Implement the MVE VRHADD insn, which performs a rounded halving
addition.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/helper-mve.h    | 8 ++++++++
 target/arm/mve.decode      | 3 +++
 target/arm/mve_helper.c    | 6 ++++++
 target/arm/translate-mve.c | 2 ++
 4 files changed, 19 insertions(+)

diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
index 34a46ed38ee..2f0cf99359a 100644
--- a/target/arm/helper-mve.h
+++ b/target/arm/helper-mve.h
@@ -238,6 +238,14 @@ DEF_HELPER_FLAGS_4(mve_vqdmullbw, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
 DEF_HELPER_FLAGS_4(mve_vqdmullth, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
 DEF_HELPER_FLAGS_4(mve_vqdmulltw, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
 
+DEF_HELPER_FLAGS_4(mve_vrhaddsb, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vrhaddsh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vrhaddsw, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+
+DEF_HELPER_FLAGS_4(mve_vrhaddub, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vrhadduh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vrhadduw, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+
 DEF_HELPER_FLAGS_4(mve_vadd_scalarb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(mve_vadd_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(mve_vadd_scalarw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
diff --git a/target/arm/mve.decode b/target/arm/mve.decode
index 3a2a7e75a3a..6b969902df0 100644
--- a/target/arm/mve.decode
+++ b/target/arm/mve.decode
@@ -157,6 +157,9 @@ VQRDMLSDHX       1111 1110 0 . .. ... 0 ... 1 1110 . 0 . 0 ... 1 @2op
 VQDMULLB         111 . 1110 0 . 11 ... 0 ... 0 1111 . 0 . 0 ... 1 @2op_sz28
 VQDMULLT         111 . 1110 0 . 11 ... 0 ... 1 1111 . 0 . 0 ... 1 @2op_sz28
 
+VRHADD_S         111 0 1111 0 . .. ... 0 ... 0 0001 . 1 . 0 ... 0 @2op
+VRHADD_U         111 1 1111 0 . .. ... 0 ... 0 0001 . 1 . 0 ... 0 @2op
+
 # Vector miscellaneous
 
 VCLS             1111 1111 1 . 11 .. 00 ... 0 0100 01 . 0 ... 0 @1op
diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c
index 7c5b36caae9..a8ff921144d 100644
--- a/target/arm/mve_helper.c
+++ b/target/arm/mve_helper.c
@@ -546,6 +546,12 @@ DO_2OP_U(vshlu, DO_VSHLU)
 DO_2OP_S(vrshls, DO_VRSHLS)
 DO_2OP_U(vrshlu, DO_VRSHLU)
 
+#define DO_RHADD_S(N, M) (((int64_t)(N) + (M) + 1) >> 1)
+#define DO_RHADD_U(N, M) (((uint64_t)(N) + (M) + 1) >> 1)
+
+DO_2OP_S(vrhadds, DO_RHADD_S)
+DO_2OP_U(vrhaddu, DO_RHADD_U)
+
 static inline int32_t do_sat_bhw(int64_t val, int64_t min, int64_t max, bool *s)
 {
     if (val > max) {
diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c
index ca1203e650d..a4efb9bc3eb 100644
--- a/target/arm/translate-mve.c
+++ b/target/arm/translate-mve.c
@@ -418,6 +418,8 @@ DO_2OP(VQDMLSDH, vqdmlsdh)
 DO_2OP(VQDMLSDHX, vqdmlsdhx)
 DO_2OP(VQRDMLSDH, vqrdmlsdh)
 DO_2OP(VQRDMLSDHX, vqrdmlsdhx)
+DO_2OP(VRHADD_S, vrhadds)
+DO_2OP(VRHADD_U, vrhaddu)
 
 static bool trans_VQDMULLB(DisasContext *s, arg_2op *a)
 {
-- 
2.20.1