84445dd13c
AMDGPU: Use gfx9 carry-less add/sub instructions
...
llvm-svn: 319491
2017-11-30 22:51:26 +00:00
a0342dc9eb
[AMDGPU][MC][GFX8][GFX9] Corrected names of integer v_{add/addc/sub/subrev/subb/subbrev}
...
See bug 34765: https://bugs.llvm.org//show_bug.cgi?id=34765
Reviewers: tamazov, SamWot, arsenm, vpykhtin
Differential Revision: https://reviews.llvm.org/D40088
llvm-svn: 318675
2017-11-20 18:24:21 +00:00
6c29c5acfe
AMDGPU: Allow SIShrinkInstructions to work in non-SSA
...
Immediates can be folded as long as the immediate is a vreg.
Also undo commuting instructions if it didn't fold an immediate.
llvm-svn: 307575
2017-07-10 19:53:57 +00:00
9aa45f047f
AMDGPU: Add macro fusion schedule DAG mutation
...
Try to increase opportunities to shrink vcc uses.
llvm-svn: 307313
2017-07-06 20:57:05 +00:00
982aee6a38
[AMDGPU] Switch scalarize global loads ON by default
...
Differential revision: https://reviews.llvm.org/D34407
llvm-svn: 307097
2017-07-04 17:32:00 +00:00
e4a741376b
Revert r307026, "[AMDGPU] Switch scalarize global loads ON by default"
...
It broke a testcase.
Failing Tests (1):
LLVM :: CodeGen/AMDGPU/alignbit-pat.ll
llvm-svn: 307054
2017-07-04 02:14:18 +00:00
ea7f08bee5
[AMDGPU] Switch scalarize global loads ON by default
...
Differential revision: https://reviews.llvm.org/D34407
llvm-svn: 307026
2017-07-03 14:54:11 +00:00
3dbeefa978
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel
...
Currently the default C calling convention functions are treated
the same as compute kernels. Make this explicit so the default
calling convention can be changed to a non-kernel.
Converted with perl -pi -e 's/define void/define amdgpu_kernel void/'
on the relevant test directories (and undoing in one place that actually
wanted a non-kernel).
llvm-svn: 298444
2017-03-21 21:39:51 +00:00
ee3f0acf20
AMDGPU: Make i32 uaddo/usubo legal
...
llvm-svn: 293514
2017-01-30 18:11:38 +00:00
45bb48ea19
R600 -> AMDGPU rename
...
llvm-svn: 239657
2015-06-13 03:28:10 +00:00
Matt Arsenault