| Commit message (Expand) | Author | Age | Files | Lines |
* | atom: Use volatile pointers for cl_khr_{global,local}_int32_{base,extended}_a... | Jan Vesely | 2018-06-21 | 14 | -20/+20 |
* | atom: Consolidate cl_khr_{local,global}_int32_{base,extended}_atomics impleme... | Jan Vesely | 2018-06-21 | 21 | -148/+66 |
* | atomic: Provide function implementation of atomic_{dec,inc} | Jan Vesely | 2018-06-21 | 5 | -2/+34 |
* | atom: Consolidate cl_khr_int64_{base,extended}_atomics declarations | Jan Vesely | 2018-06-21 | 9 | -32/+27 |
* | atom: Consolidate cl_khr_{local,global}_int32_{base,extended}_atomics declara... | Jan Vesely | 2018-06-21 | 17 | -32/+58 |
* | atomic: Cleanup atomic_cmpxchg header | Jan Vesely | 2018-06-21 | 1 | -15/+4 |
* | atomic: Move define cleanup to shared include | Jan Vesely | 2018-06-21 | 9 | -26/+8 |
* | Update copyright year to 2018. | Paul Robinson | 2018-06-18 | 1 | -1/+1 |
* | r600/fmin: Flush denormals before calling builtin. | Jan Vesely | 2018-06-07 | 2 | -0/+31 |
* | r600/fmax: Flush denormals before calling builtin. | Jan Vesely | 2018-06-07 | 2 | -0/+30 |
* | math/fma: Add fp32 software implementation | Jan Vesely | 2018-06-07 | 7 | -5/+192 |
* | Add initial support for half precision builtins | Jan Vesely | 2018-05-17 | 57 | -29/+690 |
* | rootn: Use denormal path only | Jan Vesely | 2018-05-15 | 1 | -10/+1 |
* | remquo: Flush denormals if not supported | Jan Vesely | 2018-05-03 | 1 | -0/+2 |
* | remquo: Port from amd builtins | Jan Vesely | 2018-05-03 | 8 | -0/+307 |
* | math: Add helper function to flush denormals if not supported. | Jan Vesely | 2018-05-03 | 1 | -0/+19 |
* | clc_sqrt: Reuse unary_decl.inc | Jan Vesely | 2018-05-02 | 2 | -50/+3 |
* | relational/select: Condition types for half are short/ushort, not char/uchar | Jan Vesely | 2018-04-25 | 1 | -2/+2 |
* | log10: Use sw implementation from amd builtins | Jan Vesely | 2018-04-23 | 5 | -19/+173 |
* | powr: Use denormal path only | Jan Vesely | 2018-04-17 | 1 | -11/+1 |
* | pown: Use denormal path only | Jan Vesely | 2018-04-17 | 1 | -11/+1 |
* | pow: Use denormal path only | Jan Vesely | 2018-04-17 | 1 | -11/+1 |
* | amdgcn/fmin: Fix typos that reduced precision | Jan Vesely | 2018-04-17 | 1 | -3/+3 |
* | exp10: Port from amd builtins | Jan Vesely | 2018-04-17 | 5 | -11/+157 |
* | hypot: Port from amd builtins | Jan Vesely | 2018-04-10 | 5 | -4/+108 |
* | select: simplify implementation and fix fp16 | Jan Vesely | 2018-04-06 | 1 | -18/+4 |
* | fmod: Port from amd_builtins | Jan Vesely | 2018-04-06 | 6 | -12/+196 |
* | r600: Update datalayout after LLVM r328656 | Jan Vesely | 2018-04-05 | 4 | -4/+4 |
* | amdgcn: Update datalayout after LLVM r328656 | Jan Vesely | 2018-04-05 | 4 | -4/+4 |
* | remainder: Port from amd builtins | Jan Vesely | 2018-03-19 | 6 | -0/+235 |
* | nan: Implement | Jan Vesely | 2018-03-12 | 6 | -0/+52 |
* | travis: Add build using llvm-6 | Jan Vesely | 2018-03-12 | 1 | -0/+22 |
* | amdgcn/fmax: fcanonicalize operands | Jan Vesely | 2018-03-08 | 2 | -0/+32 |
* | amdgcn/fmin: fcanonicalize operands | Jan Vesely | 2018-03-08 | 2 | -0/+32 |
* | amdgcn,popcount: Workaround broken llvm.ctpop intrinsic on some GCN ASICs | Jan Vesely | 2018-03-08 | 3 | -0/+24 |
* | integer/gentype: Add __CLC_VECSIZE macro | Jan Vesely | 2018-03-08 | 1 | -0/+96 |
* | popcount: Provide function implementation rather than intrinsic redirect | Jan Vesely | 2018-03-08 | 7 | -6/+21 |
* | lgamma_r: Move code from .inc to .cl file | Jan Vesely | 2018-03-06 | 2 | -475/+496 |
* | frexp: Reuse types provided by gentype.inc | Jan Vesely | 2018-03-06 | 2 | -78/+53 |
* | select: Add vector implementation | Jan Vesely | 2018-03-06 | 5 | -1/+91 |
* | minmag: Condition variable needs to be the same bitwidth as operands | Jan Vesely | 2018-03-06 | 2 | -2/+21 |
* | maxmag: Condition variable needs to be the same bitwidth as operands | Jan Vesely | 2018-03-06 | 2 | -2/+21 |
* | Move cl_khr_fp64 exntension enablement to gentype include lists | Jan Vesely | 2018-03-06 | 26 | -87/+7 |
* | utils: Adapt to llvm r325155 | Jan Vesely | 2018-02-23 | 1 | -0/+4 |
* | amdgcn: Fix build after GDS/const AS swap in r325030 | Jan Vesely | 2018-02-23 | 17 | -14/+72 |
* | amdgcn: Fix datalayout after addition of 32bit const AS in r324747 | Jan Vesely | 2018-02-23 | 4 | -4/+4 |
* | r600: Fix datalayout after clang r324101 | Jan Vesely | 2018-02-23 | 16 | -4/+109 |
* | amdgcn: Fix datalayout after clang r324101 | Jan Vesely | 2018-02-23 | 18 | -5/+153 |
* | amdgpu/half_recip: Switch implementation to native_recip | Jan Vesely | 2018-02-13 | 2 | -0/+7 |
* | amdgpu/half_log2: Switch implementation to native_log2 | Jan Vesely | 2018-02-13 | 2 | -0/+7 |