[Qemu-devel] [PULL 76/76] target-arm: A64: Add support for FCVT between half, single and double

[Peter Maydell]

Add support for FCVT between half, single and double precision.

Signed-off-by: Peter Maydell <address@hidden>
Reviewed-by: Richard Henderson <address@hidden>
---
 target-arm/helper.c        | 20 +++++++++++++
 target-arm/helper.h        |  2 ++
 target-arm/translate-a64.c | 75 +++++++++++++++++++++++++++++++++++++++++++++-
 3 files changed, 96 insertions(+), 1 deletion(-)

diff --git a/target-arm/helper.c b/target-arm/helper.c
index c6a6281..c708f15 100644
--- a/target-arm/helper.c
+++ b/target-arm/helper.c
@@ -4089,6 +4089,26 @@ uint32_t HELPER(vfp_fcvt_f32_to_f16)(float32 a, 
CPUARMState *env)
     return do_fcvt_f32_to_f16(a, env, &env->vfp.fp_status);
 }
 
+float64 HELPER(vfp_fcvt_f16_to_f64)(uint32_t a, CPUARMState *env)
+{
+    int ieee = (env->vfp.xregs[ARM_VFP_FPSCR] & (1 << 26)) == 0;
+    float64 r = float16_to_float64(make_float16(a), ieee, &env->vfp.fp_status);
+    if (ieee) {
+        return float64_maybe_silence_nan(r);
+    }
+    return r;
+}
+
+uint32_t HELPER(vfp_fcvt_f64_to_f16)(float64 a, CPUARMState *env)
+{
+    int ieee = (env->vfp.xregs[ARM_VFP_FPSCR] & (1 << 26)) == 0;
+    float16 r = float64_to_float16(a, ieee, &env->vfp.fp_status);
+    if (ieee) {
+        r = float16_maybe_silence_nan(r);
+    }
+    return float16_val(r);
+}
+
 #define float32_two make_float32(0x40000000)
 #define float32_three make_float32(0x40400000)
 #define float32_one_point_five make_float32(0x3fc00000)
diff --git a/target-arm/helper.h b/target-arm/helper.h
index 7532e29..70872df 100644
--- a/target-arm/helper.h
+++ b/target-arm/helper.h
@@ -154,6 +154,8 @@ DEF_HELPER_2(vfp_fcvt_f16_to_f32, f32, i32, env)
 DEF_HELPER_2(vfp_fcvt_f32_to_f16, i32, f32, env)
 DEF_HELPER_2(neon_fcvt_f16_to_f32, f32, i32, env)
 DEF_HELPER_2(neon_fcvt_f32_to_f16, i32, f32, env)
+DEF_HELPER_FLAGS_2(vfp_fcvt_f16_to_f64, TCG_CALL_NO_RWG, f64, i32, env)
+DEF_HELPER_FLAGS_2(vfp_fcvt_f64_to_f16, TCG_CALL_NO_RWG, i32, f64, env)
 
 DEF_HELPER_4(vfp_muladdd, f64, f64, f64, f64, ptr)
 DEF_HELPER_4(vfp_muladds, f32, f32, f32, f32, ptr)
diff --git a/target-arm/translate-a64.c b/target-arm/translate-a64.c
index 345a47b..cf80c46 100644
--- a/target-arm/translate-a64.c
+++ b/target-arm/translate-a64.c
@@ -3498,6 +3498,72 @@ static void handle_fp_1src_double(DisasContext *s, int 
opcode, int rd, int rn)
     tcg_temp_free_i64(tcg_res);
 }
 
+static void handle_fp_fcvt(DisasContext *s, int opcode,
+                           int rd, int rn, int dtype, int ntype)
+{
+    switch (ntype) {
+    case 0x0:
+    {
+        TCGv_i32 tcg_rn = read_fp_sreg(s, rn);
+        if (dtype == 1) {
+            /* Single to double */
+            TCGv_i64 tcg_rd = tcg_temp_new_i64();
+            gen_helper_vfp_fcvtds(tcg_rd, tcg_rn, cpu_env);
+            write_fp_dreg(s, rd, tcg_rd);
+            tcg_temp_free_i64(tcg_rd);
+        } else {
+            /* Single to half */
+            TCGv_i32 tcg_rd = tcg_temp_new_i32();
+            gen_helper_vfp_fcvt_f32_to_f16(tcg_rd, tcg_rn, cpu_env);
+            /* write_fp_sreg is OK here because top half of tcg_rd is zero */
+            write_fp_sreg(s, rd, tcg_rd);
+            tcg_temp_free_i32(tcg_rd);
+        }
+        tcg_temp_free_i32(tcg_rn);
+        break;
+    }
+    case 0x1:
+    {
+        TCGv_i64 tcg_rn = read_fp_dreg(s, rn);
+        TCGv_i32 tcg_rd = tcg_temp_new_i32();
+        if (dtype == 0) {
+            /* Double to single */
+            gen_helper_vfp_fcvtsd(tcg_rd, tcg_rn, cpu_env);
+        } else {
+            /* Double to half */
+            gen_helper_vfp_fcvt_f64_to_f16(tcg_rd, tcg_rn, cpu_env);
+            /* write_fp_sreg is OK here because top half of tcg_rd is zero */
+        }
+        write_fp_sreg(s, rd, tcg_rd);
+        tcg_temp_free_i32(tcg_rd);
+        tcg_temp_free_i64(tcg_rn);
+        break;
+    }
+    case 0x3:
+    {
+        TCGv_i32 tcg_rn = read_fp_sreg(s, rn);
+        tcg_gen_ext16u_i32(tcg_rn, tcg_rn);
+        if (dtype == 0) {
+            /* Half to single */
+            TCGv_i32 tcg_rd = tcg_temp_new_i32();
+            gen_helper_vfp_fcvt_f16_to_f32(tcg_rd, tcg_rn, cpu_env);
+            write_fp_sreg(s, rd, tcg_rd);
+            tcg_temp_free_i32(tcg_rd);
+        } else {
+            /* Half to double */
+            TCGv_i64 tcg_rd = tcg_temp_new_i64();
+            gen_helper_vfp_fcvt_f16_to_f64(tcg_rd, tcg_rn, cpu_env);
+            write_fp_dreg(s, rd, tcg_rd);
+            tcg_temp_free_i64(tcg_rd);
+        }
+        tcg_temp_free_i32(tcg_rn);
+        break;
+    }
+    default:
+        abort();
+    }
+}
+
 /* C3.6.25 Floating point data-processing (1 source)
  *   31  30  29 28       24 23  22  21 20    15 14       10 9    5 4    0
  * +---+---+---+-----------+------+---+--------+-----------+------+------+
@@ -3513,9 +3579,16 @@ static void disas_fp_1src(DisasContext *s, uint32_t insn)
 
     switch (opcode) {
     case 0x4: case 0x5: case 0x7:
+    {
         /* FCVT between half, single and double precision */
-        unsupported_encoding(s, insn);
+        int dtype = extract32(opcode, 0, 2);
+        if (type == 2 || dtype == type) {
+            unallocated_encoding(s);
+            return;
+        }
+        handle_fp_fcvt(s, opcode, rd, rn, dtype, type);
         break;
+    }
     case 0x0 ... 0x3:
     case 0x8 ... 0xc:
     case 0xe ... 0xf:
-- 
1.8.5