diff options
| author | Jan Hubicka <hubicka@ucw.cz> | 2017-10-23 17:10:09 +0200 |
|---|---|---|
| committer | Jan Hubicka <hubicka@gcc.gnu.org> | 2017-10-23 15:10:09 +0000 |
| commit | df41dbaf7eae8dcb0841b62647f7504ed13a1d64 (patch) | |
| tree | 231d0369100a82c6aaacef580a138587db0e8b3d /libgcc | |
| parent | 47a6cc4e2932003063c2b56021f4b31bdeb5f746 (diff) | |
| download | gcc-df41dbaf7eae8dcb0841b62647f7504ed13a1d64.zip gcc-df41dbaf7eae8dcb0841b62647f7504ed13a1d64.tar.gz gcc-df41dbaf7eae8dcb0841b62647f7504ed13a1d64.tar.bz2 | |
i386.c (dimode_scalar_chain::compute_convert_gain): Use xmm_move instead of sse_move.
* i386.c (dimode_scalar_chain::compute_convert_gain): Use
xmm_move instead of sse_move.
(sse_store_index): New function.
(ix86_register_move_cost): Be more sensible about mismatch stall;
model AVX moves correctly; make difference between sse->integer and
integer->sse.
(ix86_builtin_vectorization_cost): Model correctly aligned and unaligned
moves; make difference between SSE and AVX.
* i386.h (processor_costs): Remove sse_move; add xmm_move, ymm_move
and zmm_move. Increase size of sse load and store tables;
add unaligned load and store tables; add ssemmx_to_integer.
* x86-tune-costs.h: Update all entries according to real
move latencies from Agner Fog's manual and chip documentation.
From-SVN: r254012
Diffstat (limited to 'libgcc')
0 files changed, 0 insertions, 0 deletions