From 58b8c5a87b0bac61bb88e802fc742fdc0d3e6699 Mon Sep 17 00:00:00 2001
From: Jan Beulich <jbeulich@suse.com>
Date: Tue, 23 Jul 2019 08:07:49 +0000
Subject: [PATCH] x86/AVX512: improve generated code for
 mask-to-vector-register conversions

Conversion of comparison results to full vectors does, when VPMOVM2* are
unavailable, not require any intermediate VMOVDQ{A,U}*: Simply use
embedded masking on VPTERNLOG* right away, which is available with
AVX512F (while VPMOVM2{D,Q} are available only with AVX512DQ).

Note that the chosen immediate is only one of many possible ones; I was
trying to make the insn here distinguishable from the pre-existing uses
of vpternlog.

gcc/
2019-07-23  Jan Beulich  <jbeulich@suse.com>

	* config/i386/sse.md (<avx512>_cvtmask2<ssemodesuffix><mode>):
	Require only AVX512F.
	(*<avx512>_cvtmask2<ssemodesuffix><mode>): Likewise.  Add
	alternative expanding to vpternlog.

From-SVN: r273719
---
 gcc/ChangeLog          |  7 +++++++
 gcc/config/i386/sse.md | 16 ++++++++++------
 2 files changed, 17 insertions(+), 6 deletions(-)

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 3e8953fc097..3b39269f085 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,10 @@
+2019-07-23  Jan Beulich  <jbeulich@suse.com>
+
+	* config/i386/sse.md (<avx512>_cvtmask2<ssemodesuffix><mode>):
+	Require only AVX512F.
+	(*<avx512>_cvtmask2<ssemodesuffix><mode>): Likewise.  Add
+	alternative expanding to vpternlog.
+
 2019-07-23  Martin Liska  <mliska@suse.cz>
 
 	* dwarf2out.c (gen_producer_string): Canonize -flto=N
diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index 8abd1617b6f..fa8f13f5796 100644
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -6565,21 +6565,25 @@
 	  (match_dup 2)
 	  (match_dup 3)
 	  (match_operand:<avx512fmaskmode> 1 "register_operand")))]
-  "TARGET_AVX512DQ"
+  "TARGET_AVX512F"
   "{
     operands[2] = CONSTM1_RTX (<MODE>mode);
     operands[3] = CONST0_RTX (<MODE>mode);
   }")
 
 (define_insn "*<avx512>_cvtmask2<ssemodesuffix><mode>"
-  [(set (match_operand:VI48_AVX512VL 0 "register_operand" "=v")
+  [(set (match_operand:VI48_AVX512VL 0 "register_operand" "=v,v")
 	(vec_merge:VI48_AVX512VL
 	  (match_operand:VI48_AVX512VL 2 "vector_all_ones_operand")
 	  (match_operand:VI48_AVX512VL 3 "const0_operand")
-	  (match_operand:<avx512fmaskmode> 1 "register_operand" "k")))]
-  "TARGET_AVX512DQ"
-  "vpmovm2<ssemodesuffix>\t{%1, %0|%0, %1}"
-  [(set_attr "prefix" "evex")
+	  (match_operand:<avx512fmaskmode> 1 "register_operand" "k,Yk")))]
+  "TARGET_AVX512F"
+  "@
+   vpmovm2<ssemodesuffix>\t{%1, %0|%0, %1}
+   vpternlog<ssemodesuffix>\t{$0x81, %0, %0, %0%{%1%}%{z%}|%0%{%1%}%{z%}, %0, %0, 0x81}"
+  [(set_attr "isa" "avx512dq,*")
+   (set_attr "length_immediate" "0,1")
+   (set_attr "prefix" "evex")
    (set_attr "mode" "<sseinsnmode>")])
 
 (define_insn "sse2_cvtps2pd<mask_name>"
-- 
2.30.2