Hi! While for __mulbitint3 we actually don't negate anything and perform the multiplication in unsigned style always, for __divmodbitint4 if the operands aren't unsigned and are negative, we negate them first and then try to negate them as needed at the end. quotient is negated if just one of the operands was negated and the other wasn't or vice versa, and remainder is negated if the first operand was negated. The case which doesn't work correctly is if due to limited range of the operands we perform the division/modulo in some smaller number of limbs and then extend it to the desired precision of the quotient and/or remainder results. If they aren't negated, the extension is done with memset to 0, if they are negated, the extension was done with memset to -1. The problem is that if the quotient or remainder is zero, then bitint_negate negates it again to zero (that is ok), but we should then extend with memset to 0, not memset to -1.
The following patch achieves that by letting bitint_negate also check if the negated operand is zero and changes the memset argument based on that. Bootstrapped/regtested on x86_64-linux and i686-linux, ok for trunk? 2024-03-15 Jakub Jelinek <ja...@redhat.com> PR libgcc/114327 * libgcc2.c (bitint_negate): Return UWtype bitwise or of all the limbs before negation rather than void. (__divmodbitint4): Determine whether to fill in the upper limbs after negation based on whether bitint_negate returned 0 or non-zero, rather then always filling with -1. * gcc.dg/torture/bitint-63.c: New test. --- libgcc/libgcc2.c.jj 2024-02-02 22:14:14.946684874 +0100 +++ libgcc/libgcc2.c 2024-03-14 13:37:38.227332706 +0100 @@ -1642,19 +1642,22 @@ __mulbitint3 (UBILtype *ret, SItype retp #ifdef L_divmodbitint4 /* D = -S. */ -static void +static UWtype bitint_negate (UBILtype *d, const UBILtype *s, SItype n) { UWtype c = 1; + UWtype r = 0; do { UWtype sv = *s, lo; + r |= sv; s += BITINT_INC; c = __builtin_add_overflow (~sv, c, &lo); *d = lo; d += BITINT_INC; } while (--n); + return r; } /* D -= S * L. */ @@ -1977,10 +1980,10 @@ __divmodbitint4 (UBILtype *q, SItype qpr n = qn; else n = un - vn + 1; - bitint_negate (q + BITINT_END (qn - 1, 0), - q2 + BITINT_END (un - vn, 0), n); + SItype c = bitint_negate (q + BITINT_END (qn - 1, 0), + q2 + BITINT_END (un - vn, 0), n) ? -1 : 0; if (qn > n) - __builtin_memset (q + BITINT_END (0, n), -1, + __builtin_memset (q + BITINT_END (0, n), c, (qn - n) * sizeof (UWtype)); } else @@ -1999,11 +2002,11 @@ __divmodbitint4 (UBILtype *q, SItype qpr if (uprec < 0) { /* Negative remainder. */ - bitint_negate (r + BITINT_END (rn - 1, 0), - r + BITINT_END (rn - 1, 0), - rn > vn ? vn : rn); + SItype c = bitint_negate (r + BITINT_END (rn - 1, 0), + r + BITINT_END (rn - 1, 0), + rn > vn ? vn : rn) ? -1 : 0; if (rn > vn) - __builtin_memset (r + BITINT_END (0, vn), -1, + __builtin_memset (r + BITINT_END (0, vn), c, (rn - vn) * sizeof (UWtype)); } else --- gcc/testsuite/gcc.dg/torture/bitint-63.c.jj 2024-03-14 13:46:31.591938158 +0100 +++ gcc/testsuite/gcc.dg/torture/bitint-63.c 2024-03-14 13:45:58.306399642 +0100 @@ -0,0 +1,30 @@ +/* PR libgcc/114327 */ +/* { dg-do run { target bitint } } */ +/* { dg-options "-std=c23" } */ +/* { dg-skip-if "" { ! run_expensive_tests } { "*" } { "-O0" "-O2" } } */ +/* { dg-skip-if "" { ! run_expensive_tests } { "-flto" } { "" } } */ + +#if __BITINT_MAXWIDTH__ >= 256 +_BitInt(256) +foo (_BitInt(256) b, _BitInt(256) c) +{ + return b % c; +} + +_BitInt(256) +bar (_BitInt(256) b, _BitInt(256) c) +{ + return b / c; +} +#endif + +int +main () +{ +#if __BITINT_MAXWIDTH__ >= 256 + if (foo (-0x9e9b9fe60wb, 1wb)) + __builtin_abort (); + if (bar (1wb, -0x9e9b9fe60wb)) + __builtin_abort (); +#endif +} Jakub