static int b, c; static char d; static short e = -1L; static int *j = &c; void foo(void); void bar150_(void); void bar173_(void); static char(a)(char k, char l) { return k + l; } static void g(unsigned k, int l) { if (l) if (!k) foo(); if (k) bar150_(); } static const unsigned char h(); static char i(int k) { if (k) bar173_(); c <= 0 >= b; if (k) return c; return c; } static void f(char k, unsigned) { char m = h(8 != c); g(m && 8, k); } static const unsigned char h(int k) { d = i(c); *j = a(e, d < k < k && c) ^ k; b = 0; return c; } int main() { f(c, b); } gcc-9ec5d6de735 (trunk) -O3 cannot eliminate the call to foo but gcc-releases/gcc-13.1.0 -O3 can. ----------------------------------------------------------------------- gcc-9ec5d6de7355c15b3811150d1581dab5bd489966 -O3 case.c -S -o case.s --------- OUTPUT --------- main: .LFB5: .cfi_startproc pushq %rbp .cfi_def_cfa_offset 16 .cfi_offset 6, -16 pushq %rbx .cfi_def_cfa_offset 24 .cfi_offset 3, -24 subq $8, %rsp .cfi_def_cfa_offset 32 movl c(%rip), %ebx cmpl $8, %ebx setne %bpl testl %ebx, %ebx jne .L9 movl $-2, c(%rip) xorl %eax, %eax movl %eax, b(%rip) .L4: call bar150_ .L6: addq $8, %rsp .cfi_remember_state .cfi_def_cfa_offset 24 xorl %eax, %eax popq %rbx .cfi_def_cfa_offset 16 popq %rbp .cfi_def_cfa_offset 8 ret .p2align 4,,10 .p2align 3 .L9: .cfi_restore_state call bar173_ movl c(%rip), %edx movzbl %bpl, %ebp movl $0, b(%rip) movsbl %dl, %eax cmpl %eax, %ebp setg %al movzbl %al, %eax cmpl %eax, %ebp setg %al testl %edx, %edx setne %dl andl %edx, %eax subl $1, %eax movsbl %al, %eax xorl %ebp, %eax movl %eax, c(%rip) testb %bl, %bl je .L3 testb %al, %al jne .L4 call foo jmp .L6 .L3: testb %al, %al je .L6 jmp .L4 ---------- END OUTPUT --------- ----------------------------------------------------------------------- gcc-2b98cc24d6af0432a74f6dad1c722ce21c1f7458 -O3 case.c -S -o case.s --------- OUTPUT --------- main: .LFB5: .cfi_startproc movl c(%rip), %eax pushq %rbx .cfi_def_cfa_offset 16 .cfi_offset 3, -16 xorl %ebx, %ebx cmpl $8, %eax setne %bl testl %eax, %eax jne .L10 .L2: cmpl %eax, %ebx setg %al movzbl %al, %eax cmpl %eax, %ebx jg .L3 notl %ebx .L4: movl %ebx, c(%rip) movl $0, b(%rip) call bar150_ xorl %eax, %eax popq %rbx .cfi_remember_state .cfi_def_cfa_offset 8 ret .L3: .cfi_restore_state cmpl $1, c(%rip) sbbb %bl, %bl xorl $1, %ebx movsbl %bl, %ebx jmp .L4 .L10: call bar173_ movsbl c(%rip), %eax jmp .L2 ---------- END OUTPUT --------- ----------------------------------------------------------------------- Bisects to r14-573-g69f1a8af45d
So the difference here is basically doing the following manually: ``` #if 0 static char i(int k) { if (k) bar173_(); c <= 0 >= b; if (k) return c; return c; } #else static char i(int k) { if (k) bar173_(); c <= 0 >= b; int t; if (k) t = c; else t = c; return t; } #endif ``` and we used to do some jump threading previously such that the load of the c would be in the `if (k)` branch after the call to `bar173_()`. The only pass which moves it like that is pre which happens maybe later but too late for jump threading to happen for the optimizations. I have not looked into why this makes a difference either. maybe because there is another jump threading where we know c is 0 ... Confirmed.
Looks like this is fixed on the trunk ...
This has been fixed with Richi's r14-3982-g9ea74d235c7e78 ( better DCE after forwprop). Given the title of the patch I guess it's safe to declare this fixed.