Skip to content

[SYCL] Support limit max alloc memory within 2GB for host-pinned memory - #27559

Draft
arthw wants to merge 1 commit into
ggml-org:masterfrom
arthw:add_pin_mem_2g
Draft

[SYCL] Support limit max alloc memory within 2GB for host-pinned memory#27559
arthw wants to merge 1 commit into
ggml-org:masterfrom
arthw:add_pin_mem_2g

Conversation

@arthw

@arthw arthw commented Aug 22, 2026

Copy link
Copy Markdown
Contributor

Overview

It's fix the issue: #27038

Additional information

Define env var: GGML_SYCL_HOST_PINNED_MEM_2G to control this feature, default is close.

Limit the max alloc memory within 2GB can on linux results in no additional CPU utilization during DMA. USM allocations above 2 GiB take the relaxed/large-allocation path, which serializes H2D copies with compute and prevents copy/compute overlap.
It will impact the startup time. Need more test.

Requirements

@github-actions github-actions Bot added documentation Improvements or additions to documentation ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language labels Aug 22, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

documentation Improvements or additions to documentation ggml changes relating to the ggml tensor library for machine learning SYCL https://en.wikipedia.org/wiki/SYCL - GPU programming language

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant