target/riscv: add support for zfinx

  - update extension check REQUIRE_ZFINX_OR_F
  - update single float point register read/write
  - disable nanbox_s check

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>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
Message-Id: <20220211043920.28981-4-liweiwei@iscas.ac.cn>
Signed-off-by: Alistair Francis <alistair.francis@wdc.com>

1 files changed, 218 insertions, 96 deletions

diff --git a/target/riscv/insn_trans/trans_rvf.c.inc b/target/riscv/insn_trans/trans_rvf.c.inc
index 0aac87f7db..a1d3eb52ad 100644
--- a/target/riscv/insn_trans/trans_rvf.c.inc
+++ b/target/riscv/insn_trans/trans_rvf.c.inc
@@ -20,7 +20,14 @@
 
 #define REQUIRE_FPU do {\
     if (ctx->mstatus_fs == 0) \
-        return false;                       \
+        if (!ctx->cfg_ptr->ext_zfinx) \
+            return false; \
+} while (0)
+
+#define REQUIRE_ZFINX_OR_F(ctx) do {\
+    if (!ctx->cfg_ptr->ext_zfinx) { \
+        REQUIRE_EXT(ctx, RVF); \
+    } \
 } while (0)
 
 static bool trans_flw(DisasContext *ctx, arg_flw *a)
@@ -55,10 +62,16 @@ static bool trans_fsw(DisasContext *ctx, arg_fsw *a)
 static bool trans_fmadd_s(DisasContext *ctx, arg_fmadd_s *a)
 {
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVF);
+    REQUIRE_ZFINX_OR_F(ctx);
+
+    TCGv_i64 dest = dest_fpr(ctx, a->rd);
+    TCGv_i64 src1 = get_fpr_hs(ctx, a->rs1);
+    TCGv_i64 src2 = get_fpr_hs(ctx, a->rs2);
+    TCGv_i64 src3 = get_fpr_hs(ctx, a->rs3);
+
     gen_set_rm(ctx, a->rm);
-    gen_helper_fmadd_s(cpu_fpr[a->rd], cpu_env, cpu_fpr[a->rs1],
-                       cpu_fpr[a->rs2], cpu_fpr[a->rs3]);
+    gen_helper_fmadd_s(dest, cpu_env, src1, src2, src3);
+    gen_set_fpr_hs(ctx, a->rd, dest);
     mark_fs_dirty(ctx);
     return true;
 }
@@ -66,10 +79,16 @@ static bool trans_fmadd_s(DisasContext *ctx, arg_fmadd_s *a)
 static bool trans_fmsub_s(DisasContext *ctx, arg_fmsub_s *a)
 {
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVF);
+    REQUIRE_ZFINX_OR_F(ctx);
+
+    TCGv_i64 dest = dest_fpr(ctx, a->rd);
+    TCGv_i64 src1 = get_fpr_hs(ctx, a->rs1);
+    TCGv_i64 src2 = get_fpr_hs(ctx, a->rs2);
+    TCGv_i64 src3 = get_fpr_hs(ctx, a->rs3);
+
     gen_set_rm(ctx, a->rm);
-    gen_helper_fmsub_s(cpu_fpr[a->rd], cpu_env, cpu_fpr[a->rs1],
-                       cpu_fpr[a->rs2], cpu_fpr[a->rs3]);
+    gen_helper_fmsub_s(dest, cpu_env, src1, src2, src3);
+    gen_set_fpr_hs(ctx, a->rd, dest);
     mark_fs_dirty(ctx);
     return true;
 }
@@ -77,10 +96,16 @@ static bool trans_fmsub_s(DisasContext *ctx, arg_fmsub_s *a)
 static bool trans_fnmsub_s(DisasContext *ctx, arg_fnmsub_s *a)
 {
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVF);
+    REQUIRE_ZFINX_OR_F(ctx);
+
+    TCGv_i64 dest = dest_fpr(ctx, a->rd);
+    TCGv_i64 src1 = get_fpr_hs(ctx, a->rs1);
+    TCGv_i64 src2 = get_fpr_hs(ctx, a->rs2);
+    TCGv_i64 src3 = get_fpr_hs(ctx, a->rs3);
+
     gen_set_rm(ctx, a->rm);
-    gen_helper_fnmsub_s(cpu_fpr[a->rd], cpu_env, cpu_fpr[a->rs1],
-                        cpu_fpr[a->rs2], cpu_fpr[a->rs3]);
+    gen_helper_fnmsub_s(dest, cpu_env, src1, src2, src3);
+    gen_set_fpr_hs(ctx, a->rd, dest);
     mark_fs_dirty(ctx);
     return true;
 }
@@ -88,10 +113,16 @@ static bool trans_fnmsub_s(DisasContext *ctx, arg_fnmsub_s *a)
 static bool trans_fnmadd_s(DisasContext *ctx, arg_fnmadd_s *a)
 {
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVF);
+    REQUIRE_ZFINX_OR_F(ctx);
+
+    TCGv_i64 dest = dest_fpr(ctx, a->rd);
+    TCGv_i64 src1 = get_fpr_hs(ctx, a->rs1);
+    TCGv_i64 src2 = get_fpr_hs(ctx, a->rs2);
+    TCGv_i64 src3 = get_fpr_hs(ctx, a->rs3);
+
     gen_set_rm(ctx, a->rm);
-    gen_helper_fnmadd_s(cpu_fpr[a->rd], cpu_env, cpu_fpr[a->rs1],
-                        cpu_fpr[a->rs2], cpu_fpr[a->rs3]);
+    gen_helper_fnmadd_s(dest, cpu_env, src1, src2, src3);
+    gen_set_fpr_hs(ctx, a->rd, dest);
     mark_fs_dirty(ctx);
     return true;
 }
@@ -99,11 +130,15 @@ static bool trans_fnmadd_s(DisasContext *ctx, arg_fnmadd_s *a)
 static bool trans_fadd_s(DisasContext *ctx, arg_fadd_s *a)
 {
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVF);
+    REQUIRE_ZFINX_OR_F(ctx);
+
+    TCGv_i64 dest = dest_fpr(ctx, a->rd);
+    TCGv_i64 src1 = get_fpr_hs(ctx, a->rs1);
+    TCGv_i64 src2 = get_fpr_hs(ctx, a->rs2);
 
