perf: Threadify Rust interpreter #349
Merged
Conversation
This file contains 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
This change leverages a technique named "threaded interpreter" to speedup the Rust interpreter. Basically, it splits a giant match statement into multiple smaller individual functions, each handling a specific opcode. When we have a group of opcodes(e.g., a basic block), we can extract the handler function(also named "thread") for each instruction's opcode. Then we can simple run each handler function to execute each instructions. This way we can aid CPU's branch predictor to better predict what code to execute next. Note this work is inspired from @mohanson's original work at here: nervosnetwork@8422373 Reference: * http://www.emulators.com/docs/nx25_nostradamus.htm
|
Testing on a Ryzen 3900x, this change brings 10% performance boost to the Rust interpreter benchmarking secp256k1: |
xxuejie
force-pushed
the
threadify-rust-interpreter
branch
from
e5b2e17
to
26dbf92
Compare
mohanson
approved these changes
Jun 7, 2023
mohanson
pushed a commit
to libraries/ckb-vm
that referenced
this pull request
Jul 21, 2023
* perf: Threadify Rust interpreter This change leverages a technique named "threaded interpreter" to speedup the Rust interpreter. Basically, it splits a giant match statement into multiple smaller individual functions, each handling a specific opcode. When we have a group of opcodes(e.g., a basic block), we can extract the handler function(also named "thread") for each instruction's opcode. Then we can simple run each handler function to execute each instructions. This way we can aid CPU's branch predictor to better predict what code to execute next. Note this work is inspired from @mohanson's original work at here: nervosnetwork@8422373 Reference: * http://www.emulators.com/docs/nx25_nostradamus.htm * test: Add a test to ensure opcodes are defined sequentially
mohanson
pushed a commit
that referenced
this pull request
Jul 21, 2023
* perf: Threadify Rust interpreter This change leverages a technique named "threaded interpreter" to speedup the Rust interpreter. Basically, it splits a giant match statement into multiple smaller individual functions, each handling a specific opcode. When we have a group of opcodes(e.g., a basic block), we can extract the handler function(also named "thread") for each instruction's opcode. Then we can simple run each handler function to execute each instructions. This way we can aid CPU's branch predictor to better predict what code to execute next. Note this work is inspired from @mohanson's original work at here: 8422373 Reference: * http://www.emulators.com/docs/nx25_nostradamus.htm * test: Add a test to ensure opcodes are defined sequentially
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
This change leverages a technique named "threaded interpreter" to speedup the Rust interpreter. Basically, it splits a giant match statement into multiple smaller individual functions, each handling a specific opcode. When we have a group of opcodes(e.g., a basic block), we can extract the handler function(also named "thread") for each instruction's opcode. Then we can simple run each handler function to execute each instructions. This way we can aid CPU's branch predictor to better predict what code to execute next.
Note this work is inspired from @mohanson's original work at here:
8422373
Reference: