public inbox for gcc-patches@gcc.gnu.org
 help / color / mirror / Atom feed
From: Jan Beulich <jbeulich@suse.com>
To: "gcc-patches@gcc.gnu.org" <gcc-patches@gcc.gnu.org>
Cc: Hongtao Liu <hongtao.liu@intel.com>,
	Kirill Yukhin <kirill.yukhin@gmail.com>
Subject: [PATCH 4/5] x86: further PR target/100711-like splitting
Date: Wed, 21 Jun 2023 08:27:51 +0200	[thread overview]
Message-ID: <b2607ae7-045a-d1bc-2cc8-d2f114677cb6@suse.com> (raw)
In-Reply-To: <04f99abe-a563-d093-23b7-4abf0f91633d@suse.com>

With respective two-operand bitwise operations now expressable by a
single VPTERNLOG, add splitters to also deal with ior and xor
counterparts of the original and-only case. Note that the splitters need
to be separate, as the placement of "not" differs in the final insns
(*iornot<mode>3, *xnor<mode>3) which are intended to pick up one half of
the result.

gcc/

	* config/i386/sse.md: New splitters to simplify
	not;vec_duplicate;{ior,xor} as vec_duplicate;{iornot,xnor}.

gcc/testsuite/

	* gcc.target/i386/pr100711-4.c: New test.
	* gcc.target/i386/pr100711-5.c: New test.

--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -17366,6 +17366,36 @@
 			(match_dup 2)))]
   "operands[3] = gen_reg_rtx (<MODE>mode);")
 
+(define_split
+  [(set (match_operand:VI 0 "register_operand")
+	(ior:VI
+	  (vec_duplicate:VI
+	    (not:<ssescalarmode>
+	      (match_operand:<ssescalarmode> 1 "nonimmediate_operand")))
+	  (match_operand:VI 2 "vector_operand")))]
+  "<MODE_SIZE> == 64 || TARGET_AVX512VL
+   || (TARGET_AVX512F && !TARGET_PREFER_AVX256)"
+  [(set (match_dup 3)
+	(vec_duplicate:VI (match_dup 1)))
+   (set (match_dup 0)
+	(ior:VI (not:VI (match_dup 3)) (match_dup 2)))]
+  "operands[3] = gen_reg_rtx (<MODE>mode);")
+
+(define_split
+  [(set (match_operand:VI 0 "register_operand")
+	(xor:VI
+	  (vec_duplicate:VI
+	    (not:<ssescalarmode>
+	      (match_operand:<ssescalarmode> 1 "nonimmediate_operand")))
+	  (match_operand:VI 2 "vector_operand")))]
+  "<MODE_SIZE> == 64 || TARGET_AVX512VL
+   || (TARGET_AVX512F && !TARGET_PREFER_AVX256)"
+  [(set (match_dup 3)
+	(vec_duplicate:VI (match_dup 1)))
+   (set (match_dup 0)
+	(not:VI (xor:VI (match_dup 3) (match_dup 2))))]
+  "operands[3] = gen_reg_rtx (<MODE>mode);")
+
 (define_insn "*andnot<mode>3_mask"
   [(set (match_operand:VI48_AVX512VL 0 "register_operand" "=v")
 	(vec_merge:VI48_AVX512VL
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr100711-4.c
@@ -0,0 +1,42 @@
+/* { dg-do compile } */
+/* { dg-options "-mavx512bw -mno-avx512vl -mprefer-vector-width=512 -O2" } */
+
+typedef char v64qi __attribute__ ((vector_size (64)));
+typedef short v32hi __attribute__ ((vector_size (64)));
+typedef int v16si __attribute__ ((vector_size (64)));
+typedef long long v8di __attribute__((vector_size (64)));
+
+v64qi foo_v64qi (char a, v64qi b)
+{
+    return (__extension__ (v64qi) {~a, ~a, ~a, ~a, ~a, ~a, ~a, ~a,
+                                   ~a, ~a, ~a, ~a, ~a, ~a, ~a, ~a,
+                                   ~a, ~a, ~a, ~a, ~a, ~a, ~a, ~a,
+                                   ~a, ~a, ~a, ~a, ~a, ~a, ~a, ~a,
+				   ~a, ~a, ~a, ~a, ~a, ~a, ~a, ~a,
+				   ~a, ~a, ~a, ~a, ~a, ~a, ~a, ~a,
+				   ~a, ~a, ~a, ~a, ~a, ~a, ~a, ~a,
+				   ~a, ~a, ~a, ~a, ~a, ~a, ~a, ~a}) | b;
+}
+
+v32hi foo_v32hi (short a, v32hi b)
+{
+    return (__extension__ (v32hi) {~a, ~a, ~a, ~a, ~a, ~a, ~a, ~a,
+                                   ~a, ~a, ~a, ~a, ~a, ~a, ~a, ~a,
+                                   ~a, ~a, ~a, ~a, ~a, ~a, ~a, ~a,
+				   ~a, ~a, ~a, ~a, ~a, ~a, ~a, ~a}) | b;
+}
+
+v16si foo_v16si (int a, v16si b)
+{
+    return (__extension__ (v16si) {~a, ~a, ~a, ~a, ~a, ~a, ~a, ~a,
+				   ~a, ~a, ~a, ~a, ~a, ~a, ~a, ~a}) | b;
+}
+
+v8di foo_v8di (long long a, v8di b)
+{
+    return (__extension__ (v8di) {~a, ~a, ~a, ~a, ~a, ~a, ~a, ~a}) | b;
+}
+
+/* { dg-final { scan-assembler-times "vpternlog\[dq\]\[ \\t\]+\\\$0xbb" 4 { target { ! ia32 } } } } */
+/* { dg-final { scan-assembler-times "vpternlog\[dq\]\[ \\t\]+\\\$0xbb" 2 { target { ia32 } } } } */
+/* { dg-final { scan-assembler-times "vpternlog\[dq\]\[ \\t\]+\\\$0xdd" 2 { target { ia32 } } } } */
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr100711-5.c
@@ -0,0 +1,40 @@
+/* { dg-do compile } */
+/* { dg-options "-mavx512bw -mno-avx512vl -mprefer-vector-width=512 -O2" } */
+
+typedef char v64qi __attribute__ ((vector_size (64)));
+typedef short v32hi __attribute__ ((vector_size (64)));
+typedef int v16si __attribute__ ((vector_size (64)));
+typedef long long v8di __attribute__((vector_size (64)));
+
+v64qi foo_v64qi (char a, v64qi b)
+{
+    return (__extension__ (v64qi) {~a, ~a, ~a, ~a, ~a, ~a, ~a, ~a,
+                                   ~a, ~a, ~a, ~a, ~a, ~a, ~a, ~a,
+                                   ~a, ~a, ~a, ~a, ~a, ~a, ~a, ~a,
+                                   ~a, ~a, ~a, ~a, ~a, ~a, ~a, ~a,
+				   ~a, ~a, ~a, ~a, ~a, ~a, ~a, ~a,
+				   ~a, ~a, ~a, ~a, ~a, ~a, ~a, ~a,
+				   ~a, ~a, ~a, ~a, ~a, ~a, ~a, ~a,
+				   ~a, ~a, ~a, ~a, ~a, ~a, ~a, ~a}) ^ b;
+}
+
+v32hi foo_v32hi (short a, v32hi b)
+{
+    return (__extension__ (v32hi) {~a, ~a, ~a, ~a, ~a, ~a, ~a, ~a,
+                                   ~a, ~a, ~a, ~a, ~a, ~a, ~a, ~a,
+                                   ~a, ~a, ~a, ~a, ~a, ~a, ~a, ~a,
+				   ~a, ~a, ~a, ~a, ~a, ~a, ~a, ~a}) ^ b;
+}
+
+v16si foo_v16si (int a, v16si b)
+{
+    return (__extension__ (v16si) {~a, ~a, ~a, ~a, ~a, ~a, ~a, ~a,
+				   ~a, ~a, ~a, ~a, ~a, ~a, ~a, ~a}) ^ b;
+}
+
+v8di foo_v8di (long long a, v8di b)
+{
+    return (__extension__ (v8di) {~a, ~a, ~a, ~a, ~a, ~a, ~a, ~a}) ^ b;
+}
+
+/* { dg-final { scan-assembler-times "vpternlog\[dq\]\[ \\t\]+\\\$0x99" 4 } } */


