target/arm: Convert Neon narrowing moves to decodetree

Convert the Neon narrowing moves VMQNV, VQMOVN, VQMOVUN in the 2-reg-misc
group to decodetree.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20200616170844.13318-5-peter.maydell@linaro.org

3 files changed, 70 insertions, 79 deletions

diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode
index ad9e17fd73..2277b4c7b5 100644
--- a/target/arm/neon-dp.decode
+++ b/target/arm/neon-dp.decode
@@ -439,6 +439,8 @@ Vimm_1r          1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm
 
     @2misc       .... ... .. . .. size:2 .. .... . .... q:1 . . .... \
                  &2misc vm=%vm_dp vd=%vd_dp
+    @2misc_q0    .... ... .. . .. size:2 .. .... . .... . . . .... \
+                 &2misc vm=%vm_dp vd=%vd_dp q=0
 
     VREV64       1111 001 11 . 11 .. 00 .... 0 0000 . . 0 .... @2misc
 
@@ -450,6 +452,13 @@ Vimm_1r          1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm
 
     VUZP         1111 001 11 . 11 .. 10 .... 0 0010 . . 0 .... @2misc
     VZIP         1111 001 11 . 11 .. 10 .... 0 0011 . . 0 .... @2misc
+
+    VMOVN        1111 001 11 . 11 .. 10 .... 0 0100 0 . 0 .... @2misc_q0
+    # VQMOVUN: unsigned result (source is always signed)
+    VQMOVUN      1111 001 11 . 11 .. 10 .... 0 0100 1 . 0 .... @2misc_q0
+    # VQMOVN: signed result, source may be signed (_S) or unsigned (_U)
+    VQMOVN_S     1111 001 11 . 11 .. 10 .... 0 0101 0 . 0 .... @2misc_q0
+    VQMOVN_U     1111 001 11 . 11 .. 10 .... 0 0101 1 . 0 .... @2misc_q0
   ]
 
   # Subgroup for size != 0b11
diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
index f4799dd977..b062097285 100644
--- a/target/arm/translate-neon.inc.c
+++ b/target/arm/translate-neon.inc.c
@@ -3243,3 +3243,62 @@ static bool trans_VZIP(DisasContext *s, arg_2misc *a)
     };
     return do_zip_uzp(s, a, fn[a->q][a->size]);
 }
+
+static bool do_vmovn(DisasContext *s, arg_2misc *a,
+                     NeonGenNarrowEnvFn *narrowfn)
+{
+    TCGv_i64 rm;
+    TCGv_i32 rd0, rd1;
+
+    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->vm & 1) {
+        return false;
+    }
+
+    if (!narrowfn) {
+        return false;
+    }
+
+    if (!vfp_access_check(s)) {
+        return true;
+    }
+
+    rm = tcg_temp_new_i64();
+    rd0 = tcg_temp_new_i32();
+    rd1 = tcg_temp_new_i32();
+
+    neon_load_reg64(rm, a->vm);
+    narrowfn(rd0, cpu_env, rm);
+    neon_load_reg64(rm, a->vm + 1);
+    narrowfn(rd1, cpu_env, rm);
+    neon_store_reg(a->vd, 0, rd0);
+    neon_store_reg(a->vd, 1, rd1);
+    tcg_temp_free_i64(rm);
+    return true;
+}
+
+#define DO_VMOVN(INSN, FUNC)                                    \
+    static bool trans_##INSN(DisasContext *s, arg_2misc *a)     \
+    {                                                           \
+        static NeonGenNarrowEnvFn * const narrowfn[] = {        \
+            FUNC##8,                                            \
+            FUNC##16,                                           \
+            FUNC##32,                                           \
+            NULL,                                               \
+        };                                                      \
+        return do_vmovn(s, a, narrowfn[a->size]);               \
+    }
+
+DO_VMOVN(VMOVN, gen_neon_narrow_u)
+DO_VMOVN(VQMOVUN, gen_helper_neon_unarrow_sat)
+DO_VMOVN(VQMOVN_S, gen_helper_neon_narrow_sat_s)
+DO_VMOVN(VQMOVN_U, gen_helper_neon_narrow_sat_u)
diff --git a/target/arm/translate.c b/target/arm/translate.c
index 442f287d86..8ecae264e1 100644
--- a/target/arm/translate.c
+++ b/target/arm/translate.c
@@ -2975,46 +2975,6 @@ static void gen_neon_trn_u16(TCGv_i32 t0, TCGv_i32 t1)
     tcg_temp_free_i32(rd);
 }
 
