target/riscv: add support for zdinx

  -- update extension check REQUIRE_ZDINX_OR_D
  -- update double float point register read/write

Co-authored-by: ardxwe <ardxwe@gmail.com>
Signed-off-by: Weiwei Li <liweiwei@iscas.ac.cn>
Signed-off-by: Junqiang Wang <wangjunqiang@iscas.ac.cn>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Message-Id: <20220211043920.28981-5-liweiwei@iscas.ac.cn>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>

2 files changed, 259 insertions, 78 deletions

diff --git a/target/riscv/insn_trans/trans_rvd.c.inc b/target/riscv/insn_trans/trans_rvd.c.inc
index 091ed3a..1397c1c 100644
--- a/target/riscv/insn_trans/trans_rvd.c.inc
+++ b/target/riscv/insn_trans/trans_rvd.c.inc
@@ -18,6 +18,19 @@
  * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#define REQUIRE_ZDINX_OR_D(ctx) do { \
+    if (!ctx->cfg_ptr->ext_zdinx) { \
+        REQUIRE_EXT(ctx, RVD); \
+    } \
+} while (0)
+
+#define REQUIRE_EVEN(ctx, reg) do { \
+    if (ctx->cfg_ptr->ext_zdinx && (get_xl(ctx) == MXL_RV32) && \
+        ((reg) & 0x1)) { \
+        return false; \
+    } \
+} while (0)
+
 static bool trans_fld(DisasContext *ctx, arg_fld *a)
 {
     TCGv addr;
@@ -47,10 +60,17 @@ static bool trans_fsd(DisasContext *ctx, arg_fsd *a)
 static bool trans_fmadd_d(DisasContext *ctx, arg_fmadd_d *a)
 {
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVD);
+    REQUIRE_ZDINX_OR_D(ctx);
+    REQUIRE_EVEN(ctx, a->rd | a->rs1 | a->rs2 | a->rs3);
+
+    TCGv_i64 dest = dest_fpr(ctx, a->rd);
+    TCGv_i64 src1 = get_fpr_d(ctx, a->rs1);
+    TCGv_i64 src2 = get_fpr_d(ctx, a->rs2);
+    TCGv_i64 src3 = get_fpr_d(ctx, a->rs3);
+
     gen_set_rm(ctx, a->rm);
-    gen_helper_fmadd_d(cpu_fpr[a->rd], cpu_env, cpu_fpr[a->rs1],
-                       cpu_fpr[a->rs2], cpu_fpr[a->rs3]);
+    gen_helper_fmadd_d(dest, cpu_env, src1, src2, src3);
+    gen_set_fpr_d(ctx, a->rd, dest);
     mark_fs_dirty(ctx);
     return true;
 }
@@ -58,10 +78,17 @@ static bool trans_fmadd_d(DisasContext *ctx, arg_fmadd_d *a)
 static bool trans_fmsub_d(DisasContext *ctx, arg_fmsub_d *a)
 {
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVD);
+    REQUIRE_ZDINX_OR_D(ctx);
+    REQUIRE_EVEN(ctx, a->rd | a->rs1 | a->rs2 | a->rs3);
+
+    TCGv_i64 dest = dest_fpr(ctx, a->rd);
+    TCGv_i64 src1 = get_fpr_d(ctx, a->rs1);
+    TCGv_i64 src2 = get_fpr_d(ctx, a->rs2);
+    TCGv_i64 src3 = get_fpr_d(ctx, a->rs3);
+
     gen_set_rm(ctx, a->rm);
-    gen_helper_fmsub_d(cpu_fpr[a->rd], cpu_env, cpu_fpr[a->rs1],
-                       cpu_fpr[a->rs2], cpu_fpr[a->rs3]);
+    gen_helper_fmsub_d(dest, cpu_env, src1, src2, src3);
+    gen_set_fpr_d(ctx, a->rd, dest);
     mark_fs_dirty(ctx);
     return true;
 }
@@ -69,10 +96,17 @@ static bool trans_fmsub_d(DisasContext *ctx, arg_fmsub_d *a)
 static bool trans_fnmsub_d(DisasContext *ctx, arg_fnmsub_d *a)
 {
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVD);
+    REQUIRE_ZDINX_OR_D(ctx);
+    REQUIRE_EVEN(ctx, a->rd | a->rs1 | a->rs2 | a->rs3);
+
+    TCGv_i64 dest = dest_fpr(ctx, a->rd);
+    TCGv_i64 src1 = get_fpr_d(ctx, a->rs1);
+    TCGv_i64 src2 = get_fpr_d(ctx, a->rs2);
+    TCGv_i64 src3 = get_fpr_d(ctx, a->rs3);
+
     gen_set_rm(ctx, a->rm);
-    gen_helper_fnmsub_d(cpu_fpr[a->rd], cpu_env, cpu_fpr[a->rs1],
-                        cpu_fpr[a->rs2], cpu_fpr[a->rs3]);
+    gen_helper_fnmsub_d(dest, cpu_env, src1, src2, src3);
+    gen_set_fpr_d(ctx, a->rd, dest);
     mark_fs_dirty(ctx);
     return true;
 }
@@ -80,10 +114,17 @@ static bool trans_fnmsub_d(DisasContext *ctx, arg_fnmsub_d *a)
 static bool trans_fnmadd_d(DisasContext *ctx, arg_fnmadd_d *a)
 {
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVD);
+    REQUIRE_ZDINX_OR_D(ctx);
+    REQUIRE_EVEN(ctx, a->rd | a->rs1 | a->rs2 | a->rs3);
+
+    TCGv_i64 dest = dest_fpr(ctx, a->rd);
+    TCGv_i64 src1 = get_fpr_d(ctx, a->rs1);
+    TCGv_i64 src2 = get_fpr_d(ctx, a->rs2);
+    TCGv_i64 src3 = get_fpr_d(ctx, a->rs3);
+
     gen_set_rm(ctx, a->rm);
-    gen_helper_fnmadd_d(cpu_fpr[a->rd], cpu_env, cpu_fpr[a->rs1],
-                        cpu_fpr[a->rs2], cpu_fpr[a->rs3]);
+    gen_helper_fnmadd_d(dest, cpu_env, src1, src2, src3);
+    gen_set_fpr_d(ctx, a->rd, dest);
     mark_fs_dirty(ctx);
     return true;
 }
@@ -91,12 +132,16 @@ static bool trans_fnmadd_d(DisasContext *ctx, arg_fnmadd_d *a)
 static bool trans_fadd_d(DisasContext *ctx, arg_fadd_d *a)
 {
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVD);
+    REQUIRE_ZDINX_OR_D(ctx);
+    REQUIRE_EVEN(ctx, a->rd | a->rs1 | a->rs2);
 
