◐ Shell
reader mode source ↗
Skip to content

gh-111786: Use separate opcode vars for Tier 1 and Tier 2#112289

Merged
gvanrossum merged 2 commits into
python:mainfrom
mdboom:alternative-workaround
Nov 20, 2023
Merged

gh-111786: Use separate opcode vars for Tier 1 and Tier 2#112289
gvanrossum merged 2 commits into
python:mainfrom
mdboom:alternative-workaround

Conversation

@mdboom

@mdboom mdboom commented Nov 20, 2023 •
edited by bedevere-app Bot
Loading

Copy link
Copy Markdown
Contributor

Suggested by @neonene: #111786 (comment)

This makes Windows about 3% faster on pyperformance benchmarks. See analysis here

@bedevere-app bedevere-app Bot mentioned this pull request Nov 20, 2023
Closed
@mdboom mdboom force-pushed the alternative-workaround branch from 00a506a to 27a5654 Compare November 20, 2023 20:24
@mdboom
pythongh-111786: Use separate opcode vars for Tier 1 and Tier 2 …
f362f9a 
This makes Windows about 3% faster on pyperformance benchmarks.
@mdboom mdboom force-pushed the alternative-workaround branch from 27a5654 to f362f9a Compare November 20, 2023 20:26
gvanrossum
gvanrossum approved these changes Nov 20, 2023
View reviewed changes

@gvanrossum gvanrossum left a comment

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Hide comment

Nice, looks very straightforward.

Though based on our offline conversation, did you find out whether Windows PGO uses -E?

@mdboom

mdboom commented Nov 20, 2023 •
edited
Loading

Copy link
Copy Markdown
Contributor Author

Though based on our offline conversation, did you find out whether Windows PGO uses -E?

I don't know, but I think that's orthogonal to this. Currently on the benchmarking infrastructure, we only pass the PYTHON_UOPS env variable to pyperformance, so it definitely has no effect during build. Independently of this, I measured what happens when you force Tier 2 on during the build, and it is about 1% faster.

@gvanrossum

gvanrossum commented Nov 20, 2023

Copy link
Copy Markdown
Member

Though based on our offline conversation, did you find out whether Windows PGO uses -E?

I don't know, but I think that's orthogonal to this. Currently on the benchmarking infrastructure, we don't pass the PYTHON_UOPS env variable to pyperformance, so it definitely has no effect during build.

Ah, sorry. Should I merge this then?

Independently of this, I measured what happens when you force Tier 2 on during the build, and it is about 1% faster.

1% faster than without Tier 2, or 1% faster than main?

@mdboom

mdboom commented Nov 20, 2023

Copy link
Copy Markdown
Contributor Author

Though based on our offline conversation, did you find out whether Windows PGO uses -E?

I don't know, but I think that's orthogonal to this. Currently on the benchmarking infrastructure, we don't pass the PYTHON_UOPS env variable to pyperformance, so it definitely has no effect during build.

Ah, sorry. Should I merge this then?

Yeah, I think that's fine.

Independently of this, I measured what happens when you force Tier 2 on during the build, and it is about 1% faster.

1% faster than without Tier 2, or 1% faster than main?

When you turn Tier 2 on during build (PGO collection), it's 1% faster than if you don't. (Using Tier 2 at runtime in both cases).

@gvanrossum

gvanrossum commented Nov 20, 2023

Copy link
Copy Markdown
Member

When you turn Tier 2 on during build (PGO collection), it's 1% faster than if you don't. (Using Tier 2 at runtime in both cases).

That's great news!

@gvanrossum gvanrossum merged commit 6a00a58 into python:main Nov 20, 2023
aisk pushed a commit to aisk/cpython that referenced this pull request Feb 11, 2024
@mdboom @aisk
pythongh-111786: Use separate opcode vars for Tier 1 and Tier 2 (pyth… …
95de6df 
…on#112289)

This makes Windows about 3% faster on pyperformance benchmarks.
Glyphack pushed a commit to Glyphack/cpython that referenced this pull request Sep 2, 2024
@mdboom @Glyphack
pythongh-111786: Use separate opcode vars for Tier 1 and Tier 2 (pyth… …
c64d740 
…on#112289)

This makes Windows about 3% faster on pyperformance benchmarks.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@gvanrossum gvanrossum

@markshannon markshannon Awaiting requested review from markshannon markshannon is a code owner

Assignees

No one assigned

Labels

skip news

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@mdboom @gvanrossum