HN Gopher Feed (2017-11-10) - page 1 of 10
Tile: A New Language for Machine Learning
70 points by hedgehoghttp://vertex.ai/blog/tile-a-new-language-for-machine-learning
rbanffy - 47 minutes ago
Not enough parentheses... ;-)
jampekka - 3 minutes ago
Come on, they still have a keyword AND two sets of parentheses
AND a sigil AND a set of braces to define a function.It's like
they couldn't agree on which syntax to use, they decided to use
vbuwivbiu - 1 hours ago
when i read "a language for X" I think "ok...no"
janekm - 1 hours ago
I had the same gut reaction, but fortunately it turns out the
article is not about a language intended for humans:?Our backend
produces custom kernels for each specific operation on each GPU.
It does this through an intermediate language called Tile. Tile
is a simple, compact language for describing machine learning
operations in a way that can be efficiently implemented on
parallel computing architectures.?
DigitalJack - 1 hours ago
Honestly, I do too. But this is just a helper language
describing kernels. It actually looks nice.
nv-vn - 1 hours ago
What's wrong with domain specific languages? SQL is a language
for database manipulation, jq is a language for querying JSON,
CSS is a language for styling documents, etc.
autokad - 1 hours ago
it would be more like an SQL for people wanting to do SQL in
ML, but its not really what the article is talking about.i need
another language to program machine learning in like i need
another hole in my head.
Isamu - 1 hours ago
From the Tile tutorial:> PlaidML uses a language called Tile to
construct GPU kernels. When used to express machine learning
operations, the Tile language is reasonably close to mathematical
notation, while also being amenable to conversion into optimized
GPU kernels. In addition, all operations expressed in Tile can be
be automatically differentiated.> Tile and PlaidML are still in
early development and the Tile language is actively changing to add
tomp - 1 hours ago
Interesting language! But, reading the manual, I don't quite
understand why they _model_ the syntax to mimic mathematics, but
then do things like implicit declaration of indices and renaming
standard math functions...
amelius - 1 hours ago
Does it apply the same tricks as , the Tensor Algebra Compiler
from MIT? https://news.ycombinator.com/item?id=15599914
hedgehog - 29 minutes ago
taco's runtime appears to be designed for large sparse data while
we designed Tile specifically for the dense linear algebra
operations in neural nets. Quite a bit of work has gone into
making the Tile runtime do the necessary optimizations to make
neural nets run efficiently on GPUs and other accelerator
designs, none at all for sparse workloads. Given that I'd expect
the internals to be fairly different.