-    gen_set_rm(ctx, a->rm);
-    gen_helper_fadd_d(cpu_fpr[a->rd], cpu_env,
-                      cpu_fpr[a->rs1], cpu_fpr[a->rs2]);
+    TCGv_i64 dest = dest_fpr(ctx, a->rd);
+    TCGv_i64 src1 = get_fpr_d(ctx, a->rs1);
+    TCGv_i64 src2 = get_fpr_d(ctx, a->rs2);
 
+    gen_set_rm(ctx, a->rm);
+    gen_helper_fadd_d(dest, cpu_env, src1, src2);
+    gen_set_fpr_d(ctx, a->rd, dest);
     mark_fs_dirty(ctx);
     return true;
 }
@@ -104,12 +149,16 @@ static bool trans_fadd_d(DisasContext *ctx, arg_fadd_d *a)
 static bool trans_fsub_d(DisasContext *ctx, arg_fsub_d *a)
 {
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVD);
+    REQUIRE_ZDINX_OR_D(ctx);
+    REQUIRE_EVEN(ctx, a->rd | a->rs1 | a->rs2);
 
-    gen_set_rm(ctx, a->rm);
-    gen_helper_fsub_d(cpu_fpr[a->rd], cpu_env,
-                      cpu_fpr[a->rs1], cpu_fpr[a->rs2]);
+    TCGv_i64 dest = dest_fpr(ctx, a->rd);
+    TCGv_i64 src1 = get_fpr_d(ctx, a->rs1);
+    TCGv_i64 src2 = get_fpr_d(ctx, a->rs2);
 
