mips: Optimize jit_lshr() and jit_lshr_u() - lightning.git - Portable just-in-time compiler library

Portable just-in-time compiler library

diff options

author	Paul Cercueil <paul@crapouillou.net>	2023年09月28日 16:50:21 +0200
committer	pcpa <paulo.cesar.pereira.de.andrade@gmail.com>	2023年10月02日 09:08:57 -0300
commit	403b8f39cb8cb70ad6f88e8b86692e2b653e3100 (patch)
tree	6991210c7a698baa05090382fdf8777bc72ddd9e /lib/jit_mips-cpu.c
parent	b9822d211619ba677950214fed17cd241aeabe67 (diff)
download	lightning-403b8f39cb8cb70ad6f88e8b86692e2b653e3100.tar.gz

mips: Optimize jit_lshr() and jit_lshr_u()

Rework the branch-less path to shrink the size of jit_lshr() by one instruction, and jit_lshr_u() by two instructions. It also uses one register less, so the whole code path that uses branches can be dropped. Finally, fix whitespace issues as the original code used sometimes tabs, sometimes spaces. Signed-off-by: Paul Cercueil <paul@crapouillou.net>

Diffstat (limited to 'lib/jit_mips-cpu.c')

-rw-r--r--

lib/jit_mips-cpu.c

1 files changed, 21 insertions, 51 deletions

diff --git a/lib/jit_mips-cpu.c b/lib/jit_mips-cpu.c
index 6a07e87..8350bf8 100644
--- a/lib/jit_mips-cpu.c
+++ b/lib/jit_mips-cpu.c

@@ -2353,72 +2353,42 @@ static void

_xlshr(jit_state_t *_jit, jit_bool_t sign,

jit_int32_t r0, jit_int32_t r1, jit_int32_t r2, jit_int32_t r3)

{

- jit_bool_t branch;

- jit_word_t over, zero, done, done_over;

- jit_int32_t t0, s0, t1, s1, t2, s2, t3, s3;

+ jit_int32_t t0, s0, t2, s2, t3, s3;

s0 = jit_get_reg(jit_class_gpr);

t0 = rn(s0);

if (r0 == r2 || r1 == r2) {

- s2 = jit_get_reg(jit_class_gpr);

- t2 = rn(s2);

- movr(t2, r2);

+ s2 = jit_get_reg(jit_class_gpr);

+ t2 = rn(s2);

+ movr(t2, r2);

}

else

- t2 = r2;

+ t2 = r2;

if (r0 == r3 || r1 == r3) {

- s3 = jit_get_reg(jit_class_gpr);

- t3 = rn(s3);

- movr(t3, r3);

- }

- else

- t3 = r3;

- if ((s1 = jit_get_reg(jit_class_gpr|jit_class_nospill|jit_class_chk))) {

- t1 = rn(s1);

- branch = 0;

+ s3 = jit_get_reg(jit_class_gpr);

+ t3 = rn(s3);

+ movr(t3, r3);

}

else

- branch = 1;

+ t3 = r3;

rsbi(t0, t3, __WORDSIZE);

lshr(r0, t2, t3);

if (sign)

- rshr(r1, t2, t0);

+ rshr(r1, t2, t0);

else

- rshr_u(r1, t2, t0);

- if (branch) {

- zero = beqi(_jit->pc.w, t3, 0);

- over = beqi(_jit->pc.w, t3, __WORDSIZE);

- done = jmpi(_jit->pc.w, 1);

- flush();

- patch_at(over, _jit->pc.w);

- /* overflow */

- movi(r0, 0);

- done_over = jmpi(_jit->pc.w, 1);

- /* zero */

- flush();

- patch_at(zero, _jit->pc.w);

- if (sign)

- rshi(r1, t2, __WORDSIZE - 1);

- else

- movi(r1, 0);

- flush();

- patch_at(done, _jit->pc.w);

- patch_at(done_over, _jit->pc.w);

+ rshr_u(r1, t2, t0);

+ if (sign) {

+ rshi(t0, t2, __WORDSIZE - 1);

+ /* zero? */

+ movzr(r1, t0, t3);

}

else {

- if (sign)

- rshi(t0, t2, __WORDSIZE - 1);

- else

- movi(t0, 0);

- /* zero? */

- movzr(r1, t0, t3);

- /* Branchless but 4 bytes longer than branching fallback */

- if (sign)

- movi(t0, 0);

- /* overflow? */

- eqi(t1, t3, __WORDSIZE);

- movnr(r0, t0, t1);

- jit_unget_reg(s1);

+ /* zero? */

+ movzr(r1, t3, t3);

}

+ /* overflow? */

+ nei(t0, t3, __WORDSIZE);

+ movzr(r0, t0, t0);

jit_unget_reg(s0);

if (t2 != r2)

jit_unget_reg(s2);

generated by cgit v1.2.3 (git 2.39.1) at 2025年09月10日 23:50:37 +0000