target/arm: Implement VFP fp16 VLDR and VSTR

Implement the fp16 versions of the VFP VLDR/VSTR (immediate).

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20200828183354.27913-12-peter.maydell@linaro.org

diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc
index 00a6363e1e11fc52c46556fd3fbc96decd8d4058..59ef4d4fbc310340ef66c2f3132ac74deb3e8632 100644 (file)
--- a/target/arm/translate-vfp.c.inc
+++ b/target/arm/translate-vfp.c.inc
@@ -886,6 +886,41 @@ static bool trans_VMOV_64_dp(DisasContext *s, arg_VMOV_64_dp *a)
     return true;
 }
 
+static bool trans_VLDR_VSTR_hp(DisasContext *s, arg_VLDR_VSTR_sp *a)
+{
+    uint32_t offset;
+    TCGv_i32 addr, tmp;
+
+    if (!dc_isar_feature(aa32_fp16_arith, s)) {
+        return false;
+    }
+
+    if (!vfp_access_check(s)) {
+        return true;
+    }
+
+    /* imm8 field is offset/2 for fp16, unlike fp32 and fp64 */
+    offset = a->imm << 1;
+    if (!a->u) {
+        offset = -offset;
+    }
+
+    /* For thumb, use of PC is UNPREDICTABLE.  */
+    addr = add_reg_for_lit(s, a->rn, offset);
+    tmp = tcg_temp_new_i32();
+    if (a->l) {
+        gen_aa32_ld16u(s, tmp, addr, get_mem_index(s));
+        neon_store_reg32(tmp, a->vd);
+    } else {
+        neon_load_reg32(tmp, a->vd);
+        gen_aa32_st16(s, tmp, addr, get_mem_index(s));
+    }
+    tcg_temp_free_i32(tmp);
+    tcg_temp_free_i32(addr);
+
+    return true;
+}
+
 static bool trans_VLDR_VSTR_sp(DisasContext *s, arg_VLDR_VSTR_sp *a)
 {
     uint32_t offset;

diff --git a/target/arm/vfp.decode b/target/arm/vfp.decode
index b213da4b55d0190a7e316c549c892d837147ece1..37f96e2d2613dbff30bb4285297ca4c415740617 100644 (file)
--- a/target/arm/vfp.decode
+++ b/target/arm/vfp.decode
@@ -79,8 +79,7 @@ VMOV_single  ---- 1110 000 l:1 .... rt:4 1010 . 001 0000    vn=%vn_sp
 VMOV_64_sp   ---- 1100 010 op:1 rt2:4 rt:4 1010 00.1 ....   vm=%vm_sp
 VMOV_64_dp   ---- 1100 010 op:1 rt2:4 rt:4 1011 00.1 ....   vm=%vm_dp
 
-# Note that the half-precision variants of VLDR and VSTR are
-# not part of this decodetree at all because they have bits [9:8] == 0b01
+VLDR_VSTR_hp ---- 1101 u:1 .0 l:1 rn:4 .... 1001 imm:8      vd=%vd_sp
 VLDR_VSTR_sp ---- 1101 u:1 .0 l:1 rn:4 .... 1010 imm:8      vd=%vd_sp
 VLDR_VSTR_dp ---- 1101 u:1 .0 l:1 rn:4 .... 1011 imm:8      vd=%vd_dp