aboutsummaryrefslogtreecommitdiff
path: root/libclc
AgeCommit message (Expand)AuthorFilesLines
2018-06-21atom: Use volatile pointers for cl_khr_{global,local}_int32_{base,extended}_a...Jan Vesely14-20/+20
2018-06-21atom: Consolidate cl_khr_{local,global}_int32_{base,extended}_atomics impleme...Jan Vesely21-148/+66
2018-06-21atomic: Provide function implementation of atomic_{dec,inc}Jan Vesely5-2/+34
2018-06-21atom: Consolidate cl_khr_int64_{base,extended}_atomics declarationsJan Vesely9-32/+27
2018-06-21atom: Consolidate cl_khr_{local,global}_int32_{base,extended}_atomics declara...Jan Vesely17-32/+58
2018-06-21atomic: Cleanup atomic_cmpxchg headerJan Vesely1-15/+4
2018-06-21atomic: Move define cleanup to shared includeJan Vesely9-26/+8
2018-06-18Update copyright year to 2018.Paul Robinson1-1/+1
2018-06-07r600/fmin: Flush denormals before calling builtin.Jan Vesely2-0/+31
2018-06-07r600/fmax: Flush denormals before calling builtin.Jan Vesely2-0/+30
2018-06-07math/fma: Add fp32 software implementationJan Vesely7-5/+192
2018-05-17Add initial support for half precision builtinsJan Vesely57-29/+690
2018-05-15rootn: Use denormal path onlyJan Vesely1-10/+1
2018-05-03remquo: Flush denormals if not supportedJan Vesely1-0/+2
2018-05-03remquo: Port from amd builtinsJan Vesely8-0/+307
2018-05-03math: Add helper function to flush denormals if not supported.Jan Vesely1-0/+19
2018-05-02clc_sqrt: Reuse unary_decl.incJan Vesely2-50/+3
2018-04-25relational/select: Condition types for half are short/ushort, not char/ucharJan Vesely1-2/+2
2018-04-23log10: Use sw implementation from amd builtinsJan Vesely5-19/+173
2018-04-17powr: Use denormal path onlyJan Vesely1-11/+1
2018-04-17pown: Use denormal path onlyJan Vesely1-11/+1
2018-04-17pow: Use denormal path onlyJan Vesely1-11/+1
2018-04-17amdgcn/fmin: Fix typos that reduced precisionJan Vesely1-3/+3
2018-04-17exp10: Port from amd builtinsJan Vesely5-11/+157
2018-04-10hypot: Port from amd builtinsJan Vesely5-4/+108
2018-04-06select: simplify implementation and fix fp16Jan Vesely1-18/+4
2018-04-06fmod: Port from amd_builtinsJan Vesely6-12/+196
2018-04-05r600: Update datalayout after LLVM r328656Jan Vesely4-4/+4
2018-04-05amdgcn: Update datalayout after LLVM r328656Jan Vesely4-4/+4
2018-03-19remainder: Port from amd builtinsJan Vesely6-0/+235
2018-03-12nan: ImplementJan Vesely6-0/+52
2018-03-12travis: Add build using llvm-6Jan Vesely1-0/+22
2018-03-08amdgcn/fmax: fcanonicalize operandsJan Vesely2-0/+32
2018-03-08amdgcn/fmin: fcanonicalize operandsJan Vesely2-0/+32
2018-03-08amdgcn,popcount: Workaround broken llvm.ctpop intrinsic on some GCN ASICsJan Vesely3-0/+24
2018-03-08integer/gentype: Add __CLC_VECSIZE macroJan Vesely1-0/+96
2018-03-08popcount: Provide function implementation rather than intrinsic redirectJan Vesely7-6/+21
2018-03-06lgamma_r: Move code from .inc to .cl fileJan Vesely2-475/+496
2018-03-06frexp: Reuse types provided by gentype.incJan Vesely2-78/+53
2018-03-06select: Add vector implementationJan Vesely5-1/+91
2018-03-06minmag: Condition variable needs to be the same bitwidth as operandsJan Vesely2-2/+21
2018-03-06maxmag: Condition variable needs to be the same bitwidth as operandsJan Vesely2-2/+21
2018-03-06Move cl_khr_fp64 exntension enablement to gentype include listsJan Vesely26-87/+7
2018-02-23utils: Adapt to llvm r325155Jan Vesely1-0/+4
2018-02-23amdgcn: Fix build after GDS/const AS swap in r325030Jan Vesely17-14/+72
2018-02-23amdgcn: Fix datalayout after addition of 32bit const AS in r324747Jan Vesely4-4/+4
2018-02-23r600: Fix datalayout after clang r324101Jan Vesely16-4/+109
2018-02-23amdgcn: Fix datalayout after clang r324101Jan Vesely18-5/+153
2018-02-13amdgpu/half_recip: Switch implementation to native_recipJan Vesely2-0/+7
2018-02-13amdgpu/half_log2: Switch implementation to native_log2Jan Vesely2-0/+7
generated by cgit v1.1 at 2024-10-10 07:11:32 +0000