Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Add performance measurement of each intrinsic function #18

Open
marktwtn opened this issue Feb 4, 2020 · 2 comments
Open

Add performance measurement of each intrinsic function #18

marktwtn opened this issue Feb 4, 2020 · 2 comments
Assignees
@marktwtn

Comments

@marktwtn
Copy link
Collaborator

marktwtn commented Feb 4, 2020

The conversion of intrinsic function may be rewritten sometimes.
A performance measurement result is good for checking whether the rewritten conversion behaves better or not.
@marktwtn marktwtn self-assigned this Feb 4, 2020
sebpop pushed a commit to sebpop/sse2neon that referenced this issue May 22, 2020
@ines @honnibal
Fix CI for Windows (DLTcollab#18)
02ac486 
* Update windows-x86_64.jsonl

* Update azure-pipelines.yml

* Delete .appveyor_generate_make.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Debug windows build

* Experiment

* Try adding conda-forge scripts

* Try using build from blis conda-forge

* Fix yaml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update build.sh

* Update build.sh

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update build.sh

* Update azure-pipelines.yml

* Update build.sh

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update setup.py

* Update setup.py

* Update azure-pipelines.yml

* Update setup.py

* Update setup.py

* Update setup.py

* Update setup.py

* Update azure-pipelines.yml

* Update setup.py

* Update windows-x86_64.jsonl

* Update azure-pipelines.yml

* Update windows-x86_64.jsonl

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update setup.py

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Update azure-pipelines.yml

* Reorganize old CI files

* Update azure-pipelines.yml

* Update setup.py

* Update azure-pipelines.yml

* Update setup.py

* Update setup.py

* Update azure-pipelines.yml

* Update README.md [ci skip]

* Update azure-pipelines.yml


Co-authored-by: Matthew Honnibal <[email protected]>
@emoon
Copy link

emoon commented Jun 22, 2022

Somewhat related, but not exactly the same:

Something would be nice would be to have a list of all the implemented intrinsics and to how many NEON intrinsics that is needed to implement it. While this doesn't give you a 1:1 mapping to how fast something is, it still gives the user and idea what might be good to avoid.

@Starbuck5
Copy link

Starbuck5 commented Mar 26, 2023 •
edited
Loading

In in a similar view, the emscripten SIMD page (https://emscripten.org/docs/porting/simd.html) has an emoji for each instruction.

✅ Wasm SIMD has a native opcode that matches the x86 SSE instruction, should yield native performance

💡 while the Wasm SIMD spec does not provide a proper performance guarantee, given a suitably smart enough compiler and a runtime VM path, this intrinsic should be able to generate the identical native SSE instruction.

🟡 there is some information missing (e.g. type or alignment information) for a Wasm VM to be guaranteed to be able to reconstruct the intended x86 SSE opcode. This might cause a penalty depending on the target CPU hardware family, especially on older CPU generations.

⚠️ the underlying x86 SSE instruction is not available, but it is emulated via at most few other Wasm SIMD instructions, causing a small penalty.

❌ the underlying x86 SSE instruction is not exposed by the Wasm SIMD specification, so it must be emulated via a slow path, e.g. a sequence of several slower SIMD instructions, or a scalar implementation.

💣 the underlying x86 SSE opcode is not available in Wasm SIMD, and the implementation must resort to such a slow emulated path, that a workaround rethinking the algorithm at a higher level is advised.

💭 the given SSE intrinsic is available to let applications compile, but does nothing.

⚫ the given SSE intrinsic is not available. Referencing the intrinsic will cause a compiler error.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@marktwtn marktwtn

Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@emoon @marktwtn @Starbuck5