On Wed, Aug 4, 2021 at 11:46 AM Uros Bizjak <ubiz...@gmail.com> wrote:
>
> On Wed, Aug 4, 2021 at 3:34 PM H.J. Lu <hjl.to...@gmail.com> wrote:
> >
> > On Tue, Aug 3, 2021 at 6:56 AM H.J. Lu <hjl.to...@gmail.com> wrote:
> > >
> > > 1. Update x86 STORE_MAX_PIECES to use OImode and XImode only if inter-unit
> > > move is enabled since x86 uses vec_duplicate, which is enabled only when
> > > inter-unit move is enabled, to implement store_by_pieces.
> > > 2. Update op_by_pieces_d::op_by_pieces_d to set m_max_size to
> > > STORE_MAX_PIECES for store_by_pieces and to COMPARE_MAX_PIECES for
> > > compare_by_pieces.
> > >
> > > gcc/
> > >
> > >         PR target/101742
> > >         * expr.c (op_by_pieces_d::op_by_pieces_d): Set m_max_size to
> > >         STORE_MAX_PIECES for store_by_pieces and to COMPARE_MAX_PIECES
> > >         for compare_by_pieces.
> > >         * config/i386/i386.h (STORE_MAX_PIECES): Use OImode and XImode
> > >         only if TARGET_INTER_UNIT_MOVES_TO_VEC is true.
> > >
> > > gcc/testsuite/
> > >
> > >         PR target/101742
> > >         * gcc.target/i386/pr101742a.c: New test.
> > >         * gcc.target/i386/pr101742b.c: Likewise.
> > > ---
> > >  gcc/config/i386/i386.h                    | 20 +++++++++++---------
> > >  gcc/expr.c                                |  6 +++++-
> > >  gcc/testsuite/gcc.target/i386/pr101742a.c | 16 ++++++++++++++++
> > >  gcc/testsuite/gcc.target/i386/pr101742b.c |  4 ++++
> > >  4 files changed, 36 insertions(+), 10 deletions(-)
> > >  create mode 100644 gcc/testsuite/gcc.target/i386/pr101742a.c
> > >  create mode 100644 gcc/testsuite/gcc.target/i386/pr101742b.c
> > >
> > > diff --git a/gcc/config/i386/i386.h b/gcc/config/i386/i386.h
> > > index bed9cd9da18..9b416abd5f4 100644
> > > --- a/gcc/config/i386/i386.h
> > > +++ b/gcc/config/i386/i386.h
> > > @@ -1783,15 +1783,17 @@ typedef struct ix86_args {
> > >  /* STORE_MAX_PIECES is the number of bytes at a time that we can
> > >     store efficiently.  */
> > >  #define STORE_MAX_PIECES \
> > > -  ((TARGET_AVX512F && !TARGET_PREFER_AVX256) \
> > > -   ? 64 \
> > > -   : ((TARGET_AVX \
> > > -       && !TARGET_PREFER_AVX128 \
> > > -       && !TARGET_AVX256_SPLIT_UNALIGNED_STORE) \
> > > -      ? 32 \
> > > -      : ((TARGET_SSE2 \
> > > -         && TARGET_SSE_UNALIGNED_STORE_OPTIMAL) \
> > > -        ? 16 : UNITS_PER_WORD)))
> > > +  (TARGET_INTER_UNIT_MOVES_TO_VEC \
> > > +   ? ((TARGET_AVX512F && !TARGET_PREFER_AVX256) \
> > > +      ? 64 \
> > > +      : ((TARGET_AVX \
> > > +         && !TARGET_PREFER_AVX128 \
> > > +         && !TARGET_AVX256_SPLIT_UNALIGNED_STORE) \
> > > +         ? 32 \
> > > +         : ((TARGET_SSE2 \
> > > +             && TARGET_SSE_UNALIGNED_STORE_OPTIMAL) \
> > > +             ? 16 : UNITS_PER_WORD))) \
> > > +   : UNITS_PER_WORD)
> > >
> > >  /* If a memory-to-memory move would take MOVE_RATIO or more simple
> > >     move-instruction pairs, we will do a cpymem or libcall instead.
> >
> > expr.c has been fixed.   Here is the v2 patch for x86 backend.
> > OK for master?
>
> OK, but please add the comment about vec_duplicate before the define
> to explain the situation with TARGET_INTER_UNIT_MOVES_TO_VEC.

This is what I am checking in with

/* STORE_MAX_PIECES is the number of bytes at a time that we can store
   efficiently.  Allow 16/32/64 bytes only if inter-unit move is enabled
   since vec_duplicate enabled by inter-unit move is used to implement
   store_by_pieces of 16/32/64 bytes.  */

> Thanks,
> Uros.

