v0.2.2

define equality with other arrays

v0.2.1

distribute

reset

A whole bunch of internals and API cleanups!

fixes

Merge pull request #61 from bicycle1885/refactor-compute

Refactor compute.jl

bug fix

fix bug when there are multiple workers without any affine chunks

This loop was going into infinite loop since `proc` doesn't change here.

another locality optimization

Scheduler now doesn't randomly pick a task when a worker doesn't have any task with some locally available data. It will instead stop using that worker and wait for some worker with the right affinity to come and pick up the task. This gives massive speedups in some JuliaDB datasets that are slow to serialize/deserialize.

bug fix in `affinity`

v0.1.2

fixes to affinity

LRU cache

Thunks can now be slated to be cached using the cache kwarg. Once a cached thunk is evaluated, the result will be kept around in the worker's memory until Dagger.MAX_MEMORY[] is exceeded by all tracked objects in memory, at which point the results are dropped from cache in an LRU order. Thunks whose results get dropped will be re-evaluated. This feature is not used by Dagger's array library yet.

This release also has some minor optimizations to scheduler bootstrap code.

First release

v0.1.0

don't hijack Base-level methods