@@ -154,7 +154,7 @@ extern bool have_isa_3_00;
#define TCG_TARGET_HAS_shs_vec 0
#define TCG_TARGET_HAS_shv_vec 1
#define TCG_TARGET_HAS_cmp_vec 1
-#define TCG_TARGET_HAS_mul_vec 0
+#define TCG_TARGET_HAS_mul_vec 1
#define TCG_TARGET_HAS_sat_vec 1
#define TCG_TARGET_HAS_minmax_vec 1
#define TCG_TARGET_HAS_bitsel_vec 0
@@ -3,3 +3,11 @@
* emitted by tcg_expand_vec_op. For those familiar with GCC internals,
* consider these to be UNSPEC with names.
*/
+
+DEF(ppc_mrgh_vec, 1, 2, 0, IMPLVEC)
+DEF(ppc_mrgl_vec, 1, 2, 0, IMPLVEC)
+DEF(ppc_msum_vec, 1, 3, 0, IMPLVEC)
+DEF(ppc_muleu_vec, 1, 2, 0, IMPLVEC)
+DEF(ppc_mulou_vec, 1, 2, 0, IMPLVEC)
+DEF(ppc_pkum_vec, 1, 2, 0, IMPLVEC)
+DEF(ppc_rotl_vec, 1, 2, 0, IMPLVEC)
@@ -526,6 +526,25 @@ static int tcg_target_const_match(tcg_target_long val, TCGType type,
#define VSRAB VX4(772)
#define VSRAH VX4(836)
#define VSRAW VX4(900)
+#define VRLB VX4(4)
+#define VRLH VX4(68)
+#define VRLW VX4(132)
+
+#define VMULEUB VX4(520)
+#define VMULEUH VX4(584)
+#define VMULOUB VX4(8)
+#define VMULOUH VX4(72)
+#define VMSUMUHM VX4(38)
+
+#define VMRGHB VX4(12)
+#define VMRGHH VX4(76)
+#define VMRGHW VX4(140)
+#define VMRGLB VX4(268)
+#define VMRGLH VX4(332)
+#define VMRGLW VX4(396)
+
+#define VPKUHUM VX4(14)
+#define VPKUWUM VX4(78)
#define VAND VX4(1028)
#define VANDC VX4(1092)
@@ -2878,6 +2897,7 @@ int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type, unsigned vece)
case INDEX_op_sarv_vec:
return vece <= MO_32;
case INDEX_op_cmp_vec:
+ case INDEX_op_mul_vec:
case INDEX_op_shli_vec:
case INDEX_op_shri_vec:
case INDEX_op_sari_vec:
@@ -2990,7 +3010,13 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
smax_op[4] = { VMAXSB, VMAXSH, VMAXSW, 0 },
shlv_op[4] = { VSLB, VSLH, VSLW, 0 },
shrv_op[4] = { VSRB, VSRH, VSRW, 0 },
- sarv_op[4] = { VSRAB, VSRAH, VSRAW, 0 };
+ sarv_op[4] = { VSRAB, VSRAH, VSRAW, 0 },
+ mrgh_op[4] = { VMRGHB, VMRGHH, VMRGHW, 0 },
+ mrgl_op[4] = { VMRGLB, VMRGLH, VMRGLW, 0 },
+ muleu_op[4] = { VMULEUB, VMULEUH, 0, 0 },
+ mulou_op[4] = { VMULOUB, VMULOUH, 0, 0 },
+ pkum_op[4] = { VPKUHUM, VPKUWUM, 0, 0 },
+ rotl_op[4] = { VRLB, VRLH, VRLW, 0 };
TCGType type = vecl + TCG_TYPE_V64;
TCGArg a0 = args[0], a1 = args[1], a2 = args[2];
@@ -3079,6 +3105,29 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
}
break;
+ case INDEX_op_ppc_mrgh_vec:
+ insn = mrgh_op[vece];
+ break;
+ case INDEX_op_ppc_mrgl_vec:
+ insn = mrgl_op[vece];
+ break;
+ case INDEX_op_ppc_muleu_vec:
+ insn = muleu_op[vece];
+ break;
+ case INDEX_op_ppc_mulou_vec:
+ insn = mulou_op[vece];
+ break;
+ case INDEX_op_ppc_pkum_vec:
+ insn = pkum_op[vece];
+ break;
+ case INDEX_op_ppc_rotl_vec:
+ insn = rotl_op[vece];
+ break;
+ case INDEX_op_ppc_msum_vec:
+ tcg_debug_assert(vece == MO_16);
+ tcg_out32(s, VMSUMUHM | VRT(a0) | VRA(a1) | VRB(a2) | VRC(args[3]));
+ return;
+
case INDEX_op_mov_vec: /* Always emitted via tcg_out_mov. */
case INDEX_op_dupi_vec: /* Always emitted via tcg_out_movi. */
case INDEX_op_dup_vec: /* Always emitted via tcg_out_dup_vec. */
@@ -3148,6 +3197,53 @@ static void expand_vec_cmp(TCGType type, unsigned vece, TCGv_vec v0,
