@@ -141,6 +141,7 @@ typedef enum {
#define TCG_TARGET_HAS_sat_vec 1
#define TCG_TARGET_HAS_minmax_vec 1
#define TCG_TARGET_HAS_bitsel_vec 0
+#define TCG_TARGET_HAS_cmpsel_vec 0
#define TCG_TARGET_DEFAULT_MO (0)
#define TCG_TARGET_HAS_MEMORY_BSWAP 1
@@ -191,6 +191,7 @@ extern bool have_avx2;
#define TCG_TARGET_HAS_sat_vec 1
#define TCG_TARGET_HAS_minmax_vec 1
#define TCG_TARGET_HAS_bitsel_vec 0
+#define TCG_TARGET_HAS_cmpsel_vec 0
#define TCG_TARGET_deposit_i32_valid(ofs, len) \
(((ofs) == 0 && (len) == 8) || ((ofs) == 8 && (len) == 8) || \
@@ -1002,6 +1002,8 @@ void tcg_gen_cmp_vec(TCGCond cond, unsigned vece, TCGv_vec r,
void tcg_gen_bitsel_vec(unsigned vece, TCGv_vec r, TCGv_vec a,
TCGv_vec b, TCGv_vec c);
+void tcg_gen_cmpsel_vec(TCGCond cond, unsigned vece, TCGv_vec r,
+ TCGv_vec a, TCGv_vec b, TCGv_vec c, TCGv_vec d);
void tcg_gen_ld_vec(TCGv_vec r, TCGv_ptr base, TCGArg offset);
void tcg_gen_st_vec(TCGv_vec r, TCGv_ptr base, TCGArg offset);
@@ -257,6 +257,7 @@ DEF(sarv_vec, 1, 2, 0, IMPLVEC | IMPL(TCG_TARGET_HAS_shv_vec))
DEF(cmp_vec, 1, 2, 1, IMPLVEC)
DEF(bitsel_vec, 1, 3, 0, IMPLVEC | IMPL(TCG_TARGET_HAS_bitsel_vec))
+DEF(cmpsel_vec, 1, 4, 1, IMPLVEC | IMPL(TCG_TARGET_HAS_cmpsel_vec))
DEF(last_generic, 0, 0, 0, TCG_OPF_NOT_PRESENT)
@@ -188,6 +188,7 @@ typedef uint64_t TCGRegSet;
#define TCG_TARGET_HAS_sat_vec 0
#define TCG_TARGET_HAS_minmax_vec 0
#define TCG_TARGET_HAS_bitsel_vec 0
+#define TCG_TARGET_HAS_cmpsel_vec 0
#else
#define TCG_TARGET_MAYBE_vec 1
#endif
@@ -119,6 +119,11 @@ bool tcg_can_emit_vecop_list(const TCGOpcode *list,
continue;
}
break;
+ case INDEX_op_cmpsel_vec:
+ if (tcg_can_emit_vec_op(INDEX_op_cmp_vec, type, vece)) {
+ continue;
+ }
+ break;
default:
break;
}
@@ -159,6 +164,20 @@ void vec_gen_4(TCGOpcode opc, TCGType type, unsigned vece,
op->args[3] = c;
}
+static void vec_gen_6(TCGOpcode opc, TCGType type, unsigned vece, TCGArg r,
+ TCGArg a, TCGArg b, TCGArg c, TCGArg d, TCGArg e)
+{
+ TCGOp *op = tcg_emit_op(opc);
+ TCGOP_VECL(op) = type - TCG_TYPE_V64;
+ TCGOP_VECE(op) = vece;
+ op->args[0] = r;
+ op->args[1] = a;
+ op->args[2] = b;
+ op->args[3] = c;
+ op->args[4] = d;
+ op->args[5] = e;
+}
+
static void vec_gen_op2(TCGOpcode opc, unsigned vece, TCGv_vec r, TCGv_vec a)
{
TCGTemp *rt = tcgv_vec_temp(r);
@@ -717,3 +736,43 @@ void tcg_gen_bitsel_vec(unsigned vece, TCGv_vec r, TCGv_vec a,
tcg_temp_free_vec(t);
}
}
+
+void tcg_gen_cmpsel_vec(TCGCond cond, unsigned vece, TCGv_vec r,
+ TCGv_vec a, TCGv_vec b, TCGv_vec c, TCGv_vec d)
+{
+ TCGTemp *rt = tcgv_vec_temp(r);
+ TCGTemp *at = tcgv_vec_temp(a);
+ TCGTemp *bt = tcgv_vec_temp(b);
