[PATCH v4 13/16] tcg: Expand usadd/ussub with umin/umax

[Richard Henderson]

For usadd, we only have to consider overflow.  Since ~B + B == -1,
the maximum value for A that saturates is ~B.

For ussub, we only have to consider underflow.  The minimum value
that saturates to 0 from A - B is B.

Signed-off-by: Richard Henderson <richard.hender...@linaro.org>
---
 tcg/tcg-op-vec.c | 37 +++++++++++++++++++++++++++++++++++--
 1 file changed, 35 insertions(+), 2 deletions(-)

diff --git a/tcg/tcg-op-vec.c b/tcg/tcg-op-vec.c
index 15e026ae49..7705a49c0b 100644
--- a/tcg/tcg-op-vec.c
+++ b/tcg/tcg-op-vec.c
@@ -119,6 +119,18 @@ bool tcg_can_emit_vecop_list(const TCGOpcode *list,
                 continue;
             }
             break;
+        case INDEX_op_usadd_vec:
+            if (tcg_can_emit_vec_op(INDEX_op_umin_vec, type, vece) ||
+                tcg_can_emit_vec_op(INDEX_op_cmp_vec, type, vece)) {
+                continue;
+            }
+            break;
+        case INDEX_op_ussub_vec:
+            if (tcg_can_emit_vec_op(INDEX_op_umax_vec, type, vece) ||
+                tcg_can_emit_vec_op(INDEX_op_cmp_vec, type, vece)) {
+                continue;
+            }
+            break;
         case INDEX_op_cmpsel_vec:
         case INDEX_op_smin_vec:
         case INDEX_op_smax_vec:
@@ -603,7 +615,18 @@ void tcg_gen_ssadd_vec(unsigned vece, TCGv_vec r, TCGv_vec 
a, TCGv_vec b)
 
 void tcg_gen_usadd_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b)
 {
-    do_op3_nofail(vece, r, a, b, INDEX_op_usadd_vec);
+    if (!do_op3(vece, r, a, b, INDEX_op_usadd_vec)) {
+        const TCGOpcode *hold_list = tcg_swap_vecop_list(NULL);
+        TCGv_vec t = tcg_temp_new_vec_matching(r);
+
+        /* usadd(a, b) = min(a, ~b) + b */
+        tcg_gen_not_vec(vece, t, b);
+        tcg_gen_umin_vec(vece, t, t, a);
+        tcg_gen_add_vec(vece, r, r, b);
+
+        tcg_temp_free_vec(t);
+        tcg_swap_vecop_list(hold_list);
+    }
 }
 
 void tcg_gen_sssub_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b)
@@ -613,7 +636,17 @@ void tcg_gen_sssub_vec(unsigned vece, TCGv_vec r, TCGv_vec 
a, TCGv_vec b)
 
 void tcg_gen_ussub_vec(unsigned vece, TCGv_vec r, TCGv_vec a, TCGv_vec b)
 {
-    do_op3_nofail(vece, r, a, b, INDEX_op_ussub_vec);
+    if (!do_op3(vece, r, a, b, INDEX_op_ussub_vec)) {
+        const TCGOpcode *hold_list = tcg_swap_vecop_list(NULL);
+        TCGv_vec t = tcg_temp_new_vec_matching(r);
+
+        /* ussub(a, b) = max(a, b) - b */
+        tcg_gen_umax_vec(vece, t, a, b);
+        tcg_gen_sub_vec(vece, r, t, b);
+
+        tcg_temp_free_vec(t);
+        tcg_swap_vecop_list(hold_list);
+    }
 }
 
 static void do_minmax(unsigned vece, TCGv_vec r, TCGv_vec a,
-- 
2.25.1