5e1e64e50bca1d2f4000d10fcfb344d697b9a91e
3 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 enricobuehler
|
5e1e64e50b |
perf(latency): T2.5b — NV12 compute CSC on the LINEAR/gamescope zero-copy path
apple / swift (push) Successful in 1m21s
apple / screenshots (push) Successful in 6m23s
ci / web (push) Successful in 54s
arch / build-publish (push) Successful in 10m52s
ci / docs-site (push) Successful in 1m7s
decky / build-publish (push) Successful in 35s
android / android (push) Successful in 13m2s
docker / build-push (., web/Dockerfile, punktfunk-web) (push) Successful in 16s
docker / build-push (ci, ci/fedora-rpm.Dockerfile, punktfunk-fedora-rpm) (push) Successful in 16s
docker / build-push (docs-site, docs-site/Dockerfile, punktfunk-docs) (push) Successful in 11s
ci / bench (push) Successful in 6m8s
docker / build-push (ci, ci/rust-ci.Dockerfile, punktfunk-rust-ci) (push) Successful in 7m56s
docker / build-push (--build-arg FEDORA_VERSION=44, ci, ci/fedora-rpm.Dockerfile, punktfunk-fedora44-rpm) (push) Successful in 9m44s
docker / deploy-docs (push) Successful in 24s
deb / build-publish (push) Successful in 11m52s
ci / rust (push) Successful in 27m4s
rpm / build-publish (43, bazzite, punktfunk-fedora-rpm) (push) Successful in 20m26s
rpm / build-publish (44, fedora-44, punktfunk-fedora44-rpm) (push) Successful in 20m20s
design/latency-reduction-2026-07.md T2.5's Linux half: the LINEAR dmabuf path (gamescope's only offer) fed NVENC RGB, paying its internal RGB->YUV CSC on the SM the game is saturating — the exact contention §5.A removed everywhere else. The Vulkan bridge now carries a buffer-to-buffer RGB->NV12 compute shader (rgb2nv12_buf.comp, BT.709 limited, coefficient-identical to pf-encode's rgb2yuv.comp; whole-word writes so no 8-bit-storage feature is needed): import dmabuf -> dispatch CSC into the exportable buffer -> CUDA de-strides both planes into a pooled two-plane NV12 buffer. PUNKTFUNK_NV12 (default-on) now covers LINEAR; a CSC failure latches RGB for the stream (mid-frame fallback, no dropped frame); 4:4:4 LINEAR sessions stay RGB (never silently subsample). New ImportKind::LinearNv12 rides the existing worker IPC (appended last per the wire-tag rule); cursor stays downstream (blend_nv12). Validated: .21 clippy -D warnings (pf-zerocopy/pf-capture/host+nvenc) + 17 zero-copy tests. Owed: on-glass gamescope session (visual + dmon sm% check). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> |
||
|
enricobuehler
|
22b352c1da |
chore(release): bump workspace version to 0.13.0
apple / swift (push) Successful in 1m19s
audit / bun-audit (push) Successful in 13s
audit / cargo-audit (push) Successful in 2m8s
ci / web (push) Successful in 53s
release / apple (push) Successful in 5m45s
ci / docs-site (push) Successful in 1m3s
decky / build-publish (push) Successful in 23s
docker / build-push (--build-arg FEDORA_VERSION=44, ci, ci/fedora-rpm.Dockerfile, punktfunk-fedora44-rpm) (push) Successful in 10s
docker / build-push (., web/Dockerfile, punktfunk-web) (push) Successful in 40s
docker / build-push (ci, ci/fedora-rpm.Dockerfile, punktfunk-fedora-rpm) (push) Successful in 9s
ci / bench (push) Successful in 5m26s
docker / build-push (ci, ci/rust-ci.Dockerfile, punktfunk-rust-ci) (push) Successful in 10s
apple / screenshots (push) Successful in 6m27s
windows-host / package (push) Successful in 15m6s
arch / build-publish (push) Successful in 10m50s
docker / build-push (docs-site, docs-site/Dockerfile, punktfunk-docs) (push) Successful in 1m1s
windows-msix / package (arm64, C:\Users\Public\ffmpeg-arm64, --no-default-features, aarch64-pc-windows-msvc, C:\t-a64) (push) Successful in 3m58s
android / android (push) Successful in 16m0s
docker / deploy-docs (push) Successful in 11s
flatpak / build-publish (push) Failing after 8m9s
windows-msix / package (x64, C:\Users\Public\ffmpeg, , x86_64-pc-windows-msvc, C:\t) (push) Successful in 4m11s
deb / build-publish (push) Successful in 13m4s
ci / rust (push) Successful in 19m37s
windows / build (aarch64-pc-windows-msvc) (push) Successful in 5m6s
rpm / build-publish (44, fedora-44, punktfunk-fedora44-rpm) (push) Successful in 14m10s
rpm / build-publish (43, bazzite, punktfunk-fedora-rpm) (push) Successful in 14m26s
windows / build (x86_64-pc-windows-msvc) (push) Successful in 5m51s
The eight W6 leaf crates hardcoded 0.12.0 instead of inheriting the workspace version — switched to version.workspace = true so the next bump is one line again. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> |
||
|
enricobuehler
|
85bc5b9a3f |
refactor(host/W6.2): extract the Linux zero-copy GPU plumbing into the pf-zerocopy leaf crate
linux/zerocopy/* (CUDA context/buffers + EGL/Vulkan dmabuf import + the isolated import worker) and linux/dmabuf_fence.rs move wholesale into crates/pf-zerocopy, so the coming pf-frame vocabulary crate (FramePayload::Cuda owns a DeviceBuffer) and the pf-encode/pf-capture subsystem crates can reach the GPU plumbing without the host orchestrator in between (plan §W6). Content stays Linux-only; the crate compiles to an empty lib elsewhere, so dependents carry a plain dependency. drm_fourcc deliberately does NOT move: it consumes the frame vocabulary (PixelFormat), which sits ABOVE pf-zerocopy — it lives with capture for now and moves into pf-frame next. cuda's ffi re-export bumps pub(crate)->pub (the raw CUdeviceptr vocabulary is consumed across the crate boundary by the encode backends). A crate::zerocopy shim module keeps every existing path valid until capture/encode themselves move out. Verified: Linux clippy -D warnings (pf-zerocopy --all-targets + host nvenc,vulkan-encode,pyrowave --all-targets) + 17/17 pf-zerocopy tests + 321/321 host tests; Windows clippy nvenc,amf-qsv --all-targets Finished exit 0. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |