target/arm: Implement DUPQ for SME2p1/SVE2p1

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-89-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index db16849731d86d46336795a7a0095d17683e7a00..2650e00f80b6eacec96b357f0f01067e43bc25b9 100644 (file)
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -577,6 +577,12 @@ DUP_s           00000101 .. 1 00000 001110 ..... .....          @rd_rn
 DUP_x           00000101 .. 1 ..... 001000 rn:5 rd:5 \
                 &rri imm=%imm7_22_16
 
+# SVE Permute Vector - one source quadwords
+DUPQ            00000101 001 imm:4    1 001001 rn:5 rd:5        &rri_esz esz=0
+DUPQ            00000101 001 imm:3   10 001001 rn:5 rd:5        &rri_esz esz=1
+DUPQ            00000101 001 imm:2  100 001001 rn:5 rd:5        &rri_esz esz=2
+DUPQ            00000101 001 imm:1 1000 001001 rn:5 rd:5        &rri_esz esz=3
+
 # SVE insert SIMD&FP scalar register
 INSR_f          00000101 .. 1 10100 001110 ..... .....          @rdn_rm
 

diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index 53db8851bf4c7428578c2e045775735838e4d542..e33b2eb2a4ea118dab3348bfec8466523469ea7f 100644 (file)
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -2249,6 +2249,27 @@ static bool trans_DUP_x(DisasContext *s, arg_DUP_x *a)
     return true;
 }
 
+static bool trans_DUPQ(DisasContext *s, arg_DUPQ *a)
+{
+    unsigned vl, dofs, nofs;
+
+    if (!dc_isar_feature(aa64_sme2p1_or_sve2p1, s)) {
+        return false;
+    }
+    if (!sve_access_check(s)) {
+        return true;
+    }
+
+    vl = vec_full_reg_size(s);
+    dofs = vec_full_reg_offset(s, a->rd);
+    nofs = vec_reg_offset(s, a->rn, a->imm, a->esz);
+
+    for (unsigned i = 0; i < vl; i += 16) {
+        tcg_gen_gvec_dup_mem(a->esz, dofs + i, nofs + i, 16, 16);
+    }
+    return true;
+}
+
 static void do_insr_i64(DisasContext *s, arg_rrr_esz *a, TCGv_i64 val)
 {
     typedef void gen_insr(TCGv_ptr, TCGv_ptr, TCGv_i64, TCGv_i32);