public inbox for gcc-patches@gcc.gnu.org
 help / color / mirror / Atom feed
From: liuhongt <hongtao.liu@intel.com>
To: gcc-patches@gcc.gnu.org
Subject: [PATCH] Extend 64-bit vector bit_op patterns with ?r alternative
Date: Thu, 14 Jul 2022 13:33:51 +0800	[thread overview]
Message-ID: <20220714053351.7073-1-hongtao.liu@intel.com> (raw)
In-Reply-To: <CAFULd4a2im9GfjFo8X5u79SinBU1WiTLOAThsmELyG__y3Pxvg@mail.gmail.com>

And split it to GPR-version instruction after reload.

> ?r was introduced under the assumption that we want vector values
> mostly in vector registers. Currently there are no instructions with
> memory or immediate operand, so that made sense at the time. Let's
> keep ?r until logic instructions with mem/imm operands are introduced.
> So, for the patch that adds 64-bit vector logic in GPR, I would advise
> to first introduce only register operands. mem/imm operands should be
Update patch to add ?r to 64-bit bit_op patterns.

Bootstrapped and regtested on x86_64-pc-linux-gnu{-m32,}.
No big imact on SPEC2017(Most same binary).

Ok for trunk?

gcc/ChangeLog:

	PR target/106038
	* config/i386/mmx.md (<code><mode>3): Expand
	with (clobber (reg:CC flags_reg)) under TARGET_64BIT
	(mmx_code><mode>3): Ditto.
	(*mmx_<code><mode>3_gpr): New define_insn, add post_reload
	splitter after it.
	(mmx_andnot<mode>3_gpr): Ditto.
	(<code><mode>3): Extend follow define_split from VI_16_32 to
	VI_16_32_64.
	(*andnot<mode>3): Ditto.
	(mmxinsnmode): New mode attribute.
	(VI_16_32_64): New mode iterator.
	(*mov<mode>_imm): Refactor with mmxinsnmode.
	* config/i386/predicates.md

gcc/testsuite/ChangeLog:

	* gcc.target/i386/pr106038-1.c: New test.
	* gcc.target/i386/pr106038-2.c: New test.
	* gcc.target/i386/pr106038-3.c: New test.
---
 gcc/config/i386/mmx.md                     | 131 +++++++++++++++------
 gcc/testsuite/gcc.target/i386/pr106038-1.c |  61 ++++++++++
 gcc/testsuite/gcc.target/i386/pr106038-2.c |  35 ++++++
 gcc/testsuite/gcc.target/i386/pr106038-3.c |  17 +++
 4 files changed, 210 insertions(+), 34 deletions(-)
 create mode 100644 gcc/testsuite/gcc.target/i386/pr106038-1.c
 create mode 100644 gcc/testsuite/gcc.target/i386/pr106038-2.c
 create mode 100644 gcc/testsuite/gcc.target/i386/pr106038-3.c

diff --git a/gcc/config/i386/mmx.md b/gcc/config/i386/mmx.md
index 3294c1e6274..5f7e40bd7a1 100644
--- a/gcc/config/i386/mmx.md
+++ b/gcc/config/i386/mmx.md
@@ -75,6 +75,11 @@ (define_mode_iterator V_16_32_64
     (V8QI "TARGET_64BIT") (V4HI "TARGET_64BIT") (V4HF "TARGET_64BIT")
     (V2SI "TARGET_64BIT") (V2SF "TARGET_64BIT")])
 
+(define_mode_iterator VI_16_32_64
+   [V2QI V4QI V2HI
+    (V8QI "TARGET_64BIT") (V4HI "TARGET_64BIT")
+    (V2SI "TARGET_64BIT")])
+
 ;; V2S* modes
 (define_mode_iterator V2FI [V2SF V2SI])
 
@@ -86,6 +91,14 @@ (define_mode_attr mmxvecsize
   [(V8QI "b") (V4QI "b") (V2QI "b")
    (V4HI "w") (V2HI "w") (V2SI "d") (V1DI "q")])
 
