public inbox for gcc-patches@gcc.gnu.org
 help / color / mirror / Atom feed
From: Andrew Stubbs <ams@codesourcery.com>
To: <gcc-patches@gcc.gnu.org>, <richard.sandiford@arm.com>
Subject: Re: [PATCH 11/25] Simplify vec_merge according to the mask.
Date: Thu, 27 Sep 2018 21:14:00 -0000	[thread overview]
Message-ID: <d5d2761d-08c8-7498-f6f9-b4f793000637@codesourcery.com> (raw)
In-Reply-To: <87h8ia29qr.fsf@arm.com>

[-- Attachment #1: Type: text/plain, Size: 402 bytes --]

On 27/09/18 17:19, Richard Sandiford wrote:
> But we wouldn't recurse for PRE_INC, MEM or ASM_OPERANDS, since they
> have the wrong rtx class.  AFAICT no current unary, binary or ternary
> operator has that level of side-effect (and that's a good thing).

OK, in that case I'll remove it and we can cross that bridge if we come 
to it.

This patch should also address your other concerns.

OK?

Andrew

[-- Attachment #2: 180927-simplify-merge-mask.patch --]
[-- Type: text/x-patch, Size: 6623 bytes --]

Simplify vec_merge according to the mask.

This patch was part of the original patch we acquired from Honza and Martin.

It simplifies nested vec_merge operations using the same mask.

Self-tests are included.

2018-09-27  Andrew Stubbs  <ams@codesourcery.com>
	    Jan Hubicka  <jh@suse.cz>
	    Martin Jambor  <mjambor@suse.cz>

	* simplify-rtx.c (simplify_merge_mask): New function.
	(simplify_ternary_operation): Use it, also see if VEC_MERGEs with the
	same masks are used in op1 or op2.
	(test_vec_merge): New function.
	(test_vector_ops): Call test_vec_merge.

diff --git a/gcc/simplify-rtx.c b/gcc/simplify-rtx.c
index b4c6883..9bc5386 100644
--- a/gcc/simplify-rtx.c
+++ b/gcc/simplify-rtx.c
@@ -5578,6 +5578,68 @@ simplify_cond_clz_ctz (rtx x, rtx_code cmp_code, rtx true_val, rtx false_val)
   return NULL_RTX;
 }
 
