[PATCH v2 56/57] target/arm: Implement MVE VADDV

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

Implement the MVE VADDV insn, which performs an addition
across vector lanes.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/helper-mve.h    |  7 +++++++
 target/arm/mve.decode      |  2 ++
 target/arm/mve_helper.c    | 24 +++++++++++++++++++++
 target/arm/translate-mve.c | 43 ++++++++++++++++++++++++++++++++++++++
 4 files changed, 76 insertions(+)

diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
index 161308b67e6..4bbb9b3ae2c 100644
--- a/target/arm/helper-mve.h
+++ b/target/arm/helper-mve.h
@@ -348,3 +348,10 @@ DEF_HELPER_FLAGS_4(mve_vrmlaldavhuw, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64)
 
 DEF_HELPER_FLAGS_4(mve_vrmlsldavhsw, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64)
 DEF_HELPER_FLAGS_4(mve_vrmlsldavhxsw, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64)
+
+DEF_HELPER_FLAGS_3(mve_vaddvsb, TCG_CALL_NO_WG, i32, env, ptr, i32)
+DEF_HELPER_FLAGS_3(mve_vaddvub, TCG_CALL_NO_WG, i32, env, ptr, i32)
+DEF_HELPER_FLAGS_3(mve_vaddvsh, TCG_CALL_NO_WG, i32, env, ptr, i32)
+DEF_HELPER_FLAGS_3(mve_vaddvuh, TCG_CALL_NO_WG, i32, env, ptr, i32)
+DEF_HELPER_FLAGS_3(mve_vaddvsw, TCG_CALL_NO_WG, i32, env, ptr, i32)
+DEF_HELPER_FLAGS_3(mve_vaddvuw, TCG_CALL_NO_WG, i32, env, ptr, i32)
diff --git a/target/arm/mve.decode b/target/arm/mve.decode
index 695097dcca4..d9ece7be5da 100644
--- a/target/arm/mve.decode
+++ b/target/arm/mve.decode
@@ -252,6 +252,8 @@ 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
 
+# 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
 
 # Predicate operations
 %mask_22_13      22:1 13:3
diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c
index e5b8016e377..20931f317ba 100644
--- a/target/arm/mve_helper.c
+++ b/target/arm/mve_helper.c
@@ -1149,3 +1149,27 @@ DO_LDAVH(vrmlaldavhuw, 4, uint32_t, false, int128_add, int128_add, int128_make64
 
 DO_LDAVH(vrmlsldavhsw, 4, int32_t, false, int128_add, int128_sub, int128_makes64)
 DO_LDAVH(vrmlsldavhxsw, 4, int32_t, true, int128_add, int128_sub, int128_makes64)
+
+/* Vector add across vector */
+#define DO_VADDV(OP, ESIZE, TYPE)                               \
+    uint32_t HELPER(glue(mve_, OP))(CPUARMState *env, void *vm, \
+                                    uint32_t ra)                \
+    {                                                           \
+        uint16_t mask = mve_element_mask(env);                  \
+        unsigned e;                                             \
+        TYPE *m = vm;                                           \
+        for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) {      \
+            if (mask & 1) {                                     \
+                ra += m[H##ESIZE(e)];                           \
+            }                                                   \
+        }                                                       \
+        mve_advance_vpt(env);                                   \
+        return ra;                                              \
+    }                                                           \
+
+DO_VADDV(vaddvsb, 1, uint8_t)
+DO_VADDV(vaddvsh, 2, uint16_t)
+DO_VADDV(vaddvsw, 4, uint32_t)
+DO_VADDV(vaddvub, 1, uint8_t)
+DO_VADDV(vaddvuh, 2, uint16_t)
+DO_VADDV(vaddvuw, 4, uint32_t)
diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c
index ca619dad14a..3d54ad1270a 100644
--- a/target/arm/translate-mve.c
+++ b/target/arm/translate-mve.c
@@ -33,6 +33,7 @@ typedef void MVEGenOneOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr);
 typedef void MVEGenTwoOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr);
 typedef void MVEGenTwoOpScalarFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32);
 typedef void MVEGenDualAccOpFn(TCGv_i64, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i64);
+typedef void MVEGenVADDVFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32);
 
 /* Return the offset of a Qn register (same semantics as aa32_vfp_qreg()) */
 static inline long mve_qreg_offset(unsigned reg)
@@ -743,3 +744,45 @@ static bool trans_VPST(DisasContext *s, arg_VPST *a)
     mve_update_and_store_eci(s);
     return true;
 }
+
+static bool trans_VADDV(DisasContext *s, arg_VADDV *a)
+{
+    /* VADDV: vector add across vector */
+    static MVEGenVADDVFn * const fns[4][2] = {
+        { gen_helper_mve_vaddvsb, gen_helper_mve_vaddvub },
+        { gen_helper_mve_vaddvsh, gen_helper_mve_vaddvuh },
+        { gen_helper_mve_vaddvsw, gen_helper_mve_vaddvuw },
+        { NULL, NULL }
+    };
+    TCGv_ptr qm;
+    TCGv_i32 rda;
+
+    if (!dc_isar_feature(aa32_mve, s) ||
+        a->size == 3) {
+        return false;
+    }
+    if (!mve_eci_check(s) || !vfp_access_check(s)) {
+        return true;
+    }
+
+    /*
+     * This insn is subject to beat-wise execution. Partial execution
+     * of an A=0 (no-accumulate) insn which does not execute the first
+     * beat must start with the current value of Rda, not zero.
+     */
+    if (a->a || mve_skip_first_beat(s)) {
+        /* Accumulate input from Rda */
+        rda = load_reg(s, a->rda);
+    } else {
+        /* Accumulate starting at zero */
+        rda = tcg_const_i32(0);
+    }
+
+    qm = mve_qreg_ptr(a->qm);
+    fns[a->size][a->u](rda, cpu_env, qm, rda);
+    store_reg(s, a->rda, rda);
+    tcg_temp_free_ptr(qm);
+
+    mve_update_eci(s);
+    return true;
+}
-- 
2.20.1