[PATCH] x86: Verify that PUSH/POP can be skipped

[H.J. Lu]

For

---
int f(int);

int advance(int dz)
{
    if (dz > 0)
        return (dz + dz) * dz;
    else
        return dz * f(dz);
}
---

Before r15-1619-g3b9b8d6cfdf593

advance(int):
        push    rbx
        mov     ebx, edi
        test    edi, edi
        jle     .L2
        imul    ebx, edi
        lea     eax, [rbx+rbx]
        pop     rbx
        ret
.L2:
        call    f(int)
        imul    eax, ebx
        pop     rbx
        ret

After

 advance(int):
        test    edi, edi
        jle     .L2
        imul    edi, edi
        lea     eax, [rdi+rdi]
        ret
.L2:
        sub     rsp, 24
        mov     DWORD PTR [rsp+12], edi
        call    f(int)
        imul    eax, DWORD PTR [rsp+12]
        add     rsp, 24
        ret

There's no call in if branch, it's not optimal to push rbx at the entry
of the function, it can be sinked to else branch. When "jle .L2" is not
taken, it can save one push instruction.  Update pr111673.c to verify
that this optimization isn't turned off.

PR rtl-optimization/111673
* gcc.target/i386/pr111673.c: Verify that PUSH/POP can be
skipped.


-- 
H.J.

From 6606ec5573e724295bdceb572ddc2813f021709f Mon Sep 17 00:00:00 2001
From: "H.J. Lu" <hjl.to...@gmail.com>
Date: Fri, 7 Feb 2025 13:49:30 +0800
Subject: [PATCH] x86: Verify that PUSH/POP can be skipped

For

---
int f(int);

int advance(int dz)
{
    if (dz > 0)
        return (dz + dz) * dz;
    else
        return dz * f(dz);
}
---

Before r15-1619-g3b9b8d6cfdf593

advance(int):
        push    rbx
        mov     ebx, edi
        test    edi, edi
        jle     .L2
        imul    ebx, edi
        lea     eax, [rbx+rbx]
        pop     rbx
        ret
.L2:
        call    f(int)
        imul    eax, ebx
        pop     rbx
        ret

After

 advance(int):
        test    edi, edi
        jle     .L2
        imul    edi, edi
        lea     eax, [rdi+rdi]
        ret
.L2:
        sub     rsp, 24
        mov     DWORD PTR [rsp+12], edi
        call    f(int)
        imul    eax, DWORD PTR [rsp+12]
        add     rsp, 24
        ret

There's no call in if branch, it's not optimal to push rbx at the entry
of the function, it can be sinked to else branch. When "jle .L2" is not
taken, it can save one push instruction.  Update pr111673.c to verify
that this optimization isn't turned off.

	PR rtl-optimization/111673
	* gcc.target/i386/pr111673.c: Verify that PUSH/POP can be
	skipped.

Signed-off-by: H.J. Lu <hjl.to...@gmail.com>
---
 gcc/testsuite/gcc.target/i386/pr111673.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/gcc/testsuite/gcc.target/i386/pr111673.c b/gcc/testsuite/gcc.target/i386/pr111673.c
index 8d8a5a764f0..b9ceacf7651 100644
--- a/gcc/testsuite/gcc.target/i386/pr111673.c
+++ b/gcc/testsuite/gcc.target/i386/pr111673.c
@@ -1,5 +1,19 @@
 /* { dg-do compile { target { ! ia32 } } } */
 /* { dg-options "-O2 -fdump-rtl-pro_and_epilogue" } */
+/* Keep labels and directives ('.cfi_startproc', '.cfi_endproc').  */
+/* { dg-final { check-function-bodies "**" "" "" { target "*-*-*" } {^\t?\.}  } } */
+
+/*
+**advance:
+**.LFB0:
+**	.cfi_startproc
+**	testl	%edi, %edi
+**	jle	.L2
+**	imull	%edi, %edi
+**	leal	\(%rdi,%rdi\), %eax
+**	ret
+**...
+*/
 
 /* Verify there is an early return without the prolog and shrink-wrap
    the function. */
-- 
2.48.1