     gen_set_rm(ctx, a->rm);
-    gen_helper_fadd_s(cpu_fpr[a->rd], cpu_env,
-                      cpu_fpr[a->rs1], cpu_fpr[a->rs2]);
+    gen_helper_fadd_s(dest, cpu_env, src1, src2);
+    gen_set_fpr_hs(ctx, a->rd, dest);
     mark_fs_dirty(ctx);
     return true;
 }
@@ -111,11 +146,15 @@ static bool trans_fadd_s(DisasContext *ctx, arg_fadd_s *a)
 static bool trans_fsub_s(DisasContext *ctx, arg_fsub_s *a)
 {
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVF);
+    REQUIRE_ZFINX_OR_F(ctx);
+
+    TCGv_i64 dest = dest_fpr(ctx, a->rd);
+    TCGv_i64 src1 = get_fpr_hs(ctx, a->rs1);
+    TCGv_i64 src2 = get_fpr_hs(ctx, a->rs2);
 
     gen_set_rm(ctx, a->rm);
-    gen_helper_fsub_s(cpu_fpr[a->rd], cpu_env,
-                      cpu_fpr[a->rs1], cpu_fpr[a->rs2]);
+    gen_helper_fsub_s(dest, cpu_env, src1, src2);
+    gen_set_fpr_hs(ctx, a->rd, dest);
     mark_fs_dirty(ctx);
     return true;
 }
@@ -123,11 +162,15 @@ static bool trans_fsub_s(DisasContext *ctx, arg_fsub_s *a)
 static bool trans_fmul_s(DisasContext *ctx, arg_fmul_s *a)
 {
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVF);
+    REQUIRE_ZFINX_OR_F(ctx);
+
+    TCGv_i64 dest = dest_fpr(ctx, a->rd);
+    TCGv_i64 src1 = get_fpr_hs(ctx, a->rs1);
+    TCGv_i64 src2 = get_fpr_hs(ctx, a->rs2);
 
