70a270da5f
Add initial support for half precision builtins
...
v2: fix fmax implementation
use consistent checks for __CLC_FP_SIZE
add missing TODOs
fix whitespace in definitions.h
v3: undef ZERO in modf.inc
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
reviewer: Jeroen Ketema <j.ketema@xs4all.nl>
Reviewed-by: Aaron Watry <awatry@gmail.com>
Tested-by: Aaron Watry <awatry@gmail.com>
llvm-svn: 332677
2018-05-17 22:55:30 +00:00
8fa100dfe3
amdgcn/fmin: Fix typos that reduced precision
...
Not sure how these sneaked in.
Fixes fminD and few other tests(fractD, cosD) on carrizo
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
Reviewed-by: Aaron Watry <awatry@gmail.com>
llvm-svn: 330198
2018-04-17 18:11:29 +00:00
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
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
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
Jan Vesely