+/* Try to simplify X given that it appears within operand OP of a
+   VEC_MERGE operation whose mask is MASK.  X need not use the same
+   vector mode as the VEC_MERGE, but it must have the same number of
+   elements.
+
+   Return the simplified X on success, otherwise return NULL_RTX.  */
+
+rtx
+simplify_merge_mask (rtx x, rtx mask, int op)
+{
+  gcc_assert (VECTOR_MODE_P (GET_MODE (x)));
+  poly_uint64 nunits = GET_MODE_NUNITS (GET_MODE (x));
+  if (GET_CODE (x) == VEC_MERGE && rtx_equal_p (XEXP (x, 2), mask))
+    {
+      if (side_effects_p (XEXP (x, 1 - op)))
+	return NULL_RTX;
+
+      return XEXP (x, op);
+    }
+  if (UNARY_P (x)
+      && VECTOR_MODE_P (GET_MODE (XEXP (x, 0)))
+      && known_eq (GET_MODE_NUNITS (GET_MODE (XEXP (x, 0))), nunits))
+    {
+      rtx top0 = simplify_merge_mask (XEXP (x, 0), mask, op);
+      if (top0)
+	return simplify_gen_unary (GET_CODE (x), GET_MODE (x), top0,
+				   GET_MODE (XEXP (x, 0)));
+    }
+  if (BINARY_P (x)
+      && VECTOR_MODE_P (GET_MODE (XEXP (x, 0)))
+      && known_eq (GET_MODE_NUNITS (GET_MODE (XEXP (x, 0))), nunits)
+      && VECTOR_MODE_P (GET_MODE (XEXP (x, 1)))
+      && known_eq (GET_MODE_NUNITS (GET_MODE (XEXP (x, 1))), nunits))
+    {
+      rtx top0 = simplify_merge_mask (XEXP (x, 0), mask, op);
+      rtx top1 = simplify_merge_mask (XEXP (x, 1), mask, op);
+      if (top0 || top1)
+	return simplify_gen_binary (GET_CODE (x), GET_MODE (x),
+				    top0 ? top0 : XEXP (x, 0),
+				    top1 ? top1 : XEXP (x, 1));
+    }
+  if (GET_RTX_CLASS (GET_CODE (x)) == RTX_TERNARY
+      && VECTOR_MODE_P (GET_MODE (XEXP (x, 0)))
+      && known_eq (GET_MODE_NUNITS (GET_MODE (XEXP (x, 0))), nunits)
+      && VECTOR_MODE_P (GET_MODE (XEXP (x, 1)))
+      && known_eq (GET_MODE_NUNITS (GET_MODE (XEXP (x, 1))), nunits)
+      && VECTOR_MODE_P (GET_MODE (XEXP (x, 2)))
+      && known_eq (GET_MODE_NUNITS (GET_MODE (XEXP (x, 2))), nunits))
+    {
+      rtx top0 = simplify_merge_mask (XEXP (x, 0), mask, op);
+      rtx top1 = simplify_merge_mask (XEXP (x, 1), mask, op);
+      rtx top2 = simplify_merge_mask (XEXP (x, 2), mask, op);
+      if (top0 || top1 || top2)
+	return simplify_gen_ternary (GET_CODE (x), GET_MODE (x),
+				     GET_MODE (XEXP (x, 0)),
+				     top0 ? top0 : XEXP (x, 0),
+				     top1 ? top1 : XEXP (x, 1),
+				     top2 ? top2 : XEXP (x, 2));
+    }
+  return NULL_RTX;
+}
+
 \f
 /* Simplify CODE, an operation with result mode MODE and three operands,
    OP0, OP1, and OP2.  OP0_MODE was the mode of OP0 before it became
@@ -5967,6 +6029,16 @@ simplify_ternary_operation (enum rtx_code code, machine_mode mode,
 	  && !side_effects_p (op2) && !side_effects_p (op1))
 	return op0;
 
+      if (!side_effects_p (op2))
+	{
+	  rtx top0 = simplify_merge_mask (op0, op2, 0);
+	  rtx top1 = simplify_merge_mask (op1, op2, 1);
+	  if (top0 || top1)
+	    return simplify_gen_ternary (code, mode, mode,
+					 top0 ? top0 : op0,
+					 top1 ? top1 : op1, op2);
+	}
+
       break;
 
     default:
@@ -6856,6 +6928,69 @@ test_vector_ops_series (machine_mode mode, rtx scalar_reg)
 					    constm1_rtx));
 }
 
