bm-20241025-azure-x86_64-brandtbucher-justin_no_externs-3.14.0a1+-64b198a-pystats-generators-vs-base.md

Execution counts

Execution counts for Tier 1 instructions.

The "miss ratio" column shows the percentage of times the instruction executed that it deoptimized. When this happens, the base unspecialized instruction is not counted.

Name	Base Count	Head Count	Change
YIELD_VALUE	376,548,780	376,548,780	0.0%
LOAD_FAST	57,740,640	57,740,640	0.0%
STORE_FAST	42,002,880	42,002,880	0.0%
LOAD_CONST	36,006,060	36,006,060	0.0%
RETURN_CONST	36,002,100	36,002,100	0.0%
LOAD_FAST_LOAD_FAST	30,003,300	30,003,300	0.0%
ENTER_EXECUTOR	24,021,360	24,021,360	0.0%
POP_TOP	24,004,920	24,004,920	0.0%
INTERPRETER_EXIT	24,001,260	24,001,260	0.0%
RETURN_GENERATOR	24,000,600	24,000,600	0.0%
END_SEND	24,000,300	24,000,300	0.0%
RESUME_CHECK	18,021,580	18,021,580	0.0%
LOAD_GLOBAL_MODULE	18,002,220	18,002,220	0.0%
STORE_ATTR_INSTANCE_VALUE	18,001,800	18,001,800	0.0%
LOAD_ATTR_INSTANCE_VALUE	15,735,000	15,735,000	0.0%
POP_JUMP_IF_FALSE	12,005,800	12,005,800	0.0%
LOAD_GLOBAL_BUILTIN	12,001,680	12,001,680	0.0%
CALL_PY_EXACT_ARGS	12,001,560	12,001,560	0.0%
RETURN_VALUE	12,001,440	12,001,440	0.0%
CALL_LEN	12,001,320	12,001,320	0.0%
COMPARE_OP_INT	12,001,320	12,001,320	0.0%
BINARY_SLICE	12,001,200	12,001,200	0.0%
BINARY_SUBSCR	6,002,080	6,002,080	0.0%
BINARY_OP	6,002,080	6,002,080	0.0%
EXIT_INIT_CHECK	6,000,600	6,000,600	0.0%
BINARY_OP_ADD_INT	6,000,600	6,000,600	0.0%
CALL_ALLOC_AND_ENTER_INIT	6,000,600	6,000,600	0.0%
SEND_GEN	16,380	16,380	0.0%
JUMP_BACKWARD_NO_INTERRUPT	14,820	14,820	0.0%
TO_BOOL_NONE	2,960	2,960	0.0%
GET_YIELD_FROM_ITER	1,560	1,560	0.0%
TO_BOOL_ALWAYS_TRUE	1,500	1,500	0.0%
PUSH_NULL	420	420	0.0%
CALL	400	400	0.0%
CALL_BUILTIN_CLASS	360	360	0.0%
JUMP_BACKWARD	320	320	0.0%
GET_ITER	300	300	0.0%
LOAD_ATTR	300	300	0.0%
CALL_NON_PY_GENERAL	300	300	0.0%
FOR_ITER_RANGE	280	280	0.0%
LOAD_GLOBAL	260	260	0.0%
FOR_ITER_GEN	260	260	0.0%
END_FOR	240	240	0.0%
LOAD_ATTR_MODULE	240	240	0.0%
BUILD_TUPLE	120	120	0.0%
CALL_FUNCTION_EX	120	120	0.0%
LOAD_DEREF	120	120	0.0%
POP_JUMP_IF_TRUE	120	120	0.0%
LOAD_ATTR_METHOD_NO_DICT	120	120	0.0%
LOAD_ATTR_METHOD_WITH_VALUES	120	120	0.0%
TO_BOOL	100	100	0.0%
COMPARE_OP	80	80	0.0%
MAKE_FUNCTION	60	60	0.0%
NOP	60	60	0.0%
BUILD_LIST	60	60	0.0%
CALL_INTRINSIC_1	60	60	0.0%
COPY_FREE_VARS	60	60	0.0%
FOR_ITER	60	60	0.0%
IS_OP	60	60	0.0%
JUMP_FORWARD	60	60	0.0%
LIST_EXTEND	60	60	0.0%
MAKE_CELL	60	60	0.0%
POP_JUMP_IF_NOT_NONE	60	60	0.0%
SET_FUNCTION_ATTRIBUTE	60	60	0.0%
STORE_DEREF	60	60	0.0%
STORE_FAST_STORE_FAST	60	60	0.0%
BINARY_OP_SUBTRACT_FLOAT	60	60	0.0%
BINARY_SUBSCR_TUPLE_INT	60	60	0.0%
CALL_METHOD_DESCRIPTOR_NOARGS	60	60	0.0%
CALL_METHOD_DESCRIPTOR_O	60	60	0.0%
CALL_PY_GENERAL	60	60	0.0%
TO_BOOL_BOOL	60	60	0.0%
UNPACK_SEQUENCE_TWO_TUPLE	60	60	0.0%
UNPACK_SEQUENCE	20	20	0.0%

