From: "Roger Sayle" <roger@nextmovesoftware.com>
To: "'Uros Bizjak'" <ubizjak@gmail.com>
Cc: <gcc-patches@gcc.gnu.org>
Subject: RE: [x86 PATCH] PR rtl-optimization/96692: ((A|B)^C)^A using andn with -mbmi.
Date: Mon, 4 Jul 2022 18:27:29 +0100 [thread overview]
Message-ID: <007501d88fcb$56f15820$04d40860$@nextmovesoftware.com> (raw)
In-Reply-To: <CAFULd4bqesr_QcjkKVLN53Lxbx-rV57kk3bhyOag36oTwFwFGQ@mail.gmail.com>
[-- Attachment #1: Type: text/plain, Size: 3745 bytes --]
Hi Uros,
Thanks for the review. This patch implements all of your suggestions, both
removing ix86_pre_reload_split from the combine splitter(s), and dividing
the original splitter up into four simpler variants, that use match_dup to
handle the variants/permutations caused by operator commutativity.
This revised patch has been tested on x86_64-pc-linux-gnu with make bootstrap
and make -k check, both with and without --target_board=unix{-m32} with no
new failures. Ok for mainline?
2022-07-04 Roger Sayle <roger@nextmovesoftware.com>
Uroš Bizjak <ubizjak@gmail.com>
gcc/ChangeLog
PR rtl-optimization/96692
* config/i386/i386.md (define_split): Split ((A | B) ^ C) ^ D
as (X & ~Y) ^ Z on target BMI when either C or D is A or B.
gcc/testsuite/ChangeLog
PR rtl-optimization/96692
* gcc.target/i386/bmi-andn-4.c: New test case.
Thanks again,
Roger
--
> -----Original Message-----
> From: Uros Bizjak <ubizjak@gmail.com>
> Sent: 26 June 2022 18:08
> To: Roger Sayle <roger@nextmovesoftware.com>
> Cc: gcc-patches@gcc.gnu.org
> Subject: Re: [x86 PATCH] PR rtl-optimization/96692: ((A|B)^C)^A using andn with
> -mbmi.
>
> On Sun, Jun 26, 2022 at 2:04 PM Roger Sayle <roger@nextmovesoftware.com>
> wrote:
> >
> >
> > This patch addresses PR rtl-optimization/96692 on x86_64, by providing
> > a define_split for combine to convert the three operation ((A|B)^C)^D
> > into a two operation sequence using andn when either A or B is the
> > same register as C or D. This is essentially a reassociation problem
> > that's only a win if the target supports an and-not instruction (as with -mbmi).
> >
> > Hence for the new test case:
> >
> > int f(int a, int b, int c)
> > {
> > return (a ^ b) ^ (a | c);
> > }
> >
> > GCC on x86_64-pc-linux-gnu wth -O2 -mbmi would previously generate:
> >
> > xorl %edi, %esi
> > orl %edx, %edi
> > movl %esi, %eax
> > xorl %edi, %eax
> > ret
> >
> > but with this patch now generates:
> >
> > andn %edx, %edi, %eax
> > xorl %esi, %eax
> > ret
> >
> > I'll investigate whether this optimization can also be implemented
> > more generically in simplify_rtx when the backend provides accurate
> > rtx_costs for "(and (not ..." (as there's no optab for andn).
> >
> > This patch has been tested on x86_64-pc-linux-gnu with make bootstrap
> > and make -k check, both with and without --target_board=unix{-m32},
> > with no new failures. Ok for mainline?
> >
> >
> > 2022-06-26 Roger Sayle <roger@nextmovesoftware.com>
> >
> > gcc/ChangeLog
> > PR rtl-optimization/96692
> > * config/i386/i386.md (define_split): Split ((A | B) ^ C) ^ D
> > as (X & ~Y) ^ Z on target BMI when either C or D is A or B.
> >
> > gcc/testsuite/ChangeLog
> > PR rtl-optimization/96692
> > * gcc.target/i386/bmi-andn-4.c: New test case.
>
> + "TARGET_BMI
> + && ix86_pre_reload_split ()
> + && (rtx_equal_p (operands[1], operands[3])
> + || rtx_equal_p (operands[1], operands[4])
> + || (REG_P (operands[2])
> + && (rtx_equal_p (operands[2], operands[3])
> + || rtx_equal_p (operands[2], operands[4]))))"
>
> You don't need a ix86_pre_reload_split for combine splitter*
>
> OTOH, please split the pattern to two for each commutative operand and use
> (match_dup x) instead. Something similar to [1].
>
> *combine splitter is described in the documentation as the splitter pattern that
> does *not* match any existing insn pattern.
>
> [1] https://gcc.gnu.org/pipermail/gcc-patches/2022-June/596804.html
>
> Uros.
[-- Attachment #2: patchbm3.txt --]
[-- Type: text/plain, Size: 3670 bytes --]
diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index 20c3b9a..d114754 100644
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -10522,6 +10522,82 @@
(set (match_dup 0) (match_op_dup 1
[(and:SI (match_dup 3) (match_dup 2))
(const_int 0)]))])
+
+;; Variant 1 of 4: Split ((A | B) ^ A) ^ C as (B & ~A) ^ C.
