From 95020d33ad6991fe4fbdccf70e7133116cac68f4 Mon Sep 17 00:00:00 2001
From: Roger Sayle <roger@nextmovesoftware.com>
Date: Fri, 16 Jun 2023 16:18:27 +0100
Subject: [PATCH] PR target/31985: Improve memory operand use with doubleword
 add.

This patch addresses the last remaining issue with PR target/31985, that
GCC could make better use of memory addressing modes when implementing
double word addition.  This is achieved by adding a define_insn_and_split
that combines an *add<dwi>3_doubleword with a *concat<mode><dwi>3, so
that the components of the concat can be used directly, without first
being loaded into a double word register.

For test_c in the bugzilla PR:

Before:
        pushl   %ebx
        subl    $16, %esp
        movl    28(%esp), %eax
        movl    36(%esp), %ecx
        movl    32(%esp), %ebx
        movl    24(%esp), %edx
        addl    %ecx, %eax
        adcl    %ebx, %edx
        movl    %eax, 8(%esp)
        movl    %edx, 12(%esp)
        addl    $16, %esp
        popl    %ebx
        ret

After:
test_c:
        subl    $20, %esp
        movl    36(%esp), %eax
        movl    32(%esp), %edx
        addl    28(%esp), %eax
        adcl    24(%esp), %edx
        movl    %eax, 8(%esp)
        movl    %edx, 12(%esp)
        addl    $20, %esp
        ret

2023-06-16  Roger Sayle  <roger@nextmovesoftware.com>
	    Uros Bizjak  <ubizjak@gmail.com>

gcc/ChangeLog
	PR target/31985
	* config/i386/i386.md (*add<dwi>3_doubleword_concat): New
	define_insn_and_split combine *add<dwi>3_doubleword with
	a *concat<mode><dwi>3 for more efficient lowering after reload.

gcc/testsuite/ChangeLog
	PR target/31985
	* gcc.target/i386/pr31985.c: New test case.
---
 gcc/config/i386/i386.md                 | 30 +++++++++++++++++++++++++
 gcc/testsuite/gcc.target/i386/pr31985.c | 14 ++++++++++++
 2 files changed, 44 insertions(+)
 create mode 100644 gcc/testsuite/gcc.target/i386/pr31985.c

diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index 394c767190cc..93794c178613 100644
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -6172,6 +6172,36 @@
 	      (clobber (reg:CC FLAGS_REG))])]
  "split_double_mode (<DWI>mode, &operands[0], 2, &operands[0], &operands[3]);")
 
+(define_insn_and_split "*add<dwi>3_doubleword_concat"
+  [(set (match_operand:<DWI> 0 "register_operand" "=&r")
+	(plus:<DWI>
+	  (any_or_plus:<DWI>
+	    (ashift:<DWI>
+	      (zero_extend:<DWI>
+		(match_operand:DWIH 2 "nonimmediate_operand" "rm"))
+	      (match_operand:QI 3 "const_int_operand"))
+	    (zero_extend:<DWI>
+	      (match_operand:DWIH 4 "nonimmediate_operand" "rm")))
+	  (match_operand:<DWI> 1 "register_operand" "0")))
+   (clobber (reg:CC FLAGS_REG))]
+  "INTVAL (operands[3]) == <MODE_SIZE> * BITS_PER_UNIT"
+  "#"
+  "&& reload_completed"
+  [(parallel [(set (reg:CCC FLAGS_REG)
+		   (compare:CCC
+		     (plus:DWIH (match_dup 1) (match_dup 4))
+		     (match_dup 1)))
+	      (set (match_dup 0)
+		   (plus:DWIH (match_dup 1) (match_dup 4)))])
+   (parallel [(set (match_dup 5)
+		   (plus:DWIH
+		     (plus:DWIH
+		       (ltu:DWIH (reg:CC FLAGS_REG) (const_int 0))
+		       (match_dup 6))
+		     (match_dup 2)))
+	      (clobber (reg:CC FLAGS_REG))])]
+ "split_double_mode (<DWI>mode, &operands[0], 2, &operands[0], &operands[5]);")
+
 (define_insn "*add<mode>_1"
   [(set (match_operand:SWI48 0 "nonimmediate_operand" "=rm,r,r,r")
 	(plus:SWI48
diff --git a/gcc/testsuite/gcc.target/i386/pr31985.c b/gcc/testsuite/gcc.target/i386/pr31985.c
new file mode 100644
index 000000000000..a6de1b5b1431
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr31985.c
@@ -0,0 +1,14 @@
+/* { dg-do compile { target ia32 } } */
+/* { dg-options "-O2" } */
+
+void test_c (unsigned int a, unsigned int b, unsigned int c, unsigned int d)
+{
+  volatile unsigned int x, y;
+  unsigned long long __a = b | ((unsigned long long)a << 32);
+  unsigned long long __b = d | ((unsigned long long)c << 32);
+  unsigned long long __c = __a + __b;
+  x = (unsigned int)(__c & 0xffffffff);
+  y = (unsigned int)(__c >> 32);
+}
+
+/* { dg-final { scan-assembler-times "movl" 4 } } */
-- 
2.47.2