Hi:
For struct initialization, when it fits in a TImode, gcc will use
pinsr insn which causes poor codegen described in PR93897 and PR96562.
Bootstrap is ok, regression test is ok for i386/x86-64 backend.
Ok for trunk?
ChangeLog
gcc/
PR target/96562
PR target/93897
* config/i386/i386-expand.c (ix86_expand_pinsr): Don't use
pinsr for TImode.
gcc/testsuite/
* gcc.target/i386/pr96562-1.c: New test.
--
BR,
Hongtao
From f91e0f6a7da7de0ed1f1b10d07b1fe53f377330e Mon Sep 17 00:00:00 2001
From: liuhongt <hongtao....@intel.com>
Date: Wed, 12 Aug 2020 10:48:17 +0800
Subject: [PATCH] Don't use pinsr for store_bit_field when dst is TImode.
gcc/
PR target/96562
PR target/93897
* config/i386/i386-expand.c (ix86_expand_pinsr): Don't use
pinsr for TImode.
gcc/testsuite/
* gcc.target/i386/pr96562-1.c: New test.
---
gcc/config/i386/i386-expand.c | 1 -
gcc/testsuite/gcc.target/i386/pr96562-1.c | 81 +++++++++++++++++++++++
2 files changed, 81 insertions(+), 1 deletion(-)
create mode 100644 gcc/testsuite/gcc.target/i386/pr96562-1.c
diff --git a/gcc/config/i386/i386-expand.c b/gcc/config/i386/i386-expand.c
index e194214804b..29809d69782 100644
--- a/gcc/config/i386/i386-expand.c
+++ b/gcc/config/i386/i386-expand.c
@@ -20333,7 +20333,6 @@ ix86_expand_pinsr (rtx *operands)
case E_V4SImode:
case E_V2DImode:
case E_V1TImode:
- case E_TImode:
{
machine_mode srcmode, dstmode;
rtx (*pinsr)(rtx, rtx, rtx, rtx);
diff --git a/gcc/testsuite/gcc.target/i386/pr96562-1.c b/gcc/testsuite/gcc.target/i386/pr96562-1.c
new file mode 100644
index 00000000000..6ebeeb1fb17
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr96562-1.c
@@ -0,0 +1,81 @@
+/* { dg-do compile} */
+/* { dg-options "-msse4.1 -O2" } */
+/* { dg-final { scan-assembler-not "pinsr" } } */
+
+typedef struct
+{
+ long long a;
+ int b;
+} st1;
+
+typedef struct
+{
+ long long a;
+ int b;
+ short c;
+} st2;
+
+typedef struct
+{
+ long long a;
+ int b;
+ short c;
+ char d;
+} st3;
+
+typedef struct
+{
+ int b;
+ long long a;
+} st4;
+
+typedef struct
+{
+ short c;
+ int b;
+ long long a;
+} st5;
+
+typedef struct
+{
+ char d;
+ short c;
+ int b;
+ long long a;
+} st6;
+
+st1
+foo1 (long long a, int b)
+{
+ return (st1){a, b};
+}
+
+st2
+foo2 (long long a, int b, short c)
+{
+ return (st2){a, b, c};
+}
+
+st3
+foo3 (long long a, int b, short c, char d)
+{
+ return (st3){a, b, c, d};
+}
+
+st4
+foo4 (long long a, int b)
+{
+ return (st4){b, a};
+}
+
+st5
+foo5 (long long a, int b, short c)
+{
+ return (st5){c, b, a};
+}
+
+st6
+foo6 (long long a, int b, short c, char d)
+{
+ return (st6){d, c, b, a};
+}
--
2.18.1