  parent reply	other threads:[~2023-06-21  6:27 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-06-21  6:24 [PATCH 0/5] x86: make better use of VPTERNLOG{D,Q} Jan Beulich
2023-06-21  6:25 ` [PATCH 1/5] x86: use VPTERNLOG for further bitwise two-vector operations Jan Beulich
2023-06-25  4:42   ` Hongtao Liu
2023-06-25  5:52     ` Jan Beulich
2023-06-25  7:13       ` Hongtao Liu
2023-06-25  7:23         ` Hongtao Liu
2023-06-25  7:30           ` Hongtao Liu
2023-06-25 13:35             ` Jan Beulich
2023-06-26  0:42               ` Hongtao Liu
2023-06-21  6:27 ` [PATCH 2/5] x86: use VPTERNLOG also for certain andnot forms Jan Beulich
2023-06-25  4:58   ` Hongtao Liu
2023-06-21  6:27 ` [PATCH 3/5] x86: allow memory operand for AVX2 splitter for PR target/100711 Jan Beulich
2023-06-25  4:58   ` Hongtao Liu
2023-06-21  6:27 ` Jan Beulich [this message]
2023-06-25  5:06   ` [PATCH 4/5] x86: further PR target/100711-like splitting Hongtao Liu
2023-06-25  6:16     ` Jan Beulich
2023-06-25  6:27       ` Hongtao Liu
2023-06-21  6:28 ` [PATCH 5/5] x86: yet more " Jan Beulich
2023-06-25  5:12   ` Hongtao Liu
2023-06-25  6:25     ` Jan Beulich
2023-06-25  6:35       ` Hongtao Liu
2023-06-25  6:41         ` Hongtao Liu
2023-11-06 11:10           ` Jan Beulich
2023-11-06 13:48             ` Hongtao Liu

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=b2607ae7-045a-d1bc-2cc8-d2f114677cb6@suse.com \
    --to=jbeulich@suse.com \
    --cc=gcc-patches@gcc.gnu.org \
    --cc=hongtao.liu@intel.com \
    --cc=kirill.yukhin@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).