diff mbox series

[v2,069/101] target/arm: Implement SME2p1 Multiple Zero

Message ID 20250621235037.74091-70-richard.henderson@linaro.org
State New
Headers show
Series target/arm: Implement FEAT_SME2p1 | expand

Commit Message

Richard Henderson June 21, 2025, 11:50 p.m. UTC 
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/tcg/translate-sme.c | 20 ++++++++++++++++++++
 target/arm/tcg/sme.decode      | 23 +++++++++++++++++++++++
 2 files changed, 43 insertions(+)
diff mbox series

Patch

diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c
index 186d46ecbf..4d82666d84 100644
--- a/target/arm/tcg/translate-sme.c
+++ b/target/arm/tcg/translate-sme.c
@@ -158,6 +158,26 @@  static bool trans_ZERO_zt0(DisasContext *s, arg_ZERO_zt0 *a)
     return true;
 }
 
+static bool trans_ZERO_za(DisasContext *s, arg_ZERO_za *a)
+{
+    if (!dc_isar_feature(aa64_sme2p1, s)) {
+        return false;
+    }
+    if (sme_sm_enabled_check(s)) {
+        int svl = streaming_vec_reg_size(s);
+        int vstride = svl / a->ngrp;
+        TCGv_ptr t_za = get_zarray(s, a->rv, a->off, a->ngrp);
+
+        for (int r = 0; r < a->ngrp; ++r) {
+            for (int i = 0; i < a->nvec; ++i) {
+                int o_za = (r * vstride + i) * sizeof(ARMVectorReg);
+                tcg_gen_gvec_dup_imm_var(MO_64, t_za, o_za, svl, svl, 0);
+            }
+        }
+    }
+    return true;
+}
+
 static bool do_mova_tile(DisasContext *s, arg_mova_p *a, bool to_vec)
 {
     static gen_helper_gvec_4 * const h_fns[5] = {
diff --git a/target/arm/tcg/sme.decode b/target/arm/tcg/sme.decode
index 80fe02190c..d0dce75a0d 100644
--- a/target/arm/tcg/sme.decode
+++ b/target/arm/tcg/sme.decode
@@ -885,3 +885,26 @@  SEL             11000001 esz:2 1 ....0 100 ... ....0 ....0  \
                 n=2 zd=%zd_ax2 zn=%zn_ax2 zm=%zm_ax2 pg=%sel_pg
 SEL             11000001 esz:2 1 ...01 100 ... ...00 ...00  \
                 n=4 zd=%zd_ax4 zn=%zn_ax4 zm=%zm_ax4 pg=%sel_pg
+
+### SME Multiple Zero
+
+&zero_za        rv off ngrp nvec
+
+ZERO_za         11000000 000011 000 .. 0000000000 off:3 \
+                &zero_za ngrp=2 nvec=1 rv=%mova_rv
+ZERO_za         11000000 000011 100 .. 0000000000 off:3 \
+                &zero_za ngrp=4 nvec=1 rv=%mova_rv
+
+ZERO_za         11000000 000011 001 .. 0000000000 ...   \
+                &zero_za ngrp=1 nvec=2 rv=%mova_rv off=%off3_x2
+ZERO_za         11000000 000011 010 .. 0000000000 0..   \
+                &zero_za ngrp=2 nvec=2 rv=%mova_rv off=%off2_x2
+ZERO_za         11000000 000011 011 .. 0000000000 0..   \
+                &zero_za ngrp=4 nvec=2 rv=%mova_rv off=%off2_x2
+
+ZERO_za         11000000 000011 101 .. 0000000000 0..   \
+                &zero_za ngrp=1 nvec=4 rv=%mova_rv off=%off2_x4
+ZERO_za         11000000 000011 110 .. 0000000000 00.   \
+                &zero_za ngrp=2 nvec=4 rv=%mova_rv off=%off1_x4
+ZERO_za         11000000 000011 111 .. 0000000000 00.   \
+                &zero_za ngrp=4 nvec=4 rv=%mova_rv off=%off1_x4