target/arm: Implement MVE VMLAS

Implement the MVE VMLAS insn, which multiplies a vector by a vector
and adds a scalar.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>

target/arm/helper-mve.h

@@ -347,6 +347,10 @@ DEF_HELPER_FLAGS_4(mve_vqdmullb_scalarw, TCG_CALL_NO_WG, void, env, ptr, ptr, i3
 DEF_HELPER_FLAGS_4(mve_vqdmullt_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(mve_vqdmullt_scalarw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
 
+DEF_HELPER_FLAGS_4(mve_vmlasb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vmlash, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(mve_vmlasw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
+
 DEF_HELPER_FLAGS_4(mve_vmlaldavsh, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64)
 DEF_HELPER_FLAGS_4(mve_vmlaldavsw, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64)
 DEF_HELPER_FLAGS_4(mve_vmlaldavxsh, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64)

target/arm/mve.decode

@@ -345,6 +345,9 @@ VBRSR            1111 1110 0 . .. ... 1 ... 1 1110 . 110 .... @2scalar
 VQDMULH_scalar   1110 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar
 VQRDMULH_scalar  1111 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar
 
+# The U bit (28) is don't-care because it does not affect the result
+VMLAS            111- 1110 0 . .. ... 1 ... 1 1110 . 100 .... @2scalar
+
 # Vector add across vector
 {
   VADDV          111 u:1 1110 1111 size:2 01 ... 0 1111 0 0 a:1 0 qm:3 0 rda=%rdalo

target/arm/mve_helper.c

@@ -948,6 +948,22 @@ DO_VQDMLADH_OP(vqrdmlsdhxw, 4, int32_t, 1, 1, do_vqdmlsdh_w)
         mve_advance_vpt(env);                                           \
     }
 
+/* "accumulating" version where FN takes d as well as n and m */
+#define DO_2OP_ACC_SCALAR(OP, ESIZE, TYPE, FN)                          \
+    void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, void *vn,   \
+                                uint32_t rm)                            \
+    {                                                                   \
+        TYPE *d = vd, *n = vn;                                          \
+        TYPE m = rm;                                                    \
+        uint16_t mask = mve_element_mask(env);                          \
+        unsigned e;                                                     \
+        for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) {              \
+            mergemask(&d[H##ESIZE(e)],                                  \
+                      FN(d[H##ESIZE(e)], n[H##ESIZE(e)], m), mask);     \
+        }                                                               \
+        mve_advance_vpt(env);                                           \
+    }
+
 /* provide unsigned 2-op scalar helpers for all sizes */
 #define DO_2OP_SCALAR_U(OP, FN)                 \
     DO_2OP_SCALAR(OP##b, 1, uint8_t, FN)        \
@@ -958,6 +974,11 @@ DO_VQDMLADH_OP(vqrdmlsdhxw, 4, int32_t, 1, 1, do_vqdmlsdh_w)
     DO_2OP_SCALAR(OP##h, 2, int16_t, FN)        \
     DO_2OP_SCALAR(OP##w, 4, int32_t, FN)
 
+#define DO_2OP_ACC_SCALAR_U(OP, FN)             \
+    DO_2OP_ACC_SCALAR(OP##b, 1, uint8_t, FN)    \
+    DO_2OP_ACC_SCALAR(OP##h, 2, uint16_t, FN)   \
+    DO_2OP_ACC_SCALAR(OP##w, 4, uint32_t, FN)
+
 DO_2OP_SCALAR_U(vadd_scalar, DO_ADD)
 DO_2OP_SCALAR_U(vsub_scalar, DO_SUB)
 DO_2OP_SCALAR_U(vmul_scalar, DO_MUL)
@@ -987,6 +1008,11 @@ DO_2OP_SAT_SCALAR(vqrdmulh_scalarb, 1, int8_t, DO_QRDMULH_B)
 DO_2OP_SAT_SCALAR(vqrdmulh_scalarh, 2, int16_t, DO_QRDMULH_H)
 DO_2OP_SAT_SCALAR(vqrdmulh_scalarw, 4, int32_t, DO_QRDMULH_W)
 
+/* Vector by vector plus scalar */
+#define DO_VMLAS(D, N, M) ((N) * (D) + (M))
+
+DO_2OP_ACC_SCALAR_U(vmlas, DO_VMLAS)
+
 /*
  * Long saturating scalar ops. As with DO_2OP_L, TYPE and H are for the
  * input (smaller) type and LESIZE, LTYPE, LH for the output (long) type.

target/arm/translate-mve.c

@@ -596,6 +596,7 @@ DO_2OP_SCALAR(VQSUB_U_scalar, vqsubu_scalar)
 DO_2OP_SCALAR(VQDMULH_scalar, vqdmulh_scalar)
 DO_2OP_SCALAR(VQRDMULH_scalar, vqrdmulh_scalar)
 DO_2OP_SCALAR(VBRSR, vbrsr)
+DO_2OP_SCALAR(VMLAS, vmlas)
 
 static bool trans_VQDMULLB_scalar(DisasContext *s, arg_2scalar *a)
 {