Skip to content

Commit

Permalink
target/loongarch: Add fixed point arithmetic instruction translation
Browse files Browse the repository at this point in the history 
This includes:
- ADD.{W/D}, SUB.{W/D}
- ADDI.{W/D}, ADDU16ID
- ALSL.{W[U]/D}
- LU12I.W, LU32I.D LU52I.D
- SLT[U], SLT[U]I
- PCADDI, PCADDU12I, PCADDU18I, PCALAU12I
- AND, OR, NOR, XOR, ANDN, ORN
- MUL.{W/D}, MULH.{W[U]/D[U]}
- MULW.D.W[U]
- DIV.{W[U]/D[U]}, MOD.{W[U]/D[U]}
- ANDI, ORI, XORI

Signed-off-by: Song Gao <gaosong@loongson.cn>
Signed-off-by: Xiaojuan Yang <yangxiaojuan@loongson.cn>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20220606124333.2060567-5-yangxiaojuan@loongson.cn>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
  • Loading branch information
@gaosong-loongson @rth7680
gaosong-loongson authored and rth7680 committed Jun 6, 2022
1 parent f8da88d commit 143d678
Show file tree
Hide file tree
Showing 4 changed files with 485 additions and 0 deletions.
304 changes: 304 additions & 0 deletions target/loongarch/insn_trans/trans_arith.c.inc
View file
@@ -0,0 +1,304 @@
/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
* Copyright (c) 2021 Loongson Technology Corporation Limited
*/

static bool gen_rrr(DisasContext *ctx, arg_rrr *a,
DisasExtend src1_ext, DisasExtend src2_ext,
DisasExtend dst_ext, void (*func)(TCGv, TCGv, TCGv))
{
TCGv dest = gpr_dst(ctx, a->rd, dst_ext);
TCGv src1 = gpr_src(ctx, a->rj, src1_ext);
TCGv src2 = gpr_src(ctx, a->rk, src2_ext);

func(dest, src1, src2);
gen_set_gpr(a->rd, dest, dst_ext);

return true;
}

static bool gen_rri_v(DisasContext *ctx, arg_rr_i *a,
DisasExtend src_ext, DisasExtend dst_ext,
void (*func)(TCGv, TCGv, TCGv))
{
TCGv dest = gpr_dst(ctx, a->rd, dst_ext);
TCGv src1 = gpr_src(ctx, a->rj, src_ext);
TCGv src2 = tcg_constant_tl(a->imm);

func(dest, src1, src2);
gen_set_gpr(a->rd, dest, dst_ext);

return true;
}

static bool gen_rri_c(DisasContext *ctx, arg_rr_i *a,
DisasExtend src_ext, DisasExtend dst_ext,
void (*func)(TCGv, TCGv, target_long))
{
TCGv dest = gpr_dst(ctx, a->rd, dst_ext);
TCGv src1 = gpr_src(ctx, a->rj, src_ext);

func(dest, src1, a->imm);
gen_set_gpr(a->rd, dest, dst_ext);

return true;
}

static bool gen_rrr_sa(DisasContext *ctx, arg_rrr_sa *a,
DisasExtend src_ext, DisasExtend dst_ext,
void (*func)(TCGv, TCGv, TCGv, target_long))
{
TCGv dest = gpr_dst(ctx, a->rd, dst_ext);
TCGv src1 = gpr_src(ctx, a->rj, src_ext);
TCGv src2 = gpr_src(ctx, a->rk, src_ext);

func(dest, src1, src2, a->sa);
gen_set_gpr(a->rd, dest, dst_ext);

return true;
}

static bool trans_lu12i_w(DisasContext *ctx, arg_lu12i_w *a)
{
TCGv dest = gpr_dst(ctx, a->rd, EXT_NONE);

tcg_gen_movi_tl(dest, a->imm << 12);
gen_set_gpr(a->rd, dest, EXT_NONE);

return true;
}

static bool gen_pc(DisasContext *ctx, arg_r_i *a,
target_ulong (*func)(target_ulong, int))
{
TCGv dest = gpr_dst(ctx, a->rd, EXT_NONE);
target_ulong addr = func(ctx->base.pc_next, a->imm);

