mirror of
https://github.com/yuzu-emu/unicorn.git
synced 2024-12-23 17:55:27 +00:00
tcg/aarch64: Fix tcg_out_movi
There were some patterns, like 0x0000_ffff_ffff_00ff, for which we would select to begin a multi-insn sequence with MOVN, but would fail to set the 0x0000 lane back from 0xffff. Backports commit 50b468d42107a2c646b1c566ed17d9ec362c51c4 from qemu
This commit is contained in:
parent
a03666f2f2
commit
6820964e2f
|
@ -585,11 +585,9 @@ static void tcg_out_logicali(TCGContext *s, AArch64Insn insn, TCGType ext,
|
|||
static void tcg_out_movi(TCGContext *s, TCGType type, TCGReg rd,
|
||||
tcg_target_long value)
|
||||
{
|
||||
AArch64Insn insn;
|
||||
int i, wantinv, shift;
|
||||
tcg_target_long svalue = value;
|
||||
tcg_target_long ivalue = ~value;
|
||||
tcg_target_long imask;
|
||||
|
||||
/* For 32-bit values, discard potential garbage in value. For 64-bit
|
||||
values within [2**31, 2**32-1], we can create smaller sequences by
|
||||
|
@ -635,43 +633,36 @@ static void tcg_out_movi(TCGContext *s, TCGType type, TCGReg rd,
|
|||
|
||||
/* Would it take fewer insns to begin with MOVN? For the value and its
|
||||
inverse, count the number of 16-bit lanes that are 0. */
|
||||
for (i = wantinv = imask = 0; i < 64; i += 16) {
|
||||
for (i = wantinv = 0; i < 64; i += 16) {
|
||||
tcg_target_long mask = 0xffffull << i;
|
||||
if ((value & mask) == 0) {
|
||||
wantinv -= 1;
|
||||
}
|
||||
if ((ivalue & mask) == 0) {
|
||||
wantinv += 1;
|
||||
imask |= mask;
|
||||
}
|
||||
}
|
||||
|
||||
/* If we had more 0xffff than 0x0000, invert VALUE and use MOVN. */
|
||||
insn = I3405_MOVZ;
|
||||
if (wantinv > 0) {
|
||||
value = ivalue;
|
||||
insn = I3405_MOVN;
|
||||
wantinv -= ((value & mask) == 0);
|
||||
wantinv += ((ivalue & mask) == 0);
|
||||
}
|
||||
|
||||
if (wantinv <= 0) {
|
||||
/* Find the lowest lane that is not 0x0000. */
|
||||
shift = ctz64(value) & (63 & -16);
|
||||
tcg_out_insn_3405(s, insn, type, rd, value >> shift, shift);
|
||||
|
||||
if (wantinv > 0) {
|
||||
/* Re-invert the value, so MOVK sees non-inverted bits. */
|
||||
value = ~value;
|
||||
/* Clear out all the 0xffff lanes. */
|
||||
value ^= imask;
|
||||
}
|
||||
tcg_out_insn(s, 3405, MOVZ, type, rd, value >> shift, shift);
|
||||
/* Clear out the lane that we just set. */
|
||||
value &= ~(0xffffUL << shift);
|
||||
|
||||
/* Iterate until all lanes have been set, and thus cleared from VALUE. */
|
||||
/* Iterate until all non-zero lanes have been processed. */
|
||||
while (value) {
|
||||
shift = ctz64(value) & (63 & -16);
|
||||
tcg_out_insn(s, 3405, MOVK, type, rd, value >> shift, shift);
|
||||
value &= ~(0xffffUL << shift);
|
||||
}
|
||||
} else {
|
||||
/* Like above, but with the inverted value and MOVN to start. */
|
||||
shift = ctz64(ivalue) & (63 & -16);
|
||||
tcg_out_insn(s, 3405, MOVN, type, rd, ivalue >> shift, shift);
|
||||
ivalue &= ~(0xffffUL << shift);
|
||||
while (ivalue) {
|
||||
shift = ctz64(ivalue) & (63 & -16);
|
||||
/* Provide MOVK with the non-inverted value. */
|
||||
tcg_out_insn(s, 3405, MOVK, type, rd, ~(ivalue >> shift), shift);
|
||||
ivalue &= ~(0xffffUL << shift);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/* Define something more legible for general use. */
|
||||
|
|
Loading…
Reference in a new issue