}
}
+static void expand_vec_mul(TCGType type, unsigned vece, TCGv_vec v0,
+ TCGv_vec v1, TCGv_vec v2)
+{
+ TCGv_vec t1 = tcg_temp_new_vec(type);
+ TCGv_vec t2 = tcg_temp_new_vec(type);
+ TCGv_vec t3, t4;
+
+ switch (vece) {
+ case MO_8:
+ case MO_16:
+ vec_gen_3(INDEX_op_ppc_muleu_vec, type, vece, tcgv_vec_arg(t1),
+ tcgv_vec_arg(v1), tcgv_vec_arg(v2));
+ vec_gen_3(INDEX_op_ppc_mulou_vec, type, vece, tcgv_vec_arg(t2),
+ tcgv_vec_arg(v1), tcgv_vec_arg(v2));
+ vec_gen_3(INDEX_op_ppc_mrgh_vec, type, vece + 1, tcgv_vec_arg(v0),
+ tcgv_vec_arg(t1), tcgv_vec_arg(t2));
+ vec_gen_3(INDEX_op_ppc_mrgl_vec, type, vece + 1, tcgv_vec_arg(t1),
+ tcgv_vec_arg(t1), tcgv_vec_arg(t2));
+ vec_gen_3(INDEX_op_ppc_pkum_vec, type, vece, tcgv_vec_arg(v0),
+ tcgv_vec_arg(v0), tcgv_vec_arg(t1));
+ break;
+
+ case MO_32:
+ t3 = tcg_temp_new_vec(type);
+ t4 = tcg_temp_new_vec(type);
+ tcg_gen_dupi_vec(MO_8, t4, -16);
+ vec_gen_3(INDEX_op_ppc_rotl_vec, type, MO_32, tcgv_vec_arg(t1),
+ tcgv_vec_arg(v2), tcgv_vec_arg(t4));
+ vec_gen_3(INDEX_op_ppc_mulou_vec, type, MO_16, tcgv_vec_arg(t2),
+ tcgv_vec_arg(v1), tcgv_vec_arg(v2));
+ tcg_gen_dupi_vec(MO_8, t3, 0);
+ vec_gen_4(INDEX_op_ppc_msum_vec, type, MO_16, tcgv_vec_arg(t3),
+ tcgv_vec_arg(v1), tcgv_vec_arg(t1), tcgv_vec_arg(t3));
+ vec_gen_3(INDEX_op_shlv_vec, type, MO_32, tcgv_vec_arg(t3),
+ tcgv_vec_arg(t3), tcgv_vec_arg(t4));
+ tcg_gen_add_vec(MO_32, v0, t2, t3);
+ tcg_temp_free_vec(t3);
+ tcg_temp_free_vec(t4);
+ break;
+
+ default:
+ g_assert_not_reached();
+ }
+ tcg_temp_free_vec(t1);
+ tcg_temp_free_vec(t2);
+}
+
void tcg_expand_vec_op(TCGOpcode opc, TCGType type, unsigned vece,
TCGArg a0, ...)
{
@@ -3174,6 +3270,10 @@ void tcg_expand_vec_op(TCGOpcode opc, TCGType type, unsigned vece,
v2 = temp_tcgv_vec(arg_temp(a2));
expand_vec_cmp(type, vece, v0, v1, v2, va_arg(va, TCGArg));
break;
+ case INDEX_op_mul_vec:
+ v2 = temp_tcgv_vec(arg_temp(a2));
+ expand_vec_mul(type, vece, v0, v1, v2);
+ break;
default:
g_assert_not_reached();
}
@@ -3220,6 +3320,8 @@ static const TCGTargetOpDef *tcg_target_op_def(TCGOpcode op)
static const TCGTargetOpDef v_r = { .args_ct_str = { "v", "r" } };
static const TCGTargetOpDef v_v = { .args_ct_str = { "v", "v" } };
static const TCGTargetOpDef v_v_v = { .args_ct_str = { "v", "v", "v" } };
+ static const TCGTargetOpDef v_v_v_v
+ = { .args_ct_str = { "v", "v", "v", "v" } };
switch (op) {
case INDEX_op_goto_ptr:
@@ -3375,6 +3477,12 @@ static const TCGTargetOpDef *tcg_target_op_def(TCGOpcode op)
case INDEX_op_shlv_vec:
case INDEX_op_shrv_vec:
case INDEX_op_sarv_vec:
+ case INDEX_op_ppc_mrgh_vec:
+ case INDEX_op_ppc_mrgl_vec:
+ case INDEX_op_ppc_muleu_vec:
+ case INDEX_op_ppc_mulou_vec:
+ case INDEX_op_ppc_pkum_vec:
+ case INDEX_op_ppc_rotl_vec:
return &v_v_v;
case INDEX_op_not_vec:
case INDEX_op_dup_vec:
@@ -3383,6 +3491,8 @@ static const TCGTargetOpDef *tcg_target_op_def(TCGOpcode op)
case INDEX_op_st_vec:
case INDEX_op_dupm_vec:
return &v_r;
+ case INDEX_op_ppc_msum_vec:
+ return &v_v_v_v;
default:
return NULL;