That wasn't an implied claim because we're not discussing metrics for judging quality.
> That CoreML models are prolific on Apple platforms? That Apple devices are prolific? correct and non-controversial > An enormous number of people and products [use CoreML on Apple platforms] non-sequitur EDIT: i see…
if you're interested in this you might be interested in https://github.com/jbush001/NyuziProcessor
how ironic that her blog post on how to access paywalled articles is currently "Access Denied" https://holly.witteman.ca/index.php/2017/12/11/getting-acces...
you don't transpose it before the matmul, you always have it transposed (i.e., when you print the weights of a linear layer in pytorch, you're actually seeing (A^t)^t and what's stored is A^t.
a polyhedral compiler wouldn't find this either - polyhedral compilation is for finding optimal schedules for loop nests i.e., the order in which independent (wrt dataflow) iterations run. as far as i know you, a…
there is no way a general purpose compiler will figure this out. op is probably talking about something like halide or tvm or torchscript jit.
>You miss my point no you miss my point >making slow Python code run faster there is not a single org anywhere in the world that uses pure python to do numerics. kids do that during their first linear algebra or ml…
since this post might attract people that are mathematica powerusers: how good are mathematicas optimization routines vs commercial solvers like gurobi or cplex? reason i ask is i'm spinning up project that'll require a…
>jit compile Python given who you are (googling your name) i'm surprised that you would say this. jax does not jit compile python in any sense of the word `Python`. jax is a tracing mechanism for a very particular set…
>missing the point facts 1. this is a thread about cpython. jax is as relevant to users of cpython as CUDA or OpenCL or whatever. jax cannot do absolutely anything with e.g. django. 2. for all intents and purposes all…
these two things have nothing to do with each other. jax doesn't compile numpy, it reimplemnts the api using `ufunc`. in general, every single numerical kernel is always mapped to kind of compiled code.
That wasn't an implied claim because we're not discussing metrics for judging quality.
> That CoreML models are prolific on Apple platforms? That Apple devices are prolific? correct and non-controversial > An enormous number of people and products [use CoreML on Apple platforms] non-sequitur EDIT: i see…
if you're interested in this you might be interested in https://github.com/jbush001/NyuziProcessor
how ironic that her blog post on how to access paywalled articles is currently "Access Denied" https://holly.witteman.ca/index.php/2017/12/11/getting-acces...
you don't transpose it before the matmul, you always have it transposed (i.e., when you print the weights of a linear layer in pytorch, you're actually seeing (A^t)^t and what's stored is A^t.
a polyhedral compiler wouldn't find this either - polyhedral compilation is for finding optimal schedules for loop nests i.e., the order in which independent (wrt dataflow) iterations run. as far as i know you, a…
there is no way a general purpose compiler will figure this out. op is probably talking about something like halide or tvm or torchscript jit.
>You miss my point no you miss my point >making slow Python code run faster there is not a single org anywhere in the world that uses pure python to do numerics. kids do that during their first linear algebra or ml…
since this post might attract people that are mathematica powerusers: how good are mathematicas optimization routines vs commercial solvers like gurobi or cplex? reason i ask is i'm spinning up project that'll require a…
>jit compile Python given who you are (googling your name) i'm surprised that you would say this. jax does not jit compile python in any sense of the word `Python`. jax is a tracing mechanism for a very particular set…
>missing the point facts 1. this is a thread about cpython. jax is as relevant to users of cpython as CUDA or OpenCL or whatever. jax cannot do absolutely anything with e.g. django. 2. for all intents and purposes all…
these two things have nothing to do with each other. jax doesn't compile numpy, it reimplemnts the api using `ufunc`. in general, every single numerical kernel is always mapped to kind of compiled code.