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
b424954682
amdgpu/half_recip: Switch implementation to native_recip
...
Reviewer: Tom Stellard <tstellar@redhat.com>
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 325061
2018-02-13 22:09:46 +00:00
ed28c4458a
amdgpu/half_log2: Switch implementation to native_log2
...
Reviewer: Tom Stellard <tstellar@redhat.com>
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 325060
2018-02-13 22:09:44 +00:00
86cbf56a4b
amdgpu/half_log10: Switch implementation to native_log10
...
Reviewer: Tom Stellard <tstellar@redhat.com>
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 325059
2018-02-13 22:09:42 +00:00
65fd65efbf
amdgpu/half_log: Switch implementation to native_log
...
Reviewer: Tom Stellard <tstellar@redhat.com>
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 325058
2018-02-13 22:09:41 +00:00
2d3b6dfdca
amdgpu/half_exp2: Switch implementation to native_exp2
...
Reviewer: Tom Stellard <tstellar@redhat.com>
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 325057
2018-02-13 22:09:38 +00:00
021264c75a
amdgpu/half_exp10: Switch implementation to native_exp10
...
Reviewer: Tom Stellard <tstellar@redhat.com>
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 325056
2018-02-13 22:09:37 +00:00
4879dd7471
amdgpu/half_exp: Switch implementation to native_exp
...
Reviewer: Tom Stellard <tstellar@redhat.com>
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 325055
2018-02-13 22:09:35 +00:00
bca92445ba
amdgpu/half_sqrt: Switch implementation to native_sqrt
...
Reviewer: Tom Stellard <tstellar@redhat.com>
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 325054
2018-02-13 22:09:33 +00:00
aad28681c2
amdgpu/half_rsqrt: Switch implementation to native_rsqrt
...
Reviewer: Tom Stellard <tstellar@redhat.com>
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 325053
2018-02-13 22:09:31 +00:00
8dc6e98d47
amdgpu: Add workaround for unimplemented llvm.exp intrinsic
...
Reviewer: Jeroen Ketema
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 317935
2017-11-10 22:16:25 +00:00
47e093da9b
math: Implement native_log10
...
Use llvm instrinsic by default
Provide amdgpu workaround
v2: drop old amd copyrights
Reviewer: Aaron Watry
Reviewed-by: Vedran Miletić <vedran@miletic.net>
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 316588
2017-10-25 16:49:22 +00:00
9fedbb9d8e
amdgpu/math: Don't use llvm instrinsic for native_log
...
AMDGPU targets don't have insturction for it,
so it'll be expanded to C * log2 anyway.
v2: use native_log2 instead of the more precise sw implementation
v3: move to amdgpu
v4: drop old AMD copyright
Reviewer: Aaron Watry
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 316587
2017-10-25 16:49:17 +00:00
1de1444d62
Do not include clc_nextafter header globally
...
Drop unused clc/math/clc_nextafter.h header
Reviewer: Jeroen Ketema
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
llvm-svn: 315190
2017-10-08 19:33:58 +00:00
fbfd828d2a
Replace nextafter implementation
...
This one passes conformance.
llvm-svn: 280961
2016-09-08 16:37:56 +00:00
633d749da7
amdgpu: Use right builtn for rsq
...
The r600 path has never actually worked sinced double is not implemented
there.
llvm-svn: 276009
2016-07-19 19:02:01 +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
a48e15c6cb
Split sources for amdgcn and r600
...
Most files remain in a common amdgpu directory.
Also switches barriers to to use convergent,
and use llvm.amdgcn.s.barrier.
This now requires 3.9/trunk to build amdgcn.
llvm-svn: 260777
2016-02-13 01:01:59 +00:00
Jan Vesely