ShuriZma
/
xemu
mirror of https://github.com/xemu-project/xemu.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

target/ppc: Rewrite trans_ADDG6S 

Compute all carry bits in parallel instead of a loop.

Reviewed-by: Daniel Henrique Barboza <danielhb413@gmail.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
This commit is contained in:
Richard Henderson 2023-02-26 08:45:26 -10:00
parent a88c0cfadf
commit 4fe0e9db0a
1 changed files with 23 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

44
target/ppc/translate/fixedpoint-impl.c.inc
View File

@ -484,33 +484,35 @@ static bool trans_PEXTD(DisasContext *ctx, arg_X *a)
static bool trans_ADDG6S(DisasContext *ctx, arg_X *a) static bool trans_ADDG6S(DisasContext *ctx, arg_X *a)
{ {
const uint64_t carry_bits = 0x1111111111111111ULL; const target_ulong carry_bits = (target_ulong)-1 / 0xf;
TCGv t0, t1, carry, zero = tcg_constant_tl(0); TCGv in1, in2, carryl, carryh, tmp;
TCGv zero = tcg_constant_tl(0);
REQUIRE_INSNS_FLAGS2(ctx, BCDA_ISA206); REQUIRE_INSNS_FLAGS2(ctx, BCDA_ISA206);
t0 = tcg_temp_new(); in1 = cpu_gpr[a->ra];
t1 = tcg_const_tl(0); in2 = cpu_gpr[a->rb];
carry = tcg_const_tl(0); tmp = tcg_temp_new();
carryl = tcg_temp_new();
carryh = tcg_temp_new();
for (int i = 0; i < 16; i++) { /* Addition with carry. */
tcg_gen_shri_tl(t0, cpu_gpr[a->ra], i * 4); tcg_gen_add2_tl(carryl, carryh, in1, zero, in2, zero);
tcg_gen_andi_tl(t0, t0, 0xf); /* Addition without carry. */
tcg_gen_add_tl(t1, t1, t0); tcg_gen_xor_tl(tmp, in1, in2);
/* Difference between the two is carry in to each bit. */
tcg_gen_xor_tl(carryl, carryl, tmp);
tcg_gen_shri_tl(t0, cpu_gpr[a->rb], i * 4); /*
tcg_gen_andi_tl(t0, t0, 0xf); * The carry-out that we're looking for is the carry-in to
tcg_gen_add_tl(t1, t1, t0); * the next nibble. Shift the double-word down one nibble,
* which puts all of the bits back into one word.
*/
tcg_gen_extract2_tl(carryl, carryl, carryh, 4);
tcg_gen_andi_tl(t1, t1, 0x10); /* Invert, isolate the carry bits, and produce 6's. */
tcg_gen_setcond_tl(TCG_COND_NE, t1, t1, zero); tcg_gen_andc_tl(carryl, tcg_constant_tl(carry_bits), carryl);
tcg_gen_muli_tl(cpu_gpr[a->rt], carryl, 6);
tcg_gen_shli_tl(t0, t1, i * 4);
tcg_gen_or_tl(carry, carry, t0);
}
tcg_gen_xori_tl(carry, carry, (target_long)carry_bits);
tcg_gen_muli_tl(cpu_gpr[a->rt], carry, 6);
return true; return true;
} }