+/* Verify simplify_merge_mask works correctly.  */
+
+static void
+test_vec_merge (machine_mode mode)
+{
+  rtx op0 = make_test_reg (mode);
+  rtx op1 = make_test_reg (mode);
+  rtx op2 = make_test_reg (mode);
+  rtx op3 = make_test_reg (mode);
+  rtx op4 = make_test_reg (mode);
+  rtx op5 = make_test_reg (mode);
+  rtx mask1 = make_test_reg (SImode);
+  rtx mask2 = make_test_reg (SImode);
+  rtx vm1 = gen_rtx_VEC_MERGE (mode, op0, op1, mask1);
+  rtx vm2 = gen_rtx_VEC_MERGE (mode, op2, op3, mask1);
+  rtx vm3 = gen_rtx_VEC_MERGE (mode, op4, op5, mask1);
+
+  /* Simple vec_merge.  */
+  ASSERT_EQ (op0, simplify_merge_mask (vm1, mask1, 0));
+  ASSERT_EQ (op1, simplify_merge_mask (vm1, mask1, 1));
+  ASSERT_EQ (NULL_RTX, simplify_merge_mask (vm1, mask2, 0));
+  ASSERT_EQ (NULL_RTX, simplify_merge_mask (vm1, mask2, 1));
+
+  /* Nested vec_merge.
+     It's tempting to make this simplify right down to opN, but we don't
+     because all the simplify_* functions assume that the operands have
+     already been simplified.  */
+  rtx nvm = gen_rtx_VEC_MERGE (mode, vm1, vm2, mask1);
+  ASSERT_EQ (vm1, simplify_merge_mask (nvm, mask1, 0));
+  ASSERT_EQ (vm2, simplify_merge_mask (nvm, mask1, 1));
+
+  /* Intermediate unary op. */
+  rtx unop = gen_rtx_NOT (mode, vm1);
+  ASSERT_RTX_EQ (gen_rtx_NOT (mode, op0),
+		 simplify_merge_mask (unop, mask1, 0));
+  ASSERT_RTX_EQ (gen_rtx_NOT (mode, op1),
+		 simplify_merge_mask (unop, mask1, 1));
+
+  /* Intermediate binary op. */
+  rtx binop = gen_rtx_PLUS (mode, vm1, vm2);
+  ASSERT_RTX_EQ (gen_rtx_PLUS (mode, op0, op2), 
+		 simplify_merge_mask (binop, mask1, 0));
+  ASSERT_RTX_EQ (gen_rtx_PLUS (mode, op1, op3),
+		 simplify_merge_mask (binop, mask1, 1));
+
+  /* Intermediate ternary op. */
+  rtx tenop = gen_rtx_FMA (mode, vm1, vm2, vm3);
+  ASSERT_RTX_EQ (gen_rtx_FMA (mode, op0, op2, op4),
+		 simplify_merge_mask (tenop, mask1, 0));
+  ASSERT_RTX_EQ (gen_rtx_FMA (mode, op1, op3, op5),
+		 simplify_merge_mask (tenop, mask1, 1));
+
+  /* Side effects.  */
+  rtx badop0 = gen_rtx_PRE_INC (mode, op0);
+  rtx badvm = gen_rtx_VEC_MERGE (mode, badop0, op1, mask1);
+  ASSERT_EQ (badop0, simplify_merge_mask (badvm, mask1, 0));
+  ASSERT_EQ (NULL_RTX, simplify_merge_mask (badvm, mask1, 1));
+
+  /* Called indirectly.  */
+  ASSERT_RTX_EQ (gen_rtx_VEC_MERGE (mode, op0, op3, mask1),
+		 simplify_rtx (nvm));
+}
+
 /* Verify some simplifications involving vectors.  */
 
 static void
@@ -6871,6 +7006,7 @@ test_vector_ops ()
 	  if (GET_MODE_CLASS (mode) == MODE_VECTOR_INT
 	      && maybe_gt (GET_MODE_NUNITS (mode), 2))
 	    test_vector_ops_series (mode, scalar_reg);
+	  test_vec_merge (mode);
 	}
     }
 }

  reply	other threads:[~2018-09-27 21:11 UTC|newest]

