@gmarkall

Professional interests: Python, CUDA, @numba_jit. Personal interests: RISC-V, PSXDev, OSHW, 日本語. Fun: family, cycling, running. Also @gmarkall@mastodon.social

 Lincoln, UK
gmarkall.wordpress.com
Joined May 2010
  • Tweets3.9K
  • Following603
  • Followers1.1K
188Media
Apparently it's #MyTwitterAnniversary, so I'll use it as an opportunity to link to the Mastodon account I now use: mastodon.social/@gmarkall
3
379
Quick reminder that I'm mainly t[oo|wee]ting on Mastodon these days: mastodon.social/@gmarkall

Graham Markall (@[email protected])

414 Posts, 420 Following, 321 Followers · Professional interests: Python, CUDA, Compilers. Personal interests: RISC-V, PSXDev, OSHW, 日本語. Recreation: family time, cycling, running, cooking.

mastodon.social
3
372
Me on Mastodon: mastodon.social/@gmarkall I don't plan to disable this account, but I'm generally posting there these days.

Graham Markall (@[email protected])

414 Posts, 420 Following, 321 Followers · Professional interests: Python, CUDA, Compilers. Personal interests: RISC-V, PSXDev, OSHW, 日本語. Recreation: family time, cycling, running, cooking.

mastodon.social
1
2
549
Do you know about automatic differentiation and / or Enzyme? Could you help sketch out how AD support for @numba_jit could be implemented? Issue / thread: github.com/numba/numba/issue…

Autodiff support in Numba · Issue #8565 · numba/numba

Feature request It would be great if Numba supported automatic differentiation. Maybe using Enzyme would be the easiest way as it operates directly on the IR of LLVM. Another possible source of ins...

github.com
2
2
5
I've been on Mastodon a while but I got out of the habit of using it - this is my account that I'm starting to get active with again: mastodon.social/@gmarkall (is this usually written as @[email protected]?). It has an old profile pic, still need to upload my current one.

Graham Markall (@[email protected])

414 Posts, 420 Following, 321 Followers · Professional interests: Python, CUDA, Compilers. Personal interests: RISC-V, PSXDev, OSHW, 日本語. Recreation: family time, cycling, running, cooking.

mastodon.social
2
I've been experimenting with using CUDA Unified Memory for the Python heap, towards a general goal of experimenting with a more unified CPU / GPU execution model within CPython, implemented as PyMemAllocatorEx instances. I have a few thoughts so far...
1
6
more replies
5. "CPython Internals" by @anthonypjshaw is a great intro / reference to CPython, saved me a lot of time, and got me up to speed quickly for this endeavour. Highly recommended if you want to poke about with this sort of stuff! (realpython.com/products/cpyt…)

CPython Internals Book – Real Python

Unlock the inner workings of the Python language, compile the Python interpreter from source code, and participate in the development of CPython. The "CPython Internals" book shows you exactly how.

realpython.com
1
3
6. Finally, maybe this should have been a blog post with some code! Would that be interesting? What else should be answered / elaborated on if I write this up?
2
7
Graham Markall retweeted
RAPIDS AI@RAPIDSai26 Oct 2022
Do more on GPUs with less code - check out @gmarkall's new blog on the @numba_jit high-level API medium.com/rapids-ai/extendi…
10
1
20
Graham Markall retweeted
Numba@numba_jit25 Oct 2022
Public service announcement: Yes, the Numba team is aware of the Python 3.11 release. 💥 Yes, we are working on it. 💪Please refrain from opening additional Issues on our tracker and subscribe instead to github.com/numba/llvmlite/pu… and github.com/numba/numba/issue… 🙏🙏🙏
1
3
1
34
Lil identify xei9pa2AeQu6
Jeff Geerling
@geerlingguy18 Oct 2022
your rap name is "lil" + the last message you sent in IRC
2
Do you use the GPU in Python? If so, for what, and what library do you use? 🤔
51
21
289
"Use a font that is way too small" - every corporate Powerpoint template for technical talks ever
1
With @numba_jit 0.56 you can use the High-level API to extend the CUDA target. Much simpler to use than the low-level API, this notebook shows how to use it for some quick examples: github.com/gmarkall/extendin… HLA docs: numba.readthedocs.io/en/stab… Pic: using it to implement clock64()
Implementation of the clock64() CUDA function using Numba's High-level API

ALT Implementation of the clock64() CUDA function using Numba's High-level API

1
2
12
Money-saving tip: instead of buying an expensive chef's knife, simply take a PCIe slot blanking plate out of a cheap PC case.
21
Load more