Skip to content

Xnn weight cache #17762

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
lucylq wants to merge 1 commit into
base: main
Choose a base branch
from
+10 −4
Draft

Xnn weight cache #17762

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 10 additions & 4 deletions backends/xnnpack/runtime/XNNWeightsCache.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,3 @@
/*
* Copyright (c) Meta Platforms, Inc. and affiliates.
* All rights reserved.
Expand Down Expand Up @@ -27,18 +27,18 @@

XNNWeightsCache::XNNWeightsCache() {
weights_cache_.context = this;
weights_cache_.look_up = (size_t(*)(
weights_cache_.look_up = (size_t (*)(
void*, const xnn_weights_cache_look_up_key*))XNNWeightsCache::look_up;
weights_cache_.reserve_space =
(void* (*)(void*, size_t))XNNWeightsCache::reserve_space;
weights_cache_.look_up_or_insert =
(size_t(*)(void*, const xnn_weights_cache_look_up_key*, void*, size_t))
(size_t (*)(void*, const xnn_weights_cache_look_up_key*, void*, size_t))
XNNWeightsCache::look_up_or_insert;
weights_cache_.is_finalized = (bool (*)(void*))XNNWeightsCache::is_finalized;
weights_cache_.offset_to_addr =
(void* (*)(void*, size_t))XNNWeightsCache::offset_to_addr;
weights_cache_.delete_cache =
(enum xnn_status(*)(void*))XNNWeightsCache::delete_cache;
(enum xnn_status (*)(void*))XNNWeightsCache::delete_cache;
}

Error XNNWeightsCache::initialize_for_runtime(
Expand Down Expand Up @@ -207,8 +207,14 @@
size_t offset = context->look_up(context, cache_key);

if (offset != SIZE_MAX) {
// When XNNPACK's look_up already returned a cache hit, it skips packing
// and calls look_up_or_insert with ptr = NULL. In this case, trust the
// cache and return the existing offset without comparing.
if (ptr == nullptr) {
return offset;
}
void* saved_ptr = context->offset_to_addr(context, offset);
if (0 == memcmp(ptr, saved_ptr, size)) {
if (saved_ptr != nullptr && 0 == memcmp(ptr, saved_ptr, size)) {
return offset;
}
// Failure, cache is out of date
Expand Down
Loading