+    gen_set_rm(ctx, a->rm);
+    gen_helper_fsub_d(dest, cpu_env, src1, src2);
+    gen_set_fpr_d(ctx, a->rd, dest);
     mark_fs_dirty(ctx);
     return true;
 }
@@ -117,12 +166,16 @@ static bool trans_fsub_d(DisasContext *ctx, arg_fsub_d *a)
 static bool trans_fmul_d(DisasContext *ctx, arg_fmul_d *a)
 {
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVD);
+    REQUIRE_ZDINX_OR_D(ctx);
+    REQUIRE_EVEN(ctx, a->rd | a->rs1 | a->rs2);
 
-    gen_set_rm(ctx, a->rm);
-    gen_helper_fmul_d(cpu_fpr[a->rd], cpu_env,
-                      cpu_fpr[a->rs1], cpu_fpr[a->rs2]);
+    TCGv_i64 dest = dest_fpr(ctx, a->rd);
+    TCGv_i64 src1 = get_fpr_d(ctx, a->rs1);
+    TCGv_i64 src2 = get_fpr_d(ctx, a->rs2);
 
+    gen_set_rm(ctx, a->rm);
+    gen_helper_fmul_d(dest, cpu_env, src1, src2);
+    gen_set_fpr_d(ctx, a->rd, dest);
     mark_fs_dirty(ctx);
     return true;
 }
@@ -130,12 +183,16 @@ static bool trans_fmul_d(DisasContext *ctx, arg_fmul_d *a)
 static bool trans_fdiv_d(DisasContext *ctx, arg_fdiv_d *a)
 {
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVD);
+    REQUIRE_ZDINX_OR_D(ctx);
+    REQUIRE_EVEN(ctx, a->rd | a->rs1 | a->rs2);
 
-    gen_set_rm(ctx, a->rm);
-    gen_helper_fdiv_d(cpu_fpr[a->rd], cpu_env,
-                      cpu_fpr[a->rs1], cpu_fpr[a->rs2]);
+    TCGv_i64 dest = dest_fpr(ctx, a->rd);
+    TCGv_i64 src1 = get_fpr_d(ctx, a->rs1);
+    TCGv_i64 src2 = get_fpr_d(ctx, a->rs2);
 
+    gen_set_rm(ctx, a->rm);
+    gen_helper_fdiv_d(dest, cpu_env, src1, src2);
+    gen_set_fpr_d(ctx, a->rd, dest);
     mark_fs_dirty(ctx);
     return true;
 }
@@ -143,23 +200,34 @@ static bool trans_fdiv_d(DisasContext *ctx, arg_fdiv_d *a)
 static bool trans_fsqrt_d(DisasContext *ctx, arg_fsqrt_d *a)
 {
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVD);
+    REQUIRE_ZDINX_OR_D(ctx);
+    REQUIRE_EVEN(ctx, a->rd | a->rs1);
 
-    gen_set_rm(ctx, a->rm);
-    gen_helper_fsqrt_d(cpu_fpr[a->rd], cpu_env, cpu_fpr[a->rs1]);
+    TCGv_i64 dest = dest_fpr(ctx, a->rd);
+    TCGv_i64 src1 = get_fpr_d(ctx, a->rs1);
 
+    gen_set_rm(ctx, a->rm);
+    gen_helper_fsqrt_d(dest, cpu_env, src1);
+    gen_set_fpr_d(ctx, a->rd, dest);
     mark_fs_dirty(ctx);
     return true;
 }
 