+ TCGTemp *ct = tcgv_vec_temp(c);
+ TCGTemp *dt = tcgv_vec_temp(d);
+ TCGArg ri = temp_arg(rt);
+ TCGArg ai = temp_arg(at);
+ TCGArg bi = temp_arg(bt);
+ TCGArg ci = temp_arg(ct);
+ TCGArg di = temp_arg(dt);
+ TCGType type = rt->base_type;
+ const TCGOpcode *hold_list;
+ int can;
+
+ tcg_debug_assert(at->base_type >= type);
+ tcg_debug_assert(bt->base_type >= type);
+ tcg_debug_assert(ct->base_type >= type);
+ tcg_debug_assert(dt->base_type >= type);
+
+ tcg_assert_listed_vecop(INDEX_op_cmpsel_vec);
+ hold_list = tcg_swap_vecop_list(NULL);
+ can = tcg_can_emit_vec_op(INDEX_op_cmpsel_vec, type, vece);
+
+ if (can > 0) {
+ vec_gen_6(INDEX_op_cmpsel_vec, type, vece, ri, ai, bi, ci, di, cond);
+ } else if (can < 0) {
+ tcg_expand_vec_op(INDEX_op_cmpsel_vec, type, vece,
+ ri, ai, bi, ci, di, cond);
+ } else {
+ TCGv_vec t = tcg_temp_new_vec(type);
+ tcg_gen_cmp_vec(cond, vece, t, a, b);
+ tcg_gen_bitsel_vec(vece, r, t, c, d);
+ tcg_temp_free_vec(t);
+ }
+ tcg_swap_vecop_list(hold_list);
+}
@@ -1648,6 +1648,8 @@ bool tcg_op_supported(TCGOpcode op)
return have_vec && TCG_TARGET_HAS_minmax_vec;
case INDEX_op_bitsel_vec:
return have_vec && TCG_TARGET_HAS_bitsel_vec;
+ case INDEX_op_cmpsel_vec:
+ return have_vec && TCG_TARGET_HAS_cmpsel_vec;
default:
tcg_debug_assert(op > INDEX_op_last_generic && op < NB_OPS);
@@ -2028,6 +2030,7 @@ static void tcg_dump_ops(TCGContext *s, bool have_prefs)
case INDEX_op_setcond_i64:
case INDEX_op_movcond_i64:
case INDEX_op_cmp_vec:
+ case INDEX_op_cmpsel_vec:
if (op->args[k] < ARRAY_SIZE(cond_name)
&& cond_name[op->args[k]]) {
col += qemu_log(",%s", cond_name[op->args[k++]]);
@@ -631,6 +631,13 @@ E.g. VECL=1 -> 64 << 1 -> v128, and VECE=2 -> 1 << 2 -> i32.
Bitwise select, v0 = (v2 & v1) | (v3 & ~v1), across the entire vector.
+* cmpsel_vec v0, c1, c2, v3, v4, cond
+
+ Select elements based on comparison results:
+ for (i = 0; i < n; ++i) {
+ v0[i] = (c1[i] cond c2[i]) ? v3[i] : v4[i].
+ }
+
*********
Note 1: Some shortcuts are defined when the last operand is known to be
Perform a per-element conditional move. This combination operation is easier to implement on some host vector units than plain cmp+bitsel. Omit the usual gvec interface, as this is intended to be used by target-specific gvec expansion call-backs. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/aarch64/tcg-target.h | 1 + tcg/i386/tcg-target.h | 1 + tcg/tcg-op.h | 2 ++ tcg/tcg-opc.h | 1 + tcg/tcg.h | 1 + tcg/tcg-op-vec.c | 59 ++++++++++++++++++++++++++++++++++++++++ tcg/tcg.c | 3 ++ tcg/README | 7 +++++ 8 files changed, 75 insertions(+) -- 2.17.1