target/arm: Implement CNTP (predicate as counter) for SME2/SVE2p1

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-88-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

4 files changed, 54 insertions, 1 deletions

diff --git a/target/arm/tcg/helper-sve.h b/target/arm/tcg/helper-sve.h
index 906da38..733828a 100644
--- a/target/arm/tcg/helper-sve.h
+++ b/target/arm/tcg/helper-sve.h
@@ -937,6 +937,7 @@ DEF_HELPER_FLAGS_4(sve_brkn, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_4(sve_brkns, TCG_CALL_NO_RWG, i32, ptr, ptr, ptr, i32)
 
 DEF_HELPER_FLAGS_3(sve_cntp, TCG_CALL_NO_RWG, i64, ptr, ptr, i32)
+DEF_HELPER_FLAGS_2(sve2p1_cntp_c, TCG_CALL_NO_RWG_SE, i64, i32, i32)
 
 DEF_HELPER_FLAGS_3(sve_whilel, TCG_CALL_NO_RWG, i32, ptr, i32, i32)
 DEF_HELPER_FLAGS_3(sve_whileg, TCG_CALL_NO_RWG, i32, ptr, i32, i32)
diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index 0df3312..db16849 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -784,7 +784,8 @@ BRKN            00100101 0. 01100001 .... 0 .... 0 ....         @pd_pg_pn_s
 ### SVE Predicate Count Group
 
 # SVE predicate count
-CNTP            00100101 .. 100 000 10 .... 0 .... .....        @rd_pg4_pn
+CNTP            00100101 ..    100 000 10 ....     0 .... ..... @rd_pg4_pn
+CNTP_c          00100101 esz:2 100 000 10 000 vl:1 1 rn:4 rd:5
 
 # SVE inc/dec register by predicate count
 INCDECP_r       00100101 .. 10110 d:1 10001 00 .... .....     @incdec_pred u=1
diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index 6512df5..def841f 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -4178,6 +4178,27 @@ uint64_t HELPER(sve_cntp)(void *vn, void *vg, uint32_t pred_desc)
     return sum;
 }
 
+uint64_t HELPER(sve2p1_cntp_c)(uint32_t png, uint32_t desc)
+{
+    int pl = FIELD_EX32(desc, PREDDESC, OPRSZ);
+    int vl = pl * 8;
+    unsigned v_esz = FIELD_EX32(desc, PREDDESC, ESZ);
+    int lg2_width = FIELD_EX32(desc, PREDDESC, DATA) + 1;
+    DecodeCounter p = decode_counter(png, vl, v_esz);
+    unsigned maxelem = (vl << lg2_width) >> v_esz;
+    unsigned count = p.count;
+
+    if (p.invert) {
+        if (count >= maxelem) {
+            return 0;
+        }
+        count = maxelem - count;
+    } else {
+        count = MIN(count, maxelem);
+    }
+    return count >> p.lg2_stride;
+}
+
 /* C.f. Arm pseudocode EncodePredCount */
 static uint64_t encode_pred_count(uint32_t elements, uint32_t count,
                                   uint32_t esz, bool invert)
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index 079d310..53db885 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -3052,6 +3052,36 @@ static bool trans_CNTP(DisasContext *s, arg_CNTP *a)
     return true;
 }
 
+static bool trans_CNTP_c(DisasContext *s, arg_CNTP_c *a)
+{
+    TCGv_i32 t_png;
+    uint32_t desc = 0;
+
+    if (dc_isar_feature(aa64_sve2p1, s)) {
+        if (!sve_access_check(s)) {
+            return true;
+        }
+    } else if (dc_isar_feature(aa64_sme2, s)) {
+        if (!sme_sm_enabled_check(s)) {
+            return true;
+        }
+    } else {
+        return false;
+    }
+
+    t_png = tcg_temp_new_i32();
+    tcg_gen_ld16u_i32(t_png, tcg_env,
+                      pred_full_reg_offset(s, a->rn) ^
+                      (HOST_BIG_ENDIAN ? 6 : 0));
+
+    desc = FIELD_DP32(desc, PREDDESC, OPRSZ, pred_full_reg_size(s));
+    desc = FIELD_DP32(desc, PREDDESC, ESZ, a->esz);
+    desc = FIELD_DP32(desc, PREDDESC, DATA, a->vl);
+
+    gen_helper_sve2p1_cntp_c(cpu_reg(s, a->rd), t_png, tcg_constant_i32(desc));
+    return true;
+}
+
 static bool trans_INCDECP_r(DisasContext *s, arg_incdec_pred *a)
 {
     if (!dc_isar_feature(aa64_sve, s)) {