 static bool trans_fsgnj_d(DisasContext *ctx, arg_fsgnj_d *a)
 {
+    REQUIRE_FPU;
+    REQUIRE_ZDINX_OR_D(ctx);
+    REQUIRE_EVEN(ctx, a->rd | a->rs1 | a->rs2);
+
+    TCGv_i64 dest = dest_fpr(ctx, a->rd);
     if (a->rs1 == a->rs2) { /* FMOV */
-        tcg_gen_mov_i64(cpu_fpr[a->rd], cpu_fpr[a->rs1]);
+        dest = get_fpr_d(ctx, a->rs1);
     } else {
-        tcg_gen_deposit_i64(cpu_fpr[a->rd], cpu_fpr[a->rs2],
-                            cpu_fpr[a->rs1], 0, 63);
+        TCGv_i64 src1 = get_fpr_d(ctx, a->rs1);
+        TCGv_i64 src2 = get_fpr_d(ctx, a->rs2);
+        tcg_gen_deposit_i64(dest, src2, src1, 0, 63);
     }
+    gen_set_fpr_d(ctx, a->rd, dest);
     mark_fs_dirty(ctx);
     return true;
 }
@@ -167,15 +235,22 @@ static bool trans_fsgnj_d(DisasContext *ctx, arg_fsgnj_d *a)
 static bool trans_fsgnjn_d(DisasContext *ctx, arg_fsgnjn_d *a)
 {
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVD);
+    REQUIRE_ZDINX_OR_D(ctx);
+    REQUIRE_EVEN(ctx, a->rd | a->rs1 | a->rs2);
+
+    TCGv_i64 dest = dest_fpr(ctx, a->rd);
+    TCGv_i64 src1 = get_fpr_d(ctx, a->rs1);
+
     if (a->rs1 == a->rs2) { /* FNEG */
-        tcg_gen_xori_i64(cpu_fpr[a->rd], cpu_fpr[a->rs1], INT64_MIN);
+        tcg_gen_xori_i64(dest, src1, INT64_MIN);
     } else {
+        TCGv_i64 src2 = get_fpr_d(ctx, a->rs2);
         TCGv_i64 t0 = tcg_temp_new_i64();
-        tcg_gen_not_i64(t0, cpu_fpr[a->rs2]);
-        tcg_gen_deposit_i64(cpu_fpr[a->rd], t0, cpu_fpr[a->rs1], 0, 63);
+        tcg_gen_not_i64(t0, src2);
+        tcg_gen_deposit_i64(dest, t0, src1, 0, 63);
         tcg_temp_free_i64(t0);
     }
+    gen_set_fpr_d(ctx, a->rd, dest);
     mark_fs_dirty(ctx);
     return true;
 }
@@ -183,15 +258,22 @@ static bool trans_fsgnjn_d(DisasContext *ctx, arg_fsgnjn_d *a)
 static bool trans_fsgnjx_d(DisasContext *ctx, arg_fsgnjx_d *a)
 {
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVD);
+    REQUIRE_ZDINX_OR_D(ctx);
+    REQUIRE_EVEN(ctx, a->rd | a->rs1 | a->rs2);
+
+    TCGv_i64 dest = dest_fpr(ctx, a->rd);
+    TCGv_i64 src1 = get_fpr_d(ctx, a->rs1);
+
     if (a->rs1 == a->rs2) { /* FABS */
-        tcg_gen_andi_i64(cpu_fpr[a->rd], cpu_fpr[a->rs1], ~INT64_MIN);
+        tcg_gen_andi_i64(dest, src1, ~INT64_MIN);
     } else {
+        TCGv_i64 src2 = get_fpr_d(ctx, a->rs2);
         TCGv_i64 t0 = tcg_temp_new_i64();
-        tcg_gen_andi_i64(t0, cpu_fpr[a->rs2], INT64_MIN);
-        tcg_gen_xor_i64(cpu_fpr[a->rd], cpu_fpr[a->rs1], t0);
+        tcg_gen_andi_i64(t0, src2, INT64_MIN);
+        tcg_gen_xor_i64(dest, src1, t0);
         tcg_temp_free_i64(t0);
     }
+    gen_set_fpr_d(ctx, a->rd, dest);
     mark_fs_dirty(ctx);
     return true;
 }
@@ -199,11 +281,15 @@ static bool trans_fsgnjx_d(DisasContext *ctx, arg_fsgnjx_d *a)
 static bool trans_fmin_d(DisasContext *ctx, arg_fmin_d *a)
 {
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVD);
+    REQUIRE_ZDINX_OR_D(ctx);
+    REQUIRE_EVEN(ctx, a->rd | a->rs1 | a->rs2);
 
