pytato 2021.1

Imagine TensorFlow, but aimed at HPC. Produces a data flow graph, where the edges carry arrays and the nodes are (give or take) static-control programs that compute array outputs from inputs, possibly (but not necessarily) expressed in Loopy. A core assumption is that the graph represents a computation that’s being repeated often enough that it is worthwhile to do expensive processing on it (code generation, fusion, OpenCL compilation, etc).

• Documentation (read how things work)

Example:

import pytato as pt
import numpy as np

ns = pt.Namespace()
pt.SizeParameter(ns, "n")  # -> prescribes shape=(), dtype=np.intp
a = pt.Placeholder(ns, "a", "n,n", dtype=np.float32)

# Also: pt.roll
# If we can: np.roll
a2a = a@(2*a)

aat = a@a.T

# FIXME: those names are only local...?
# maybe change name of DictOfNamedArrays
result = pt.DictOfNamedArrays({"a2a": a2a, "aat": aat})

prg = pt.generate_loopy(result)

Pytato is licensed to you under the MIT/X Consortium license. See the documentation for further details.