target/arm: Implement EXTQ for SME2p1/SVE2p1

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-90-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

2 files changed, 51 insertions, 0 deletions

diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index 2650e00..af4fb96 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -583,6 +583,8 @@ 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
 
+EXTQ            00000101 0110 imm:4 001001 rn:5 rd:5            &rri
+
 # 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 e33b2eb..a918da3 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -2202,6 +2202,55 @@ static bool do_EXT(DisasContext *s, int rd, int rn, int rm, int imm)
 TRANS_FEAT(EXT, aa64_sve, do_EXT, a->rd, a->rn, a->rm, a->imm)
 TRANS_FEAT(EXT_sve2, aa64_sve2, do_EXT, a->rd, a->rn, (a->rn + 1) % 32, a->imm)
 
+static bool trans_EXTQ(DisasContext *s, arg_EXTQ *a)
+{
+    unsigned vl, dofs, sofs0, sofs1, sofs2, imm;
+
+    if (!dc_isar_feature(aa64_sme2p1_or_sve2p1, s)) {
+        return false;
+    }
+    if (!sve_access_check(s)) {
+        return true;
+    }
+
+    imm = a->imm;
+    if (imm == 0) {
+        /* So far we never optimize Zdn with MOVPRFX, so zd = zn is a nop. */
+        return true;
+    }
+
+    vl = vec_full_reg_size(s);
+    dofs = vec_full_reg_offset(s, a->rd);
+    sofs2 = vec_full_reg_offset(s, a->rn);
+
+    if (imm & 8) {
+        sofs0 = dofs + 8;
+        sofs1 = sofs2;
+        sofs2 += 8;
+    } else {
+        sofs0 = dofs;
+        sofs1 = dofs + 8;
+    }
+    imm = (imm & 7) << 3;
+
+    for (unsigned i = 0; i < vl; i += 16) {
+        TCGv_i64 s0 = tcg_temp_new_i64();
+        TCGv_i64 s1 = tcg_temp_new_i64();
+        TCGv_i64 s2 = tcg_temp_new_i64();
+
+        tcg_gen_ld_i64(s0, tcg_env, sofs0 + i);
+        tcg_gen_ld_i64(s1, tcg_env, sofs1 + i);
+        tcg_gen_ld_i64(s2, tcg_env, sofs2 + i);
+
+        tcg_gen_extract2_i64(s0, s0, s1, imm);
+        tcg_gen_extract2_i64(s1, s1, s2, imm);
+
+        tcg_gen_st_i64(s0, tcg_env, dofs + i);
+        tcg_gen_st_i64(s1, tcg_env, dofs + i + 8);
+    }
+    return true;
+}
+
 /*
  *** SVE Permute - Unpredicated Group
  */