host-utils: Implemented unsigned 256-by-128 division

Based on already existing QEMU implementation, created an unsigned 256
bit by 128 bit division needed to implement the vector divide extended
unsigned instruction from PowerISA3.1

Signed-off-by: Lucas Mateus Castro (alqotel) <lucas.araujo@eldorado.org.br>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20220525134954.85056-5-lucas.araujo@eldorado.org.br>
Signed-off-by: Daniel Henrique Barboza <danielhb413@gmail.com>
This commit is contained in:
Lucas Mateus Castro (alqotel) 2022-05-25 10:49:50 -03:00 committed by Daniel Henrique Barboza
parent 9a1f0866a3
commit 4724bbd284
3 changed files with 169 additions and 0 deletions

View file

@ -266,3 +266,132 @@ void ulshift(uint64_t *plow, uint64_t *phigh, int32_t shift, bool *overflow)
*plow = *plow << shift;
}
}
/*
* Unsigned 256-by-128 division.
* Returns the remainder via r.
* Returns lower 128 bit of quotient.
* Needs a normalized divisor (most significant bit set to 1).
*
* Adapted from include/qemu/host-utils.h udiv_qrnnd,
* from the GNU Multi Precision Library - longlong.h __udiv_qrnnd
* (https://gmplib.org/repo/gmp/file/tip/longlong.h)
*
* Licensed under the GPLv2/LGPLv3
*/
static Int128 udiv256_qrnnd(Int128 *r, Int128 n1, Int128 n0, Int128 d)
{
Int128 d0, d1, q0, q1, r1, r0, m;
uint64_t mp0, mp1;
d0 = int128_make64(int128_getlo(d));
d1 = int128_make64(int128_gethi(d));
r1 = int128_remu(n1, d1);
q1 = int128_divu(n1, d1);
mp0 = int128_getlo(q1);
mp1 = int128_gethi(q1);
mulu128(&mp0, &mp1, int128_getlo(d0));
m = int128_make128(mp0, mp1);
r1 = int128_make128(int128_gethi(n0), int128_getlo(r1));
if (int128_ult(r1, m)) {
q1 = int128_sub(q1, int128_one());
r1 = int128_add(r1, d);
if (int128_uge(r1, d)) {
if (int128_ult(r1, m)) {
q1 = int128_sub(q1, int128_one());
r1 = int128_add(r1, d);
}
}
}
r1 = int128_sub(r1, m);
r0 = int128_remu(r1, d1);
q0 = int128_divu(r1, d1);
mp0 = int128_getlo(q0);
mp1 = int128_gethi(q0);
mulu128(&mp0, &mp1, int128_getlo(d0));
m = int128_make128(mp0, mp1);
r0 = int128_make128(int128_getlo(n0), int128_getlo(r0));
if (int128_ult(r0, m)) {
q0 = int128_sub(q0, int128_one());
r0 = int128_add(r0, d);
if (int128_uge(r0, d)) {
if (int128_ult(r0, m)) {
q0 = int128_sub(q0, int128_one());
r0 = int128_add(r0, d);
}
}
}
r0 = int128_sub(r0, m);
*r = r0;
return int128_or(int128_lshift(q1, 64), q0);
}
/*
* Unsigned 256-by-128 division.
* Returns the remainder.
* Returns quotient via plow and phigh.
* Also returns the remainder via the function return value.
*/
Int128 divu256(Int128 *plow, Int128 *phigh, Int128 divisor)
{
Int128 dhi = *phigh;
Int128 dlo = *plow;
Int128 rem, dhighest;
int sh;
if (!int128_nz(divisor) || !int128_nz(dhi)) {
*plow = int128_divu(dlo, divisor);
*phigh = int128_zero();
return int128_remu(dlo, divisor);
} else {
sh = clz128(divisor);
if (int128_ult(dhi, divisor)) {
if (sh != 0) {
/* normalize the divisor, shifting the dividend accordingly */
divisor = int128_lshift(divisor, sh);
dhi = int128_or(int128_lshift(dhi, sh),
int128_urshift(dlo, (128 - sh)));
dlo = int128_lshift(dlo, sh);
}
*phigh = int128_zero();
*plow = udiv256_qrnnd(&rem, dhi, dlo, divisor);
} else {
if (sh != 0) {
/* normalize the divisor, shifting the dividend accordingly */
divisor = int128_lshift(divisor, sh);
dhighest = int128_rshift(dhi, (128 - sh));
dhi = int128_or(int128_lshift(dhi, sh),
int128_urshift(dlo, (128 - sh)));
dlo = int128_lshift(dlo, sh);
*phigh = udiv256_qrnnd(&dhi, dhighest, dhi, divisor);
} else {
/*
* dhi >= divisor
* Since the MSB of divisor is set (sh == 0),
* (dhi - divisor) < divisor
*
* Thus, the high part of the quotient is 1, and we can
* calculate the low part with a single call to udiv_qrnnd
* after subtracting divisor from dhi
*/
dhi = int128_sub(dhi, divisor);
*phigh = int128_one();
}
*plow = udiv256_qrnnd(&rem, dhi, dlo, divisor);
}
/*
* since the dividend/divisor might have been normalized,
* the remainder might also have to be shifted back
*/
rem = int128_urshift(rem, sh);
return rem;
}
}