+(define_split
+ [(set (match_operand:SWI48 0 "register_operand")
+ (xor:SWI48
+ (xor:SWI48
+ (ior:SWI48 (match_operand:SWI48 1 "register_operand")
+ (match_operand:SWI48 2 "nonimmediate_operand"))
+ (match_dup 1))
+ (match_operand:SWI48 3 "nonimmediate_operand")))
+ (clobber (reg:CC FLAGS_REG))]
+ "TARGET_BMI"
+ [(parallel
+ [(set (match_dup 4) (and:SWI48 (not:SWI48 (match_dup 1)) (match_dup 2)))
+ (clobber (reg:CC FLAGS_REG))])
+ (parallel
+ [(set (match_dup 0) (xor:SWI48 (match_dup 4) (match_dup 3)))
+ (clobber (reg:CC FLAGS_REG))])]
+ "operands[4] = gen_reg_rtx (<MODE>mode);")
+
+;; Variant 2 of 4: Split ((A | B) ^ B) ^ C as (A & ~B) ^ C.
+(define_split
+ [(set (match_operand:SWI48 0 "register_operand")
+ (xor:SWI48
+ (xor:SWI48
+ (ior:SWI48 (match_operand:SWI48 1 "register_operand")
+ (match_operand:SWI48 2 "register_operand"))
+ (match_dup 2))
+ (match_operand:SWI48 3 "nonimmediate_operand")))
+ (clobber (reg:CC FLAGS_REG))]
+ "TARGET_BMI"
+ [(parallel
+ [(set (match_dup 4) (and:SWI48 (not:SWI48 (match_dup 2)) (match_dup 1)))
+ (clobber (reg:CC FLAGS_REG))])
+ (parallel
+ [(set (match_dup 0) (xor:SWI48 (match_dup 4) (match_dup 3)))
+ (clobber (reg:CC FLAGS_REG))])]
+ "operands[4] = gen_reg_rtx (<MODE>mode);")
+
+;; Variant 3 of 4: Split ((A | B) ^ C) ^ A as (B & ~A) ^ C.
+(define_split
+ [(set (match_operand:SWI48 0 "register_operand")
+ (xor:SWI48
+ (xor:SWI48
+ (ior:SWI48 (match_operand:SWI48 1 "register_operand")
+ (match_operand:SWI48 2 "nonimmediate_operand"))
+ (match_operand:SWI48 3 "nonimmediate_operand"))
+ (match_dup 1)))
+ (clobber (reg:CC FLAGS_REG))]
+ "TARGET_BMI"
+ [(parallel
+ [(set (match_dup 4) (and:SWI48 (not:SWI48 (match_dup 1)) (match_dup 2)))
+ (clobber (reg:CC FLAGS_REG))])
+ (parallel
+ [(set (match_dup 0) (xor:SWI48 (match_dup 4) (match_dup 3)))
+ (clobber (reg:CC FLAGS_REG))])]
+ "operands[4] = gen_reg_rtx (<MODE>mode);")
+
+;; Variant 4 of 4: Split ((A | B) ^ C) ^ B as (A & ~B) ^ C.
+(define_split
+ [(set (match_operand:SWI48 0 "register_operand")
+ (xor:SWI48
+ (xor:SWI48
+ (ior:SWI48 (match_operand:SWI48 1 "register_operand")
+ (match_operand:SWI48 2 "register_operand"))
+ (match_operand:SWI48 3 "nonimmediate_operand"))
+ (match_dup 2)))
+ (clobber (reg:CC FLAGS_REG))]
+ "TARGET_BMI"
+ [(parallel
+ [(set (match_dup 4) (and:SWI48 (not:SWI48 (match_dup 2)) (match_dup 1)))
+ (clobber (reg:CC FLAGS_REG))])
+ (parallel
+ [(set (match_dup 0) (xor:SWI48 (match_dup 4) (match_dup 3)))
+ (clobber (reg:CC FLAGS_REG))])]
+ "operands[4] = gen_reg_rtx (<MODE>mode);")
\f
;; Logical inclusive and exclusive OR instructions
diff --git a/gcc/testsuite/gcc.target/i386/bmi-andn-4.c b/gcc/testsuite/gcc.target/i386/bmi-andn-4.c
new file mode 100644
index 0000000..fb89529
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/bmi-andn-4.c
@@ -0,0 +1,9 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mbmi" } */
+
+int f(int a, int b, int c)
+{
+ return (a ^ b) ^ (a | c);
+}
+
+/* { dg-final { scan-assembler "andn\[ \\t\]+" } } */
next prev parent reply other threads:[~2022-07-04 17:27 UTC|newest]
Thread overview: 5+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-06-26 12:04 Roger Sayle
2022-06-26 17:07 ` Uros Bizjak
2022-06-27 15:03 ` Segher Boessenkool
2022-07-04 17:27 ` Roger Sayle [this message]
2022-07-04 18:51 ` Uros Bizjak
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='007501d88fcb$56f15820$04d40860$@nextmovesoftware.com' \
--to=roger@nextmovesoftware.com \
--cc=gcc-patches@gcc.gnu.org \
--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).