[Qemu-devel] [PATCH 11/11] target-arm: Implement fcsel with movcond

[Richard Henderson <rth@twiddle.net>]

Signed-off-by: Richard Henderson <rth@twiddle.net>
---
 target-arm/translate-a64.c | 48 ++++++++++++++++++++--------------------------
 1 file changed, 21 insertions(+), 27 deletions(-)

diff --git a/target-arm/translate-a64.c b/target-arm/translate-a64.c
index 5539ae3..1302cec 100644
--- a/target-arm/translate-a64.c
+++ b/target-arm/translate-a64.c
@@ -4262,20 +4262,6 @@ static void disas_fp_ccomp(DisasContext *s, uint32_t insn)
     tcg_temp_free_i64(t_flags);
 }
 
-/* copy src FP register to dst FP register; type specifies single or double */
-static void gen_mov_fp2fp(DisasContext *s, int type, int dst, int src)
-{
-    if (type) {
-        TCGv_i64 v = read_fp_dreg(s, src);
-        write_fp_dreg(s, dst, v);
-        tcg_temp_free_i64(v);
-    } else {
-        TCGv_i32 v = read_fp_sreg(s, src);
-        write_fp_sreg(s, dst, v);
-        tcg_temp_free_i32(v);
-    }
-}
-
 /* C3.6.24 Floating point conditional select
  *   31  30  29 28       24 23  22  21 20  16 15  12 11 10 9    5 4    0
  * +---+---+---+-----------+------+---+------+------+-----+------+------+
@@ -4285,7 +4271,8 @@ static void gen_mov_fp2fp(DisasContext *s, int type, int dst, int src)
 static void disas_fp_csel(DisasContext *s, uint32_t insn)
 {
     unsigned int mos, type, rm, cond, rn, rd;
-    TCGLabel *label_continue = NULL;
+    TCGv_i64 t_true, t_false, t_zero;
+    DisasCompare c;
 
     mos = extract32(insn, 29, 3);
     type = extract32(insn, 22, 2); /* 0 = single, 1 = double */
@@ -4303,21 +4290,28 @@ static void disas_fp_csel(DisasContext *s, uint32_t insn)
         return;
     }
 
-    if (cond < 0x0e) { /* not always */
-        TCGLabel *label_match = gen_new_label();
-        label_continue = gen_new_label();
-        arm_gen_test_cc(cond, label_match);
-        /* nomatch: */
-        gen_mov_fp2fp(s, type, rd, rm);
-        tcg_gen_br(label_continue);
-        gen_set_label(label_match);
+    if (type) {
+        t_true = read_fp_dreg(s, rn);
+        t_false = read_fp_dreg(s, rm);
+    } else {
+        /* Zero-extend sreg inputs to 64-bits now.  */
+        t_true = tcg_temp_new_i64();
+        t_false = tcg_temp_new_i64();
+        tcg_gen_ld32u_i64(t_true, cpu_env, fp_reg_offset(s, rn, MO_32));
+        tcg_gen_ld32u_i64(t_false, cpu_env, fp_reg_offset(s, rm, MO_32));
     }
 
-    gen_mov_fp2fp(s, type, rd, rn);
+    arm_test_cc(&c, cond);
+    t_zero = tcg_const_i64(0);
+    tcg_gen_movcond_i64(c.cond, t_true, c.value, t_zero, t_true, t_false);
+    tcg_temp_free_i64(t_zero);
+    tcg_temp_free_i64(t_false);
+    arm_free_cc(&c);
 
-    if (cond < 0x0e) { /* continue */
-        gen_set_label(label_continue);
-    }
+    /* Note that sregs write back zeros to the high bits,
+       and we've already done the zero-extension.  */
+    write_fp_dreg(s, rd, t_true);
+    tcg_temp_free_i64(t_true);
 }
 
 /* C3.6.25 Floating-point data-processing (1 source) - single precision */
-- 
2.1.0