Jan Vesely
|
f96b1b88f8
|
amdgcn/fmax: fcanonicalize operands
v_max instruction needs canonicalized operands.
Passes CTS on carrizo
Reviewer: Aaron Watry <awatry@gmail.com>
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 327076
|
2018-03-08 23:01:01 +00:00 |
|
Jan Vesely
|
e724e346ab
|
amdgcn/fmin: fcanonicalize operands
v_min instruction needs canonicalized operands.
Passes CTS on carrizo
Reviewer: Aaron Watry <awatry@gmail.com>
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 327075
|
2018-03-08 23:00:58 +00:00 |
|
Matt Arsenault
|
b456c6dd56
|
Replace llvm.AMDGPU.ldexp with llvm.amdgcn.ldexp
It didn't really work on r600 to begin with, which should
get its own intrinsic.
llvm-svn: 275813
|
2016-07-18 16:42:50 +00:00 |