Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

What I wish someone had told me about tensor computation libraries

eigenfoo.xyz

Post reply on HN
Print view View original

21–30 of 89 posts

Re: What I wish someone had told me about tensor computation libraries

#21

Post by kyllo »

dragandj wrote: post #14

Let me chip in with some self-promotion. This book explains and executes every single line of code interactively, from low level operations to high-level networks that do everything automatically. The code is built on the state of the art performance operations of oneDNN (Intel, CPU) and cuDNN (CUDA, GPU). Very concise readable and understandable by humans. https://aiprobook.com/deep-learning-for-programmers/ Here's…

"Deep Learning in Clojure with Fewer Parentheses than Keras and Python"

Love it! :D What better way to define a neural network in code than an S-expression?

Re: What I wish someone had told me about tensor computation libraries

#22

Post by godelski »

dragandj wrote: post #14

Let me chip in with some self-promotion. This book explains and executes every single line of code interactively, from low level operations to high-level networks that do everything automatically. The code is built on the state of the art performance operations of oneDNN (Intel, CPU) and cuDNN (CUDA, GPU). Very concise readable and understandable by humans. https://aiprobook.com/deep-learning-for-programmers/ Here's…

I'd actually love that material in C++/CUDA.

Re: What I wish someone had told me about tensor computation libraries

#23

Post by dragandj »

godelski wrote: post #22
dragandj wrote: post #14

Let me chip in with some self-promotion. This book explains and executes every single line of code interactively, from low level operations to high-level networks that do everything automatically. The code is built on the state of the art performance operations of oneDNN (Intel, CPU) and cuDNN (CUDA, GPU). Very concise readable and understandable by humans. https://aiprobook.com/deep-learning-for-programmers/ Here's…

I'd actually love that material in C++/CUDA.

If only C++ supported interactive REPL and the rest of Clojure/Lisp goodies, that might be possible. However, the code is CLOSELY related to the actual CUDA/C++ api. It's a lot simpler, concise, and everything, but I explain everything so that you can use the relevant parts with cuDNN and DNNL APIs in any language that you're most proficient in.

Re: What I wish someone had told me about tensor computation libraries

#24

Post by gameswithgo »

joshuamorton wrote: post #12
37ef_ced3 wrote: post #7

NN-512 ( https://NN-512.com ) Generate fully vectorized, stand-alone, human-readable C99 code for neural net inference, and understand exactly what's happening. For example, watch the code run with Linux's perf top and see the relative costs of each layer of the computation. Total transparency, no dependencies outside the C POSIX library

In what sense is this "better"? The generated code is like __m512i wfs16 = _mm512_castsi256_si512(_mm512_cvtps_ph(wf25, _MM_FROUND_TO_NEAREST_INT|_MM_FROUND_NO_EXC)); fs16 = _mm512_inserti64x4(wfs16, _mm512_cvtps_ph(wf26, _MM_FROUND_TO_NEAREST_INT|_MM_FROUND_NO_EXC), 1); _mm512_mask_storeu_epi32(wfPtr1+230400+38400*i5+768*c2+128*k1+64*m2+16*f3, 3855, wfs16); _mm512_mask_storeu_epi32(wfPtr1+345584+38400*i5+768*c2+128*…

i can read it! but then i spent months fiddling with intel intrinsics as a hobby

Re: What I wish someone had told me about tensor computation libraries

#25

Post by dekhn »

dragandj wrote: post #23
godelski wrote: post #22

Earlier quoted context omitted.

I'd actually love that material in C++/CUDA.

If only C++ supported interactive REPL and the rest of Clojure/Lisp goodies, that might be possible. However, the code is CLOSELY related to the actual CUDA/C++ api. It's a lot simpler, concise, and everything, but I explain everything so that you can use the relevant parts with cuDNN and DNNL APIs in any language that you're most proficient in.

Does Cling C++ interpreter do what you want? https://github.com/root-project/cling

Re: What I wish someone had told me about tensor computation libraries

#26

Post by dragandj »

dekhn wrote: post #25
dragandj wrote: post #23

Earlier quoted context omitted.

If only C++ supported interactive REPL and the rest of Clojure/Lisp goodies, that might be possible. However, the code is CLOSELY related to the actual CUDA/C++ api. It's a lot simpler, concise, and everything, but I explain everything so that you can use the relevant parts with cuDNN and DNNL APIs in any language that you're most proficient in.

