target/arm: Simplify do_long_3d and do_2scalar_long

In both cases, we can sink the write-back and perform
the accumulate into the normal destination temps.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20201030022618.785675-11-richard.henderson@linaro.org
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc
index c2d67160f9ed2be647b7a7386284c044d7f8216d..1c16c56e7ec6d0a8e59b1b85d5a801b938f16376 100644 (file)
--- a/target/arm/translate-neon.c.inc
+++ b/target/arm/translate-neon.c.inc
@@ -2037,17 +2037,14 @@ static bool do_long_3d(DisasContext *s, arg_3diff *a,
     if (accfn) {
         tmp = tcg_temp_new_i64();
         read_neon_element64(tmp, a->vd, 0, MO_64);
-        accfn(tmp, tmp, rd0);
-        write_neon_element64(tmp, a->vd, 0, MO_64);
+        accfn(rd0, tmp, rd0);
         read_neon_element64(tmp, a->vd, 1, MO_64);
-        accfn(tmp, tmp, rd1);
-        write_neon_element64(tmp, a->vd, 1, MO_64);
+        accfn(rd1, tmp, rd1);
         tcg_temp_free_i64(tmp);
-    } else {
-        write_neon_element64(rd0, a->vd, 0, MO_64);
-        write_neon_element64(rd1, a->vd, 1, MO_64);
     }
 
+    write_neon_element64(rd0, a->vd, 0, MO_64);
+    write_neon_element64(rd1, a->vd, 1, MO_64);
     tcg_temp_free_i64(rd0);
     tcg_temp_free_i64(rd1);
 
@@ -2670,16 +2667,14 @@ static bool do_2scalar_long(DisasContext *s, arg_2scalar *a,
     if (accfn) {
         TCGv_i64 t64 = tcg_temp_new_i64();
         read_neon_element64(t64, a->vd, 0, MO_64);
-        accfn(t64, t64, rn0_64);
-        write_neon_element64(t64, a->vd, 0, MO_64);
+        accfn(rn0_64, t64, rn0_64);
         read_neon_element64(t64, a->vd, 1, MO_64);
-        accfn(t64, t64, rn1_64);
-        write_neon_element64(t64, a->vd, 1, MO_64);
+        accfn(rn1_64, t64, rn1_64);
         tcg_temp_free_i64(t64);
-    } else {
-        write_neon_element64(rn0_64, a->vd, 0, MO_64);
-        write_neon_element64(rn1_64, a->vd, 1, MO_64);
     }
+
+    write_neon_element64(rn0_64, a->vd, 0, MO_64);
+    write_neon_element64(rn1_64, a->vd, 1, MO_64);
     tcg_temp_free_i64(rn0_64);
     tcg_temp_free_i64(rn1_64);
     return true;