[PULL 22/57] target/arm: Implement MVE VAND, VBIC, VORR, VORN, VEOR

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

Implement the MVE vector logical operations operating
on two registers.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210617121628.20116-12-peter.maydell@linaro.org
---
 target/arm/helper-mve.h    |  6 ++++++
 target/arm/mve.decode      |  9 +++++++++
 target/arm/mve_helper.c    | 26 ++++++++++++++++++++++++++
 target/arm/translate-mve.c | 37 +++++++++++++++++++++++++++++++++++++
 4 files changed, 78 insertions(+)

diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
index 64c3f9e049e..01b6123f250 100644
--- a/target/arm/helper-mve.h
+++ b/target/arm/helper-mve.h
@@ -63,3 +63,9 @@ DEF_HELPER_FLAGS_3(mve_vnegh, TCG_CALL_NO_WG, void, env, ptr, ptr)
 DEF_HELPER_FLAGS_3(mve_vnegw, TCG_CALL_NO_WG, void, env, ptr, ptr)
 DEF_HELPER_FLAGS_3(mve_vfnegh, TCG_CALL_NO_WG, void, env, ptr, ptr)
 DEF_HELPER_FLAGS_3(mve_vfnegs, TCG_CALL_NO_WG, void, env, ptr, ptr)
+
+DEF_HELPER_FLAGS_4(mve_vand, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vbic, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+DEF_HELPER_FLAGS_4(mve_vorr, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr)
+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)
diff --git a/target/arm/mve.decode b/target/arm/mve.decode
index 09849917f5a..332e0b8d1d6 100644
--- a/target/arm/mve.decode
+++ b/target/arm/mve.decode
@@ -25,6 +25,7 @@
 
 &vldr_vstr rn qd imm p a w size l u
 &1op qd qm size
+&2op qd qm qn size
 
 @vldr_vstr ....... . . . . l:1 rn:4 ... ...... imm:7 &vldr_vstr qd=%qd u=0
 # Note that both Rn and Qd are 3 bits only (no D bit)
@@ -32,6 +33,7 @@
 
 @1op .... .... .... size:2 .. .... .... .... .... &1op qd=%qd qm=%qm
 @1op_nosz .... .... .... .... .... .... .... .... &1op qd=%qd qm=%qm size=0
+@2op_nosz .... .... .... .... .... .... .... .... &2op qd=%qd qm=%qm qn=%qn size=0
 
 # Vector loads and stores
 
@@ -68,6 +70,13 @@ VLDR_VSTR        1110110 1 a:1 . w:1 . .... ... 111101 .......   @vldr_vstr \
 VLDR_VSTR        1110110 1 a:1 . w:1 . .... ... 111110 .......   @vldr_vstr \
                  size=2 p=1
 
+# Vector 2-op
+VAND             1110 1111 0 . 00 ... 0 ... 0 0001 . 1 . 1 ... 0 @2op_nosz
+VBIC             1110 1111 0 . 01 ... 0 ... 0 0001 . 1 . 1 ... 0 @2op_nosz
+VORR             1110 1111 0 . 10 ... 0 ... 0 0001 . 1 . 1 ... 0 @2op_nosz
+VORN             1110 1111 0 . 11 ... 0 ... 0 0001 . 1 . 1 ... 0 @2op_nosz
+VEOR             1111 1111 0 . 00 ... 0 ... 0 0001 . 1 . 1 ... 0 @2op_nosz
+
 # 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 e17ffdccac5..da62b0e012b 100644
--- a/target/arm/mve_helper.c
+++ b/target/arm/mve_helper.c
@@ -322,3 +322,29 @@ DO_1OP(vnegw, 4, int32_t, DO_NEG)
 /* We can do these 64 bits at a time */
 DO_1OP(vfnegh, 8, uint64_t, DO_FNEGH)
 DO_1OP(vfnegs, 8, uint64_t, DO_FNEGS)
+
+#define DO_2OP(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;                                                     \
+        for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) {              \
+            mergemask(&d[H##ESIZE(e)],                                  \
+                      FN(n[H##ESIZE(e)], m[H##ESIZE(e)]), mask);        \
+        }                                                               \
+        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))
+#define DO_ORN(N, M)  ((N) | ~(M))
+#define DO_EOR(N, M)  ((N) ^ (M))
+
+DO_2OP(vand, 8, uint64_t, DO_AND)
+DO_2OP(vbic, 8, uint64_t, DO_BIC)
+DO_2OP(vorr, 8, uint64_t, DO_ORR)
+DO_2OP(vorn, 8, uint64_t, DO_ORN)
+DO_2OP(veor, 8, uint64_t, DO_EOR)
diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c
index 3714be7f8d1..2546567774c 100644
--- a/target/arm/translate-mve.c
+++ b/target/arm/translate-mve.c
@@ -30,6 +30,7 @@
 
 typedef void MVEGenLdStFn(TCGv_ptr, TCGv_ptr, TCGv_i32);
 typedef void MVEGenOneOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr);
+typedef void MVEGenTwoOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr);
 
 /* Return the offset of a Qn register (same semantics as aa32_vfp_qreg()) */
 static inline long mve_qreg_offset(unsigned reg)
@@ -294,3 +295,39 @@ static bool trans_VNEG_fp(DisasContext *s, arg_1op *a)
     }
     return do_1op(s, a, fns[a->size]);
 }
+
+static bool do_2op(DisasContext *s, arg_2op *a, MVEGenTwoOpFn fn)
+{
+    TCGv_ptr qd, qn, qm;
+
+    if (!dc_isar_feature(aa32_mve, s) ||
+        !mve_check_qreg_bank(s, a->qd | a->qn | a->qm) ||
+        !fn) {
+        return false;
+    }
+    if (!mve_eci_check(s) || !vfp_access_check(s)) {
+        return true;
+    }
+
+    qd = mve_qreg_ptr(a->qd);
+    qn = mve_qreg_ptr(a->qn);
+    qm = mve_qreg_ptr(a->qm);
+    fn(cpu_env, qd, qn, qm);
+    tcg_temp_free_ptr(qd);
+    tcg_temp_free_ptr(qn);
+    tcg_temp_free_ptr(qm);
+    mve_update_eci(s);
+    return true;
+}
+
+#define DO_LOGIC(INSN, HELPER)                                  \
+    static bool trans_##INSN(DisasContext *s, arg_2op *a)       \
+    {                                                           \
+        return do_2op(s, a, HELPER);                            \
+    }
+
+DO_LOGIC(VAND, gen_helper_mve_vand)
+DO_LOGIC(VBIC, gen_helper_mve_vbic)
+DO_LOGIC(VORR, gen_helper_mve_vorr)
+DO_LOGIC(VORN, gen_helper_mve_vorn)
+DO_LOGIC(VEOR, gen_helper_mve_veor)
-- 
2.20.1