target/arm: Optimize MVE logic ops

When not predicating, implement the MVE bitwise logical insns
directly using TCG vector operations.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210913095440.13462-5-peter.maydell@linaro.org

target/arm/translate-mve.c

@@ -64,6 +64,16 @@ static TCGv_ptr mve_qreg_ptr(unsigned reg)
     return ret;
 }
 
+static bool mve_no_predication(DisasContext *s)
+{
+    /*
+     * Return true if we are executing the entire MVE instruction
+     * with no predication or partial-execution, and so we can safely
+     * use an inline TCG vector implementation.
+     */
+    return s->eci == 0 && s->mve_no_pred;
+}
+
 static bool mve_check_qreg_bank(DisasContext *s, int qmask)
 {
     /*
@@ -774,7 +784,8 @@ 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)
+static bool do_2op_vec(DisasContext *s, arg_2op *a, MVEGenTwoOpFn fn,
+                       GVecGen3Fn *vecfn)
 {
     TCGv_ptr qd, qn, qm;
 
@@ -787,28 +798,38 @@ static bool do_2op(DisasContext *s, arg_2op *a, MVEGenTwoOpFn fn)
         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);
+    if (vecfn && mve_no_predication(s)) {
+        vecfn(a->size, mve_qreg_offset(a->qd), mve_qreg_offset(a->qn),
+              mve_qreg_offset(a->qm), 16, 16);
+    } else {
+        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 do_2op(DisasContext *s, arg_2op *a, MVEGenTwoOpFn *fn)
+{
+    return do_2op_vec(s, a, fn, NULL);
+}
+
+#define DO_LOGIC(INSN, HELPER, VECFN)                           \
     static bool trans_##INSN(DisasContext *s, arg_2op *a)       \
     {                                                           \
-        return do_2op(s, a, HELPER);                            \
+        return do_2op_vec(s, a, HELPER, VECFN);                 \
     }
 
-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)
+DO_LOGIC(VAND, gen_helper_mve_vand, tcg_gen_gvec_and)
+DO_LOGIC(VBIC, gen_helper_mve_vbic, tcg_gen_gvec_andc)
+DO_LOGIC(VORR, gen_helper_mve_vorr, tcg_gen_gvec_or)
+DO_LOGIC(VORN, gen_helper_mve_vorn, tcg_gen_gvec_orc)
+DO_LOGIC(VEOR, gen_helper_mve_veor, tcg_gen_gvec_xor)
 
 static bool trans_VPSEL(DisasContext *s, arg_2op *a)
 {