target/arm: Implement SME2 ADD/SUB (array results, multiple vectors)

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-34-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index 8b81c0a0cedfdc2459e0065c94b4edae8619b4a6..a6dee08661e7d1e4c7bf1334d51dc6734761ad10 100644 (file)
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -260,3 +260,23 @@ SUB_azz_n1_s    11000001 0010 .... 0 .. 110 ..... 11 ...    @azz_nx1_o3 n=2
 SUB_azz_n1_s    11000001 0011 .... 0 .. 110 ..... 11 ...    @azz_nx1_o3 n=4
 SUB_azz_n1_d    11000001 0110 .... 0 .. 110 ..... 11 ...    @azz_nx1_o3 n=2
 SUB_azz_n1_d    11000001 0111 .... 0 .. 110 ..... 11 ...    @azz_nx1_o3 n=4
+
+### SME2 Multi-vector Multiple Array Vectors
+
+%zn_ax2         6:4 !function=times_2
+%zn_ax4         7:3 !function=times_4
+
+@azz_2x2_o3     ........ ... ..... . .. ... ..... .. off:3  \
+                &azz_n n=2 rv=%mova_rv zn=%zn_ax2 zm=%zm_ax2
+@azz_4x4_o3     ........ ... ..... . .. ... ..... .. off:3  \
+                &azz_n n=4 rv=%mova_rv zn=%zn_ax4 zm=%zm_ax4
+
+ADD_azz_nn_s    11000001 101 ....0 0 .. 110 ....0 10 ...    @azz_2x2_o3
+ADD_azz_nn_s    11000001 101 ...01 0 .. 110 ...00 10 ...    @azz_4x4_o3
+ADD_azz_nn_d    11000001 111 ....0 0 .. 110 ....0 10 ...    @azz_2x2_o3
+ADD_azz_nn_d    11000001 111 ...01 0 .. 110 ...00 10 ...    @azz_4x4_o3
+
+SUB_azz_nn_s    11000001 101 ....0 0 .. 110 ....0 11 ...    @azz_2x2_o3
+SUB_azz_nn_s    11000001 101 ...01 0 .. 110 ...00 11 ...    @azz_4x4_o3
+SUB_azz_nn_d    11000001 111 ....0 0 .. 110 ....0 11 ...    @azz_2x2_o3
+SUB_azz_nn_d    11000001 111 ...01 0 .. 110 ...00 11 ...    @azz_4x4_o3

diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index 4bb880d9ef8b7ed3dd715a4f424261fa82bc3fcc..aabdb96675114db086022685011328df85dad5e8 100644 (file)
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -775,3 +775,33 @@ TRANS_FEAT(ADD_azz_n1_s, aa64_sme2, do_azz_n1, a, MO_32, tcg_gen_gvec_add_var)
 TRANS_FEAT(SUB_azz_n1_s, aa64_sme2, do_azz_n1, a, MO_32, tcg_gen_gvec_sub_var)
 TRANS_FEAT(ADD_azz_n1_d, aa64_sme2_i16i64, do_azz_n1, a, MO_64, tcg_gen_gvec_add_var)
 TRANS_FEAT(SUB_azz_n1_d, aa64_sme2_i16i64, do_azz_n1, a, MO_64, tcg_gen_gvec_sub_var)
+
+/* Add/Sub each vector Z[m*N] to each Z[n*N] with result in ZA[d*N]. */
+static bool do_azz_nn(DisasContext *s, arg_azz_n *a, int esz,
+                      GVecGen3FnVar *fn)
+{
+    TCGv_ptr t_za;
+    int svl, n;
+
+    if (!sme_smza_enabled_check(s)) {
+        return true;
+    }
+
+    n = a->n;
+    t_za = get_zarray(s, a->rv, a->off, n, 1);
+    svl = streaming_vec_reg_size(s);
+
+    for (int i = 0; i < n; ++i) {
+        int o_za = (svl / n * sizeof(ARMVectorReg)) * i;
+        int o_zn = vec_full_reg_offset(s, a->zn + i);
+        int o_zm = vec_full_reg_offset(s, a->zm + i);
+
+        fn(esz, t_za, o_za, tcg_env, o_zn, tcg_env, o_zm, svl, svl);
+    }
+    return true;
+}
+
+TRANS_FEAT(ADD_azz_nn_s, aa64_sme2, do_azz_nn, a, MO_32, tcg_gen_gvec_add_var)
+TRANS_FEAT(SUB_azz_nn_s, aa64_sme2, do_azz_nn, a, MO_32, tcg_gen_gvec_sub_var)
+TRANS_FEAT(ADD_azz_nn_d, aa64_sme2_i16i64, do_azz_nn, a, MO_64, tcg_gen_gvec_add_var)
+TRANS_FEAT(SUB_azz_nn_d, aa64_sme2_i16i64, do_azz_nn, a, MO_64, tcg_gen_gvec_sub_var)