llvm-project.git/libc/test/integration/src/stdlib/gpu/aligned_alloc.cpp, branch main Unnamed repository; edit this file 'description' to name the repository. [libc] Fix internal alignment in allcoator (#146738) 2025-07-02T17:29:01+00:00 Joseph Huber huberjn@outlook.com 2025-07-02T17:29:01+00:00 50f40a5327ad9f8a4a57bb2bf7679f489f86b726 Summary: The allocator interface is supposed to have 16 byte alignment (to keep it consistent with the CPU allocator. We could probably drop this to 8 if desires.) But this was not enforced because the number of bytes used for the bitfield sometimes resulted in alignment of 8 instead of 16. Explicitly align the number of bytes to be a multiple of 16 even if unused. 
Summary:
The allocator interface is supposed to have 16 byte alignment (to keep
it consistent with the CPU allocator. We could probably drop this to 8
if desires.) But this was not enforced because the number of bytes used
for the bitfield sometimes resulted in alignment of 8 instead of 16.
Explicitly align the number of bytes to be a multiple of 16 even if
unused.
 [libc] Efficiently implement `aligned_alloc` for AMDGPU (#146585) 2025-07-02T14:25:57+00:00 Joseph Huber huberjn@outlook.com 2025-07-02T14:25:57+00:00 24828c8c45d7f258159afca251aa853a5fc59150 Summary: This patch uses the actual allocator interface to implement `aligned_alloc`. We do this by simply rounding up the amount allocated. Because of how index calculation works, any offset within an allocated pointer will still map to the same chunk, so we can just adjust internally and it will free all the same. 
Summary:
This patch uses the actual allocator interface to implement
`aligned_alloc`. We do this by simply rounding up the amount allocated.
Because of how index calculation works, any offset within an allocated
pointer will still map to the same chunk, so we can just adjust
internally and it will free all the same.