Pair counts

Pair counts for top 100 opcode pairs

Pairs of specialized operations that deoptimize and are then followed by the corresponding unspecialized instruction are not counted as pairs.

Not included in comparative output.

Predecessor/Successor Pairs

Top 5 predecessors and successors of each Tier 1 opcode.

This does not include the unspecialized instructions that occur after a specialized instruction deoptimizes.

Not included in comparative output.

Specialization stats

Specialization stats by family

BINARY_OP

specialization stats for BINARY_OP family

Kind	Base Count	Base Ratio	Head Count	Head Ratio	Change
deferred ⓘ Lists the number of "deferred" (i.e. not specialized) instructions executed.	6,000,600	50.0%	6,000,600	50.0%	0.0%
hit ⓘ Specialized instructions that complete.	6,000,660	50.0%	6,000,660	50.0%	0.0%

Success	Base Count	Base Ratio	Head Count	Head Ratio	Change
Success	20	1.4%	20	1.4%	0.0%
Failure	1,460	98.6%	1,460	98.6%	0.0%

Failure kind	Base Count	Base Ratio	Head Count	Head Ratio	Change
floor divide	1,460	100.0%	1,460	100.0%	0.0%

BINARY_SLICE

specialization stats for BINARY_SLICE family

Kind	Base Count	Base Ratio	Head Count	Head Ratio	Change
deferred ⓘ Lists the number of "deferred" (i.e. not specialized) instructions executed.	12,001,200	100.0%	12,001,200	100.0%	0.0%

BINARY_SUBSCR

specialization stats for BINARY_SUBSCR family

Kind	Base Count	Base Ratio	Head Count	Head Ratio	Change
deferred ⓘ Lists the number of "deferred" (i.e. not specialized) instructions executed.	6,000,600	100.0%	6,000,600	100.0%	0.0%
hit ⓘ Specialized instructions that complete.	60	0.0%	60	0.0%	0.0%

Success	Base Count	Base Ratio	Head Count	Head Ratio	Change
Success	20	1.4%	20	1.4%	0.0%
Failure	1,460	98.6%	1,460	98.6%	0.0%

Failure kind	Base Count	Base Ratio	Head Count	Head Ratio	Change
sequence int	1,460	100.0%	1,460	100.0%	0.0%

CALL

specialization stats for CALL family

Kind	Base Count	Base Ratio	Head Count	Head Ratio	Change
hit ⓘ Specialized instructions that complete.	30,003,960	100.0%	30,003,960	100.0%	0.0%

Success	Base Count	Base Ratio	Head Count	Head Ratio	Change
Success	400	100.0%	400	100.0%	0.0%
Failure	0	0.0%	0	0.0%

COMPARE_OP

specialization stats for COMPARE_OP family

Kind	Base Count	Base Ratio	Head Count	Head Ratio	Change
deferred ⓘ Lists the number of "deferred" (i.e. not specialized) instructions executed.	60	0.0%	60	0.0%	0.0%
hit ⓘ Specialized instructions that complete.	12,001,320	100.0%	12,001,320	100.0%	0.0%

Success	Base Count	Base Ratio	Head Count	Head Ratio	Change
Success	0	0.0%	0	0.0%
Failure	20	100.0%	20	100.0%	0.0%

Failure kind	Base Count	Base Ratio	Head Count	Head Ratio	Change
list	20	100.0%	20	100.0%	0.0%

FOR_ITER

specialization stats for FOR_ITER family

Kind	Base Count	Base Ratio	Head Count	Head Ratio	Change
deferred ⓘ Lists the number of "deferred" (i.e. not specialized) instructions executed.	60	0.0%	60	0.0%	0.0%
hit ⓘ Specialized instructions that complete.	24,000,520	100.0%	24,000,520	100.0%	0.0%