     gen_set_rm(ctx, a->rm);
-    gen_helper_fmul_s(cpu_fpr[a->rd], cpu_env,
-                      cpu_fpr[a->rs1], cpu_fpr[a->rs2]);
+    gen_helper_fmul_s(dest, cpu_env, src1, src2);
+    gen_set_fpr_hs(ctx, a->rd, dest);
     mark_fs_dirty(ctx);
     return true;
 }
@@ -135,11 +178,15 @@ static bool trans_fmul_s(DisasContext *ctx, arg_fmul_s *a)
 static bool trans_fdiv_s(DisasContext *ctx, arg_fdiv_s *a)
 {
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVF);
+    REQUIRE_ZFINX_OR_F(ctx);
+
+    TCGv_i64 dest = dest_fpr(ctx, a->rd);
+    TCGv_i64 src1 = get_fpr_hs(ctx, a->rs1);
+    TCGv_i64 src2 = get_fpr_hs(ctx, a->rs2);
 
     gen_set_rm(ctx, a->rm);
-    gen_helper_fdiv_s(cpu_fpr[a->rd], cpu_env,
-                      cpu_fpr[a->rs1], cpu_fpr[a->rs2]);
+    gen_helper_fdiv_s(dest, cpu_env, src1, src2);
+    gen_set_fpr_hs(ctx, a->rd, dest);
     mark_fs_dirty(ctx);
     return true;
 }
@@ -147,10 +194,14 @@ static bool trans_fdiv_s(DisasContext *ctx, arg_fdiv_s *a)
 static bool trans_fsqrt_s(DisasContext *ctx, arg_fsqrt_s *a)
 {
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVF);
+    REQUIRE_ZFINX_OR_F(ctx);
+
+    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_fsqrt_s(cpu_fpr[a->rd], cpu_env, cpu_fpr[a->rs1]);
+    gen_helper_fsqrt_s(dest, cpu_env, src1);
+    gen_set_fpr_hs(ctx, a->rd, dest);
     mark_fs_dirty(ctx);
     return true;
 }
@@ -158,22 +209,37 @@ static bool trans_fsqrt_s(DisasContext *ctx, arg_fsqrt_s *a)
 static bool trans_fsgnj_s(DisasContext *ctx, arg_fsgnj_s *a)
 {
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVF);
+    REQUIRE_ZFINX_OR_F(ctx);
+
+    TCGv_i64 dest = dest_fpr(ctx, a->rd);
+    TCGv_i64 src1 = get_fpr_hs(ctx, a->rs1);
 
     if (a->rs1 == a->rs2) { /* FMOV */
-        gen_check_nanbox_s(cpu_fpr[a->rd], cpu_fpr[a->rs1]);
+        if (!ctx->cfg_ptr->ext_zfinx) {
+            gen_check_nanbox_s(dest, src1);
+        } else {
+            tcg_gen_ext32s_i64(dest, src1);
+        }
     } else { /* FSGNJ */
-        TCGv_i64 rs1 = tcg_temp_new_i64();
-        TCGv_i64 rs2 = tcg_temp_new_i64();
-
-        gen_check_nanbox_s(rs1, cpu_fpr[a->rs1]);
-        gen_check_nanbox_s(rs2, cpu_fpr[a->rs2]);
-
-        /* This formulation retains the nanboxing of rs2. */
-        tcg_gen_deposit_i64(cpu_fpr[a->rd], rs2, rs1, 0, 31);
-        tcg_temp_free_i64(rs1);
-        tcg_temp_free_i64(rs2);
+        TCGv_i64 src2 = get_fpr_hs(ctx, a->rs2);
+
+        if (!ctx->cfg_ptr->ext_zfinx) {
+            TCGv_i64 rs1 = tcg_temp_new_i64();
+            TCGv_i64 rs2 = tcg_temp_new_i64();
+            gen_check_nanbox_s(rs1, src1);
+            gen_check_nanbox_s(rs2, src2);
+
+            /* This formulation retains the nanboxing of rs2 in normal 'F'. */
+            tcg_gen_deposit_i64(dest, rs2, rs1, 0, 31);
+
+            tcg_temp_free_i64(rs1);
+            tcg_temp_free_i64(rs2);
+        } else {
+            tcg_gen_deposit_i64(dest, src2, src1, 0, 31);
+            tcg_gen_ext32s_i64(dest, dest);
+        }
     }
+    gen_set_fpr_hs(ctx, a->rd, dest);
     mark_fs_dirty(ctx);
     return true;
 }
@@ -183,16 +249,27 @@ static bool trans_fsgnjn_s(DisasContext *ctx, arg_fsgnjn_s *a)
     TCGv_i64 rs1, rs2, mask;
 