-    gen_helper_fmin_d(cpu_fpr[a->rd], cpu_env,
-                      cpu_fpr[a->rs1], cpu_fpr[a->rs2]);
+    TCGv_i64 dest = dest_fpr(ctx, a->rd);
+    TCGv_i64 src1 = get_fpr_d(ctx, a->rs1);
+    TCGv_i64 src2 = get_fpr_d(ctx, a->rs2);
 
+    gen_helper_fmin_d(dest, cpu_env, src1, src2);
+    gen_set_fpr_d(ctx, a->rd, dest);
     mark_fs_dirty(ctx);
     return true;
 }
@@ -211,11 +297,15 @@ static bool trans_fmin_d(DisasContext *ctx, arg_fmin_d *a)
 static bool trans_fmax_d(DisasContext *ctx, arg_fmax_d *a)
 {
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVD);
+    REQUIRE_ZDINX_OR_D(ctx);
+    REQUIRE_EVEN(ctx, a->rd | a->rs1 | a->rs2);
 
-    gen_helper_fmax_d(cpu_fpr[a->rd], cpu_env,
-                      cpu_fpr[a->rs1], cpu_fpr[a->rs2]);
+    TCGv_i64 dest = dest_fpr(ctx, a->rd);
+    TCGv_i64 src1 = get_fpr_d(ctx, a->rs1);
+    TCGv_i64 src2 = get_fpr_d(ctx, a->rs2);
 
+    gen_helper_fmax_d(dest, cpu_env, src1, src2);
+    gen_set_fpr_d(ctx, a->rd, dest);
     mark_fs_dirty(ctx);
     return true;
 }
@@ -223,11 +313,15 @@ static bool trans_fmax_d(DisasContext *ctx, arg_fmax_d *a)
 static bool trans_fcvt_s_d(DisasContext *ctx, arg_fcvt_s_d *a)
 {
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVD);
+    REQUIRE_ZDINX_OR_D(ctx);
+    REQUIRE_EVEN(ctx, a->rs1);
 
-    gen_set_rm(ctx, a->rm);
-    gen_helper_fcvt_s_d(cpu_fpr[a->rd], cpu_env, cpu_fpr[a->rs1]);
+    TCGv_i64 dest = dest_fpr(ctx, a->rd);
+    TCGv_i64 src1 = get_fpr_d(ctx, a->rs1);
 
+    gen_set_rm(ctx, a->rm);
+    gen_helper_fcvt_s_d(dest, cpu_env, src1);
+    gen_set_fpr_hs(ctx, a->rd, dest);
     mark_fs_dirty(ctx);
     return true;
 }
@@ -235,11 +329,15 @@ static bool trans_fcvt_s_d(DisasContext *ctx, arg_fcvt_s_d *a)
 static bool trans_fcvt_d_s(DisasContext *ctx, arg_fcvt_d_s *a)
 {
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVD);
+    REQUIRE_ZDINX_OR_D(ctx);
+    REQUIRE_EVEN(ctx, a->rd);
 
-    gen_set_rm(ctx, a->rm);
-    gen_helper_fcvt_d_s(cpu_fpr[a->rd], cpu_env, cpu_fpr[a->rs1]);
+    TCGv_i64 dest = dest_fpr(ctx, a->rd);
+    TCGv_i64 src1 = get_fpr_hs(ctx, a->rs1);
 
+    gen_set_rm(ctx, a->rm);
+    gen_helper_fcvt_d_s(dest, cpu_env, src1);
+    gen_set_fpr_d(ctx, a->rd, dest);
     mark_fs_dirty(ctx);
     return true;
 }
@@ -247,11 +345,14 @@ static bool trans_fcvt_d_s(DisasContext *ctx, arg_fcvt_d_s *a)
 static bool trans_feq_d(DisasContext *ctx, arg_feq_d *a)
 {
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVD);
+    REQUIRE_ZDINX_OR_D(ctx);
+    REQUIRE_EVEN(ctx, a->rs1 | a->rs2);
 