tcg_gen_movi_tl(dest, addr);
gen_set_gpr(a->rd, dest, EXT_NONE);

return true;
}

static void gen_slt(TCGv dest, TCGv src1, TCGv src2)
{
tcg_gen_setcond_tl(TCG_COND_LT, dest, src1, src2);
}

static void gen_sltu(TCGv dest, TCGv src1, TCGv src2)
{
tcg_gen_setcond_tl(TCG_COND_LTU, dest, src1, src2);
}

static void gen_mulh_w(TCGv dest, TCGv src1, TCGv src2)
{
tcg_gen_mul_i64(dest, src1, src2);
tcg_gen_sari_i64(dest, dest, 32);
}

static void gen_mulh_d(TCGv dest, TCGv src1, TCGv src2)
{
TCGv discard = tcg_temp_new();
tcg_gen_muls2_tl(discard, dest, src1, src2);
tcg_temp_free(discard);
}

static void gen_mulh_du(TCGv dest, TCGv src1, TCGv src2)
{
TCGv discard = tcg_temp_new();
tcg_gen_mulu2_tl(discard, dest, src1, src2);
tcg_temp_free(discard);
}

static void prep_divisor_d(TCGv ret, TCGv src1, TCGv src2)
{
TCGv t0 = tcg_temp_new();
TCGv t1 = tcg_temp_new();
TCGv zero = tcg_constant_tl(0);

/*
* If min / -1, set the divisor to 1.
* This avoids potential host overflow trap and produces min.
* If x / 0, set the divisor to 1.
* This avoids potential host overflow trap;
* the required result is undefined.
*/
tcg_gen_setcondi_tl(TCG_COND_EQ, ret, src1, INT64_MIN);
tcg_gen_setcondi_tl(TCG_COND_EQ, t0, src2, -1);
tcg_gen_setcondi_tl(TCG_COND_EQ, t1, src2, 0);
tcg_gen_and_tl(ret, ret, t0);
tcg_gen_or_tl(ret, ret, t1);
tcg_gen_movcond_tl(TCG_COND_NE, ret, ret, zero, ret, src2);

tcg_temp_free(t0);
tcg_temp_free(t1);
}

static void prep_divisor_du(TCGv ret, TCGv src2)
{
TCGv zero = tcg_constant_tl(0);
TCGv one = tcg_constant_tl(1);

/*
* If x / 0, set the divisor to 1.
* This avoids potential host overflow trap;
* the required result is undefined.
*/
tcg_gen_movcond_tl(TCG_COND_EQ, ret, src2, zero, one, src2);
}

static void gen_div_d(TCGv dest, TCGv src1, TCGv src2)
{
TCGv t0 = tcg_temp_new();
prep_divisor_d(t0, src1, src2);
tcg_gen_div_tl(dest, src1, t0);
tcg_temp_free(t0);
}

static void gen_rem_d(TCGv dest, TCGv src1, TCGv src2)
{
TCGv t0 = tcg_temp_new();
prep_divisor_d(t0, src1, src2);
tcg_gen_rem_tl(dest, src1, t0);
tcg_temp_free(t0);
}

static void gen_div_du(TCGv dest, TCGv src1, TCGv src2)
{
TCGv t0 = tcg_temp_new();
prep_divisor_du(t0, src2);
tcg_gen_divu_tl(dest, src1, t0);
tcg_temp_free(t0);
}

static void gen_rem_du(TCGv dest, TCGv src1, TCGv src2)
{
TCGv t0 = tcg_temp_new();
prep_divisor_du(t0, src2);
tcg_gen_remu_tl(dest, src1, t0);
tcg_temp_free(t0);
}

static void gen_div_w(TCGv dest, TCGv src1, TCGv src2)
{
TCGv t0 = tcg_temp_new();
/* We need not check for integer overflow for div_w. */
prep_divisor_du(t0, src2);
tcg_gen_div_tl(dest, src1, t0);
tcg_temp_free(t0);
}