+;; Mapping to same size integral mode.
+(define_mode_attr mmxinsnmode
+  [(V8QI "DI") (V4QI "SI") (V2QI "HI")
+   (V4HI "DI") (V2HI "SI")
+   (V2SI "DI")
+   (V4HF "DI") (V2HF "SI")
+   (V2SF "DI")])
+
 (define_mode_attr mmxdoublemode
   [(V8QI "V8HI") (V4HI "V4SI")])
 
@@ -350,22 +363,7 @@ (define_insn_and_split "*mov<mode>_imm"
   HOST_WIDE_INT val = ix86_convert_const_vector_to_integer (operands[1],
 							    <MODE>mode);
   operands[1] = GEN_INT (val);
-  machine_mode mode;
-  switch (GET_MODE_SIZE (<MODE>mode))
-    {
-    case 2:
-      mode = HImode;
-      break;
-    case 4:
-      mode = SImode;
-      break;
-    case 8:
-      mode = DImode;
-      break;
-    default:
-      gcc_unreachable ();
-    }
-  operands[0] = lowpart_subreg (mode, operands[0], <MODE>mode);
+  operands[0] = lowpart_subreg (<mmxinsnmode>mode, operands[0], <MODE>mode);
 })
 
 ;; For TARGET_64BIT we always round up to 8 bytes.
@@ -2878,6 +2876,31 @@ (define_insn "mmx_andnot<mode>3"
    (set_attr "type" "mmxadd,sselog,sselog,sselog")
    (set_attr "mode" "DI,TI,TI,TI")])
 
+(define_insn "mmx_andnot<mode>3_gpr"
+  [(set (match_operand:MMXMODEI 0 "register_operand" "=?r,y,x,x,v")
+	(and:MMXMODEI
+	  (not:MMXMODEI (match_operand:MMXMODEI 1 "register_operand" "r,0,0,x,v"))
+	  (match_operand:MMXMODEI 2 "register_mmxmem_operand" "r,ym,x,x,v")))
+   (clobber (reg:CC FLAGS_REG))]
+  "TARGET_64BIT && (TARGET_MMX || TARGET_SSE2)"
+  "#"
+  [(set_attr "isa" "bmi,*,sse2_noavx,avx,avx512vl")
+   (set_attr "mmx_isa" "*,native,*,*,*")
+   (set_attr "type" "alu,mmxadd,sselog,sselog,sselog")
+   (set_attr "mode" "DI,DI,TI,TI,TI")])
+
+(define_split
+  [(set (match_operand:MMXMODEI 0 "register_operand")
+	(and:MMXMODEI
+	  (not:MMXMODEI (match_operand:MMXMODEI 1 "register_mmxmem_operand"))
+	  (match_operand:MMXMODEI 2 "register_mmxmem_operand")))
+   (clobber (reg:CC FLAGS_REG))]
+  "reload_completed
+   && (TARGET_MMX || TARGET_MMX_WITH_SSE)
+   && !GENERAL_REGNO_P (REGNO (operands[0]))"
+  [(set (match_dup 0)
+	(and:<MODE> (not:<MODE> (match_dup 1)) (match_dup 2)))])
+
 (define_insn "*andnot<mode>3"
   [(set (match_operand:VI_16_32 0 "register_operand" "=?&r,?r,x,x,v")
         (and:VI_16_32
@@ -2892,20 +2915,20 @@ (define_insn "*andnot<mode>3"
    (set_attr "mode" "SI,SI,TI,TI,TI")])
 
