aboutsummaryrefslogtreecommitdiff
path: root/libclc/clc/lib
AgeCommit message (Expand)AuthorFilesLines
2026-01-12[libclc] Remove llvm-link --override flag and make implementation self-contai...Wenju He7-48/+39
2026-01-06[libclc] Compile clc_convert_float2int.cl and clc_convert_int2float.cl separa...Wenju He2-3/+2
2025-12-19[libclc] Improve __clc_min/max/clamp implementation (#172599)Wenju He6-5/+43
2025-12-19[libclc][NFC] Move convert builtins from Python generator to .cl sources (#17...Wenju He8-0/+739
2025-12-05[libclc] Add OpenCL atomic_*_explicit builtins (#168318)Wenju He2-10/+8
2025-11-26[libclc] Use __scoped_atomic_udec/uinc_wrap to implement _clc_atomic_dec/inc ...Wenju He3-3/+3
2025-11-25[libclc] Add atomic_init, atomic_flag_clear and atomic_flag_test_and_set (#16...Wenju He3-0/+52
2025-11-13[libclc] Fix floating-point __clc_atomic_store/exchange cast mismatch (#167625)Wenju He4-17/+24
2025-11-05[NFC][libclc] Rename clc_cbrt.inc to clc_cbrt.h (#166330)Wenju He1-0/+1
2025-10-27[libclc] Implement integer __clc_abs using __builtin_elementwise_abs (#164957)Wenju He1-2/+9
2025-10-21[libclc] Fix double NAN_MASK in __clc_nan (#163522)Wenju He1-1/+1
2025-10-20[NFC][libclc] Simplify degrees, radians and smoothstep macros (#164203)Wenju He7-89/+72
2025-10-20[libclc] Move functions definition from header clc_sincos_piby4.inc into clc_...Wenju He8-6/+160
2025-09-22[libclc] Fix ctest failures after 7f3661128b1e: adjust external check and mak...Wenju He2-2/+2
2025-09-19[Clang] Rename elementwise builtins to `clzg` and `ctzg` (#157128)Joseph Huber2-2/+2
2025-09-18[libclc] Remove __attribute__((always_inline)) (#158791)Wenju He3-8/+8
2025-09-09[NFC][libclc] Replace _CLC_V_V_VP_VECTORIZE macro with use of unary_def_with_...Wenju He1-62/+9
2025-09-05[libclc] Implement erf/erfc vector function with loop since scalar function i...Wenju He2-2/+2
2025-09-05[libclc] Override generic symbol using llvm-link --override flag instead of u...Wenju He3-10/+5
2025-09-03[NFC][libclc] Move _CLC_V_V_VP_VECTORIZE macro into clc_lgamma_r.cl and delet...Wenju He38-38/+54
2025-09-01[libclc] update __clc_mem_fence: add MemorySemantic arg and use __builtin_amd...Wenju He4-31/+54
2025-08-21[libclc] Use elementwise ctlz/cttz builtins for CLC clz/ctz (#154535)Fraser Cormack4-64/+24
2025-08-19[libclc] Implement __clc_get_local_size/__clc_get_max_sub_group_size for amdg...Wenju He3-0/+37
2025-08-18[NFC][libclc] add missing __CLC_ prefix all internal macros (#153523)Wenju He123-780/+793
2025-08-18[libclc] Fix out-of-bound value for workitem functions according to OpenCL sp...Wenju He4-4/+4
2025-08-11[libclc] Implement clc_log/sinpi/sqrt with __nv_* functions (#150174)Wenju He6-0/+174
2025-08-06[libclc] Move mem_fence and barrier to clc library (#151446)Wenju He6-0/+86
2025-07-29[libclc] Optimize generic CLC fmin/fmax (#128506)Fraser Cormack9-214/+9
2025-07-29[libclc] Add generic native half implementation of __clc_normalize (#150165)Wenju He1-9/+8
2025-07-29[libclc] Simplify unary_def_scalarize.inc's use in __clc_erf/erfc/tgamma (#15...Wenju He3-55/+21
2025-07-18[libclc] Add generic implementation of some atomic functions in OpenCL spec s...Wenju He16-0/+389
2025-07-18[libclc] Add generic implementation of bitfield_insert/extract,bit_reverse (#...Wenju He8-0/+110
2025-07-18[libclc] Enable `clang fp reciprocal` in clc_native_divide/recip/rsqrt/tan (#...Wenju He4-0/+4
2025-07-10[libclc] Declare workitem built-ins in clc, move ptx-nvidiacl workitem built-...Wenju He19-0/+346
2025-07-07[NFC][libclc] Rename __CLC_FUNCTION to either FUNCTION or __IMPL_FUNCTION (#1...Wenju He35-35/+35
2025-07-02[libclc] Add missing clc_lgamma_r with generic address space pointer arg (#14...Wenju He1-0/+7
2025-07-02[libclc] Add __clc_nan implementation with signed nancode argument (#146485)Wenju He1-0/+4
2025-06-30[NFC][libclc] Refactor _CLC_*_VECTORIZE macros to functions in .inc files (#1...Wenju He25-99/+205
2025-06-25[libclc] Avoid out-of-range float-to-int. (#145698)Harald van Dijk4-16/+36
2025-06-25[NFC][libclc] Replace and delete _CLC_DEFINE_UNARY/BINARY/TERNARY_BUILTIN mac...Wenju He1-24/+4
2025-06-06[NFC][libclc] Simplify clc_dot and dot implementation (#142922)Wenju He2-55/+28
2025-06-05[libclc] Add (fast) normalize to CLC; add half overloads (#139759)Fraser Cormack5-0/+146
2025-05-29[libclc] Move prefetch to clc library (#141721)Wenju He3-0/+27
2025-05-28[libclc] Move vload & vstore to CLC library (#141755)Fraser Cormack5-0/+488
2025-05-22[libclc] Move step to the CLC library; add missing half variants (#140936)Fraser Cormack3-0/+25
2025-05-21[libclc] Support the generic address space (#137183)Fraser Cormack5-0/+24
2025-05-21[libclc] Move all remquo address spaces to CLC library (#140871)Fraser Cormack2-257/+280
2025-05-21[libclc] Re-use shuffle_decl.inc in OpenCL shuffle2 declaration (#140679)Wenju He2-4/+3
2025-05-19[libclc] Mov erf & erfc to CLC library (#140524)Fraser Cormack3-0/+1041
2025-05-16[libclc] Improving vector code generated from scalar code (#140008)Wenju He1-11/+13