[inductor] add decompositions for aten.angle #105609
Closed
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/105609
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit bed8776: This comment was automatically generated by Dr. CI and updates every 15 minutes. |
jansel
approved these changes
Jul 19, 2023
torch/_inductor/decomposition.py
Outdated
| # if x >= 0, return 0 | ||
| # if x < 0, return pi | ||
| # if x is nan, return nan | ||
| ret = torch.where(x.real < 0, math.pi, 0.0) |
There was a problem hiding this comment.
Suggested change
| ret = torch.where(x.real < 0, math.pi, 0.0) | |
| ret = torch.where(x < 0, math.pi, 0.0) |
|
Can you show an example of the output code? For complex numbers we might just end up using fallbacks. |
Sure! For below code: import torch
@torch.compile
def f(x):
return torch.angle(x)
x = torch.tensor([-1, 1, 0, float("inf"), 1j]) # 1j is complex.
f(x)The output is following. Is it a fallback? It seems properly handled at least for CPU. |
|
Looks good, thanks! |
|
@pytorchbot merge |
Merge startedYour change will be merged once all checks pass (ETA 0-4 Hours). Learn more about merging in the wiki. Questions? Feedback? Please reach out to the PyTorch DevX Team |
pytorchmergebot
pushed a commit
that referenced
this pull request
Oct 24, 2023
Tracks #98161 Complex number support in Pytorch isn't ideal today as complex operations will mostly end up taken care of by the aten runtime, except for `torch.angle` which is handled in [105609](#105609). In general a better way to handle that could be to decompose complex operations first so that more opportunities for fusion could be unveiled, and then to have Triton take care of non-continuous (strided) tensor operations more efficiently. This change adds support to decompose complex addtions. ``` @triton.jit def triton_(in_ptr0, in_ptr1, out_ptr0, xnumel, XBLOCK : tl.constexpr): xnumel = 6 xoffset = tl.program_id(0) * XBLOCK xindex = xoffset + tl.arange(0, XBLOCK)[:] xmask = xindex < xnumel x0 = xindex tmp0 = tl.load(in_ptr0 + (x0), xmask) tmp1 = tl.load(in_ptr1 + (x0), xmask) tmp2 = tmp0 + tmp1 tl.store(out_ptr0 + (x0), tmp2, xmask) ``` Pull Request resolved: #110740 Approved by: https://github.com/jansel
xuhancn
pushed a commit
to xuhancn/pytorch
that referenced
this pull request
Nov 7, 2023
Tracks pytorch#98161 Complex number support in Pytorch isn't ideal today as complex operations will mostly end up taken care of by the aten runtime, except for `torch.angle` which is handled in [105609](pytorch#105609). In general a better way to handle that could be to decompose complex operations first so that more opportunities for fusion could be unveiled, and then to have Triton take care of non-continuous (strided) tensor operations more efficiently. This change adds support to decompose complex addtions. ``` @triton.jit def triton_(in_ptr0, in_ptr1, out_ptr0, xnumel, XBLOCK : tl.constexpr): xnumel = 6 xoffset = tl.program_id(0) * XBLOCK xindex = xoffset + tl.arange(0, XBLOCK)[:] xmask = xindex < xnumel x0 = xindex tmp0 = tl.load(in_ptr0 + (x0), xmask) tmp1 = tl.load(in_ptr1 + (x0), xmask) tmp2 = tmp0 + tmp1 tl.store(out_ptr0 + (x0), tmp2, xmask) ``` Pull Request resolved: pytorch#110740 Approved by: https://github.com/jansel
Skylion007
pushed a commit
to Skylion007/pytorch
that referenced
this pull request
Nov 14, 2023
Tracks pytorch#98161 Complex number support in Pytorch isn't ideal today as complex operations will mostly end up taken care of by the aten runtime, except for `torch.angle` which is handled in [105609](pytorch#105609). In general a better way to handle that could be to decompose complex operations first so that more opportunities for fusion could be unveiled, and then to have Triton take care of non-continuous (strided) tensor operations more efficiently. This change adds support to decompose complex addtions. ``` @triton.jit def triton_(in_ptr0, in_ptr1, out_ptr0, xnumel, XBLOCK : tl.constexpr): xnumel = 6 xoffset = tl.program_id(0) * XBLOCK xindex = xoffset + tl.arange(0, XBLOCK)[:] xmask = xindex < xnumel x0 = xindex tmp0 = tl.load(in_ptr0 + (x0), xmask) tmp1 = tl.load(in_ptr1 + (x0), xmask) tmp2 = tmp0 + tmp1 tl.store(out_ptr0 + (x0), tmp2, xmask) ``` Pull Request resolved: pytorch#110740 Approved by: https://github.com/jansel
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Fixes #105564.
Added tests.
CPU benchmarking result:
Before decomposition:
After decomposition:
cc @voznesenskym @penguinwu @EikanWang @jgong5 @Guobing-Chen @XiaobingSuper @zhuhaozhe @blzheng @Xia-Weiwen @wenzhe-nrv @jiayisunx @peterbell10 @ipiszy @ngimel @yf225 @chenyang78 @kadeng @muchulee8 @aakhundov