summaryrefslogtreecommitdiffstats
path: root/libclc/amdgpu/lib/math
Commit message (Expand)AuthorAgeFilesLines
* Add initial support for half precision builtinsJan Vesely2018-05-172-0/+12
* amdgpu/half_recip: Switch implementation to native_recipJan Vesely2018-02-131-0/+6
* amdgpu/half_log2: Switch implementation to native_log2Jan Vesely2018-02-131-0/+6
* amdgpu/half_log10: Switch implementation to native_log10Jan Vesely2018-02-131-0/+6
* amdgpu/half_log: Switch implementation to native_logJan Vesely2018-02-131-0/+6
* amdgpu/half_exp2: Switch implementation to native_exp2Jan Vesely2018-02-131-0/+6
* amdgpu/half_exp10: Switch implementation to native_exp10Jan Vesely2018-02-131-0/+6
* amdgpu/half_exp: Switch implementation to native_expJan Vesely2018-02-131-0/+6
* amdgpu/half_sqrt: Switch implementation to native_sqrtJan Vesely2018-02-131-0/+6
* amdgpu/half_rsqrt: Switch implementation to native_rsqrtJan Vesely2018-02-132-0/+17
* amdgpu: Add workaround for unimplemented llvm.exp intrinsicJan Vesely2017-11-102-0/+8
* math: Implement native_log10Jan Vesely2017-10-252-0/+8
* amdgpu/math: Don't use llvm instrinsic for native_logJan Vesely2017-10-252-0/+8
* Do not include clc_nextafter header globallyJan Vesely2017-10-081-0/+1
* Replace nextafter implementationMatt Arsenault2016-09-081-0/+5
* amdgpu: Use right builtn for rsqMatt Arsenault2016-07-191-1/+6
* Replace llvm.AMDGPU.ldexp with llvm.amdgcn.ldexpMatt Arsenault2016-07-181-47/+0
* Split sources for amdgcn and r600Matt Arsenault2016-02-133-0/+110
OpenPOWER on IntegriCloud