tcg/loongarch64: Lower add/sub_vec to vadd/vsub

Lower the following ops:

- add_vec
- sub_vec

Signed-off-by: Jiajie Chen <c@jia.je>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20230908022302.180442-6-c@jia.je>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
This commit is contained in:
Jiajie Chen 2023-09-08 10:21:12 +08:00 committed by Richard Henderson
parent d8b6fa593d
commit e9d7c8cf95
3 changed files with 63 additions and 0 deletions

View File

@ -32,4 +32,5 @@ C_O1_I2(r, rZ, ri)
C_O1_I2(r, rZ, rJ)
C_O1_I2(r, rZ, rZ)
C_O1_I2(w, w, wM)
C_O1_I2(w, w, wA)
C_O1_I4(r, rZ, rJ, rZ, rZ)

View File

@ -27,3 +27,4 @@ CONST('Z', TCG_CT_CONST_ZERO)
CONST('C', TCG_CT_CONST_C12)
CONST('W', TCG_CT_CONST_WSZ)
CONST('M', TCG_CT_CONST_VCMP)
CONST('A', TCG_CT_CONST_VADD)

View File

@ -177,6 +177,7 @@ static TCGReg tcg_target_call_oarg_reg(TCGCallReturnKind kind, int slot)
#define TCG_CT_CONST_C12 0x1000
#define TCG_CT_CONST_WSZ 0x2000
#define TCG_CT_CONST_VCMP 0x4000
#define TCG_CT_CONST_VADD 0x8000
#define ALL_GENERAL_REGS MAKE_64BIT_MASK(0, 32)
#define ALL_VECTOR_REGS MAKE_64BIT_MASK(32, 32)
@ -214,6 +215,9 @@ static bool tcg_target_const_match(int64_t val, TCGType type, int ct, int vece)
if ((ct & TCG_CT_CONST_VCMP) && -0x10 <= vec_val && vec_val <= 0x1f) {
return true;
}
if ((ct & TCG_CT_CONST_VADD) && -0x1f <= vec_val && vec_val <= 0x1f) {
return true;
}
return false;
}
@ -1621,6 +1625,51 @@ static void tcg_out_dupi_vec(TCGContext *s, TCGType type, unsigned vece,
}
}
static void tcg_out_addsub_vec(TCGContext *s, unsigned vece, const TCGArg a0,
const TCGArg a1, const TCGArg a2,
bool a2_is_const, bool is_add)
{
static const LoongArchInsn add_vec_insn[4] = {
OPC_VADD_B, OPC_VADD_H, OPC_VADD_W, OPC_VADD_D
};
static const LoongArchInsn add_vec_imm_insn[4] = {
OPC_VADDI_BU, OPC_VADDI_HU, OPC_VADDI_WU, OPC_VADDI_DU
};
static const LoongArchInsn sub_vec_insn[4] = {
OPC_VSUB_B, OPC_VSUB_H, OPC_VSUB_W, OPC_VSUB_D
};
static const LoongArchInsn sub_vec_imm_insn[4] = {
OPC_VSUBI_BU, OPC_VSUBI_HU, OPC_VSUBI_WU, OPC_VSUBI_DU
};
if (a2_is_const) {
int64_t value = sextract64(a2, 0, 8 << vece);
if (!is_add) {
value = -value;
}
/* Try vaddi/vsubi */
if (0 <= value && value <= 0x1f) {
tcg_out32(s, encode_vdvjuk5_insn(add_vec_imm_insn[vece], a0, \
a1, value));
return;
} else if (-0x1f <= value && value < 0) {
tcg_out32(s, encode_vdvjuk5_insn(sub_vec_imm_insn[vece], a0, \
a1, -value));
return;
}
/* constraint TCG_CT_CONST_VADD ensures unreachable */
g_assert_not_reached();
}
if (is_add) {
tcg_out32(s, encode_vdvjvk_insn(add_vec_insn[vece], a0, a1, a2));
} else {
tcg_out32(s, encode_vdvjvk_insn(sub_vec_insn[vece], a0, a1, a2));
}
}
static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
unsigned vecl, unsigned vece,
const TCGArg args[TCG_MAX_OP_ARGS],
@ -1712,6 +1761,12 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
}
tcg_out32(s, encode_vdvjvk_insn(insn, a0, a1, a2));
break;
case INDEX_op_add_vec:
tcg_out_addsub_vec(s, vece, a0, a1, a2, const_args[2], true);
break;
case INDEX_op_sub_vec:
tcg_out_addsub_vec(s, vece, a0, a1, a2, const_args[2], false);
break;
case INDEX_op_dupm_vec:
tcg_out_dupm_vec(s, type, vece, a0, a1, a2);
break;
@ -1728,6 +1783,8 @@ int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type, unsigned vece)
case INDEX_op_dup_vec:
case INDEX_op_dupm_vec:
case INDEX_op_cmp_vec:
case INDEX_op_add_vec:
case INDEX_op_sub_vec:
return 1;
default:
return 0;
@ -1892,6 +1949,10 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op)
case INDEX_op_cmp_vec:
return C_O1_I2(w, w, wM);
case INDEX_op_add_vec:
case INDEX_op_sub_vec:
return C_O1_I2(w, w, wA);
default:
g_assert_not_reached();
}