     TCGv dest = dest_gpr(ctx, a->rd);
+    TCGv_i64 src1 = get_fpr_d(ctx, a->rs1);
+    TCGv_i64 src2 = get_fpr_d(ctx, a->rs2);
 
-    gen_helper_feq_d(dest, cpu_env, cpu_fpr[a->rs1], cpu_fpr[a->rs2]);
+    gen_helper_feq_d(dest, cpu_env, src1, src2);
     gen_set_gpr(ctx, a->rd, dest);
     return true;
 }
@@ -259,11 +360,14 @@ static bool trans_feq_d(DisasContext *ctx, arg_feq_d *a)
 static bool trans_flt_d(DisasContext *ctx, arg_flt_d *a)
 {
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVD);
+    REQUIRE_ZDINX_OR_D(ctx);
+    REQUIRE_EVEN(ctx, a->rs1 | a->rs2);
 
     TCGv dest = dest_gpr(ctx, a->rd);
+    TCGv_i64 src1 = get_fpr_d(ctx, a->rs1);
+    TCGv_i64 src2 = get_fpr_d(ctx, a->rs2);
 
-    gen_helper_flt_d(dest, cpu_env, cpu_fpr[a->rs1], cpu_fpr[a->rs2]);
+    gen_helper_flt_d(dest, cpu_env, src1, src2);
     gen_set_gpr(ctx, a->rd, dest);
     return true;
 }
@@ -271,11 +375,14 @@ static bool trans_flt_d(DisasContext *ctx, arg_flt_d *a)
 static bool trans_fle_d(DisasContext *ctx, arg_fle_d *a)
 {
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVD);
+    REQUIRE_ZDINX_OR_D(ctx);
+    REQUIRE_EVEN(ctx, a->rs1 | a->rs2);
 
     TCGv dest = dest_gpr(ctx, a->rd);
+    TCGv_i64 src1 = get_fpr_d(ctx, a->rs1);
+    TCGv_i64 src2 = get_fpr_d(ctx, a->rs2);
 
-    gen_helper_fle_d(dest, cpu_env, cpu_fpr[a->rs1], cpu_fpr[a->rs2]);
+    gen_helper_fle_d(dest, cpu_env, src1, src2);
     gen_set_gpr(ctx, a->rd, dest);
     return true;
 }
@@ -283,11 +390,13 @@ static bool trans_fle_d(DisasContext *ctx, arg_fle_d *a)
 static bool trans_fclass_d(DisasContext *ctx, arg_fclass_d *a)
 {
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVD);
+    REQUIRE_ZDINX_OR_D(ctx);
+    REQUIRE_EVEN(ctx, a->rs1);
 
     TCGv dest = dest_gpr(ctx, a->rd);
+    TCGv_i64 src1 = get_fpr_d(ctx, a->rs1);
 
-    gen_helper_fclass_d(dest, cpu_fpr[a->rs1]);
+    gen_helper_fclass_d(dest, src1);
     gen_set_gpr(ctx, a->rd, dest);
     return true;
 }
@@ -295,12 +404,14 @@ static bool trans_fclass_d(DisasContext *ctx, arg_fclass_d *a)
 static bool trans_fcvt_w_d(DisasContext *ctx, arg_fcvt_w_d *a)
 {
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVD);
+    REQUIRE_ZDINX_OR_D(ctx);
+    REQUIRE_EVEN(ctx, a->rs1);
 
     TCGv dest = dest_gpr(ctx, a->rd);
+    TCGv_i64 src1 = get_fpr_d(ctx, a->rs1);
 
     gen_set_rm(ctx, a->rm);
-    gen_helper_fcvt_w_d(dest, cpu_env, cpu_fpr[a->rs1]);
+    gen_helper_fcvt_w_d(dest, cpu_env, src1);
     gen_set_gpr(ctx, a->rd, dest);
     return true;
 }
@@ -308,12 +419,14 @@ static bool trans_fcvt_w_d(DisasContext *ctx, arg_fcvt_w_d *a)
 static bool trans_fcvt_wu_d(DisasContext *ctx, arg_fcvt_wu_d *a)
 {
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVD);
+    REQUIRE_ZDINX_OR_D(ctx);
+    REQUIRE_EVEN(ctx, a->rs1);
 