-static inline void gen_neon_narrow(int size, TCGv_i32 dest, TCGv_i64 src)
-{
-    switch (size) {
-    case 0: gen_helper_neon_narrow_u8(dest, src); break;
-    case 1: gen_helper_neon_narrow_u16(dest, src); break;
-    case 2: tcg_gen_extrl_i64_i32(dest, src); break;
-    default: abort();
-    }
-}
-
-static inline void gen_neon_narrow_sats(int size, TCGv_i32 dest, TCGv_i64 src)
-{
-    switch (size) {
-    case 0: gen_helper_neon_narrow_sat_s8(dest, cpu_env, src); break;
-    case 1: gen_helper_neon_narrow_sat_s16(dest, cpu_env, src); break;
-    case 2: gen_helper_neon_narrow_sat_s32(dest, cpu_env, src); break;
-    default: abort();
-    }
-}
-
-static inline void gen_neon_narrow_satu(int size, TCGv_i32 dest, TCGv_i64 src)
-{
-    switch (size) {
-    case 0: gen_helper_neon_narrow_sat_u8(dest, cpu_env, src); break;
-    case 1: gen_helper_neon_narrow_sat_u16(dest, cpu_env, src); break;
-    case 2: gen_helper_neon_narrow_sat_u32(dest, cpu_env, src); break;
-    default: abort();
-    }
-}
-
-static inline void gen_neon_unarrow_sats(int size, TCGv_i32 dest, TCGv_i64 src)
-{
-    switch (size) {
-    case 0: gen_helper_neon_unarrow_sat8(dest, cpu_env, src); break;
-    case 1: gen_helper_neon_unarrow_sat16(dest, cpu_env, src); break;
-    case 2: gen_helper_neon_unarrow_sat32(dest, cpu_env, src); break;
-    default: abort();
-    }
-}
-
 static inline void gen_neon_widen(TCGv_i64 dest, TCGv_i32 src, int size, int u)
 {
     if (u) {
@@ -3035,24 +2995,6 @@ static inline void gen_neon_widen(TCGv_i64 dest, TCGv_i32 src, int size, int u)
     tcg_temp_free_i32(src);
 }
 
-static void gen_neon_narrow_op(int op, int u, int size,
-                               TCGv_i32 dest, TCGv_i64 src)
-{
-    if (op) {
-        if (u) {
-            gen_neon_unarrow_sats(size, dest, src);
-        } else {
-            gen_neon_narrow(size, dest, src);
-        }
-    } else {
-        if (u) {
-            gen_neon_narrow_satu(size, dest, src);
-        } else {
-            gen_neon_narrow_sats(size, dest, src);
-        }
-    }
-}
-
 /* Symbolic constants for op fields for Neon 2-register miscellaneous.
  * The values correspond to bits [17:16,10:7]; see the ARM ARM DDI0406B
  * table A7-13.
@@ -4994,8 +4936,7 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
                     !arm_dc_feature(s, ARM_FEATURE_V8)) {
                     return 1;
                 }
-                if ((op != NEON_2RM_VMOVN && op != NEON_2RM_VQMOVN) &&
-                    q && ((rm | rd) & 1)) {
+                if (q && ((rm | rd) & 1)) {
                     return 1;
                 }
                 switch (op) {
@@ -5004,6 +4945,7 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
                 case NEON_2RM_VPADAL: case NEON_2RM_VPADAL_U:
                 case NEON_2RM_VUZP:
                 case NEON_2RM_VZIP:
+                case NEON_2RM_VMOVN: case NEON_2RM_VQMOVN:
                     /* handled by decodetree */
                     return 1;
                 case NEON_2RM_VTRN:
@@ -5019,25 +4961,6 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
                         goto elementwise;
                     }
                     break;
-                case NEON_2RM_VMOVN: case NEON_2RM_VQMOVN:
-                    /* also VQMOVUN; op field and mnemonics don't line up */
-                    if (rm & 1) {
-                        return 1;
-                    }
-                    tmp2 = NULL;
-                    for (pass = 0; pass < 2; pass++) {
-                        neon_load_reg64(cpu_V0, rm + pass);
-                        tmp = tcg_temp_new_i32();
-                        gen_neon_narrow_op(op == NEON_2RM_VMOVN, q, size,
-                                           tmp, cpu_V0);
-                        if (pass == 0) {
-                            tmp2 = tmp;
-                        } else {
-                            neon_store_reg(rd, 0, tmp2);
-                            neon_store_reg(rd, 1, tmp);
-                        }
-                    }
-                    break;
                 case NEON_2RM_VSHLL:
                     if (q || (rd & 1)) {
                         return 1;