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVF);
+    REQUIRE_ZFINX_OR_F(ctx);
 
-    rs1 = tcg_temp_new_i64();
-    gen_check_nanbox_s(rs1, cpu_fpr[a->rs1]);
+    TCGv_i64 dest = dest_fpr(ctx, a->rd);
+    TCGv_i64 src1 = get_fpr_hs(ctx, a->rs1);
 
+    rs1 = tcg_temp_new_i64();
+    if (!ctx->cfg_ptr->ext_zfinx) {
+        gen_check_nanbox_s(rs1, src1);
+    } else {
+        tcg_gen_mov_i64(rs1, src1);
+    }
     if (a->rs1 == a->rs2) { /* FNEG */
-        tcg_gen_xori_i64(cpu_fpr[a->rd], rs1, MAKE_64BIT_MASK(31, 1));
+        tcg_gen_xori_i64(dest, rs1, MAKE_64BIT_MASK(31, 1));
     } else {
+        TCGv_i64 src2 = get_fpr_hs(ctx, a->rs2);
         rs2 = tcg_temp_new_i64();
-        gen_check_nanbox_s(rs2, cpu_fpr[a->rs2]);
+        if (!ctx->cfg_ptr->ext_zfinx) {
+            gen_check_nanbox_s(rs2, src2);
+        } else {
+            tcg_gen_mov_i64(rs2, src2);
+        }
 
         /*
          * Replace bit 31 in rs1 with inverse in rs2.
@@ -200,13 +277,17 @@ static bool trans_fsgnjn_s(DisasContext *ctx, arg_fsgnjn_s *a)
          */
         mask = tcg_constant_i64(~MAKE_64BIT_MASK(31, 1));
         tcg_gen_nor_i64(rs2, rs2, mask);
-        tcg_gen_and_i64(rs1, mask, rs1);
-        tcg_gen_or_i64(cpu_fpr[a->rd], rs1, rs2);
+        tcg_gen_and_i64(dest, mask, rs1);
+        tcg_gen_or_i64(dest, dest, rs2);
 
         tcg_temp_free_i64(rs2);
     }
+    /* signed-extended intead of nanboxing for result if enable zfinx */
+    if (ctx->cfg_ptr->ext_zfinx) {
+        tcg_gen_ext32s_i64(dest, dest);
+    }
+    gen_set_fpr_hs(ctx, a->rd, dest);
     tcg_temp_free_i64(rs1);
-
     mark_fs_dirty(ctx);
     return true;
 }
@@ -216,28 +297,45 @@ static bool trans_fsgnjx_s(DisasContext *ctx, arg_fsgnjx_s *a)
     TCGv_i64 rs1, rs2;
 
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVF);
+    REQUIRE_ZFINX_OR_F(ctx);
 
+    TCGv_i64 dest = dest_fpr(ctx, a->rd);
+    TCGv_i64 src1 = get_fpr_hs(ctx, a->rs1);
     rs1 = tcg_temp_new_i64();
-    gen_check_nanbox_s(rs1, cpu_fpr[a->rs1]);
+
+    if (!ctx->cfg_ptr->ext_zfinx) {
+        gen_check_nanbox_s(rs1, src1);
+    } else {
+        tcg_gen_mov_i64(rs1, src1);
+    }
 
     if (a->rs1 == a->rs2) { /* FABS */
-        tcg_gen_andi_i64(cpu_fpr[a->rd], rs1, ~MAKE_64BIT_MASK(31, 1));
+        tcg_gen_andi_i64(dest, rs1, ~MAKE_64BIT_MASK(31, 1));
     } else {
+        TCGv_i64 src2 = get_fpr_hs(ctx, a->rs2);
         rs2 = tcg_temp_new_i64();
-        gen_check_nanbox_s(rs2, cpu_fpr[a->rs2]);
+
+        if (!ctx->cfg_ptr->ext_zfinx) {
+            gen_check_nanbox_s(rs2, src2);
+        } else {
+            tcg_gen_mov_i64(rs2, src2);
+        }
 
