Skip to content

milnor_gpu: drop the global device mutex (thread-local resident, per-thread streams) #15

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
JoeyBF wants to merge 13 commits into
base: hpc
Choose a base branch
from
Draft

milnor_gpu: drop the global device mutex (thread-local resident, per-thread streams) #15

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
13 commits
Select commit Hold shift + click to select a range
83819ef
Revert "nassau: remove the ParallelGuard priority-inversion retry mec…
JoeyBF Jul 20, 2026
5beaf22
nassau: park retries instead of busy-spinning on ParallelGuard
claude Jul 22, 2026
80d614f
nassau: make the parallel-section guard per-thread
claude Jul 22, 2026
540b31f
nassau: test that the parallel-section guard is thread-local
claude Jul 22, 2026
2b54cf9
Merge remote-tracking branch 'origin/claude/nassau-relaxed-dependency…
JoeyBF Jul 22, 2026
dbc645e
milnor_gpu: drop the global device mutex; make the resident store thr…
JoeyBF Jul 22, 2026
f1cc8fa
milnor_gpu: bound GPU-path memory (row blocks, launch permits, shared…
JoeyBF Jul 23, 2026
a0022b7
milnor_gpu: byte-weighted launch budget + prefix-doubling master uploads
JoeyBF Jul 23, 2026
a04dd91
nassau: offload the d_s image build (signature_matrix) to the GPU mul…
JoeyBF Jul 23, 2026
bc253f6
milnor_gpu: zero the out_h accumulator on-device instead of uploading…
JoeyBF Jul 23, 2026
c433556
milnor_gpu: move the resident-master device upload off the handle lock
JoeyBF Jul 24, 2026
164b129
milnor_gpu: fill the term-data upload buffers directly, killing the p…
JoeyBF Jul 24, 2026
b02dcb3
milnor_gpu: raise GPU_PAIR_CHUNK to ~2^32 so giant multiplies stop ov…
JoeyBF Jul 24, 2026
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
Loading
Loading