https://gcc.gnu.org/bugzilla/show_bug.cgi?id=120020
--- Comment #3 from Jin Haobo <a1343922569 at outlook dot com> ---
The code in my reproduction is wrong. I will re-show the C++ code.
Reproduction C++ code (64-bit variable):
#include <cstdint>
using U = uint64_t;
struct A { U quo; U rem; };
U myDiv(U const& a, U const& b)
{
U result, dummyRemainder;
asm (
"xor %[remainder], %[remainder] \n\t"
"div %[divisor] \n\t"
: [quotient] "=a"(result), [remainder] "=d" (dummyRemainder)
: [dividendLow] "a"(a), [divisor] "rm"(b)
);
return result;
}
U myMod(U const& a, U const& b)
{
U result, dummyQuotient;
asm (
"xor %[remainder], %[remainder] \n\t"
"div %[divisor] \n\t"
: [quotient] "=a" (dummyQuotient), [remainder] "=d" (result)
: [dividendLow] "a"(a), [divisor] "rm"(b)
);
return result;
}
A myDivMod1(U const& a, U const& b)
{
A result;
result.quo = myDiv(a, b);
result.rem = myMod(a, b);
return result;
}
A myDivMod2(U const& a, U const& b)
{
A result;
asm (
"xor %[dividendRemainder], %[dividendRemainder] \n\t"
"div %[divisor] \n\t"
: [quotient] "=a"(result.quo), [dividendRemainder] "=d"
(result.rem)
: [dividendLow] "a"(a), [divisor] "rm"(b)
);
return result;
}
Current generated assembly (64-bit variable):
myDiv(unsigned long const&, unsigned long const&):
mov rax, QWORD PTR [rdi]
xor rdx, rdx
div QWORD PTR [rsi]
ret
myMod(unsigned long const&, unsigned long const&):
mov rax, QWORD PTR [rdi]
xor rdx, rdx
div QWORD PTR [rsi]
mov rax, rdx
ret
myDivMod1(unsigned long const&, unsigned long const&):
mov rax, rsi
mov rsi, QWORD PTR [rdi]
mov rcx, QWORD PTR [rax]
mov rax, rsi
xor rdx, rdx
div rcx
mov rdi, rax
mov rax, rsi
xor rdx, rdx
div rcx
mov rax, rdi
ret
myDivMod2(unsigned long const&, unsigned long const&):
mov rax, QWORD PTR [rdi]
xor rdx, rdx
div QWORD PTR [rsi]
ret
Godbolt link (GCC, generate suboptimal assembly code for myDivMod1, which is
not the same as myDivMod2)
64-bit variable: https://gcc.godbolt.org/z/7j9MsKsMr
32-bit variable: https://gcc.godbolt.org/z/EEKzWWx14
16-bit variable: https://gcc.godbolt.org/z/5j9zoxrro
8-bit variable: https://gcc.godbolt.org/z/3sWh9K6r5
Godbolt link (Clang, generate optimal assembly code for myDivMod1, which is the
same as myDivMod2)
64-bit variable: https://gcc.godbolt.org/z/cneMq3eYT
32-bit variable: https://gcc.godbolt.org/z/E1e9x65hj
16-bit variable: https://gcc.godbolt.org/z/3aq9dsa3M
8-bit variable: https://gcc.godbolt.org/z/8EG8TEzGq