LOAD_ATTR

specialization stats for LOAD_ATTR family

Kind	Base Count	Base Ratio	Head Count	Head Ratio	Change
deferred ⓘ Lists the number of "deferred" (i.e. not specialized) instructions executed.	60	0.0%	60	0.0%	0.0%
hit ⓘ Specialized instructions that complete.	96,002,820	100.0%	96,002,820	100.0%	0.0%

Success	Base Count	Base Ratio	Head Count	Head Ratio	Change
Success	220	91.7%	220	91.7%	0.0%
Failure	20	8.3%	20	8.3%	0.0%

LOAD_GLOBAL

specialization stats for LOAD_GLOBAL family

Kind	Base Count	Base Ratio	Head Count	Head Ratio	Change
hit ⓘ Specialized instructions that complete.	30,003,900	100.0%	30,003,900	100.0%	0.0%

Success	Base Count	Base Ratio	Head Count	Head Ratio	Change
Success	260	100.0%	260	100.0%	0.0%
Failure	0	0.0%	0	0.0%

SEND

specialization stats for SEND family

Kind	Base Count	Base Ratio	Head Count	Head Ratio	Change
hit ⓘ Specialized instructions that complete.	376,548,480	100.0%	376,548,480	100.0%	0.0%

STORE_ATTR

specialization stats for STORE_ATTR family

Kind	Base Count	Base Ratio	Head Count	Head Ratio	Change
hit ⓘ Specialized instructions that complete.	18,001,800	100.0%	18,001,800	100.0%	0.0%

TO_BOOL

specialization stats for TO_BOOL family

Kind	Base Count	Base Ratio	Head Count	Head Ratio	Change
deferred ⓘ Lists the number of "deferred" (i.e. not specialized) instructions executed.	60	0.0%	60	0.0%	0.0%
hit ⓘ Specialized instructions that complete.	23,999,920	100.0%	23,999,920	100.0%	0.0%
miss ⓘ Specialized instructions that deopt.	2,200	0.0%	2,200	0.0%	0.0%

Success	Base Count	Base Ratio	Head Count	Head Ratio	Change
Success	60	75.0%	60	75.0%	0.0%
Failure	20	25.0%	20	25.0%	0.0%

Failure kind	Base Count	Base Ratio	Head Count	Head Ratio	Change
sequence	20	100.0%	20	100.0%	0.0%

UNPACK_SEQUENCE

specialization stats for UNPACK_SEQUENCE family

Kind	Base Count	Base Ratio	Head Count	Head Ratio	Change
hit ⓘ Specialized instructions that complete.	60	75.0%	60	75.0%	0.0%

Success	Base Count	Base Ratio	Head Count	Head Ratio	Change
Success	20	100.0%	20	100.0%	0.0%
Failure	0	0.0%	0	0.0%

Specialization effectiveness

specialization effectiveness

All entries are execution counts. Should add up to the total number of Tier 1 instructions executed.

Instructions	Base Count	Base Ratio	Head Count	Head Ratio	Change
Basic ⓘ Instructions that are not and cannot be specialized, e.g. LOAD_FAST.	728,358,960	82.6%	728,358,960	82.6%	0.0%
Not specialized ⓘ Instructions that could be specialized but aren't, e.g. LOAD_ATTR, BINARY_SLICE.	24,006,580	2.7%	24,006,580	2.7%	0.0%
Specialized hits ⓘ Specialized instructions, e.g. LOAD_ATTR_MODULE that complete.	129,766,220	14.7%	129,766,220	14.7%	0.0%
Specialized misses ⓘ Specialized instructions, e.g. LOAD_ATTR_MODULE that deopt.	24,400	0.0%	24,400	0.0%	0.0%

Deferred by instruction

Breakdown of deferred (not specialized) instruction counts by family

Name	Base Count	Base Ratio	Head Count	Head Ratio	Change
BINARY_SLICE	12,001,200	50.0%	12,001,200	50.0%	0.0%
BINARY_SUBSCR	6,000,600	25.0%	6,000,600	25.0%	0.0%
BINARY_OP	6,000,600	25.0%	6,000,600	25.0%	0.0%
TO_BOOL	60	0.0%	60	0.0%	0.0%
COMPARE_OP	60	0.0%	60	0.0%	0.0%
FOR_ITER	60	0.0%	60	0.0%	0.0%
LOAD_ATTR	60	0.0%	60	0.0%	0.0%
STORE_SLICE	0	0.0%	0	0.0%
CACHE	0	0.0%	0	0.0%
END_FOR	0	0.0%	0	0.0%