         /*
          * Xor bit 31 in rs1 with that in rs2.
          * This formulation retains the nanboxing of rs1.
          */
-        tcg_gen_andi_i64(rs2, rs2, MAKE_64BIT_MASK(31, 1));
-        tcg_gen_xor_i64(cpu_fpr[a->rd], rs1, rs2);
+        tcg_gen_andi_i64(dest, rs2, MAKE_64BIT_MASK(31, 1));
+        tcg_gen_xor_i64(dest, rs1, dest);
 
         tcg_temp_free_i64(rs2);
     }
+    /* signed-extended intead of nanboxing for result if enable zfinx */
+    if (ctx->cfg_ptr->ext_zfinx) {
+        tcg_gen_ext32s_i64(dest, dest);
+    }
     tcg_temp_free_i64(rs1);
-
+    gen_set_fpr_hs(ctx, a->rd, dest);
     mark_fs_dirty(ctx);
     return true;
 }
@@ -245,10 +343,14 @@ static bool trans_fsgnjx_s(DisasContext *ctx, arg_fsgnjx_s *a)
 static bool trans_fmin_s(DisasContext *ctx, arg_fmin_s *a)
 {
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVF);
+    REQUIRE_ZFINX_OR_F(ctx);
+
+    TCGv_i64 dest = dest_fpr(ctx, a->rd);
+    TCGv_i64 src1 = get_fpr_hs(ctx, a->rs1);
+    TCGv_i64 src2 = get_fpr_hs(ctx, a->rs2);
 
-    gen_helper_fmin_s(cpu_fpr[a->rd], cpu_env, cpu_fpr[a->rs1],
-                      cpu_fpr[a->rs2]);
+    gen_helper_fmin_s(dest, cpu_env, src1, src2);
+    gen_set_fpr_hs(ctx, a->rd, dest);
     mark_fs_dirty(ctx);
     return true;
 }
@@ -256,10 +358,14 @@ static bool trans_fmin_s(DisasContext *ctx, arg_fmin_s *a)
 static bool trans_fmax_s(DisasContext *ctx, arg_fmax_s *a)
 {
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVF);
+    REQUIRE_ZFINX_OR_F(ctx);
+
+    TCGv_i64 dest = dest_fpr(ctx, a->rd);
+    TCGv_i64 src1 = get_fpr_hs(ctx, a->rs1);
+    TCGv_i64 src2 = get_fpr_hs(ctx, a->rs2);
 
-    gen_helper_fmax_s(cpu_fpr[a->rd], cpu_env, cpu_fpr[a->rs1],
-                      cpu_fpr[a->rs2]);
+    gen_helper_fmax_s(dest, cpu_env, src1, src2);
+    gen_set_fpr_hs(ctx, a->rd, dest);
     mark_fs_dirty(ctx);
     return true;
 }
@@ -267,12 +373,13 @@ static bool trans_fmax_s(DisasContext *ctx, arg_fmax_s *a)
 static bool trans_fcvt_w_s(DisasContext *ctx, arg_fcvt_w_s *a)
 {
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVF);
+    REQUIRE_ZFINX_OR_F(ctx);
 
     TCGv dest = dest_gpr(ctx, a->rd);
+    TCGv_i64 src1 = get_fpr_hs(ctx, a->rs1);
 
     gen_set_rm(ctx, a->rm);
-    gen_helper_fcvt_w_s(dest, cpu_env, cpu_fpr[a->rs1]);
+    gen_helper_fcvt_w_s(dest, cpu_env, src1);
     gen_set_gpr(ctx, a->rd, dest);
     return true;
 }
@@ -280,12 +387,13 @@ static bool trans_fcvt_w_s(DisasContext *ctx, arg_fcvt_w_s *a)
 static bool trans_fcvt_wu_s(DisasContext *ctx, arg_fcvt_wu_s *a)
 {
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVF);
+    REQUIRE_ZFINX_OR_F(ctx);
 
     TCGv dest = dest_gpr(ctx, a->rd);
+    TCGv_i64 src1 = get_fpr_hs(ctx, a->rs1);
 
     gen_set_rm(ctx, a->rm);
-    gen_helper_fcvt_wu_s(dest, cpu_env, cpu_fpr[a->rs1]);
+    gen_helper_fcvt_wu_s(dest, cpu_env, src1);
     gen_set_gpr(ctx, a->rd, dest);
     return true;
 }
@@ -294,14 +402,14 @@ static bool trans_fmv_x_w(DisasContext *ctx, arg_fmv_x_w *a)
 {
     /* NOTE: This was FMV.X.S in an earlier version of the ISA spec! */
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVF);
+    REQUIRE_ZFINX_OR_F(ctx);
 
