main

GGitHub[libc] Cache old slabs when allocating GPU memory (#151866)

ca006898创建于 2025年8月9日历史提交

文件	最后提交记录	最后更新时间
CMakeLists.txt	[libc] Cache old slabs when allocating GPU memory (#151866) Summary: This patch introduces a lock-free stack used to store a fixed number of slabs. Instead of going directly through RPC memory, we instead can consult the cache and use that. Currently, this means that ~64 MiB of memory will remain in-use if the user completely fills the cache. However, because we always fully destroy the object, the chunk size can be reset so they can be fully reused. This greatly improves performance in cases where the user has previously accessed malloc, lowering the difference between an implementation that does not free slabs at all and one that does. We can also skip the expensive zeroing step if the old chunk size was smaller than the previous one. Smaller chunk sizes need a larger bitfield, and because we know for a fact that the number of users remaining in this slab is zero thanks to the reference counting we can guarantee that the bitfield is all zero like when it was initialized.	1 年前
fixedstack_test.cpp	[libc] Cache old slabs when allocating GPU memory (#151866) Summary: This patch introduces a lock-free stack used to store a fixed number of slabs. Instead of going directly through RPC memory, we instead can consult the cache and use that. Currently, this means that ~64 MiB of memory will remain in-use if the user completely fills the cache. However, because we always fully destroy the object, the chunk size can be reset so they can be fully reused. This greatly improves performance in cases where the user has previously accessed malloc, lowering the difference between an implementation that does not free slabs at all and one that does. We can also skip the expensive zeroing step if the old chunk size was smaller than the previous one. Smaller chunk sizes need a larger bitfield, and because we know for a fact that the number of users remaining in this slab is zero thanks to the reference counting we can guarantee that the bitfield is all zero like when it was initialized.	1 年前
match.cpp	[libc] Fix integration tests on w64 amdgpu targets (#152303) Summary: We need malloc to return a larger size now that it's aligned properly and we use a bunch of threads. Also the match_any test was wrong because it assumed a 32-bit lanemask.	1 年前
scan_reduce.cpp	[Clang] Fix cross-lane scan when given divergent lanes (#127703) Summary: The scan operation implemented here only works if there are contiguous ones in the executation mask that can be used to propagate the result. There are two solutions to this, one is to enter 'whole-wave-mode' and forcibly turn them back on, or to do this serially. This implementation does the latter because it's more portable, but checks to see if the parallel fast-path is applicable. Needs to be backported for correct behavior and because it fixes a failing libc test.	1 年前
shuffle.cpp	[Clang] Add width handling for <gpuintrin.h> shuffle helper (#125896) Summary: The CUDA impelementation has long supported the width argument on its shuffle instrucitons, which makes it more difficult to replace those uses with this helper. This patch just correctly implements that for AMDGPU and NVPTX so it's equivalent to __shfl_sync in CUDA. This will ease porting. Fortunately these get optimized out correctly when passing in known widths.	1 年前