From ec919cfcef8d7fcbaab24d0e0d472c65e5329ca6 Mon Sep 17 00:00:00 2001
From: Jakub Jelinek <jakub@redhat.com>
Date: Mon, 30 Mar 2020 17:38:21 +0200
Subject: [PATCH] Fix vextract* masked patterns [PR93069]

The AVX512F documentation clearly states that in instructions where the
destination is a memory only merging-masking is possible, not zero-masking,
and the assembler enforces that.

The testcase in this patch fails to assemble because of
Error: unsupported masking for `vextracti32x8'
on
        vextracti32x8   $0x0, %zmm1, -64(%rsp){%k1}{z}
For the vector extraction patterns, we apparently have 7 *_maskm patterns
that only accept memory destinations and rtx_equal_p merge-masking source
for it, 7 *<mask_name> corresponding patterns that allow memory destination
only for the non-masked cases (through <store_mask_constraint>), then 2
*<mask_name> patterns (lo ssehalf V16FI and lo ssehalf VI8F_256 ones) which
do allow memory destination even for masked cases and are the cause of the
testsuite failure, because we must not allow C constraint if the destination
is m, and finally one pair of patterns (separate * and *_mask, hi ssehalf
VI4F_256), which has another issue (for which I don't have a testcase
though), where if it would match zero-masking with register destination,
it wouldn't emit the needed {z} into assembly.
The attached patch fixes those 3 issues only, perhaps more suitable for
backporting.

2020-03-30  Jakub Jelinek  <jakub@redhat.com>

	PR target/93069
	* config/i386/sse.md (vec_extract_lo_<mode><mask_name>): Use
	<store_mask_constraint> instead of m in output operand constraint.
	(vec_extract_hi_<mode><mask_name>): Use <mask_operand2> instead of
	%{%3%}.

	* gcc.target/i386/avx512vl-pr93069.c: New test.
	* gcc.dg/vect/pr93069.c: New test.
---
 gcc/ChangeLog                                    |  8 ++++++++
 gcc/config/i386/sse.md                           |  8 +++++---
 gcc/testsuite/ChangeLog                          |  6 ++++++
 gcc/testsuite/gcc.dg/vect/pr93069.c              | 10 ++++++++++
 gcc/testsuite/gcc.target/i386/avx512vl-pr93069.c | 12 ++++++++++++
 5 files changed, 41 insertions(+), 3 deletions(-)
 create mode 100644 gcc/testsuite/gcc.dg/vect/pr93069.c
 create mode 100644 gcc/testsuite/gcc.target/i386/avx512vl-pr93069.c

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 4e0545de429..c9867651c95 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,11 @@
+2020-03-30  Jakub Jelinek  <jakub@redhat.com>
+
+	PR target/93069
+	* config/i386/sse.md (vec_extract_lo_<mode><mask_name>): Use
+	<store_mask_constraint> instead of m in output operand constraint.
+	(vec_extract_hi_<mode><mask_name>): Use <mask_operand2> instead of
+	%{%3%}.
+
 2020-03-30  Alan Modra  <amodra@gmail.com>
 
 	* config/rs6000/rs6000.c (rs6000_call_aix): Emit cookie to pattern.
diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index 8f5902292c6..3221542a8cb 100644
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -8693,7 +8693,8 @@
 })
 
 (define_insn "vec_extract_lo_<mode><mask_name>"
-  [(set (match_operand:<ssehalfvecmode> 0 "nonimmediate_operand" "=v,v,m")
+  [(set (match_operand:<ssehalfvecmode> 0 "<store_mask_predicate>"
+					  "=v,v,<store_mask_constraint>")
 	(vec_select:<ssehalfvecmode>
 	  (match_operand:V16FI 1 "<store_mask_predicate>"
 				 "v,<store_mask_constraint>,v")
@@ -8750,7 +8751,8 @@
 })
 
 (define_insn "vec_extract_lo_<mode><mask_name>"
-  [(set (match_operand:<ssehalfvecmode> 0 "<store_mask_predicate>" "=v,v,m")
+  [(set (match_operand:<ssehalfvecmode> 0 "<store_mask_predicate>"
+					  "=v,v,<store_mask_constraint>")
 	(vec_select:<ssehalfvecmode>
 	  (match_operand:VI8F_256 1 "<store_mask_predicate>"
 				    "v,<store_mask_constraint>,v")
@@ -8760,7 +8762,7 @@
    && (<mask_applied> || !(MEM_P (operands[0]) && MEM_P (operands[1])))"
 {
   if (<mask_applied>)
-    return "vextract<shuffletype>64x2\t{$0x0, %1, %0%{%3%}|%0%{%3%}, %1, 0x0}";
+    return "vextract<shuffletype>64x2\t{$0x0, %1, %0<mask_operand2>|%0<mask_operand2>, %1, 0x0}";
   else
     return "#";
 }
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index 2384d0beb69..b07ba6d87d2 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,9 @@
+2020-03-30  Jakub Jelinek  <jakub@redhat.com>
+
+	PR target/93069
+	* gcc.target/i386/avx512vl-pr93069.c: New test.
+	* gcc.dg/vect/pr93069.c: New test.
+
 2020-03-29  Iain Buclaw  <ibuclaw@gdcproject.org>
 
 	* lib/gdc-utils.exp: (gdc-convert-args): Handle compilation test
diff --git a/gcc/testsuite/gcc.dg/vect/pr93069.c b/gcc/testsuite/gcc.dg/vect/pr93069.c
new file mode 100644
index 00000000000..45c740dbe9e
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/pr93069.c
@@ -0,0 +1,10 @@
+/* PR target/93069 */
+/* { dg-do assemble { target vect_simd_clones } } */
+/* { dg-options "-O2 -fopenmp-simd" } */
+
+#pragma omp declare simd
+int
+foo (int x, int y)
+{
+  return x == 0 ? x : y;
+}
diff --git a/gcc/testsuite/gcc.target/i386/avx512vl-pr93069.c b/gcc/testsuite/gcc.target/i386/avx512vl-pr93069.c
new file mode 100644
index 00000000000..b38b5ad32bb
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/avx512vl-pr93069.c
@@ -0,0 +1,12 @@
+/* PR target/93069 */
+/* { dg-do assemble { target vect_simd_clones } } */
+/* { dg-options "-O2 -fopenmp-simd -mtune=skylake-avx512" } */
+/* { dg-additional-options "-mavx512vl" { target avx512vl } } */
+/* { dg-additional-options "-mavx512dq" { target avx512dq } } */
+
+#pragma omp declare simd
+int
+foo (int x, int y)
+{
+  return x == 0 ? x : y;
+}
-- 
2.30.2