Misses by instruction

Breakdown of misses (specialized deopts) instruction counts by family

Name	Base Count	Base Ratio	Head Count	Head Ratio	Change
RESUME	22,200	47.6%	22,200	47.6%	0.0%
RESUME_CHECK	22,200	47.6%	22,200	47.6%	0.0%
TO_BOOL_NONE	1,140	2.4%	1,140	2.4%	0.0%
TO_BOOL_ALWAYS_TRUE	1,060	2.3%	1,060	2.3%	0.0%
CACHE	0	0.0%	0	0.0%
END_FOR	0	0.0%	0	0.0%
END_SEND	0	0.0%	0	0.0%
EXIT_INIT_CHECK	0	0.0%	0	0.0%
GET_ITER	0	0.0%	0	0.0%
GET_YIELD_FROM_ITER	0	0.0%	0	0.0%

Call stats

Inlined calls and frame stats

This shows what fraction of calls to Python functions are inlined (i.e. not having a call at the C level) and for those that are not, where the call comes from. The various categories overlap.

Also includes the count of frame objects created.

	Base Count	Base Ratio	Head Count	Head Ratio	Change
Calls to PyEval_EvalDefault	24,001,320	5.4%	24,001,320	5.4%	0.0%
Calls to Python functions inlined	418,551,000	94.6%	418,551,000	94.6%	0.0%
Calls via PyEval_EvalFrame (total)	24,001,320	5.4%	24,001,320	5.4%	0.0%
Calls via PyEval_EvalFrame (vector)	24,000,660	5.4%	24,000,660	5.4%	0.0%
Calls via PyEval_EvalFrame (generator)	660	0.0%	660	0.0%	0.0%
Calls via PyEval_EvalFrame (legacy)	0	0.0%	0	0.0%
Calls via PyEval_EvalFrame (function vectorcall)	24,000,660	5.4%	24,000,660	5.4%	0.0%
Calls via PyEval_EvalFrame (build class)	0	0.0%	0	0.0%
Calls via PyEval_EvalFrame (slot)	0	0.0%	0	0.0%
Calls via PyEval_EvalFrame (function ex)	60	0.0%	60	0.0%	0.0%
Calls via PyEval_EvalFrame (api)	24,000,600	5.4%	24,000,600	5.4%	0.0%
Calls via PyEval_EvalFrame (method)	0	0.0%	0	0.0%
Frame objects created	0	0.0%	0	0.0%
Frames pushed	48,003,540	10.8%	48,003,540	10.8%	0.0%

Object stats

Allocations, frees and dict materializatons

Below, "allocations" means "allocations that are not from a freelist". Total allocations = "Allocations from freelist" + "Allocations".

"Inline values" is the number of values arrays inlined into objects.

The cache hit/miss numbers are for the MRO cache, split into dunder and other names.

	Base Count	Base Ratio	Head Count	Head Ratio	Change
Method cache dunder misses	22		23		4.5%
Method cache collisions	49		51		4.1%
Method cache dunder hits	24,002,098		24,002,097		-0.0%
Frees	72,024,083		72,024,081		-0.0%
Immortal decrefs	263,883,345	19.1%	263,883,351	19.1%	0.0%
Immortal increfs	149,896,234	12.6%	149,896,235	12.6%	0.0%
Mortal decrefs	651,220,743	47.2%	651,220,739	47.2%	-0.0%
Mortal increfs	623,475,194	52.4%	623,475,195	52.4%	0.0%
Allocations from freelist	12,006,220	14.3%	12,006,220	14.3%	0.0%
Frees to freelist	12,006,200		12,006,200		0.0%
Allocations	72,023,720	85.7%	72,023,720	85.7%	0.0%
Allocations to 512 bytes	72,023,700	85.7%	72,023,700	85.7%	0.0%
Allocations to 4 kbytes	20	0.0%	20	0.0%	0.0%
Allocations over 4 kbytes	0	0.0%	0	0.0%
Inline values	6,000,600		6,000,600		0.0%
Interpreter mortal increfs	271,538,120	22.8%	271,538,120	22.8%	0.0%
Interpreter mortal decrefs	327,822,780	23.7%	327,822,780	23.7%	0.0%
Interpreter immortal increfs	143,967,700	12.1%	143,967,700	12.1%	0.0%
Interpreter immortal decrefs	137,957,280	10.0%	137,957,280	10.0%	0.0%
Materialize dict (on request)	0	0.0%	0	0.0%
Materialize dict (new key)	0	0.0%	0	0.0%
Materialize dict (too big)	0	0.0%	0	0.0%
Materialize dict (str subclass)	0	0.0%	0	0.0%
Method cache hits	188		188		0.0%
Method cache misses	32		32		0.0%

GC stats

GC collections and effectiveness

Collected/visits gives some measure of efficiency.

