* SEND specialization. Adds 2 new specialized instructions:
* SEND_VIRTUAL: for sends to virtual iterators e.g lists and tuples
* SEND_ASYNC_GEN: for sends to async generators
Tweak FOR_ITER_VIRTUAL so that SEND_VIRTUAL and FOR_ITER_VIRTUAL use equivalent guards
The function__entry and function__return probes stopped working in Python 3.11
when the interpreter was restructured around the new bytecode system. This change
restores these probes by adding DTRACE_FUNCTION_ENTRY() at the start_frame label
in bytecodes.c and DTRACE_FUNCTION_RETURN() in the RETURN_VALUE and YIELD_VALUE
instructions. The helper functions are defined in ceval.c and extract the
filename, function name, and line number from the frame before firing the probe.
This builds on the approach from https://github.com/python/cpython/pull/125019
but avoids modifying the JIT template since the JIT does not currently support
DTrace. The macros are conditionally compiled with WITH_DTRACE and are no-ops
otherwise. The tests have been updated to use modern opcode names (CALL, CALL_KW,
CALL_FUNCTION_EX) and a new bpftrace backend was added for Linux CI alongside
the existing SystemTap tests. Line probe tests were removed since that probe
was never restored after 3.11.
* Add FOR_ITER_VIRTUAL to specialize FOR_ITER for virtual iterators
* Add GET_ITER_SELF to specialize GET_ITER for iterators (including generators)
* Add GET_ITER_VIRTUAL to specialize GET_ITER for iterables as virtual iterators
* Add new (internal) _tp_iteritem function slot to PyTypeObject
* Put limited RESUME at start of genexpr for free-threading. Fix up exception handling in genexpr
This PR changes the current JIT model from trace projection to trace recording. Benchmarking: better pyperformance (about 1.7% overall) geomean versus current https://raw.githubusercontent.com/facebookexperimental/free-threading-benchmarking/refs/heads/main/results/bm-20251108-3.15.0a1%2B-7e2bc1d-JIT/bm-20251108-vultr-x86_64-Fidget%252dSpinner-tracing_jit-3.15.0a1%2B-7e2bc1d-vs-base.svg, 100% faster Richards on the most improved benchmark versus the current JIT. Slowdown of about 10-15% on the worst benchmark versus the current JIT. **Note: the fastest version isn't the one merged, as it relies on fixing bugs in the specializing interpreter, which is left to another PR**. The speedup in the merged version is about 1.1%. https://raw.githubusercontent.com/facebookexperimental/free-threading-benchmarking/refs/heads/main/results/bm-20251112-3.15.0a1%2B-f8a764a-JIT/bm-20251112-vultr-x86_64-Fidget%252dSpinner-tracing_jit-3.15.0a1%2B-f8a764a-vs-base.svg
Stats: 50% more uops executed, 30% more traces entered the last time we ran them. It also suggests our trace lengths for a real trace recording JIT are too short, as a lot of trace too long aborts https://github.com/facebookexperimental/free-threading-benchmarking/blob/main/results/bm-20251023-3.15.0a1%2B-eb73378-CLANG%2CJIT/bm-20251023-vultr-x86_64-Fidget%252dSpinner-tracing_jit-3.15.0a1%2B-eb73378-pystats-vs-base.md .
This new JIT frontend is already able to record/execute significantly more instructions than the previous JIT frontend. In this PR, we are now able to record through custom dunders, simple object creation, generators, etc. None of these were done by the old JIT frontend. Some custom dunders uops were discovered to be broken as part of this work gh-140277
The optimizer stack space check is disabled, as it's no longer valid to deal with underflow.
Pros:
* Ignoring the generated tracer code as it's automatically created, this is only additional 1k lines of code. The maintenance burden is handled by the DSL and code generator.
* `optimizer.c` is now significantly simpler, as we don't have to do strange things to recover the bytecode from a trace.
* The new JIT frontend is able to handle a lot more control-flow than the old one.
* Tracing is very low overhead. We use the tail calling interpreter/computed goto interpreter to switch between tracing mode and non-tracing mode. I call this mechanism dual dispatch, as we have two dispatch tables dispatching to each other. Specialization is still enabled while tracing.
* Better handling of polymorphism. We leverage the specializing interpreter for this.
Cons:
* (For now) requires tail calling interpreter or computed gotos. This means no Windows JIT for now :(. Not to fret, tail calling is coming soon to Windows though https://github.com/python/cpython/pull/139962
Design:
* After each instruction, the `record_previous_inst` function/label is executed. This does as the name suggests.
* The tracing interpreter lowers bytecode to uops directly so that it can obtain "fresh" values at the point of lowering.
* The tracing version behaves nearly identical to the normal interpreter, in fact it even has specialization! This allows it to run without much of a slowdown when tracing. The actual cost of tracing is only a function call and writes to memory.
* The tracing interpreter uses the specializing interpreter's deopt to naturally form the side exit chains. This allows it to side exit chain effectively, without repeating much code. We force a re-specializing when tracing a deopt.
* The tracing interpreter can even handle goto errors/exceptions, but I chose to disable them for now as it's not tested.
* Because we do not share interpreter dispatch, there is should be no significant slowdown to the original specializing interpreter on tailcall and computed got with JIT disabled. With JIT enabled, there might be a slowdown in the form of the JIT trying to trace.
* Things that could have dynamic instruction pointer effects are guarded on. The guard deopts to a new instruction --- `_DYNAMIC_EXIT`.
Optimize `LOAD_FAST` opcodes into faster versions that load borrowed references onto the operand stack when we can prove that the lifetime of the local outlives the lifetime of the temporary that is loaded onto the stack.
* Remove all 'if (0)' and 'if (1)' conditional stack effects
* Use array instead of conditional for BUILD_SLICE args
* Refactor LOAD_GLOBAL to use a common conditional uop
* Remove conditional stack effects from LOAD_ATTR specializations
* Replace conditional stack effects in LOAD_ATTR with a 0 or 1 sized array.
* Remove conditional stack effects from CALL_FUNCTION_EX
* Spill the evaluation around escaping calls in the generated interpreter and JIT.
* The code generator tracks live, cached values so they can be saved to memory when needed.
* Spills the stack pointer around escaping calls, so that the exact stack is visible to the cycle GC.
The PEP 649 implementation will require a way to load NotImplementedError
from the bytecode. @markshannon suggested implementing this by converting
LOAD_ASSERTION_ERROR into a more general mechanism for loading constants.
This PR adds this new opcode. I will work on the rest of the implementation
of the PEP separately.
Co-authored-by: Irit Katriel <[email protected]>
* Add CALL_PY_GENERAL, CALL_BOUND_METHOD_GENERAL and call CALL_NON_PY_GENERAL specializations.
* Remove CALL_PY_WITH_DEFAULTS specialization
* Use CALL_NON_PY_GENERAL in more cases when otherwise failing to specialize