 (define_split
-  [(set (match_operand:VI_16_32 0 "general_reg_operand")
-        (and:VI_16_32
-	  (not:VI_16_32 (match_operand:VI_16_32 1 "general_reg_operand"))
-	  (match_operand:VI_16_32 2 "general_reg_operand")))
+  [(set (match_operand:VI_16_32_64 0 "general_reg_operand")
+        (and:VI_16_32_64
+	  (not:VI_16_32_64 (match_operand:VI_16_32_64 1 "general_reg_operand"))
+	  (match_operand:VI_16_32_64 2 "general_reg_operand")))
    (clobber (reg:CC FLAGS_REG))]
   "TARGET_BMI && reload_completed"
   [(parallel
      [(set (match_dup 0)
-	   (and:SI (not:SI (match_dup 1)) (match_dup 2)))
+	   (and:<mmxinsnmode> (not:<mmxinsnmode> (match_dup 1)) (match_dup 2)))
       (clobber (reg:CC FLAGS_REG))])]
 {
-  operands[2] = lowpart_subreg (SImode, operands[2], <MODE>mode);
-  operands[1] = lowpart_subreg (SImode, operands[1], <MODE>mode);
-  operands[0] = lowpart_subreg (SImode, operands[0], <MODE>mode);
+  operands[2] = lowpart_subreg (<mmxinsnmode>mode, operands[2], <MODE>mode);
+  operands[1] = lowpart_subreg (<mmxinsnmode>mode, operands[1], <MODE>mode);
+  operands[0] = lowpart_subreg (<mmxinsnmode>mode, operands[0], <MODE>mode);
 })
 
 (define_split
@@ -2948,14 +2971,28 @@ (define_expand "mmx_<code><mode>3"
 	  (match_operand:MMXMODEI 1 "register_mmxmem_operand")
 	  (match_operand:MMXMODEI 2 "register_mmxmem_operand")))]
   "TARGET_MMX || TARGET_MMX_WITH_SSE"
-  "ix86_fixup_binary_operands_no_copy (<CODE>, <MODE>mode, operands);")
+{
+  ix86_fixup_binary_operands_no_copy (<CODE>, <MODE>mode, operands);
+  if (TARGET_64BIT)
+  {
+    ix86_expand_binary_operator (<CODE>, <MODE>mode, operands);
+    DONE;
+  }
+})
 
 (define_expand "<code><mode>3"
   [(set (match_operand:MMXMODEI 0 "register_operand")
 	(any_logic:MMXMODEI
 	  (match_operand:MMXMODEI 1 "register_operand")
 	  (match_operand:MMXMODEI 2 "register_operand")))]
-  "TARGET_MMX_WITH_SSE")
+  "TARGET_MMX_WITH_SSE"
+{
+  if (TARGET_64BIT)
+    {
+      ix86_expand_binary_operator (<CODE>, <MODE>mode, operands);
+      DONE;
+    }
+})
 
 (define_insn "*mmx_<code><mode>3"
   [(set (match_operand:MMXMODEI 0 "register_operand" "=y,x,x,v")
@@ -2974,6 +3011,32 @@ (define_insn "*mmx_<code><mode>3"
    (set_attr "type" "mmxadd,sselog,sselog,sselog")
    (set_attr "mode" "DI,TI,TI,TI")])
 
+(define_insn "*mmx_<code><mode>3_gpr"
+  [(set (match_operand:MMXMODEI 0 "register_operand" "=?r,y,x,x,v")
+        (any_logic:MMXMODEI
+	  (match_operand:MMXMODEI 1 "register_mmxmem_operand" "%0,0,0,x,v")
+	  (match_operand:MMXMODEI 2 "register_mmxmem_operand" "r,ym,x,x,v")))
+   (clobber (reg:CC FLAGS_REG))]
+  "TARGET_64BIT && (TARGET_MMX || TARGET_SSE2)
+   && ix86_binary_operator_ok (<CODE>, <MODE>mode, operands)"
+  "#"
+  [(set_attr "isa" "*,*,sse2_noavx,avx,avx512vl")
+   (set_attr "mmx_isa" "*,native,*,*,*")
+   (set_attr "type" "alu,mmxadd,sselog,sselog,sselog")
+   (set_attr "mode" "DI,DI,TI,TI,TI")])
+
+(define_split
+  [(set (match_operand:MMXMODEI 0 "register_operand")
+	(any_logic:MMXMODEI
+	  (match_operand:MMXMODEI 1 "register_mmxmem_operand")
+	  (match_operand:MMXMODEI 2 "register_mmxmem_operand")))
+   (clobber (reg:CC FLAGS_REG))]
+  "reload_completed && (TARGET_MMX || TARGET_MMX_WITH_SSE)
+   && !GENERAL_REGNO_P (REGNO (operands[0]))"
+ [(set (match_dup 0)
+       (any_logic:<MODE> (match_dup 1)
+			 (match_dup 2)))])
+
 (define_insn "<code><mode>3"
   [(set (match_operand:VI_16_32 0 "register_operand" "=?r,x,x,v")
         (any_logic:VI_16_32
@@ -2987,20 +3050,20 @@ (define_insn "<code><mode>3"
    (set_attr "mode" "SI,TI,TI,TI")])
 
