https://github.com/vmustya created https://github.com/llvm/llvm-project/pull/170542
The function `__opencl_get_memory_scope` incorrectly assumed that the Clang built-in `__MEMORY_SCOPE_*` macros defined as bitmasks, while they are actually defined as distinct integer values. This led to incorrect mapping of OpenCL memory fence flags to LLVM memory scopes, causing issues in generated code. The fix involves updating the `__opencl_get_memory_scope` function to return the correct `__MEMORY_SCOPE_*` values based on the provided `cl_mem_fence_flags`. Additionally, the `__opencl_get_memory_semantics` and the `__opencl_get_memory_scope` functions are marked as `static` to avoid potential multiple definition issues during linking. >From e739786038c8ed1a4e1cdf728f6e1edb875d4ae1 Mon Sep 17 00:00:00 2001 From: Victor Mustya <[email protected]> Date: Wed, 3 Dec 2025 11:39:43 -0800 Subject: [PATCH] [libclc] Fix memory fence scope mapping for OpenCL The function `__opencl_get_memory_scope` incorrectly assumed that the Clang built-in `__MEMORY_SCOPE_*` macros defined as bitmasks, while they are actually defined as distinct integer values. This led to incorrect mapping of OpenCL memory fence flags to LLVM memory scopes, causing issues in generated code. The fix involves updating the `__opencl_get_memory_scope` function to return the correct `__MEMORY_SCOPE_*` values based on the provided `cl_mem_fence_flags`. Additionally, the `__opencl_get_memory_semantics` and the `__opencl_get_memory_scope` functions are marked as `static` to avoid potential multiple definition issues during linking. --- .../opencl/include/clc/opencl/synchronization/utils.h | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/libclc/opencl/include/clc/opencl/synchronization/utils.h b/libclc/opencl/include/clc/opencl/synchronization/utils.h index a8841658598c1..a4f06ba8da6ac 100644 --- a/libclc/opencl/include/clc/opencl/synchronization/utils.h +++ b/libclc/opencl/include/clc/opencl/synchronization/utils.h @@ -13,16 +13,15 @@ #include <clc/mem_fence/clc_mem_semantic.h> #include <clc/opencl/synchronization/cl_mem_fence_flags.h> -_CLC_INLINE int __opencl_get_memory_scope(cl_mem_fence_flags flag) { - int memory_scope = 0; +static _CLC_INLINE int __opencl_get_memory_scope(cl_mem_fence_flags flag) { if (flag & CLK_GLOBAL_MEM_FENCE) - memory_scope |= __MEMORY_SCOPE_DEVICE; + return __MEMORY_SCOPE_DEVICE; if (flag & CLK_LOCAL_MEM_FENCE) - memory_scope |= __MEMORY_SCOPE_WRKGRP; - return memory_scope; + return __MEMORY_SCOPE_WRKGRP; + return __MEMORY_SCOPE_SINGLE; } -_CLC_INLINE __CLC_MemorySemantics +static _CLC_INLINE __CLC_MemorySemantics __opencl_get_memory_semantics(cl_mem_fence_flags flag) { if ((flag & CLK_LOCAL_MEM_FENCE) && (flag & CLK_GLOBAL_MEM_FENCE)) return __CLC_MEMORY_LOCAL | __CLC_MEMORY_GLOBAL; _______________________________________________ cfe-commits mailing list [email protected] https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
