Matt Arsenault
abc4f29f9c
AMDGPU: Remove custom BUILD_VECTOR combine
...
This was looping in a testcase and removing it
now slightly improves a test.
llvm-svn: 345560
2018-10-30 01:37:59 +00:00
Matt Arsenault
3ead7d7389
AMDGPU: Fix packing undef parts of build_vector
...
llvm-svn: 339511
2018-08-12 08:42:46 +00:00
Dmitry Preobrazhensky
682a654758
[AMDGPU][MC][GFX9][disassembler] Corrected decoding of op_sel_hi for v_mad_mix*
...
See bug 35148: https://bugs.llvm.org//show_bug.cgi?id=35148
Reviewers: tamazov, SamWot, arsenm
Differential Revision: https://reviews.llvm.org/D39492
llvm-svn: 318526
2017-11-17 15:15:40 +00:00
Matt Arsenault
8cbb4884a5
AMDGPU: Start selecting v_mad_mixhi_f16
...
llvm-svn: 313814
2017-09-20 21:01:24 +00:00
Matt Arsenault
76935122cc
AMDGPU: Start selecting v_mad_mixlo_f16
...
Also add some tests that should be able to use v_mad_mixhi_f16,
but do not yet. This is trickier because we don't really model
the partial update of the register done by 16-bit instructions.
llvm-svn: 313806
2017-09-20 20:28:39 +00:00