Thread overview: 187+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-09-05 11:49 [PATCH 00/25] AMD GCN Port ams
2018-09-05 11:49 ` [PATCH 01/25] Handle vectors that don't fit in an integer ams
2018-09-05 11:54   ` Jakub Jelinek
2018-09-14 16:03   ` Richard Sandiford
2018-11-15 17:20     ` Andrew Stubbs
2018-09-05 11:49 ` [PATCH 05/25] Add sorry_at diagnostic function ams
2018-09-05 13:39   ` David Malcolm
2018-09-05 13:41     ` David Malcolm
2018-09-11 10:30       ` Andrew Stubbs
2018-09-05 11:49 ` [PATCH 04/25] SPECIAL_REGNO_P ams
2018-09-05 12:21   ` Joseph Myers
2018-09-11 22:42   ` Jeff Law
2018-09-12 11:30     ` Andrew Stubbs
2018-09-13 10:03       ` Andrew Stubbs
2018-09-13 14:14         ` Andrew Stubbs
2018-09-13 14:39           ` Paul Koning
2018-09-13 14:49             ` Andrew Stubbs
2018-09-13 14:58               ` Paul Koning
2018-09-13 15:22                 ` Andrew Stubbs
2018-09-13 17:13                   ` Paul Koning
2018-09-17 22:59           ` Jeff Law
2018-10-04 19:13         ` Jeff Law
2018-09-12 15:31   ` Richard Henderson
2018-09-12 16:14     ` Andrew Stubbs
2018-09-05 11:49 ` [PATCH 02/25] Propagate address spaces to builtins ams
2018-09-20 13:09   ` Richard Biener
2018-09-22 19:22   ` Andreas Schwab
2018-09-24 16:53     ` Andrew Stubbs
2018-09-24 17:40       ` Andreas Schwab
2018-09-25 14:27     ` [patch] Fix AArch64 ILP ICE Andrew Stubbs
2018-09-26  8:55       ` Andreas Schwab
2018-09-26 13:39       ` Richard Biener
2018-09-26 16:17         ` Andrew Stubbs
2019-09-03 14:01   ` [PATCH 02/25] Propagate address spaces to builtins Kyrill Tkachov
2019-09-03 15:00     ` Jeff Law
2019-09-04 14:21       ` Kyrill Tkachov
2019-09-04 15:29         ` Kyrill Tkachov
2019-09-03 15:43     ` Andrew Stubbs
2018-09-05 11:50 ` [PATCH 12/25] Make default_static_chain return NULL in non-static functions ams
2018-09-17 18:55   ` Richard Sandiford
2018-09-28 14:23     ` Andrew Stubbs
2018-09-05 11:50 ` [PATCH 10/25] Convert BImode vectors ams
2018-09-05 11:56   ` Jakub Jelinek
2018-09-05 12:05   ` Richard Biener
2018-09-05 12:40     ` Andrew Stubbs
2018-09-05 12:44       ` Richard Biener
2018-09-11 14:36         ` Andrew Stubbs
2018-09-12 14:37           ` Richard Biener
2018-09-17  8:51   ` Richard Sandiford
2018-09-05 11:50 ` [PATCH 03/25] Improve TARGET_MANGLE_DECL_ASSEMBLER_NAME ams
2018-09-11 22:56   ` Jeff Law
2018-09-12 14:43     ` Richard Biener
2018-09-12 15:07       ` Jeff Law
2018-09-12 15:16         ` Richard Biener
2018-09-12 16:32           ` Andrew Stubbs
2018-09-12 17:39             ` Julian Brown
2018-09-15  6:01               ` Julian Brown
2018-09-19 15:23                 ` Julian Brown
2018-09-20 12:36                   ` Richard Biener
2018-09-05 11:50 ` [PATCH 08/25] Fix co-array allocation ams
     [not found]   ` <7f5064c3-afc6-b7b5-cade-f03af5b86331@moene.org>
2018-09-05 18:07     ` Janne Blomqvist
2018-09-19 16:38       ` Andrew Stubbs
2018-09-19 22:27         ` Damian Rouson
2018-09-19 22:55           ` Andrew Stubbs
2018-09-20  1:21             ` Damian Rouson
