Commit 41ba8341 authored by Paul Brook's avatar Paul Brook
Browse files

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: default avatarPaul Brook <paul@codesourcery.com>
parent 0e2029a0
......@@ -3854,7 +3854,8 @@ static int disas_neon_ls_insn(CPUState * env, DisasContext *s, uint32_t insn)
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 @@ static int disas_neon_ls_insn(CPUState * env, DisasContext *s, uint32_t insn)
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);
}
}
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment