haraldwolff/qemu-patch-raspberry4
1
0
Fork 0
Code Issues Pull requests Packages Projects Releases Wiki Activity

target-arm: optimize thumb 32-bit multiply

Browse source 
Current implementation of thumb mul instruction is implemented as a
32x32->64 multiply which then uses only 32 least significant bits of
the result. Replace that with a simple 32x32->32 multiply.

Signed-off-by: Juha Riihimäki <juha.riihimaki@nokia.com>
Acked-by: Laurent Desnogues <laurent.desnogues@gmail.com>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
This commit is contained in:
Juha.Riihimaki@nokia.com 2009-10-21 12:17:38 +02:00 committed by Aurelien Jarno
parent b75263d653
commit 7b2919a0b4
1 changed files with 1 additions and 17 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

18
target-arm/translate.c
View file

@ -310,22 +310,6 @@ static TCGv_i64 gen_muls_i64_i32(TCGv a, TCGv b)
return tmp1;
}
/* Unsigned 32x32->64 multiply. */
static void gen_mull(TCGv a, TCGv b)
{
TCGv_i64 tmp1 = tcg_temp_new_i64();
TCGv_i64 tmp2 = tcg_temp_new_i64();
tcg_gen_extu_i32_i64(tmp1, a);
tcg_gen_extu_i32_i64(tmp2, b);
tcg_gen_mul_i64(tmp1, tmp1, tmp2);
tcg_temp_free_i64(tmp2);
tcg_gen_trunc_i64_i32(a, tmp1);
tcg_gen_shri_i64(tmp1, tmp1, 32);
tcg_gen_trunc_i64_i32(b, tmp1);
tcg_temp_free_i64(tmp1);
}
/* Signed 32x32->64 multiply. */
static void gen_imull(TCGv a, TCGv b)
{
@ -8363,7 +8347,7 @@ static void disas_thumb_insn(CPUState *env, DisasContext *s)
gen_logic_CC(tmp);
break;
case 0xd: /* mul */
gen_mull(tmp, tmp2);
tcg_gen_mul_i32(tmp, tmp, tmp2);
if (!s->condexec_mask)
gen_logic_CC(tmp);
break;