2018-09-20 20:49           ` Thomas Koenig
2018-09-20 20:59             ` Damian Rouson
2018-09-21  7:38             ` Toon Moene
2018-09-23 11:57               ` Janne Blomqvist
2018-09-21 16:37             ` OpenCoarrays integration with gfortran Jerry DeLisle
2018-09-21 19:37               ` Janne Blomqvist
2018-09-21 19:44               ` Richard Biener
2018-09-21 20:25               ` Damian Rouson
2018-09-22  3:47                 ` Jerry DeLisle
2018-09-23 10:41                   ` Toon Moene
2018-09-23 18:03                     ` Bernhard Reutner-Fischer
2018-09-24 11:14                     ` Alastair McKinstry
2018-09-27 12:51                       ` Richard Biener
2018-09-20 15:59         ` [PATCH 08/25] Fix co-array allocation Janne Blomqvist
2018-09-20 16:37           ` Andrew Stubbs
2018-09-05 11:50 ` [PATCH 06/25] Remove constant vec_select restriction ams
2018-09-11 22:44   ` Jeff Law
2018-09-05 11:50 ` [PATCH 09/25] Elide repeated RTL elements ams
2018-09-11 22:46   ` Jeff Law
2018-09-12  8:47     ` Andrew Stubbs
2018-09-12 15:14       ` Jeff Law
2018-09-19 17:25     ` Andrew Stubbs
2018-09-20 11:42       ` Andrew Stubbs
2018-09-26 16:23         ` Andrew Stubbs
2018-10-04 18:24         ` Jeff Law
2018-10-11 14:28           ` Andrew Stubbs
2018-09-05 11:50 ` [PATCH 07/25] [pr82089] Don't sign-extend SFV 1 in BImode ams
2018-09-17  8:46   ` Richard Sandiford
2018-09-26 15:52     ` Andrew Stubbs
2018-09-26 16:49       ` Richard Sandiford
2018-09-27 12:20         ` Andrew Stubbs
2018-09-05 11:51 ` [PATCH 16/25] Fix IRA ICE ams
2018-09-17  9:36   ` Richard Sandiford
2018-09-18 22:00     ` Andrew Stubbs
2018-09-20 12:47       ` Richard Sandiford
2018-09-20 13:36         ` Andrew Stubbs
2018-09-05 11:51 ` [PATCH 15/25] Don't double-count early-clobber matches ams
2018-09-17  9:22   ` Richard Sandiford
2018-09-27 22:54     ` Andrew Stubbs
2018-10-04 22:43       ` Richard Sandiford
2018-10-22 15:36         ` Andrew Stubbs
2018-09-05 11:51 ` [PATCH 11/25] Simplify vec_merge according to the mask ams
2018-09-17  9:08   ` Richard Sandiford
2018-09-20 15:44     ` Andrew Stubbs
2018-09-26 16:26       ` Andrew Stubbs
2018-09-26 16:50       ` Richard Sandiford
2018-09-26 17:06         ` Andrew Stubbs
2018-09-27  7:28           ` Richard Sandiford
2018-09-27 14:13             ` Andrew Stubbs
2018-09-27 16:28               ` Richard Sandiford
2018-09-27 21:14                 ` Andrew Stubbs [this message]
2018-09-28  8:42                   ` Richard Sandiford
2018-09-28 13:50                     ` Andrew Stubbs
2019-02-22  3:40                       ` H.J. Lu
2018-09-05 11:51 ` [PATCH 18/25] Fix interleaving of Fortran stop messages ams
     [not found]   ` <994a9ec6-2494-9a83-cc84-bd8a551142c5@moene.org>
2018-09-05 18:11     ` Janne Blomqvist
2018-09-12 13:55       ` Andrew Stubbs
2018-09-05 11:51 ` [PATCH 17/25] Fix Fortran STOP ams
     [not found]   ` <c0630914-1252-1391-9bf9-f03434d46f5a@moene.org>
2018-09-05 18:09     ` Janne Blomqvist
2018-09-12 13:56       ` Andrew Stubbs