static void gen_rem_w(TCGv dest, TCGv src1, TCGv src2)
{
TCGv t0 = tcg_temp_new();
/* We need not check for integer overflow for rem_w. */
prep_divisor_du(t0, src2);
tcg_gen_rem_tl(dest, src1, t0);
tcg_temp_free(t0);
}

static void gen_alsl(TCGv dest, TCGv src1, TCGv src2, target_long sa)
{
TCGv t0 = tcg_temp_new();
tcg_gen_shli_tl(t0, src1, sa);
tcg_gen_add_tl(dest, t0, src2);
tcg_temp_free(t0);
}

static bool trans_lu32i_d(DisasContext *ctx, arg_lu32i_d *a)
{
TCGv dest = gpr_dst(ctx, a->rd, EXT_NONE);
TCGv src1 = gpr_src(ctx, a->rd, EXT_NONE);
TCGv src2 = tcg_constant_tl(a->imm);

tcg_gen_deposit_tl(dest, src1, src2, 32, 32);
gen_set_gpr(a->rd, dest, EXT_NONE);

return true;
}

static bool trans_lu52i_d(DisasContext *ctx, arg_lu52i_d *a)
{
TCGv dest = gpr_dst(ctx, a->rd, EXT_NONE);
TCGv src1 = gpr_src(ctx, a->rj, EXT_NONE);
TCGv src2 = tcg_constant_tl(a->imm);

tcg_gen_deposit_tl(dest, src1, src2, 52, 12);
gen_set_gpr(a->rd, dest, EXT_NONE);

return true;
}

static target_ulong gen_pcaddi(target_ulong pc, int imm)
{
return pc + (imm << 2);
}

static target_ulong gen_pcalau12i(target_ulong pc, int imm)
{
return (pc + (imm << 12)) & ~0xfff;
}

static target_ulong gen_pcaddu12i(target_ulong pc, int imm)
{
return pc + (imm << 12);
}

static target_ulong gen_pcaddu18i(target_ulong pc, int imm)
{
return pc + ((target_ulong)(imm) << 18);
}

static bool trans_addu16i_d(DisasContext *ctx, arg_addu16i_d *a)
{
TCGv dest = gpr_dst(ctx, a->rd, EXT_NONE);
TCGv src1 = gpr_src(ctx, a->rj, EXT_NONE);

tcg_gen_addi_tl(dest, src1, a->imm << 16);
gen_set_gpr(a->rd, dest, EXT_NONE);

