mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-08-31 05:58:33 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 7

Update adaptive.md for inline caching (GH-31817)

Browse source
This commit is contained in:
Mark Shannon 2022-03-11 14:29:10 +00:00 • committed by GitHub
parent 54ab9ad312
commit 4f74ffc5e3
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 20 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

29
Python/adaptive.md
View file

@ -14,16 +14,16 @@ A family of instructions has the following fundamental properties:
it executes the non-adaptive instruction. it executes the non-adaptive instruction.
* It has at least one specialized form of the instruction that is tailored * It has at least one specialized form of the instruction that is tailored
for a particular value or set of values at runtime. for a particular value or set of values at runtime.
* All members of the family have access to the same number of cache entries. * All members of the family must have the same number of inline cache entries,
Individual family members do not need to use all of the entries. to ensure correct execution.
Individual family members do not need to use all of the entries,
but must skip over any unused entries when executing.
The current implementation also requires the following, The current implementation also requires the following,
although these are not fundamental and may change: although these are not fundamental and may change:
* If a family uses one or more entries, then the first entry must be a * All families uses one or more inline cache entries,
`_PyAdaptiveEntry` entry. the first entry is always the counter.
* If a family uses no cache entries, then the `oparg` is used as the
counter for the adaptive instruction.
* All instruction names should start with the name of the non-adaptive * All instruction names should start with the name of the non-adaptive
instruction. instruction.
* The adaptive instruction should end in `_ADAPTIVE`. * The adaptive instruction should end in `_ADAPTIVE`.
@ -76,6 +76,10 @@ keeping `Ti` low which means minimizing branches and dependent memory
accesses (pointer chasing). These two objectives may be in conflict, accesses (pointer chasing). These two objectives may be in conflict,
requiring judgement and experimentation to design the family of instructions. requiring judgement and experimentation to design the family of instructions.
The size of the inline cache should as small as possible,
without impairing performance, to reduce the number of
`EXTENDED_ARG` jumps, and to reduce pressure on the CPU's data cache.
### Gathering data ### Gathering data
Before choosing how to specialize an instruction, it is important to gather Before choosing how to specialize an instruction, it is important to gather
@ -106,7 +110,7 @@ This can be tested quickly:
* `globals->keys->dk_version == expected_version` * `globals->keys->dk_version == expected_version`
and the operation can be performed quickly: and the operation can be performed quickly:
* `value = globals->keys->entries[index].value`. * `value = entries[cache->index].me_value;`.
Because it is impossible to measure the performance of an instruction without Because it is impossible to measure the performance of an instruction without
also measuring unrelated factors, the assessment of the quality of a also measuring unrelated factors, the assessment of the quality of a
@ -119,8 +123,7 @@ base instruction.
In general, specialized instructions should be implemented in two parts: In general, specialized instructions should be implemented in two parts:
1. A sequence of guards, each of the form 1. A sequence of guards, each of the form
`DEOPT_IF(guard-condition-is-false, BASE_NAME)`, `DEOPT_IF(guard-condition-is-false, BASE_NAME)`.
followed by a `record_cache_hit()`.
2. The operation, which should ideally have no branches and 2. The operation, which should ideally have no branches and
a minimum number of dependent memory accesses. a minimum number of dependent memory accesses.
@ -129,3 +132,11 @@ can be re-used in the operation.
If there are branches in the operation, then consider further specialization If there are branches in the operation, then consider further specialization
to eliminate the branches. to eliminate the branches.
### Maintaining stats
Finally, take care that stats are gather correctly.
After the last `DEOPT_IF` has passed, a hit should be recorded with
`STAT_INC(BASE_INSTRUCTION, hit)`.
After a optimization has been deferred in the `ADAPTIVE` form,
that should be recorded with `STAT_INC(BASE_INSTRUCTION, deferred)`.