in thread
only message in thread, other threads:[~2020-09-17 17:23 UTC | newest]
Thread overview: (only message) (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2020-09-17 17:23 [gcc(refs/vendors/redhat/heads/gcc-8-branch)] fix _mm512_{, mask_}cmp*_p[ds]_mask at -O0 [PR96174] Jakub Jelinek
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).