python-for-hpc / ramba Goto Github PK
View Code? Open in Web Editor NEWPython combination of Ray and Numba providing compiled distributed arrays, remote functions, and actors.
License: BSD 2-Clause "Simplified" License
Python combination of Ray and Numba providing compiled distributed arrays, remote functions, and actors.
License: BSD 2-Clause "Simplified" License
In particular: module parser is not available in Python 3.10+
Ray 2.0 marks placement_group parameter as deprecated
Broadcast, broadcast_to do not create DAG entries. Operations with broadcasted arrays cause errors.
Currently, data communication in deferred ops sends multiple copies of the same data if overlapping ranges are referred to by multiple slices. For the default Parallel Research Kernels stencil (a radius=2 "star" or "plus" pattern), this results in 1.5x times the minimum data volume to be transmitted. For a general 5x5 stencil, this would result in 7.5x the necessary data volume.
example:
a = ramba.array(7)
a.asarray()
returns garbage value. However, after sync or a[()], it works. This is when using DAG.
The axis option to sum can be a tuple of ints, i.e., can specify multiple axes. Currently. ramba only supports signle axis (axis option as an int).
Currently, system does not detect when different ranges of same arrays are used for reads and writes when fusing deferred loops. This can have correctness issues when same-sized but different ranges are written / read in consecutive operations. Work-around for now is to manually insert a deferred_op.do_ops() to prevent fusion of such operations.
For doing node-aware partitioning, we want the Ramba workers/RemoteStates to be grouped so that all the workers on a given node are laid out consecutively. In MPI mode, there are some configurations where the ranks are not natively laid out consecutively on the nodes. Thus, we need to have some kind of a mapping between MPI ranks and workers so that from Ramba's perspective the invariant is maintained that chunks of the worker array of size num_workers/num_nodes are laid out consecutively.
This seems to be triggered by use of numba functions. It may be related to import issues. No problem in Ray or MPI in SPMD mode.
It should be possible to convert function/lambda-based initialization and map skeletons to use deferred operations. All are per-element operations. We will need to add mechanisms to allow custom JIT functions to be called from within a deferred op, and mechanisms for providing global index arguments (tuple or otherwise) for initialization functions.
At very least, README should indicate how to install and run in simple cases.
On line 5319 copy
is a boolean arg, not callable:
Lines 5315 to 5319 in 13227ea
Unclear to me what the right fix is, .libcopy.deepcopy(self)
seems to work
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.