From 5738a64f8b3cf132b88b39af84b9f5f5a9a1554c Mon Sep 17 00:00:00 2001
From: "H.J. Lu" <hjl.tools@gmail.com>
Date: Tue, 3 Aug 2021 06:17:22 -0700
Subject: [PATCH] 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 bed9cd9da189..21fe51bba40e 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 000000000000..67ea40587dd3
--- /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 000000000000..ba19064077bf
--- /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"
-- 
2.47.2