 (define_split
-  [(set (match_operand:VI_16_32 0 "general_reg_operand")
-        (any_logic:VI_16_32
-	  (match_operand:VI_16_32 1 "general_reg_operand")
-	  (match_operand:VI_16_32 2 "general_reg_operand")))
+  [(set (match_operand:VI_16_32_64 0 "general_reg_operand")
+        (any_logic:VI_16_32_64
+	  (match_operand:VI_16_32_64 1 "general_reg_operand")
+	  (match_operand:VI_16_32_64 2 "general_reg_operand")))
    (clobber (reg:CC FLAGS_REG))]
   "reload_completed"
   [(parallel
      [(set (match_dup 0)
-	   (any_logic:SI (match_dup 1) (match_dup 2)))
+	   (any_logic:<mmxinsnmode> (match_dup 1) (match_dup 2)))
       (clobber (reg:CC FLAGS_REG))])]
 {
-  operands[2] = lowpart_subreg (SImode, operands[2], <MODE>mode);
-  operands[1] = lowpart_subreg (SImode, operands[1], <MODE>mode);
-  operands[0] = lowpart_subreg (SImode, operands[0], <MODE>mode);
+  operands[2] = lowpart_subreg (<mmxinsnmode>mode, operands[2], <MODE>mode);
+  operands[1] = lowpart_subreg (<mmxinsnmode>mode, operands[1], <MODE>mode);
+  operands[0] = lowpart_subreg (<mmxinsnmode>mode, operands[0], <MODE>mode);
 })
 
