[Bug target/112760] New: [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]

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

            Bug ID: 112760
           Summary: [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()
           Product: gcc
           Version: 14.0
            Status: UNCONFIRMED
          Keywords: wrong-code
          Severity: normal
          Priority: P3
         Component: target
          Assignee: unassigned at gcc dot gnu.org
          Reporter: zsojka at seznam dot cz
  Target Milestone: ---
              Host: x86_64-pc-linux-gnu
            Target: i686-pc-linux-gnu

Created attachment 56715
  --> https://gcc.gnu.org/bugzilla/attachment.cgi?id=56715&action=edit
reduced testcase

Output:
$ x86_64-pc-linux-gnu-gcc -m32 -O2 -fno-dce -fno-guess-branch-probability
-m8bit-idiv -mavx --param=max-cse-insns=0 testcase.c
$ ./a.out 
Aborted

The code for __builtin_add_overflow() check looks wrong:
# testcase.c:9:   u16 x = __builtin_add_overflow_p (a, g, (u16) 0);
        add     eax, ecx        # tmp110, g.0_1
        mov     eax, 1  # tmp118,
        setc    bl      #, _8
        cmovne  ebx, eax        # _8,, _8, tmp118

Comparing the code without -mavx, the breakage can be observed better:
$ diff -u a-testcase.GOOD.s a-testcase.BAD.s 
--- a-testcase.GOOD.s   2023-11-29 08:34:39.978807709 +0100
+++ a-testcase.BAD.s    2023-11-29 08:32:27.458809580 +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 -m8bit-idiv -masm=intel -mtune=generic -march=x86-64
-O2 -fno-dce -fno-guess-branch-probability --param=max-cse-insns=0
+# options passed: -m32 -m8bit-idiv -mavx -masm=intel -mtune=generic
-march=x86-64 -O2 -fno-dce -fno-guess-branch-probability
--param=max-cse-insns=0
        .text
        .p2align 4
        .globl  foo0
@@ -28,10 +28,8 @@
        movzx   esi, WORD PTR [esp+16]  # b, b
 # testcase.c:9:   u16 x = __builtin_add_overflow_p (a, g, (u16) 0);
        add     eax, ecx        # tmp110, g.0_1
-       movzx   edx, ax # tmp111, tmp110
-       setc    bl      #, _8
-       cmp     eax, edx        # tmp110, tmp111
        mov     eax, 1  # tmp118,
+       setc    bl      #, _8
        cmovne  ebx, eax        # _8,, _8, tmp118
 # testcase.c:10:   g -= g / b;
        mov     eax, ecx        # tmp119, g.0_1


The "cmovne" instruction is using the Z flag from a different comparison.



$ x86_64-pc-linux-gnu-gcc -v
Using built-in specs.
COLLECT_GCC=/repo/gcc-trunk/binary-latest-amd64/bin/x86_64-pc-linux-gnu-gcc
COLLECT_LTO_WRAPPER=/repo/gcc-trunk/binary-trunk-r14-5940-20231128183456-g3d104d93a70-checking-yes-rtl-df-extra-amd64/bin/../libexec/gcc/x86_64-pc-linux-gnu/14.0.0/lto-wrapper
Target: x86_64-pc-linux-gnu
Configured with: /repo/gcc-trunk//configure --enable-languages=c,c++
--enable-valgrind-annotations --disable-nls --enable-checking=yes,rtl,df,extra
--with-cloog --with-ppl --with-isl --build=x86_64-pc-linux-gnu
--host=x86_64-pc-linux-gnu --target=x86_64-pc-linux-gnu
--with-ld=/usr/bin/x86_64-pc-linux-gnu-ld
--with-as=/usr/bin/x86_64-pc-linux-gnu-as --disable-libstdcxx-pch
--prefix=/repo/gcc-trunk//binary-trunk-r14-5940-20231128183456-g3d104d93a70-checking-yes-rtl-df-extra-amd64
Thread model: posix
Supported LTO compression algorithms: zlib zstd
gcc version 14.0.0 20231128 (experimental) (GCC)