     TCGv dest = dest_gpr(ctx, a->rd);
-
+    TCGv_i64 src1 = get_fpr_hs(ctx, a->rs1);
 #if defined(TARGET_RISCV64)
-    tcg_gen_ext32s_tl(dest, cpu_fpr[a->rs1]);
+    tcg_gen_ext32s_tl(dest, src1);
 #else
-    tcg_gen_extrl_i64_i32(dest, cpu_fpr[a->rs1]);
+    tcg_gen_extrl_i64_i32(dest, src1);
 #endif
 
     gen_set_gpr(ctx, a->rd, dest);
@@ -311,11 +419,13 @@ static bool trans_fmv_x_w(DisasContext *ctx, arg_fmv_x_w *a)
 static bool trans_feq_s(DisasContext *ctx, arg_feq_s *a)
 {
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVF);
+    REQUIRE_ZFINX_OR_F(ctx);
 
     TCGv dest = dest_gpr(ctx, a->rd);
+    TCGv_i64 src1 = get_fpr_hs(ctx, a->rs1);
+    TCGv_i64 src2 = get_fpr_hs(ctx, a->rs2);
 
-    gen_helper_feq_s(dest, cpu_env, cpu_fpr[a->rs1], cpu_fpr[a->rs2]);
+    gen_helper_feq_s(dest, cpu_env, src1, src2);
     gen_set_gpr(ctx, a->rd, dest);
     return true;
 }
@@ -323,11 +433,13 @@ static bool trans_feq_s(DisasContext *ctx, arg_feq_s *a)
 static bool trans_flt_s(DisasContext *ctx, arg_flt_s *a)
 {
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVF);
+    REQUIRE_ZFINX_OR_F(ctx);
 
     TCGv dest = dest_gpr(ctx, a->rd);
+    TCGv_i64 src1 = get_fpr_hs(ctx, a->rs1);
+    TCGv_i64 src2 = get_fpr_hs(ctx, a->rs2);
 
-    gen_helper_flt_s(dest, cpu_env, cpu_fpr[a->rs1], cpu_fpr[a->rs2]);
+    gen_helper_flt_s(dest, cpu_env, src1, src2);
     gen_set_gpr(ctx, a->rd, dest);
     return true;
 }
@@ -335,11 +447,13 @@ static bool trans_flt_s(DisasContext *ctx, arg_flt_s *a)
 static bool trans_fle_s(DisasContext *ctx, arg_fle_s *a)
 {
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVF);
+    REQUIRE_ZFINX_OR_F(ctx);
 
     TCGv dest = dest_gpr(ctx, a->rd);
+    TCGv_i64 src1 = get_fpr_hs(ctx, a->rs1);
+    TCGv_i64 src2 = get_fpr_hs(ctx, a->rs2);
 
-    gen_helper_fle_s(dest, cpu_env, cpu_fpr[a->rs1], cpu_fpr[a->rs2]);
+    gen_helper_fle_s(dest, cpu_env, src1, src2);
     gen_set_gpr(ctx, a->rd, dest);
     return true;
 }
@@ -347,11 +461,12 @@ static bool trans_fle_s(DisasContext *ctx, arg_fle_s *a)
 static bool trans_fclass_s(DisasContext *ctx, arg_fclass_s *a)
 {
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVF);
+    REQUIRE_ZFINX_OR_F(ctx);
 
     TCGv dest = dest_gpr(ctx, a->rd);
+    TCGv_i64 src1 = get_fpr_hs(ctx, a->rs1);
 
-    gen_helper_fclass_s(dest, cpu_fpr[a->rs1]);
+    gen_helper_fclass_s(dest, cpu_env, src1);
     gen_set_gpr(ctx, a->rd, dest);
     return true;
 }
@@ -359,13 +474,14 @@ static bool trans_fclass_s(DisasContext *ctx, arg_fclass_s *a)
 static bool trans_fcvt_s_w(DisasContext *ctx, arg_fcvt_s_w *a)
 {
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVF);
+    REQUIRE_ZFINX_OR_F(ctx);
 
