llama-bench : fix unexpected global variable initialize sequence issue #11832
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
slaren
reviewed
Feb 14, 2025
slaren
approved these changes
Feb 14, 2025
orca-zhang
pushed a commit
to orca-zhang/llama.cpp
that referenced
this pull request
Feb 26, 2025
ggml-org#11832) * llama-bench : fix unexpected global variable initialize sequence issue * Update examples/llama-bench/llama-bench.cpp --------- Co-authored-by: Diego Devesa <slarengh@gmail.com>
arthw
pushed a commit
to arthw/llama.cpp
that referenced
this pull request
Feb 26, 2025
ggml-org#11832) * llama-bench : fix unexpected global variable initialize sequence issue * Update examples/llama-bench/llama-bench.cpp --------- Co-authored-by: Diego Devesa <slarengh@gmail.com>
mglambda
pushed a commit
to mglambda/llama.cpp
that referenced
this pull request
Mar 8, 2025
ggml-org#11832) * llama-bench : fix unexpected global variable initialize sequence issue * Update examples/llama-bench/llama-bench.cpp --------- Co-authored-by: Diego Devesa <slarengh@gmail.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Global variable initialize sequence is undefined across multiple components, and could introduce unexpected behaviors.
In my case, llama-bench is completely broken with my MSVC compiler.
In short, the initialize sequence of these two global variable causes the problem:
const std::string test::cpu_info = get_cpu_info();andstatic vk_instance_t vk_instance;Here's the detailed calling sequence:
1.Firstly,
const std::string test::cpu_info = get_cpu_info();getting initialized, and get_cpu_info() uses the uninitialized global variablestatic vk_instance_t vk_instance;unexpectedly:vk_instance.instance = vk::createInstance(instance_create_info);2.Then
static vk_instance_t vk_instance;getting initialized, and zeroed out the previous filled vk_instance.instance, and causing all the following calling sequence failed.