[Bug target/112760] [14 Regression] wrong code with -O2 -fno-dce -fno-guess-branch-probability -m8bit-idiv -mavx --param=max-cse-insns=0 and __builtin_add_overflow_p()

["zsojka at seznam dot cz" <gcc-bugzilla@gcc.gnu.org>]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=112760

--- Comment #1 from Zdenek Sojka <zsojka at seznam dot cz> ---
Created attachment 56716
  --> https://gcc.gnu.org/bugzilla/attachment.cgi?id=56716&action=edit
more complex testcase, with less compiler flags

Attached a testcase that needs only -O2 -mavx; might be a different issue,
though.

$ x86_64-pc-linux-gnu-gcc -m32 -O2 -mavx testcase.c
$ ./a.out 
Aborted


$ diff -u a-testcase.GOOD.s a-testcase.BAD.s 
--- a-testcase.GOOD.s   2023-11-29 08:53:43.058791568 +0100
+++ a-testcase.BAD.s    2023-11-29 08:52:39.878792460 +0100
@@ -4,7 +4,7 @@
 #      compiled by GNU C version 14.0.0 20231128 (experimental), GMP version
6.3.0, MPFR version 4.2.1, MPC version 1.3.1, isl version isl-0.26-GMP

 # GGC heuristics: --param ggc-min-expand=30 --param ggc-min-heapsize=4096
-# options passed: -m32 -masm=intel -mtune=generic -march=x86-64 -O2
+# options passed: -m32 -mavx -masm=intel -mtune=generic -march=x86-64 -O2
        .text
        .p2align 4
        .globl  foo0
@@ -37,19 +37,19 @@
        rol     ax, 8   # _5,
 # testcase.c:11:   u64 u64_1 = __builtin_bswap16 (SHL (u64_0, u8_0)) % u16_0;
        div     bx      # u16_0
-# testcase.c:12:   u8 u8_1 = __builtin_add_overflow_p (u8_0, u8_0, u8_0);
-       mov     eax, ecx        # u8_0, u8_0
 # testcase.c:13:   u32 u32_1 = foo0_u32_0 & u16_0;
        movzx   ebx, bx # u16_0, u16_0
 # testcase.c:12:   u8 u8_1 = __builtin_add_overflow_p (u8_0, u8_0, u8_0);
-       add     al, cl  # u8_0, u8_0
+       add     al, al  # u8_0, u8_0
+# testcase.c:14:   u32 u32_2 = __builtin_sub_overflow_p (0, u64_1, (u8) 0);
+       movzx   edx, dx # _6, tmp127
+# testcase.c:12:   u8 u8_1 = __builtin_add_overflow_p (u8_0, u8_0, u8_0);
        setc    al      #, _15
 # testcase.c:14:   u32 u32_2 = __builtin_sub_overflow_p (0, u64_1, (u8) 0);
        xor     ecx, ecx        # tmp133
 # testcase.c:13:   u32 u32_1 = foo0_u32_0 & u16_0;
        and     ebx, DWORD PTR foo0_u32_0       # u32_1, foo0_u32_0
 # testcase.c:14:   u32 u32_2 = __builtin_sub_overflow_p (0, u64_1, (u8) 0);
-       movzx   edx, dx # _6, tmp127
        sub     ecx, edx        # tmp132, _6
        setb    dl      #, _18
        and     ecx, -256       # tmp132,

Here, the problem is with:
# testcase.c:12:   u8 u8_1 = __builtin_add_overflow_p (u8_0, u8_0, u8_0);
        add     al, al  # u8_0, u8_0

due to the:
-# testcase.c:12:   u8 u8_1 = __builtin_add_overflow_p (u8_0, u8_0, u8_0);
-       mov     eax, ecx        # u8_0, u8_0

there is no "u8_0" in eax

Maybe the compiler tries to use an AVX instruction, that is in the end not
generated?