[PULL 30/63] tcg: Add tcg_gen_vec_add{sub}8_i32

[Richard Henderson <richard.henderson@linaro.org>]

From: LIU Zhiwei <zhiwei_liu@c-sky.com>

Implement tcg_gen_vec_add{sub}8_tl by adding corresponging i32 OP.

Signed-off-by: LIU Zhiwei <zhiwei_liu@c-sky.com>
Message-Id: <20210624105023.3852-3-zhiwei_liu@c-sky.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 include/tcg/tcg-op-gvec.h |  6 ++++++
 tcg/tcg-op-gvec.c         | 38 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 44 insertions(+)

diff --git a/include/tcg/tcg-op-gvec.h b/include/tcg/tcg-op-gvec.h
index 9b67822f54..2d5ad6ce12 100644
--- a/include/tcg/tcg-op-gvec.h
+++ b/include/tcg/tcg-op-gvec.h
@@ -402,14 +402,20 @@ 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_add8_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b);
 void tcg_gen_vec_add16_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b);
 
+void tcg_gen_vec_sub8_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_add8_tl  tcg_gen_vec_add8_i64
+#define tcg_gen_vec_sub8_tl  tcg_gen_vec_sub8_i64
 #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_add8_tl  tcg_gen_vec_add8_i32
+#define tcg_gen_vec_sub8_tl  tcg_gen_vec_sub8_i32
 #define tcg_gen_vec_add16_tl tcg_gen_vec_add16_i32
 #define tcg_gen_vec_sub16_tl tcg_gen_vec_sub16_i32
 #endif
diff --git a/tcg/tcg-op-gvec.c b/tcg/tcg-op-gvec.c
index 7ddd56c0e6..6d9a0aed62 100644
--- a/tcg/tcg-op-gvec.c
+++ b/tcg/tcg-op-gvec.c
@@ -1736,6 +1736,25 @@ void tcg_gen_vec_add8_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b)
     gen_addv_mask(d, a, b, m);
 }
 
+void tcg_gen_vec_add8_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b)
+{
+    TCGv_i32 m = tcg_constant_i32((int32_t)dup_const(MO_8, 0x80));
+    TCGv_i32 t1 = tcg_temp_new_i32();
+    TCGv_i32 t2 = tcg_temp_new_i32();
+    TCGv_i32 t3 = tcg_temp_new_i32();
+
+    tcg_gen_andc_i32(t1, a, m);
+    tcg_gen_andc_i32(t2, b, m);
+    tcg_gen_xor_i32(t3, a, b);
+    tcg_gen_add_i32(d, t1, t2);
+    tcg_gen_and_i32(t3, t3, m);
+    tcg_gen_xor_i32(d, d, t3);
+
+    tcg_temp_free_i32(t1);
+    tcg_temp_free_i32(t2);
+    tcg_temp_free_i32(t3);
+}
+
 void tcg_gen_vec_add16_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b)
 {
     TCGv_i64 m = tcg_constant_i64(dup_const(MO_16, 0x8000));
@@ -1900,6 +1919,25 @@ void tcg_gen_vec_sub8_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b)
     gen_subv_mask(d, a, b, m);
 }
 
+void tcg_gen_vec_sub8_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b)
+{
+    TCGv_i32 m = tcg_constant_i32((int32_t)dup_const(MO_8, 0x80));
+    TCGv_i32 t1 = tcg_temp_new_i32();
+    TCGv_i32 t2 = tcg_temp_new_i32();
+    TCGv_i32 t3 = tcg_temp_new_i32();
+
+    tcg_gen_or_i32(t1, a, m);
+    tcg_gen_andc_i32(t2, b, m);
+    tcg_gen_eqv_i32(t3, a, b);
+    tcg_gen_sub_i32(d, t1, t2);
+    tcg_gen_and_i32(t3, t3, m);
+    tcg_gen_xor_i32(d, d, t3);
+
+    tcg_temp_free_i32(t1);
+    tcg_temp_free_i32(t2);
+    tcg_temp_free_i32(t3);
+}
+
 void tcg_gen_vec_sub16_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b)
 {
     TCGv_i64 m = tcg_constant_i64(dup_const(MO_16, 0x8000));
-- 
2.25.1