Choose number of replications based on data
未關閉
@mdboom 已經在處理了。
開始於 2024年4月9日。
3.13
interpreter-core
performance
- 主要語言
- Python
- 星號
- 77.2k
- 分支
- 36k
- PR 合併指標
- PR 指標待擷取
描述
Currently we replicate the LOAD_FAST and STORE_FAST instructions 8 times (for opargs 0-7). The _INIT_CALL_PY_EXACT_ARGS micro-op gets replicated 5 times.
These numbers were chosen arbitrarily as initial values to test replication.
We should choose the number of replications based on actual data.
We should also look into replicating COPY and SWAP, as it is much simpler to do stack caching on instructions with a fixed stack effect.
E.g. SWAP indexes the stack using oparg, but SWAP_2 is simply SWAP_2(left, right -- right, left).
貢獻指南
從這裡開始
- 先讀完整個 Issue,再讀專案的貢獻指南。
- 在 Issue 下留言說明你要接手 —— 這能避免兩個人做同樣的事。
- Fork 儲存庫,在一個分支上完成修改。
- 送出 Pull Request,並在描述裡引用這個 Issue 編號。
評估
這個 Issue 還沒有評估資料。