tcg: Add tcg_gen_vec_add{sub}16_i32

Implement tcg_gen_vec_add{sub}16_tl by adding corresponding i32 OP.

Signed-off-by: LIU Zhiwei <zhiwei_liu@c-sky.com>
Message-Id: <20210624105023.3852-2-zhiwei_liu@c-sky.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

diff --git a/include/tcg/tcg-op-gvec.h b/include/tcg/tcg-op-gvec.h
index c69a7de984be598d2f80ff7f3a0403dec107b105..9b67822f5478f09cad40e4705f988b07837e7e47 100644 (file)
--- a/include/tcg/tcg-op-gvec.h
+++ b/include/tcg/tcg-op-gvec.h
@@ -401,4 +401,17 @@ void tcg_gen_vec_sar16i_i64(TCGv_i64 d, TCGv_i64 a, int64_t);
 void tcg_gen_vec_rotl8i_i64(TCGv_i64 d, TCGv_i64 a, int64_t c);
 void tcg_gen_vec_rotl16i_i64(TCGv_i64 d, TCGv_i64 a, int64_t c);
 
+/* 32-bit vector operations. */
+void tcg_gen_vec_add16_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b);
+
+void tcg_gen_vec_sub16_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b);
+
+#if TARGET_LONG_BITS == 64
+#define tcg_gen_vec_add16_tl tcg_gen_vec_add16_i64
+#define tcg_gen_vec_sub16_tl tcg_gen_vec_sub16_i64
+#else
+#define tcg_gen_vec_add16_tl tcg_gen_vec_add16_i32
+#define tcg_gen_vec_sub16_tl tcg_gen_vec_sub16_i32
+#endif
+
 #endif

diff --git a/tcg/tcg-op-gvec.c b/tcg/tcg-op-gvec.c
index 515db120cc62120271a847af398ff1387b5b7e99..7ddd56c0e68c89fd69345c3488936c5181daf53a 100644 (file)
--- a/tcg/tcg-op-gvec.c
+++ b/tcg/tcg-op-gvec.c
@@ -1742,6 +1742,20 @@ void tcg_gen_vec_add16_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b)
     gen_addv_mask(d, a, b, m);
 }
 
+void tcg_gen_vec_add16_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b)
+{
+    TCGv_i32 t1 = tcg_temp_new_i32();
+    TCGv_i32 t2 = tcg_temp_new_i32();
+
+    tcg_gen_andi_i32(t1, a, ~0xffff);
+    tcg_gen_add_i32(t2, a, b);
+    tcg_gen_add_i32(t1, t1, b);
+    tcg_gen_deposit_i32(d, t1, t2, 0, 16);
+
+    tcg_temp_free_i32(t1);
+    tcg_temp_free_i32(t2);
+}
+
 void tcg_gen_vec_add32_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b)
 {
     TCGv_i64 t1 = tcg_temp_new_i64();
@@ -1892,6 +1906,20 @@ void tcg_gen_vec_sub16_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b)
     gen_subv_mask(d, a, b, m);
 }
 
+void tcg_gen_vec_sub16_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b)
+{
+    TCGv_i32 t1 = tcg_temp_new_i32();
+    TCGv_i32 t2 = tcg_temp_new_i32();
+
+    tcg_gen_andi_i32(t1, b, ~0xffff);
+    tcg_gen_sub_i32(t2, a, b);
+    tcg_gen_sub_i32(t1, a, t1);
+    tcg_gen_deposit_i32(d, t1, t2, 0, 16);
+
+    tcg_temp_free_i32(t1);
+    tcg_temp_free_i32(t2);
+}
+
 void tcg_gen_vec_sub32_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b)
 {
     TCGv_i64 t1 = tcg_temp_new_i64();