     TCGv dest = dest_gpr(ctx, a->rd);
+    TCGv_i64 src1 = get_fpr_d(ctx, a->rs1);
 
     gen_set_rm(ctx, a->rm);
-    gen_helper_fcvt_wu_d(dest, cpu_env, cpu_fpr[a->rs1]);
+    gen_helper_fcvt_wu_d(dest, cpu_env, src1);
     gen_set_gpr(ctx, a->rd, dest);
     return true;
 }
@@ -321,12 +434,15 @@ static bool trans_fcvt_wu_d(DisasContext *ctx, arg_fcvt_wu_d *a)
 static bool trans_fcvt_d_w(DisasContext *ctx, arg_fcvt_d_w *a)
 {
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVD);
+    REQUIRE_ZDINX_OR_D(ctx);
+    REQUIRE_EVEN(ctx, a->rd);
 
+    TCGv_i64 dest = dest_fpr(ctx, a->rd);
     TCGv src = get_gpr(ctx, a->rs1, EXT_SIGN);
 
     gen_set_rm(ctx, a->rm);
-    gen_helper_fcvt_d_w(cpu_fpr[a->rd], cpu_env, src);
+    gen_helper_fcvt_d_w(dest, cpu_env, src);
+    gen_set_fpr_d(ctx, a->rd, dest);
 
     mark_fs_dirty(ctx);
     return true;
@@ -335,12 +451,15 @@ static bool trans_fcvt_d_w(DisasContext *ctx, arg_fcvt_d_w *a)
 static bool trans_fcvt_d_wu(DisasContext *ctx, arg_fcvt_d_wu *a)
 {
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVD);
+    REQUIRE_ZDINX_OR_D(ctx);
+    REQUIRE_EVEN(ctx, a->rd);
 
+    TCGv_i64 dest = dest_fpr(ctx, a->rd);
     TCGv src = get_gpr(ctx, a->rs1, EXT_ZERO);
 
     gen_set_rm(ctx, a->rm);
-    gen_helper_fcvt_d_wu(cpu_fpr[a->rd], cpu_env, src);
+    gen_helper_fcvt_d_wu(dest, cpu_env, src);
+    gen_set_fpr_d(ctx, a->rd, dest);
 
     mark_fs_dirty(ctx);
     return true;
@@ -350,12 +469,14 @@ static bool trans_fcvt_l_d(DisasContext *ctx, arg_fcvt_l_d *a)
 {
     REQUIRE_64BIT(ctx);
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVD);
+    REQUIRE_ZDINX_OR_D(ctx);
+    REQUIRE_EVEN(ctx, a->rs1);
 
     TCGv dest = dest_gpr(ctx, a->rd);
+    TCGv_i64 src1 = get_fpr_d(ctx, a->rs1);
 
     gen_set_rm(ctx, a->rm);
-    gen_helper_fcvt_l_d(dest, cpu_env, cpu_fpr[a->rs1]);
+    gen_helper_fcvt_l_d(dest, cpu_env, src1);
     gen_set_gpr(ctx, a->rd, dest);
     return true;
 }
@@ -364,12 +485,14 @@ static bool trans_fcvt_lu_d(DisasContext *ctx, arg_fcvt_lu_d *a)
 {
     REQUIRE_64BIT(ctx);
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVD);
+    REQUIRE_ZDINX_OR_D(ctx);
+    REQUIRE_EVEN(ctx, a->rs1);
 
     TCGv dest = dest_gpr(ctx, a->rd);
+    TCGv_i64 src1 = get_fpr_d(ctx, a->rs1);
 
     gen_set_rm(ctx, a->rm);
-    gen_helper_fcvt_lu_d(dest, cpu_env, cpu_fpr[a->rs1]);
+    gen_helper_fcvt_lu_d(dest, cpu_env, src1);
     gen_set_gpr(ctx, a->rd, dest);
     return true;
 }
@@ -392,12 +515,15 @@ static bool trans_fcvt_d_l(DisasContext *ctx, arg_fcvt_d_l *a)
 {
     REQUIRE_64BIT(ctx);
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVD);
+    REQUIRE_ZDINX_OR_D(ctx);
+    REQUIRE_EVEN(ctx, a->rd);
 
