Viewing profile — nicovasilache
nicovasilache
HN member- Joined
- Wed, Feb 14, 2018, 9:29 PM UTC
- HN karma
- 17
- Public activity
- 7 items
- HN profile
- View on Hacker News ↗
About nicovasilache
No profile information was provided.
Recent public activity
-
comment
Comment #16381326
Python bindings are in there :) This needs a tensor library callable from python that works on GPUs. One direction we are going towards is PyTorch via ATen / Torch tensors; we alre…
-
comment
Comment #16381274
This is one reason I also prefer to call TC a notation personally. We can't allocate and declare inside TC, that may change in the future but for now we went for the easiest entry …
-
comment
Comment #16381259
@phaedrus take a look at Weld from Stanford then, may also be useful to you. Edit: in addition to what @ozinenko pointed to of course..
-
comment
Comment #16380172
The thing is that compilers usually quickly go to SSA form and it is not the best IR to optimize loops in. Then you fight it to extract a high-level IR and this little process make…
-
comment
Comment #16380140
punchcards .. days .. ouch that's painful :)
-
comment
Comment #16379787
Hello, evolutionary algorithms by themselves I am not sure and don't have enough experience with atm. In our particular context the key is the intermediate representation on which …
-
comment
Comment #16379684
Hello, Tensor Comprehensions absolutely use techniques that have been existing for a few years (Halide) or many decades (polyhedral model, Einstein notation(century old?), ...). Th…