return true;
}

TRANS(add_w, gen_rrr, EXT_NONE, EXT_NONE, EXT_SIGN, tcg_gen_add_tl)
TRANS(add_d, gen_rrr, EXT_NONE, EXT_NONE, EXT_NONE, tcg_gen_add_tl)
TRANS(sub_w, gen_rrr, EXT_NONE, EXT_NONE, EXT_SIGN, tcg_gen_sub_tl)
TRANS(sub_d, gen_rrr, EXT_NONE, EXT_NONE, EXT_NONE, tcg_gen_sub_tl)
TRANS(and, gen_rrr, EXT_NONE, EXT_NONE, EXT_NONE, tcg_gen_and_tl)
TRANS(or, gen_rrr, EXT_NONE, EXT_NONE, EXT_NONE, tcg_gen_or_tl)
TRANS(xor, gen_rrr, EXT_NONE, EXT_NONE, EXT_NONE, tcg_gen_xor_tl)
TRANS(nor, gen_rrr, EXT_NONE, EXT_NONE, EXT_NONE, tcg_gen_nor_tl)
TRANS(andn, gen_rrr, EXT_NONE, EXT_NONE, EXT_NONE, tcg_gen_andc_tl)
TRANS(orn, gen_rrr, EXT_NONE, EXT_NONE, EXT_NONE, tcg_gen_orc_tl)
TRANS(slt, gen_rrr, EXT_NONE, EXT_NONE, EXT_NONE, gen_slt)
TRANS(sltu, gen_rrr, EXT_NONE, EXT_NONE, EXT_NONE, gen_sltu)
TRANS(mul_w, gen_rrr, EXT_SIGN, EXT_SIGN, EXT_SIGN, tcg_gen_mul_tl)
TRANS(mul_d, gen_rrr, EXT_NONE, EXT_NONE, EXT_NONE, tcg_gen_mul_tl)
TRANS(mulh_w, gen_rrr, EXT_SIGN, EXT_SIGN, EXT_NONE, gen_mulh_w)
TRANS(mulh_wu, gen_rrr, EXT_ZERO, EXT_ZERO, EXT_NONE, gen_mulh_w)
TRANS(mulh_d, gen_rrr, EXT_NONE, EXT_NONE, EXT_NONE, gen_mulh_d)
TRANS(mulh_du, gen_rrr, EXT_NONE, EXT_NONE, EXT_NONE, gen_mulh_du)
TRANS(mulw_d_w, gen_rrr, EXT_SIGN, EXT_SIGN, EXT_NONE, tcg_gen_mul_tl)
TRANS(mulw_d_wu, gen_rrr, EXT_ZERO, EXT_ZERO, EXT_NONE, tcg_gen_mul_tl)
TRANS(div_w, gen_rrr, EXT_SIGN, EXT_SIGN, EXT_SIGN, gen_div_w)
TRANS(mod_w, gen_rrr, EXT_SIGN, EXT_SIGN, EXT_SIGN, gen_rem_w)
TRANS(div_wu, gen_rrr, EXT_ZERO, EXT_ZERO, EXT_SIGN, gen_div_du)
TRANS(mod_wu, gen_rrr, EXT_ZERO, EXT_ZERO, EXT_SIGN, gen_rem_du)
TRANS(div_d, gen_rrr, EXT_NONE, EXT_NONE, EXT_NONE, gen_div_d)
TRANS(mod_d, gen_rrr, EXT_NONE, EXT_NONE, EXT_NONE, gen_rem_d)
TRANS(div_du, gen_rrr, EXT_NONE, EXT_NONE, EXT_NONE, gen_div_du)
TRANS(mod_du, gen_rrr, EXT_NONE, EXT_NONE, EXT_NONE, gen_rem_du)
TRANS(slti, gen_rri_v, EXT_NONE, EXT_NONE, gen_slt)
TRANS(sltui, gen_rri_v, EXT_NONE, EXT_NONE, gen_sltu)
TRANS(addi_w, gen_rri_c, EXT_NONE, EXT_SIGN, tcg_gen_addi_tl)
TRANS(addi_d, gen_rri_c, EXT_NONE, EXT_NONE, tcg_gen_addi_tl)
TRANS(alsl_w, gen_rrr_sa, EXT_NONE, EXT_SIGN, gen_alsl)
TRANS(alsl_wu, gen_rrr_sa, EXT_NONE, EXT_ZERO, gen_alsl)
TRANS(alsl_d, gen_rrr_sa, EXT_NONE, EXT_NONE, gen_alsl)
TRANS(pcaddi, gen_pc, gen_pcaddi)
TRANS(pcalau12i, gen_pc, gen_pcalau12i)
TRANS(pcaddu12i, gen_pc, gen_pcaddu12i)
TRANS(pcaddu18i, gen_pc, gen_pcaddu18i)
TRANS(andi, gen_rri_c, EXT_NONE, EXT_NONE, tcg_gen_andi_tl)
TRANS(ori, gen_rri_c, EXT_NONE, EXT_NONE, tcg_gen_ori_tl)
TRANS(xori, gen_rri_c, EXT_NONE, EXT_NONE, tcg_gen_xori_tl)
79 changes: 79 additions & 0 deletions target/loongarch/insns.decode
View file
@@ -0,0 +1,79 @@
# SPDX-License-Identifier: GPL-2.0-or-later
#
# LoongArch instruction decode definitions.
#
# Copyright (c) 2021 Loongson Technology Corporation Limited
#

