target/arm: Convert Neon VDUP (scalar) to decodetree

Convert the Neon VDUP (scalar) insn to decodetree.  (Note that we
can't call this just "VDUP" as we used that already in vfp.decode for
the "VDUP (general purpose register" insn.)

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

diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode
index 91bc770dfbc7564977b9b16abd004c138cebeb60..6d890b2161f5b85d00a8261b5662fb0cec1e068d 100644 (file)
--- a/target/arm/neon-dp.decode
+++ b/target/arm/neon-dp.decode
@@ -422,6 +422,13 @@ Vimm_1r          1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm
 
     VTBL         1111 001 1 1 . 11 .... .... 10 len:2 . op:1 . 0 .... \
                  vm=%vm_dp vn=%vn_dp vd=%vd_dp
+
+    VDUP_scalar  1111 001 1 1 . 11 index:3 1 .... 11 000 q:1 . 0 .... \
+                 vm=%vm_dp vd=%vd_dp size=0
+    VDUP_scalar  1111 001 1 1 . 11 index:2 10 .... 11 000 q:1 . 0 .... \
+                 vm=%vm_dp vd=%vd_dp size=1
+    VDUP_scalar  1111 001 1 1 . 11 index:1 100 .... 11 000 q:1 . 0 .... \
+                 vm=%vm_dp vd=%vd_dp size=2
   ]
 
   # Subgroup for size != 0b11

diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
index da0e5dbc6fd673c433b841b2ee5fd9b46d525425..a5aa56bbdeba1b8b9d3606c633216219e8d10b3e 100644 (file)
--- a/target/arm/translate-neon.inc.c
+++ b/target/arm/translate-neon.inc.c
@@ -2944,3 +2944,29 @@ static bool trans_VTBL(DisasContext *s, arg_VTBL *a)
     tcg_temp_free_i32(tmp);
     return true;
 }
+
+static bool trans_VDUP_scalar(DisasContext *s, arg_VDUP_scalar *a)
+{
+    if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
+        return false;
+    }
+
+    /* UNDEF accesses to D16-D31 if they don't exist. */
+    if (!dc_isar_feature(aa32_simd_r32, s) &&
+        ((a->vd | a->vm) & 0x10)) {
+        return false;
+    }
+
+    if (a->vd & a->q) {
+        return false;
+    }
+
+    if (!vfp_access_check(s)) {
+        return true;
+    }
+
+    tcg_gen_gvec_dup_mem(a->size, neon_reg_offset(a->vd, 0),
+                         neon_element_offset(a->vm, a->index, a->size),
+                         a->q ? 16 : 8, a->q ? 16 : 8);
+    return true;
+}

diff --git a/target/arm/translate.c b/target/arm/translate.c
index 0c6425928f6dd5d6f9620fab46223a3aedc94266..6d18892adee5df55dae32c8389ad39644216bdd7 100644 (file)
--- a/target/arm/translate.c
+++ b/target/arm/translate.c
@@ -5574,31 +5574,8 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
                     }
                     break;
                 }
-            } else if ((insn & (1 << 10)) == 0) {
-                /* VTBL, VTBX: handled by decodetree */
-                return 1;
-            } else if ((insn & 0x380) == 0) {
-                /* VDUP */
-                int element;
-                MemOp size;
-
-                if ((insn & (7 << 16)) == 0 || (q && (rd & 1))) {
-                    return 1;
-                }
-                if (insn & (1 << 16)) {
-                    size = MO_8;
-                    element = (insn >> 17) & 7;
-                } else if (insn & (1 << 17)) {
-                    size = MO_16;
-                    element = (insn >> 18) & 3;
-                } else {
-                    size = MO_32;
-                    element = (insn >> 19) & 1;
-                }
-                tcg_gen_gvec_dup_mem(size, neon_reg_offset(rd, 0),
-                                     neon_element_offset(rm, element, size),
-                                     q ? 16 : 8, q ? 16 : 8);
             } else {
+                /* VTBL, VTBX, VDUP: handled by decodetree */
                 return 1;
             }
         }