main

GGitHub[libclc] Add atomic_init, atomic_flag_clear and atomic_flag_test_and_set (#168329)

8947ba01创建于 2025年11月25日历史提交

文件	最后提交记录	最后更新时间
amdgcn	[NFC][libclc] Move _CLC_V_V_VP_VECTORIZE macro into clc_lgamma_r.cl and delete clcmacro.h (#156280) clcmacro.h only defines _CLC_V_V_VP_VECTORIZE which is only used in clc/lib/generic/math/clc_lgamma_r.cl.	10 个月前
amdgpu	[NFC][libclc] Move _CLC_V_V_VP_VECTORIZE macro into clc_lgamma_r.cl and delete clcmacro.h (#156280) clcmacro.h only defines _CLC_V_V_VP_VECTORIZE which is only used in clc/lib/generic/math/clc_lgamma_r.cl.	10 个月前
clspv	[NFC][libclc] Move _CLC_V_V_VP_VECTORIZE macro into clc_lgamma_r.cl and delete clcmacro.h (#156280) clcmacro.h only defines _CLC_V_V_VP_VECTORIZE which is only used in clc/lib/generic/math/clc_lgamma_r.cl.	10 个月前
generic	[libclc] Add atomic_init, atomic_flag_clear and atomic_flag_test_and_set (#168329)	8 个月前
ptx-nvidiacl	[libclc] update __clc_mem_fence: add MemorySemantic arg and use __builtin_amdgcn_fence for AMDGPU (#152275) It is necessary to add MemorySemantic argument for AMDGPU which means the memory or address space to which the memory ordering is applied. The MemorySemantic is also necessary for implementing the SPIR-V MemoryBarrier instruction. Additionally, the implementation of __clc_mem_fence on Intel GPUs requires the MemorySemantic argument. Using __builtin_amdgcn_fence for AMDGPU is follow-up of https://github.com/llvm/llvm-project/pull/151446#discussion_r2254006508 llvm-diff shows no change to nvptx64--nvidiacl.bc.	10 个月前
r600	[NFC][libclc] Move _CLC_V_V_VP_VECTORIZE macro into clc_lgamma_r.cl and delete clcmacro.h (#156280) clcmacro.h only defines _CLC_V_V_VP_VECTORIZE which is only used in clc/lib/generic/math/clc_lgamma_r.cl.	10 个月前
spirv	[NFC][libclc] Move _CLC_V_V_VP_VECTORIZE macro into clc_lgamma_r.cl and delete clcmacro.h (#156280) clcmacro.h only defines _CLC_V_V_VP_VECTORIZE which is only used in clc/lib/generic/math/clc_lgamma_r.cl.	10 个月前