#
# Fields
#
%sa2p1 15:2 !function=plus_1

#
# Argument sets
#
&r_i rd imm
&rrr rd rj rk
&rr_i rd rj imm
&rrr_sa rd rj rk sa

#
# Formats
#
@rrr .... ........ ..... rk:5 rj:5 rd:5 &rrr
@r_i20 .... ... imm:s20 rd:5 &r_i
@rr_i12 .... ...... imm:s12 rj:5 rd:5 &rr_i
@rr_ui12 .... ...... imm:12 rj:5 rd:5 &rr_i
@rr_i16 .... .. imm:s16 rj:5 rd:5 &rr_i
@rrr_sa2p1 .... ........ ... .. rk:5 rj:5 rd:5 &rrr_sa sa=%sa2p1

#
# Fixed point arithmetic operation instruction
#
add_w 0000 00000001 00000 ..... ..... ..... @rrr
add_d 0000 00000001 00001 ..... ..... ..... @rrr
sub_w 0000 00000001 00010 ..... ..... ..... @rrr
sub_d 0000 00000001 00011 ..... ..... ..... @rrr
slt 0000 00000001 00100 ..... ..... ..... @rrr
sltu 0000 00000001 00101 ..... ..... ..... @rrr
slti 0000 001000 ............ ..... ..... @rr_i12
sltui 0000 001001 ............ ..... ..... @rr_i12
nor 0000 00000001 01000 ..... ..... ..... @rrr
and 0000 00000001 01001 ..... ..... ..... @rrr
or 0000 00000001 01010 ..... ..... ..... @rrr
xor 0000 00000001 01011 ..... ..... ..... @rrr
orn 0000 00000001 01100 ..... ..... ..... @rrr
andn 0000 00000001 01101 ..... ..... ..... @rrr
mul_w 0000 00000001 11000 ..... ..... ..... @rrr
mulh_w 0000 00000001 11001 ..... ..... ..... @rrr
mulh_wu 0000 00000001 11010 ..... ..... ..... @rrr
mul_d 0000 00000001 11011 ..... ..... ..... @rrr
mulh_d 0000 00000001 11100 ..... ..... ..... @rrr
mulh_du 0000 00000001 11101 ..... ..... ..... @rrr
mulw_d_w 0000 00000001 11110 ..... ..... ..... @rrr
mulw_d_wu 0000 00000001 11111 ..... ..... ..... @rrr
div_w 0000 00000010 00000 ..... ..... ..... @rrr
mod_w 0000 00000010 00001 ..... ..... ..... @rrr
div_wu 0000 00000010 00010 ..... ..... ..... @rrr
mod_wu 0000 00000010 00011 ..... ..... ..... @rrr
div_d 0000 00000010 00100 ..... ..... ..... @rrr
mod_d 0000 00000010 00101 ..... ..... ..... @rrr
div_du 0000 00000010 00110 ..... ..... ..... @rrr
mod_du 0000 00000010 00111 ..... ..... ..... @rrr
alsl_w 0000 00000000 010 .. ..... ..... ..... @rrr_sa2p1
alsl_wu 0000 00000000 011 .. ..... ..... ..... @rrr_sa2p1
alsl_d 0000 00000010 110 .. ..... ..... ..... @rrr_sa2p1
lu12i_w 0001 010 .................... ..... @r_i20
lu32i_d 0001 011 .................... ..... @r_i20
lu52i_d 0000 001100 ............ ..... ..... @rr_i12
pcaddi 0001 100 .................... ..... @r_i20
pcalau12i 0001 101 .................... ..... @r_i20
pcaddu12i 0001 110 .................... ..... @r_i20
pcaddu18i 0001 111 .................... ..... @r_i20
addi_w 0000 001010 ............ ..... ..... @rr_i12
addi_d 0000 001011 ............ ..... ..... @rr_i12
addu16i_d 0001 00 ................ ..... ..... @rr_i16
andi 0000 001101 ............ ..... ..... @rr_ui12
ori 0000 001110 ............ ..... ..... @rr_ui12
xori 0000 001111 ............ ..... ..... @rr_ui12

0 comments on commit 143d678

Please sign in to comment.