Does Cling C++ interpreter do what you want? https://github.com/root-project/cling

Clojure does what I want.

Perhaps Cling can do something, or not, but I guess that's up to people who prefer Cling to find out and utilize.

Re: What I wish someone had told me about tensor computation libraries

#27

Post by magicfractal »

akhilcacharya wrote: post #18
37ef_ced3 wrote: post #16

Earlier quoted context omitted.

Google those _mm512_... intrinsics (they are part of GCC) to see what they mean. The code you pasted is converting single-precision floats to half-precision floats, and storing the half-precision floats to memory, 32 at a time. That's filter packing, which happens during initialization (and never during inference) I agree, if you don't know anything about how convolution is implemented (filter packing, data packing,…

I’m truly baffled as to why such a sophisticated and useful package is being distributed and advertised by an anonymous individual.

Probably they’re afraid because it might be related to their day job :/

Re: What I wish someone had told me about tensor computation libraries

#28

Post by signaru »

akhilcacharya wrote: post #18
37ef_ced3 wrote: post #16

Earlier quoted context omitted.

Google those _mm512_... intrinsics (they are part of GCC) to see what they mean. The code you pasted is converting single-precision floats to half-precision floats, and storing the half-precision floats to memory, 32 at a time. That's filter packing, which happens during initialization (and never during inference) I agree, if you don't know anything about how convolution is implemented (filter packing, data packing,…

I’m truly baffled as to why such a sophisticated and useful package is being distributed and advertised by an anonymous individual.

can happen if you're in a toxic workplace that will be more baffled that you have done awesome stuff in your free time.

Re: What I wish someone had told me about tensor computation libraries

#29

Post by wokwokwok »

dragandj wrote: post #14

Let me chip in with some self-promotion. This book explains and executes every single line of code interactively, from low level operations to high-level networks that do everything automatically. The code is built on the state of the art performance operations of oneDNN (Intel, CPU) and cuDNN (CUDA, GPU). Very concise readable and understandable by humans. https://aiprobook.com/deep-learning-for-programmers/ Here's…

Concise isn’t always better.

You’re throwing alway all the names of the arguments and using arbitrary words like “conv” to represent operations.

This is typical bad clojure in my experience; write once, forget wtf the magic was, throw away and rewrite it again later.

Clojure doesn’t have to be incomprehensible arcane magic that does everything in 10 lines.

The more complex the code, the more important it is that what you do is clear and clearly documented.

Don’t write a 1 line regex to solve a complicated problem; it’s the wrong tool for that job, no matter how smart your substring matches are.

You don’t win a prize for making unmaintainable code.

I similarly think the goal of being burning my concise in ML code is deeply misguided.

Re: What I wish someone had told me about tensor computation libraries

#30

Post by dragandj »

wokwokwok wrote: post #29
dragandj wrote: post #14

Let me chip in with some self-promotion. This book explains and executes every single line of code interactively, from low level operations to high-level networks that do everything automatically. The code is built on the state of the art performance operations of oneDNN (Intel, CPU) and cuDNN (CUDA, GPU). Very concise readable and understandable by humans. https://aiprobook.com/deep-learning-for-programmers/ Here's…

Concise isn’t always better. You’re throwing alway all the names of the arguments and using arbitrary words like “conv” to represent operations. This is typical bad clojure in my experience; write once, forget wtf the magic was, throw away and rewrite it again later. Clojure doesn’t have to be incomprehensible arcane magic that does everything in 10 lines. The more complex the code, the more important it is that what…

How is "conv" arbitrary? There is a function object that represents a convolutional layer in the network. It is bound to two symbols (because why not). You can either use "convolution" if you prefer full names, or "conv" if you prefer shorter. It doesn't represent the operation, but the layer. There are functions (with longer names) representing the convolution operation, which follow cuDNN and DNNL naming schemes.

Regarding the magic, I believe you haven't read my writings related to this. Exactly the opposite - there is no magic other than usual Clojure-fu, which I explain in a layered way.

But it's difficult to exactly reply to your critique, because you haven't given any example of an approach that would be good Clojure. Ok, give me an example of how you would do it in a comprehensible way (if what I provide is incomprehensible). You don't have to actually implement it. Show a non-working alternative. How would it look like?

Post reply on HN