From: liuhongt <hongtao.liu@intel.com>
To: gcc-patches@gcc.gnu.org
Cc: crazylht@gmail.com, hjl.tools@gmail.com, ubizjak@gmail.com
Subject: [PATCH] [x86] Fix incorrect implementation for mm_cvtsbh_ss.
Date: Wed, 23 Nov 2022 20:28:20 +0800 [thread overview]
Message-ID: <20221123122820.3150670-1-hongtao.liu@intel.com> (raw)
After supporting real __bf16 type, implementation of mm_cvtsbh_ss went wrong.
The patch supports extendbfsf2/truncsfbf2 with pslld/psrld,
and then refined the intrinsic with implicit conversion.
Bootstrapped and regtested on x86_64-pc-linux-gnu{-m32,}.
Ok for trunk?
gcc/ChangeLog:
PR target/107748
* config/i386/avx512bf16intrin.h (_mm_cvtsbh_ss): Refined.
* config/i386/i386.md (extendbfsf2): New define_insn.
(truncsfbf2): Ditto.
gcc/testsuite/ChangeLog:
* gcc.target/i386/extendbfsf.c: New test.
* gcc.target/i386/avx512bf16-cvtsbh2ss-1.c: Adjust testcase.
---
gcc/config/i386/avx512bf16intrin.h | 4 +--
gcc/config/i386/i386.md | 33 ++++++++++++++++++-
.../gcc.target/i386/avx512bf16-cvtsbh2ss-1.c | 3 +-
gcc/testsuite/gcc.target/i386/extendbfsf.c | 16 +++++++++
4 files changed, 50 insertions(+), 6 deletions(-)
create mode 100644 gcc/testsuite/gcc.target/i386/extendbfsf.c
diff --git a/gcc/config/i386/avx512bf16intrin.h b/gcc/config/i386/avx512bf16intrin.h
index ea1d0125b3f..4a071bcd75a 100644
--- a/gcc/config/i386/avx512bf16intrin.h
+++ b/gcc/config/i386/avx512bf16intrin.h
@@ -46,9 +46,7 @@ extern __inline float
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
_mm_cvtsbh_ss (__bf16 __A)
{
- union{ float a; unsigned int b;} __tmp;
- __tmp.b = ((unsigned int)(__A)) << 16;
- return __tmp.a;
+ return __A;
}
/* vcvtne2ps2bf16 */
diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index 01faa911b77..f5215596d44 100644
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -4961,6 +4961,21 @@ (define_insn "*extendhf<mode>2"
(set_attr "prefix" "evex")
(set_attr "mode" "<MODE>")])
+(define_insn "extendbfsf2"
+ [(set (match_operand:SF 0 "register_operand" "=x,Yw")
+ (float_extend:SF
+ (match_operand:BF 1 "register_operand" " 0,Yw")))]
+ "TARGET_SSE2"
+ "@
+ pslld\t{$16, %0|%0, 16}
+ vpslld\t{$16, %1, %0|%0, %1, 16}"
+ [(set_attr "isa" "noavx,avx")
+ (set_attr "type" "sseishft")
+ (set_attr "length_immediate" "1")
+ (set_attr "prefix_data16" "1,*")
+ (set_attr "prefix" "orig,vex")
+ (set_attr "mode" "TI")
+ (set_attr "memory" "none")])
(define_expand "extend<mode>xf2"
[(set (match_operand:XF 0 "nonimmediate_operand")
@@ -5177,7 +5192,23 @@ (define_insn "*trunc<mode>hf2"
[(set_attr "type" "ssecvt")
(set_attr "prefix" "evex")
(set_attr "mode" "HF")])
-\f
+
+(define_insn "truncsfbf2"
+ [(set (match_operand:BF 0 "register_operand" "=x,Yw")
+ (float_truncate:BF
+ (match_operand:SF 1 "register_operand" " 0,Yw")))]
+ "TARGET_SSE2"
+ "@
+ psrld\t{$16, %0|%0, 16}
+ vpsrld\t{$16, %1, %0|%0, %1, 16}"
+ [(set_attr "isa" "noavx,avx")
+ (set_attr "type" "sseishft")
+ (set_attr "length_immediate" "1")
+ (set_attr "prefix_data16" "1,*")
+ (set_attr "prefix" "orig,vex")
+ (set_attr "mode" "TI")
+ (set_attr "memory" "none")])
+
;; Signed conversion to DImode.
(define_expand "fix_truncxfdi2"
diff --git a/gcc/testsuite/gcc.target/i386/avx512bf16-cvtsbh2ss-1.c b/gcc/testsuite/gcc.target/i386/avx512bf16-cvtsbh2ss-1.c
index 8e929e6f159..edf30b583b9 100644
--- a/gcc/testsuite/gcc.target/i386/avx512bf16-cvtsbh2ss-1.c
+++ b/gcc/testsuite/gcc.target/i386/avx512bf16-cvtsbh2ss-1.c
@@ -1,8 +1,7 @@
/* { dg-do compile } */
/* { dg-options "-mavx512bf16 -O2" } */
/* { dg-additional-options "-fno-PIE -mfpmath=sse" { target ia32 } } */
-/* { dg-final { scan-assembler-times "sall\[ \\t\]+\[^\{\n\]*16" 1 } } */
-/* { dg-final { scan-assembler-times "movl" 1 } } */
+/* { dg-final { scan-assembler-times "pslld" 1 } } */
#include <immintrin.h>
diff --git a/gcc/testsuite/gcc.target/i386/extendbfsf.c b/gcc/testsuite/gcc.target/i386/extendbfsf.c
new file mode 100644
index 00000000000..f1b4c218742
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/extendbfsf.c
@@ -0,0 +1,16 @@
+/* { dg-do compile } */
+/* { dg-options "-msse2 -O2" } */
+/* { dg-final { scan-assembler-times "pslld" 1 } } */
+/* { dg-final { scan-assembler-times "psrld" 1 } } */
+
+float
+extendsfbf (__bf16 a)
+{
+ return a;
+}
+
+__bf16
+truncsfbf (float a)
+{
+ return a;
+}
--
2.27.0
next reply other threads:[~2022-11-23 12:30 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-11-23 12:28 liuhongt [this message]
2022-11-23 12:40 ` Jakub Jelinek
2022-11-23 12:59 ` Hongtao Liu
2022-11-24 1:22 ` [PATCH v2] [x86] Fix incorrect _mm_cvtsbh_ss liuhongt
2022-11-24 8:53 ` Jakub Jelinek
2022-11-24 11:30 ` Hongtao Liu
2022-11-25 5:39 ` [PATCH V3] " liuhongt
2022-11-25 9:18 ` Jakub Jelinek
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=20221123122820.3150670-1-hongtao.liu@intel.com \
--to=hongtao.liu@intel.com \
--cc=crazylht@gmail.com \
--cc=gcc-patches@gcc.gnu.org \
--cc=hjl.tools@gmail.com \
--cc=ubizjak@gmail.com \
/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).