2018-09-05 11:51 ` [PATCH 14/25] Disable inefficient vectorization of elementwise loads/stores ams
2018-09-17  9:16   ` Richard Sandiford
2018-09-17  9:54     ` Andrew Stubbs
2018-09-17 12:40       ` Richard Sandiford
2018-09-17 12:46         ` Andrew Stubbs
2018-09-20 13:01           ` Richard Biener
2018-09-20 13:51             ` Richard Sandiford
2018-09-20 14:14               ` Richard Biener
2018-09-20 14:22                 ` Richard Sandiford
2018-09-05 11:51 ` [PATCH 13/25] Create TARGET_DISABLE_CURRENT_VECTOR_SIZE ams
2018-09-17 19:31   ` Richard Sandiford
2018-09-18  9:02     ` Andrew Stubbs
2018-09-18 11:30       ` Richard Sandiford
2018-09-18 20:27         ` Andrew Stubbs
2018-09-19 13:46           ` Richard Biener
2018-09-28 12:48             ` Andrew Stubbs
2018-10-01  8:05               ` Richard Biener
2018-09-05 11:52 ` [PATCH 23/25] Testsuite: GCN is always PIE ams
2018-09-14 16:39   ` Jeff Law
2018-09-05 11:52 ` [PATCH 19/25] GCN libgfortran ams
     [not found]   ` <41281e27-ad85-e50c-8fed-6f4f6f18289c@moene.org>
2018-09-05 18:14     ` Janne Blomqvist
2018-09-06 12:37       ` Andrew Stubbs
2018-09-11 22:47   ` Jeff Law
2018-09-05 11:52 ` [PATCH 20/25] GCN libgcc ams
2018-09-05 12:32   ` Joseph Myers
2018-11-09 18:49   ` Jeff Law
2018-11-12 12:01     ` Andrew Stubbs
2018-09-05 11:52 ` [PATCH 22/25] Add dg-require-effective-target exceptions ams
2018-09-17  9:40   ` Richard Sandiford
2018-09-17 17:53   ` Mike Stump
2018-09-20 16:10     ` Andrew Stubbs
2018-09-05 11:52 ` [PATCH 24/25] Ignore LLVM's blank lines ams
2018-09-14 16:19   ` Jeff Law
2020-03-23 15:29     ` Thomas Schwinge
2020-03-24 21:05       ` Thomas Schwinge
2018-09-05 11:53 ` [PATCH 25/25] Port testsuite to GCN ams
2018-09-05 13:40 ` [PATCH 21/25] GCN Back-end (part 1/2) Andrew Stubbs
2018-11-09 19:11   ` Jeff Law
2018-11-12 12:13     ` Andrew Stubbs
2018-09-05 13:43 ` [PATCH 21/25] GCN Back-end (part 2/2) Andrew Stubbs
2018-09-05 14:22   ` Joseph Myers
2018-09-05 14:35     ` Andrew Stubbs
2018-09-05 14:44       ` Joseph Myers
2018-09-11 16:25         ` Andrew Stubbs
2018-09-11 16:41           ` Joseph Myers
2018-09-12 13:42     ` Andrew Stubbs
2018-09-12 15:32       ` Joseph Myers
2018-09-12 16:46         ` Andrew Stubbs
2018-09-12 16:50           ` Joseph Myers
2018-11-09 19:40   ` Jeff Law
2018-11-12 12:53     ` Andrew Stubbs
2018-11-12 17:20       ` Segher Boessenkool
2018-11-12 17:52         ` Andrew Stubbs
2018-11-12 18:33           ` Segher Boessenkool
2018-11-12 18:55           ` Jeff Law
2018-11-13 10:23             ` Andrew Stubbs
2018-11-13 10:33               ` Segher Boessenkool
2018-11-16 16:10             ` Segher Boessenkool
2018-11-17 14:07               ` Segher Boessenkool
2018-11-14 22:31       ` Jeff Law
2018-11-15  9:55         ` Andrew Stubbs
2018-11-16 13:33           ` Andrew Stubbs

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=d5d2761d-08c8-7498-f6f9-b4f793000637@codesourcery.com \
    --to=ams@codesourcery.com \
    --cc=gcc-patches@gcc.gnu.org \
    --cc=richard.sandiford@arm.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).