From: liuhongt <hongtao.liu@intel.com>
To: gcc-patches@gcc.gnu.org
Subject: [PATCH] [GIMPLE] Simplify (_Float16) ceil ((double) x) to .CEIL (x) when available.
Date: Fri, 24 Sep 2021 19:25:52 +0800 [thread overview]
Message-ID: <20210924112552.2524168-1-hongtao.liu@intel.com> (raw)
Hi:
Related discussion in [1] and PR.
Bootstrapped and regtest on x86_64-linux-gnu{-m32,}.
Ok for trunk?
[1] https://gcc.gnu.org/pipermail/gcc-patches/2021-July/574330.html
gcc/ChangeLog:
PR target/102464
* config/i386/i386.c (ix86_optab_supported_p):
Return true for HFmode.
* match.pd: Simplify (_Float16) ceil ((double) x) to
__builtin_ceilf16 (a) when a is _Float16 type and
direct_internal_fn_supported_p.
gcc/testsuite/ChangeLog:
* gcc.target/i386/pr102464.c: New test.
---
gcc/config/i386/i386.c | 20 +++++++-----
gcc/match.pd | 28 +++++++++++++++++
gcc/testsuite/gcc.target/i386/pr102464.c | 39 ++++++++++++++++++++++++
3 files changed, 79 insertions(+), 8 deletions(-)
create mode 100644 gcc/testsuite/gcc.target/i386/pr102464.c
diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
index ba89e111d28..3767fe9806d 100644
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@@ -23582,20 +23582,24 @@ ix86_optab_supported_p (int op, machine_mode mode1, machine_mode,
return opt_type == OPTIMIZE_FOR_SPEED;
case rint_optab:
- if (SSE_FLOAT_MODE_P (mode1)
- && TARGET_SSE_MATH
- && !flag_trapping_math
- && !TARGET_SSE4_1)
+ if (mode1 == HFmode)
+ return true;
+ else if (SSE_FLOAT_MODE_P (mode1)
+ && TARGET_SSE_MATH
+ && !flag_trapping_math
+ && !TARGET_SSE4_1)
return opt_type == OPTIMIZE_FOR_SPEED;
return true;
case floor_optab:
case ceil_optab:
case btrunc_optab:
- if (SSE_FLOAT_MODE_P (mode1)
- && TARGET_SSE_MATH
- && !flag_trapping_math
- && TARGET_SSE4_1)
+ if (mode1 == HFmode)
+ return true;
+ else if (SSE_FLOAT_MODE_P (mode1)
+ && TARGET_SSE_MATH
+ && !flag_trapping_math
+ && TARGET_SSE4_1)
return true;
return opt_type == OPTIMIZE_FOR_SPEED;
diff --git a/gcc/match.pd b/gcc/match.pd
index a9791ceb74a..9ccec8b6ce3 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -6191,6 +6191,34 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
(froms (convert float_value_p@0))
(convert (tos @0)))))
+#if GIMPLE
+(match float16_value_p
+ @0
+ (if (TYPE_MAIN_VARIANT (TREE_TYPE (@0)) == float16_type_node)))
+(for froms (BUILT_IN_TRUNCL BUILT_IN_TRUNC BUILT_IN_TRUNCF
+ BUILT_IN_FLOORL BUILT_IN_FLOOR BUILT_IN_FLOORF
+ BUILT_IN_CEILL BUILT_IN_CEIL BUILT_IN_CEILF
+ BUILT_IN_ROUNDEVENL BUILT_IN_ROUNDEVEN BUILT_IN_ROUNDEVENF
+ BUILT_IN_ROUNDL BUILT_IN_ROUND BUILT_IN_ROUNDF
+ BUILT_IN_NEARBYINTL BUILT_IN_NEARBYINT BUILT_IN_NEARBYINTF
+ BUILT_IN_RINTL BUILT_IN_RINT BUILT_IN_RINTF)
+ tos (IFN_TRUNC IFN_TRUNC IFN_TRUNC
+ IFN_FLOOR IFN_FLOOR IFN_FLOOR
+ IFN_CEIL IFN_CEIL IFN_CEIL
+ IFN_ROUNDEVEN IFN_ROUNDEVEN IFN_ROUNDEVEN
+ IFN_ROUND IFN_ROUND IFN_ROUND
+ IFN_NEARBYINT IFN_NEARBYINT IFN_NEARBYINT
+ IFN_RINT IFN_RINT IFN_RINT)
+ /* (_Float16) round ((doube) x) -> __built_in_roundf16 (x), etc.,
+ if x is a _Float16. */
+ (simplify
+ (convert (froms (convert float16_value_p@0)))
+ (if (types_match (type, TREE_TYPE (@0))
+ && direct_internal_fn_supported_p (as_internal_fn (tos),
+ type, OPTIMIZE_FOR_BOTH))
+ (tos @0))))
+#endif
+
(for froms (XFLOORL XCEILL XROUNDL XRINTL)
tos (XFLOOR XCEIL XROUND XRINT)
/* llfloorl(extend(x)) -> llfloor(x), etc., if x is a double. */
diff --git a/gcc/testsuite/gcc.target/i386/pr102464.c b/gcc/testsuite/gcc.target/i386/pr102464.c
new file mode 100644
index 00000000000..e3e060ee80b
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr102464.c
@@ -0,0 +1,39 @@
+/* PR target/102464. */
+/* { dg-do compile } */
+/* { dg-options "-O2 -mavx512fp16" } */
+
+#define FOO(FUNC,SUFFIX) \
+ _Float16 \
+ foo_##FUNC##_##SUFFIX (_Float16 a) \
+ { \
+ return __builtin_##FUNC##SUFFIX (a); \
+ }
+
+FOO (roundeven, f16);
+FOO (roundeven, f);
+FOO (roundeven, );
+FOO (roundeven, l);
+FOO (trunc, f16);
+FOO (trunc, f);
+FOO (trunc, );
+FOO (trunc, l);
+FOO (ceil, f16);
+FOO (ceil, f);
+FOO (ceil, );
+FOO (ceil, l);
+FOO (floor, f16);
+FOO (floor, f);
+FOO (floor, );
+FOO (floor, l);
+FOO (nearbyint, f16);
+FOO (nearbyint, f);
+FOO (nearbyint, );
+FOO (nearbyint, l);
+FOO (rint, f16);
+FOO (rint, f);
+FOO (rint, );
+FOO (rint, l);
+
+/* { dg-final { scan-assembler-not "vcvtsh2s\[sd\]" } } */
+/* { dg-final { scan-assembler-not "extendhfxf" } } */
+/* { dg-final { scan-assembler-times "vrndscalesh\[^\n\r\]*xmm\[0-9\]" 24 } } */
--
2.27.0
next reply other threads:[~2021-09-24 11:25 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-09-24 11:25 liuhongt [this message]
2021-09-24 16:30 ` Uros Bizjak
2021-09-27 12:53 ` Richard Biener
2021-09-28 2:07 ` Hongtao Liu
2021-09-28 7:45 ` Richard Biener
2021-09-28 20:50 ` Joseph Myers
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20210924112552.2524168-1-hongtao.liu@intel.com \
--to=hongtao.liu@intel.com \
--cc=gcc-patches@gcc.gnu.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
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).