+    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_s_w(cpu_fpr[a->rd], cpu_env, src);
-
+    gen_helper_fcvt_s_w(dest, cpu_env, src);
+    gen_set_fpr_hs(ctx, a->rd, dest);
     mark_fs_dirty(ctx);
     return true;
 }
@@ -373,13 +489,14 @@ static bool trans_fcvt_s_w(DisasContext *ctx, arg_fcvt_s_w *a)
 static bool trans_fcvt_s_wu(DisasContext *ctx, arg_fcvt_s_wu *a)
 {
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVF);
+    REQUIRE_ZFINX_OR_F(ctx);
 
+    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_s_wu(cpu_fpr[a->rd], cpu_env, src);
-
+    gen_helper_fcvt_s_wu(dest, cpu_env, src);
+    gen_set_fpr_hs(ctx, a->rd, dest);
     mark_fs_dirty(ctx);
     return true;
 }
@@ -388,13 +505,14 @@ static bool trans_fmv_w_x(DisasContext *ctx, arg_fmv_w_x *a)
 {
     /* NOTE: This was FMV.S.X in an earlier version of the ISA spec! */
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVF);
+    REQUIRE_ZFINX_OR_F(ctx);
 
+    TCGv_i64 dest = dest_fpr(ctx, a->rd);
     TCGv src = get_gpr(ctx, a->rs1, EXT_ZERO);
 
-    tcg_gen_extu_tl_i64(cpu_fpr[a->rd], src);
-    gen_nanbox_s(cpu_fpr[a->rd], cpu_fpr[a->rd]);
-
+    tcg_gen_extu_tl_i64(dest, src);
+    gen_nanbox_s(dest, dest);
+    gen_set_fpr_hs(ctx, a->rd, dest);
     mark_fs_dirty(ctx);
     return true;
 }
@@ -403,12 +521,13 @@ static bool trans_fcvt_l_s(DisasContext *ctx, arg_fcvt_l_s *a)
 {
     REQUIRE_64BIT(ctx);
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVF);
+    REQUIRE_ZFINX_OR_F(ctx);
 
     TCGv dest = dest_gpr(ctx, a->rd);
+    TCGv_i64 src1 = get_fpr_hs(ctx, a->rs1);
 
     gen_set_rm(ctx, a->rm);
-    gen_helper_fcvt_l_s(dest, cpu_env, cpu_fpr[a->rs1]);
+    gen_helper_fcvt_l_s(dest, cpu_env, src1);
     gen_set_gpr(ctx, a->rd, dest);
     return true;
 }
@@ -417,12 +536,13 @@ static bool trans_fcvt_lu_s(DisasContext *ctx, arg_fcvt_lu_s *a)
 {
     REQUIRE_64BIT(ctx);
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVF);
+    REQUIRE_ZFINX_OR_F(ctx);
 
     TCGv dest = dest_gpr(ctx, a->rd);
+    TCGv_i64 src1 = get_fpr_hs(ctx, a->rs1);
 
     gen_set_rm(ctx, a->rm);
-    gen_helper_fcvt_lu_s(dest, cpu_env, cpu_fpr[a->rs1]);
+    gen_helper_fcvt_lu_s(dest, cpu_env, src1);
     gen_set_gpr(ctx, a->rd, dest);
     return true;
 }
@@ -431,13 +551,14 @@ static bool trans_fcvt_s_l(DisasContext *ctx, arg_fcvt_s_l *a)
 {
     REQUIRE_64BIT(ctx);
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVF);
+    REQUIRE_ZFINX_OR_F(ctx);
 
+    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_s_l(cpu_fpr[a->rd], cpu_env, src);
-
+    gen_helper_fcvt_s_l(dest, cpu_env, src);
+    gen_set_fpr_hs(ctx, a->rd, dest);
     mark_fs_dirty(ctx);
     return true;
 }
@@ -446,13 +567,14 @@ static bool trans_fcvt_s_lu(DisasContext *ctx, arg_fcvt_s_lu *a)
 {
     REQUIRE_64BIT(ctx);
     REQUIRE_FPU;
-    REQUIRE_EXT(ctx, RVF);
+    REQUIRE_ZFINX_OR_F(ctx);
 
+    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_s_lu(cpu_fpr[a->rd], cpu_env, src);
-
+    gen_helper_fcvt_s_lu(dest, cpu_env, src);
+    gen_set_fpr_hs(ctx, a->rd, dest);
     mark_fs_dirty(ctx);
     return true;
 }