[PULL 31/44] target/arm: Implement MVE VPNOT

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

Implement the MVE VPNOT insn, which inverts the bits in VPR.P0
(subject to both predication and to beatwise execution).

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/helper-mve.h    |  1 +
 target/arm/mve.decode      |  1 +
 target/arm/mve_helper.c    | 17 +++++++++++++++++
 target/arm/translate-mve.c | 19 +++++++++++++++++++
 4 files changed, 38 insertions(+)

diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
index 651020aaad8..8cb941912fc 100644
--- a/target/arm/helper-mve.h
+++ b/target/arm/helper-mve.h
@@ -119,6 +119,7 @@ DEF_HELPER_FLAGS_4(mve_vorn, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
 DEF_HELPER_FLAGS_4(mve_veor, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
 
 DEF_HELPER_FLAGS_4(mve_vpsel, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_1(mve_vpnot, TCG_CALL_NO_WG, void, env)
 
 DEF_HELPER_FLAGS_4(mve_vaddb, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
 DEF_HELPER_FLAGS_4(mve_vaddh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
diff --git a/target/arm/mve.decode b/target/arm/mve.decode
index 774ee2a1a5b..40bd0c04b59 100644
--- a/target/arm/mve.decode
+++ b/target/arm/mve.decode
@@ -571,6 +571,7 @@ VCMPGT            1111 1110 0 . .. ... 1 ... 1 1111 0 0 . 0 ... 1 @vcmp
 VCMPLE            1111 1110 0 . .. ... 1 ... 1 1111 1 0 . 0 ... 1 @vcmp
 
 {
+  VPNOT           1111 1110 0 0 11 000 1 000 0 1111 0100 1101
   VPST            1111 1110 0 . 11 000 1 ... 0 1111 0100 1101 mask=%mask_22_13
   VCMPEQ_scalar   1111 1110 0 . .. ... 1 ... 0 1111 0 1 0 0 .... @vcmp_scalar
 }
diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c
index d326205cbf0..c22a00c5ed6 100644
--- a/target/arm/mve_helper.c
+++ b/target/arm/mve_helper.c
@@ -2201,6 +2201,23 @@ void HELPER(mve_vpsel)(CPUARMState *env, void *vd, void *vn, void *vm)
     mve_advance_vpt(env);
 }
 
+void HELPER(mve_vpnot)(CPUARMState *env)
+{
+    /*
+     * P0 bits for unexecuted beats (where eci_mask is 0) are unchanged.
+     * P0 bits for predicated lanes in executed bits (where mask is 0) are 0.
+     * P0 bits otherwise are inverted.
+     * (This is the same logic as VCMP.)
+     * This insn is itself subject to predication and to beat-wise execution,
+     * and after it executes VPT state advances in the usual way.
+     */
+    uint16_t mask = mve_element_mask(env);
+    uint16_t eci_mask = mve_eci_mask(env);
+    uint16_t beatpred = ~env->v7m.vpr & mask;
+    env->v7m.vpr = (env->v7m.vpr & ~(uint32_t)eci_mask) | (beatpred & eci_mask);
+    mve_advance_vpt(env);
+}
+
 #define DO_1OP_SAT(OP, ESIZE, TYPE, FN)                                 \
     void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm)         \
     {                                                                   \
diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c
index 93707fdd681..cc2e58cfe2f 100644
--- a/target/arm/translate-mve.c
+++ b/target/arm/translate-mve.c
@@ -887,6 +887,25 @@ static bool trans_VPST(DisasContext *s, arg_VPST *a)
     return true;
 }
 
+static bool trans_VPNOT(DisasContext *s, arg_VPNOT *a)
+{
+    /*
+     * Invert the predicate in VPR.P0. We have call out to
+     * a helper because this insn itself is beatwise and can
+     * be predicated.
+     */
+    if (!dc_isar_feature(aa32_mve, s)) {
+        return false;
+    }
+    if (!mve_eci_check(s) || !vfp_access_check(s)) {
+        return true;
+    }
+
+    gen_helper_mve_vpnot(cpu_env);
+    mve_update_eci(s);
+    return true;
+}
+
 static bool trans_VADDV(DisasContext *s, arg_VADDV *a)
 {
     /* VADDV: vector add across vector */
-- 
2.20.1