NEON vldN optimization
When combining multiple values as part of a NEON array load, do explcit
shift/or rather than using gen_bfi. This voids redundant mask
operations.
Signed-off-by: Paul Brook <paul@codesourcery.com>
diff --git a/target-arm/translate.c b/target-arm/translate.c
index 0eccca5..a28e2ff 100644
--- a/target-arm/translate.c
+++ b/target-arm/translate.c
@@ -3854,7 +3854,8 @@
tcg_gen_addi_i32(addr, addr, stride);
tmp2 = gen_ld16u(addr, IS_USER(s));
tcg_gen_addi_i32(addr, addr, stride);
- gen_bfi(tmp, tmp, tmp2, 16, 0xffff);
+ tcg_gen_shli_i32(tmp2, tmp2, 16);
+ tcg_gen_or_i32(tmp, tmp, tmp2);
dead_tmp(tmp2);
neon_store_reg(rd, pass, tmp);
} else {
@@ -3875,7 +3876,8 @@
if (n == 0) {
tmp2 = tmp;
} else {
- gen_bfi(tmp2, tmp2, tmp, n * 8, 0xff);
+ tcg_gen_shli_i32(tmp, tmp, n * 8);
+ tcg_gen_or_i32(tmp2, tmp2, tmp);
dead_tmp(tmp);
}
}