Thanks.

-- 
H.J.
From 9487c165afb5b6083a3fc09a2e8b7bcabfe28765 Mon Sep 17 00:00:00 2001
From: "H.J. Lu" <hjl.to...@gmail.com>
Date: Tue, 3 Aug 2021 06:17:22 -0700
Subject: [PATCH v3] x86: Update STORE_MAX_PIECES

Update STORE_MAX_PIECES to allow 16/32/64 bytes only if inter-unit move
is enabled since vec_duplicate enabled by inter-unit move is used to
implement store_by_pieces of 16/32/64 bytes.

gcc/

	PR target/101742
	* config/i386/i386.h (STORE_MAX_PIECES): Allow 16/32/64 bytes
	only if TARGET_INTER_UNIT_MOVES_TO_VEC is true.

gcc/testsuite/

	PR target/101742
	* gcc.target/i386/pr101742a.c: New test.
	* gcc.target/i386/pr101742b.c: Likewise.
---
 gcc/config/i386/i386.h                    | 26 +++++++++++++----------
 gcc/testsuite/gcc.target/i386/pr101742a.c | 16 ++++++++++++++
 gcc/testsuite/gcc.target/i386/pr101742b.c |  4 ++++
 3 files changed, 35 insertions(+), 11 deletions(-)
 create mode 100644 gcc/testsuite/gcc.target/i386/pr101742a.c
 create mode 100644 gcc/testsuite/gcc.target/i386/pr101742b.c

diff --git a/gcc/config/i386/i386.h b/gcc/config/i386/i386.h
index bed9cd9da18..21fe51bba40 100644
--- a/gcc/config/i386/i386.h
+++ b/gcc/config/i386/i386.h
@@ -1780,18 +1780,22 @@ typedef struct ix86_args {
 	  && TARGET_SSE_UNALIGNED_STORE_OPTIMAL) \
 	 ? 16 : UNITS_PER_WORD)))
 
-/* STORE_MAX_PIECES is the number of bytes at a time that we can
-   store efficiently.  */
+/* STORE_MAX_PIECES is the number of bytes at a time that we can store
+   efficiently.  Allow 16/32/64 bytes only if inter-unit move is enabled
+   since vec_duplicate enabled by inter-unit move is used to implement
+   store_by_pieces of 16/32/64 bytes.  */
 #define STORE_MAX_PIECES \
-  ((TARGET_AVX512F && !TARGET_PREFER_AVX256) \
-   ? 64 \
-   : ((TARGET_AVX \
-       && !TARGET_PREFER_AVX128 \
-       && !TARGET_AVX256_SPLIT_UNALIGNED_STORE) \
-      ? 32 \
-      : ((TARGET_SSE2 \
-	  && TARGET_SSE_UNALIGNED_STORE_OPTIMAL) \
-	 ? 16 : UNITS_PER_WORD)))
+  (TARGET_INTER_UNIT_MOVES_TO_VEC \
+   ? ((TARGET_AVX512F && !TARGET_PREFER_AVX256) \
+      ? 64 \
+      : ((TARGET_AVX \
+	  && !TARGET_PREFER_AVX128 \
+	  && !TARGET_AVX256_SPLIT_UNALIGNED_STORE) \
+	  ? 32 \
+	  : ((TARGET_SSE2 \
+	      && TARGET_SSE_UNALIGNED_STORE_OPTIMAL) \
+	      ? 16 : UNITS_PER_WORD))) \
+   : UNITS_PER_WORD)
 
 /* If a memory-to-memory move would take MOVE_RATIO or more simple
    move-instruction pairs, we will do a cpymem or libcall instead.
diff --git a/gcc/testsuite/gcc.target/i386/pr101742a.c b/gcc/testsuite/gcc.target/i386/pr101742a.c
new file mode 100644
index 00000000000..67ea40587dd
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr101742a.c
@@ -0,0 +1,16 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-O3 -mtune=nano-x2" } */
+
+int n2;
+
+__attribute__ ((simd)) char
+w7 (void)
+{
+  short int xb = n2;
+  int qp;
+
+  for (qp = 0; qp < 2; ++qp)
+    xb = xb < 1;
+
+  return xb;
+}
diff --git a/gcc/testsuite/gcc.target/i386/pr101742b.c b/gcc/testsuite/gcc.target/i386/pr101742b.c
new file mode 100644
index 00000000000..ba19064077b
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr101742b.c
@@ -0,0 +1,4 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-O3 -mtune=nano-x2 -mtune-ctrl=sse_unaligned_store_optimal" } */
+
+#include "pr101742a.c"
-- 
2.31.1

Reply via email to