[PATCH v3 30/44] target/arm: Implement MVE VQDMULH, VQRDMULH (vector)

[Peter Maydell <peter.maydell@linaro.org>]

Implement the vector forms of the MVE VQDMULH and VQRDMULH insns.

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    | 27 +++++++++++++++++++++++++++
 target/arm/translate-mve.c |  2 ++
 4 files changed, 40 insertions(+)

diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
index 41dd61264e0..c4e766c6511 100644
--- a/target/arm/helper-mve.h
+++ b/target/arm/helper-mve.h
@@ -145,6 +145,14 @@ DEF_HELPER_FLAGS_4(mve_vmulltub, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
 DEF_HELPER_FLAGS_4(mve_vmulltuh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
 DEF_HELPER_FLAGS_4(mve_vmulltuw, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
 
+DEF_HELPER_FLAGS_4(mve_vqdmulhb, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vqdmulhh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vqdmulhw, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+
+DEF_HELPER_FLAGS_4(mve_vqrdmulhb, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vqrdmulhh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vqrdmulhw, 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 a71ad7252bf..9860d43f73c 100644
--- a/target/arm/mve.decode
+++ b/target/arm/mve.decode
@@ -113,6 +113,9 @@ VMULL_BU         111 1 1110 0 . .. ... 1 ... 0 1110 . 0 . 0 ... 0 @2op
 VMULL_TS         111 0 1110 0 . .. ... 1 ... 1 1110 . 0 . 0 ... 0 @2op
 VMULL_TU         111 1 1110 0 . .. ... 1 ... 1 1110 . 0 . 0 ... 0 @2op
 
+VQDMULH          1110 1111 0 . .. ... 0 ... 0 1011 . 1 . 0 ... 0 @2op
+VQRDMULH         1111 1111 0 . .. ... 0 ... 0 1011 . 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 c9f506e260c..d17c5e4588b 100644
--- a/target/arm/mve_helper.c
+++ b/target/arm/mve_helper.c
@@ -385,6 +385,25 @@ DO_1OP(vfnegs, 8, uint64_t, DO_FNEGS)
         mve_advance_vpt(env);                                           \
     }
 
+#define DO_2OP_SAT(OP, ESIZE, TYPE, FN)                                 \
+    void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, void *vn, void *vm) \
+    {                                                                   \
+        TYPE *d = vd, *n = vn, *m = vm;                                 \
+        uint16_t mask = mve_element_mask(env);                          \
+        unsigned e;                                                     \
+        bool qc = false;                                                \
+        for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) {              \
+            bool sat = false;                                           \
+            TYPE r = FN(n[H##ESIZE(e)], m[H##ESIZE(e)], &sat);          \
+            mergemask(&d[H##ESIZE(e)], r, mask);                        \
+            qc |= sat & mask & 1;                                       \
+        }                                                               \
+        if (qc) {                                                       \
+            env->vfp.qc[0] = qc;                                        \
+        }                                                               \
+        mve_advance_vpt(env);                                           \
+    }
+
 #define DO_AND(N, M)  ((N) & (M))
 #define DO_BIC(N, M)  ((N) & ~(M))
 #define DO_ORR(N, M)  ((N) | (M))
@@ -551,6 +570,14 @@ static inline int32_t do_sat_bhw(int64_t val, int64_t min, int64_t max, bool *s)
 #define DO_QRDMULH_W(n, m, s) do_sat_bhw(((int64_t)n * m + (1 << 30)) >> 31, \
                                          INT32_MIN, INT32_MAX, s)
 
+DO_2OP_SAT(vqdmulhb, 1, int8_t, DO_QDMULH_B)
+DO_2OP_SAT(vqdmulhh, 2, int16_t, DO_QDMULH_H)
+DO_2OP_SAT(vqdmulhw, 4, int32_t, DO_QDMULH_W)
+
+DO_2OP_SAT(vqrdmulhb, 1, int8_t, DO_QRDMULH_B)
+DO_2OP_SAT(vqrdmulhh, 2, int16_t, DO_QRDMULH_H)
+DO_2OP_SAT(vqrdmulhw, 4, int32_t, DO_QRDMULH_W)
+
 #define DO_2OP_SCALAR(OP, ESIZE, TYPE, FN)                              \
     void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, void *vn,   \
                                 uint32_t rm)                            \
diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c
index f73b36cae49..ec9a9852868 100644
--- a/target/arm/translate-mve.c
+++ b/target/arm/translate-mve.c
@@ -396,6 +396,8 @@ DO_2OP(VMULL_BS, vmullbs)
 DO_2OP(VMULL_BU, vmullbu)
 DO_2OP(VMULL_TS, vmullts)
 DO_2OP(VMULL_TU, vmulltu)
+DO_2OP(VQDMULH, vqdmulh)
+DO_2OP(VQRDMULH, vqrdmulh)
 
 static bool do_2op_scalar(DisasContext *s, arg_2scalar *a,
                           MVEGenTwoOpScalarFn fn)
-- 
2.20.1