system/qemu
system/qemu
1
0
Fork 0
mirror of https://gitlab.com/qemu-project/qemu synced 2024-11-05 20:35:44 +00:00
Code Issues Projects Releases Packages Wiki Activity

NEON vldN optimization

Browse source 
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>
This commit is contained in:
Paul Brook 2010-06-11 20:01:00 +01:00
parent 0e2029a063
commit 41ba834146
1 changed files with 4 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
target-arm/translate.c
View file

@ -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);
}
}