+    TCGv_i64 dest = dest_fpr(ctx, a->rd);
     TCGv src = get_gpr(ctx, a->rs1, EXT_SIGN);
 
     gen_set_rm(ctx, a->rm);
-    gen_helper_fcvt_d_l(cpu_fpr[a->rd], cpu_env, src);
+    gen_helper_fcvt_d_l(dest, cpu_env, src);
+    gen_set_fpr_d(ctx, a->rd, dest);
 
     mark_fs_dirty(ctx);
     return true;
@@ -407,12 +533,15 @@ static bool trans_fcvt_d_lu(DisasContext *ctx, arg_fcvt_d_lu *a)
 {
     REQUIRE_64BIT(ctx);
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVD);
+    REQUIRE_ZDINX_OR_D(ctx);
+    REQUIRE_EVEN(ctx, a->rd);
 
+    TCGv_i64 dest = dest_fpr(ctx, a->rd);
     TCGv src = get_gpr(ctx, a->rs1, EXT_ZERO);
 
     gen_set_rm(ctx, a->rm);
-    gen_helper_fcvt_d_lu(cpu_fpr[a->rd], cpu_env, src);
+    gen_helper_fcvt_d_lu(dest, cpu_env, src);
+    gen_set_fpr_d(ctx, a->rd, dest);
 
     mark_fs_dirty(ctx);
     return true;
diff --git a/target/riscv/translate.c b/target/riscv/translate.c
index 10cf37b..fac998a 100644
--- a/target/riscv/translate.c
+++ b/target/riscv/translate.c
@@ -416,6 +416,31 @@ static TCGv_i64 get_fpr_hs(DisasContext *ctx, int reg_num)
     }
 }
 
+static TCGv_i64 get_fpr_d(DisasContext *ctx, int reg_num)
+{
+    if (!ctx->cfg_ptr->ext_zfinx) {
+        return cpu_fpr[reg_num];
+    }
+
+    if (reg_num == 0) {
+        return tcg_constant_i64(0);
+    }
+    switch (get_xl(ctx)) {
+    case MXL_RV32:
+    {
+        TCGv_i64 t = ftemp_new(ctx);
+        tcg_gen_concat_tl_i64(t, cpu_gpr[reg_num], cpu_gpr[reg_num + 1]);
+        return t;
+    }
+#ifdef TARGET_RISCV64
+    case MXL_RV64:
+        return cpu_gpr[reg_num];
+#endif
+    default:
+        g_assert_not_reached();
+    }
+}
+
 static TCGv_i64 dest_fpr(DisasContext *ctx, int reg_num)
 {
     if (!ctx->cfg_ptr->ext_zfinx) {
@@ -463,6 +488,33 @@ static void gen_set_fpr_hs(DisasContext *ctx, int reg_num, TCGv_i64 t)
     }
 }
 
+static void gen_set_fpr_d(DisasContext *ctx, int reg_num, TCGv_i64 t)
+{
+    if (!ctx->cfg_ptr->ext_zfinx) {
+        tcg_gen_mov_i64(cpu_fpr[reg_num], t);
+        return;
+    }
+
+    if (reg_num != 0) {
+        switch (get_xl(ctx)) {
+        case MXL_RV32:
+#ifdef TARGET_RISCV32
+            tcg_gen_extr_i64_i32(cpu_gpr[reg_num], cpu_gpr[reg_num + 1], t);
+            break;
+#else
+            tcg_gen_ext32s_i64(cpu_gpr[reg_num], t);
+            tcg_gen_sari_i64(cpu_gpr[reg_num + 1], t, 32);
+            break;
+        case MXL_RV64:
+            tcg_gen_mov_i64(cpu_gpr[reg_num], t);
+            break;
+#endif
+        default:
+            g_assert_not_reached();
+        }
+    }
+}
+
 static void gen_jal(DisasContext *ctx, int rd, target_ulong imm)
 {
     target_ulong next_pc;