Native GenAI: Amazon Bedrock & Google Gemini
Psyclone modules can now drive Amazon Bedrock and Google Gemini directly — bringing native, low-latency generative-AI inference into the real-time pub/sub fabric for building sub-second AI applications.
Psyclone modules can now drive Amazon Bedrock and Google Gemini directly — bringing native, low-latency generative-AI inference into the real-time pub/sub fabric for building sub-second AI applications.
Two macOS timeout primitives treated an absolute deadline as a relative countdown, silently turning bounded waits into infinite hangs under contention — the root cause of intermittent 30-second teardown stalls. Now fixed and soak-validated.
A ground-up CMSDK test framework: one PASS/FAIL line per object, per-test process isolation with timeouts (a crash in one test can’t take down the suite), self-healing shared-memory cleanup, and timestamped performance JSON with %-deltas for automated regression detection. 33 tests, all passing.
Psyclone and its CMSDK core now build, run, and pass the full test suite as a first-class citizen on Apple Silicon and Intel macOS — joining Linux and Windows. The entire distributed pub/sub platform, from shared-memory messaging to the PsyProbe web monitor, is now developed and validated natively on Mac hardware.
The same socket-mode and buffered-read optimisations lifted best-effort UDP messaging to 155,000 messages/second (up from ~107k) with latency down to about 6 microseconds (from 9.3us) — reinforcing Psyclone’s sub-10us real-time profile.
By keeping sockets non-blocking instead of flipping mode around every send (which cost four syscalls per message and raced the receive thread), TCP throughput more than doubled — from ~42k to ~90k msg/s — and per-message latency roughly halved, from 23.8us to ~11us.
Almost every real-time pipeline eventually needs to wait for a combination of things. Fuse three sensors before you act. Wait until both the transcript and the speaker ID have landed. Proceed once any two of five nodes report ready. Classic publish/subscribe gives you one trigger per message, so that logic has always ended up inside…