 (define_split
diff --git a/gcc/testsuite/gcc.target/i386/pr106038-1.c b/gcc/testsuite/gcc.target/i386/pr106038-1.c
new file mode 100644
index 00000000000..c026329c843
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr106038-1.c
@@ -0,0 +1,61 @@
+/* { dg-do compile } */
+/* { dg-options "-msse2 -O2" } */
+/* { dg-final { scan-assembler-not "xmm" { xfail *-*-* } } } */
+
+void
+foo (char* a, char* __restrict b)
+{
+  a[0] &= b[0];
+  a[1] &= b[1];
+  a[2] &= b[2];
+  a[3] &= b[3];
+}
+
+void
+foo1 (char* a, char* __restrict b)
+{
+  a[0] &= b[0];
+  a[1] &= b[1];
+}
+
+void
+foo2 (char* a, char* __restrict b)
+{
+  a[0] &= b[0];
+  a[1] &= b[1];
+  a[2] &= b[2];
+  a[3] &= b[3];
+  a[4] &= b[4];
+  a[5] &= b[5];
+  a[6] &= b[6];
+  a[7] &= b[7];
+}
+
+void
+foo3 (char* a, char* __restrict b)
+{
+  a[0] &= 1;
+  a[1] &= 2;
+  a[2] &= 3;
+  a[3] &= 3;
+}
+
+void
+foo4 (char* a, char* __restrict b)
+{
+  a[0] &= 1;
+  a[1] &= 2;
+}
+
+void
+foo5 (char* a, char* __restrict b)
+{
+  a[0] &= 1;
+  a[1] &= 2;
+  a[2] &= 2;
+  a[3] &= 3;
+  a[4] &= 4;
+  a[5] &= 5;
+  a[6] &= 6;
+  a[7] &= 7;
+}
diff --git a/gcc/testsuite/gcc.target/i386/pr106038-2.c b/gcc/testsuite/gcc.target/i386/pr106038-2.c
new file mode 100644
index 00000000000..87d2070784f
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr106038-2.c
@@ -0,0 +1,35 @@
+/* { dg-do compile } */
+/* { dg-options "-msse2 -O2" } */
+/* { dg-final { scan-assembler-not "xmm" { xfail *-*-* } } } */
+
+void
+foo (short* a, short* __restrict b)
+{
+  a[0] &= b[0];
+  a[1] &= b[1];
+  a[2] &= b[2];
+  a[3] &= b[3];
+}
+
+void
+foo1 (short* a, short* __restrict b)
+{
+  a[0] &= b[0];
+  a[1] &= b[1];
+}
+
+void
+foo3 (short* a, short* __restrict b)
+{
+  a[0] &= 1;
+  a[1] &= 2;
+  a[2] &= 3;
+  a[3] &= 3;
+}
+
+void
+foo4 (short* a, short* __restrict b)
+{
+  a[0] &= 1;
+  a[1] &= 2;
+}
diff --git a/gcc/testsuite/gcc.target/i386/pr106038-3.c b/gcc/testsuite/gcc.target/i386/pr106038-3.c
new file mode 100644
index 00000000000..91f7112395f
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr106038-3.c
@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-options "-msse2 -O2 -mtune=generic" } */
+/* { dg-final { scan-assembler-not "xmm" { xfail { ! ia32 } } } } */
+
+void
+foo1 (int* a, int* __restrict b)
+{
+  a[0] &= b[0];
+  a[1] &= b[1];
+}
+
+void
+foo4 (int* a, int* __restrict b)
+{
+  a[0] &= 1;
+  a[1] &= 2;
+}
-- 
2.18.1


  reply	other threads:[~2022-07-14  5:33 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-07-11  1:15 [PATCH] Allocate general register(memory/immediate) for 16/32/64-bit vector bit_op patterns liuhongt
2022-07-11  8:02 ` Uros Bizjak
2022-07-12  6:37   ` Hongtao Liu
2022-07-12  7:15     ` Uros Bizjak
2022-07-14  5:33       ` liuhongt [this message]
2022-07-14  7:22         ` [PATCH] Extend 64-bit vector bit_op patterns with ?r alternative Uros Bizjak
2022-07-14  9:32           ` Hongtao Liu
2022-07-14  9:46             ` Uros Bizjak
2022-07-18  1:59               ` [PATCH] Extend 16/32-bit vector bit_op patterns with (m, 0, i)(vertical) alternative liuhongt
2022-07-18  6:28                 ` [PATCH] Extend 16/32-bit vector bit_op patterns with (m,0,i)(vertical) alternative Uros Bizjak
2022-07-19  6:07                   ` [PATCH V2] Extend 16/32-bit vector bit_op patterns with (m, 0, i) alternative liuhongt
2022-07-19  6:34                     ` Uros Bizjak
2022-07-19  6:56                       ` Hongtao Liu
2022-07-19  9:37                         ` Uros Bizjak
2022-07-20  2:37                           ` Hongtao Liu
2022-07-20  6:14                             ` Uros Bizjak
2022-07-20  6:18                               ` Uros Bizjak
2022-07-20  6:54                                 ` Hongtao Liu
2022-07-20  7:18                                   ` Uros Bizjak
2022-07-20  7:22                                     ` Hongtao Liu
2022-07-21  5:18                                       ` [PATCH V3] " liuhongt
2022-07-21  5:55                                         ` 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=20220714053351.7073-1-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).