Generation	Base Collections	Base Objects collected	Base Object visits	Head Collections	Head Objects collected	Head Object visits
0	0	0	0	0	0	0
1	2,960	160	77,962,860	2,960	160	77,962,860
2	0	0	0	0	0	0

Optimization (Tier 2) stats

statistics about the Tier 2 optimizer

	Base Count	Base Ratio	Head Count	Head Ratio	Change
Optimization attempts ⓘ The number of times a potential trace is identified. Specifically, this occurs in the JUMP BACKWARD instruction when the counter reaches a threshold.	5,880		5,880		0.0%
Traces created ⓘ The number of traces that were successfully created.	20	0.3%	20	0.3%	0.0%
Trace stack overflow ⓘ A trace is truncated because it would require more than 5 stack frames.	0	0.0%	0	0.0%
Trace stack underflow ⓘ A potential trace is abandoned because it pops more frames than it pushes.	5,860	99.7%	5,860	99.7%	0.0%
Trace too long ⓘ A trace is truncated because it is longer than the instruction buffer.	0	0.0%	0	0.0%
Trace too short ⓘ A potential trace is abandoced because it it too short.	5,860	99.7%	5,860	99.7%	0.0%
Inner loop found ⓘ A trace is truncated because it has an inner loop	0	0.0%	0	0.0%
Recursive call ⓘ A trace is truncated because it has a recursive call.	0	0.0%	0	0.0%
Low confidence ⓘ A trace is abandoned because the likelihood of the jump to top being taken is too low.	0	0.0%	0	0.0%
Executors invalidated ⓘ The number of executors that were invalidated due to watched dictionary changes.	0	0.0%	0	0.0%
Traces executed ⓘ The number of traces that were executed	456,802,920		456,802,920		0.0%
Uops executed ⓘ The total number of uops (micro-operations) that were executed	3,613,863,000	791.1%	3,613,863,000	791.1%	0.0%

	Base Count	Base Ratio	Head Count	Head Ratio	Change
Optimizer attempts ⓘ The number of times the trace optimizer (_Py_uop_analyze_and_optimize) was run.	20		20		0.0%
Optimizer successes ⓘ The number of traces that were successfully optimized.	20	100.0%	20	100.0%	0.0%
Optimizer no memory ⓘ The number of optimizations that failed due to no memory.	0	0.0%	0	0.0%
Remove globals builtins changed ⓘ The builtins changed during optimization	0	0.0%	0	0.0%
Remove globals incorrect keys ⓘ The keys in the globals dictionary aren't what was expected	0	0.0%	0	0.0%

Trace length histogram

trace length histogram

Range	Base Count	Base Ratio	Head Count	Head Ratio	Change
<= 1	0	0.0%	0	0.0%
<= 2	0	0.0%	0	0.0%
<= 4	0	0.0%	0	0.0%
<= 8	0	0.0%	0	0.0%
<= 16	0	0.0%	0	0.0%
<= 32	20	100.0%	20	100.0%	0.0%

Optimized trace length histogram

optimized trace length histogram

Range	Base Count	Base Ratio	Head Count	Head Ratio	Change
<= 1	0	0.0%	0	0.0%
<= 2	0	0.0%	0	0.0%
<= 4	0	0.0%	0	0.0%
<= 8	0	0.0%	0	0.0%
<= 16	20	100.0%	20	100.0%	0.0%

Trace run length histogram

trace run length histogram

Range	Base Count	Base Ratio	Head Count	Head Ratio	Change
<= 1	0	0.0%	0	0.0%

Uop execution stats

uop execution stats

Name	Base Count	Head Count	Change
_MAKE_WARM	456,802,920	456,802,920	0.0%
_START_EXECUTOR	456,802,920	456,802,920	0.0%
_SET_IP	424,530,840	424,530,840	0.0%
_DYNAMIC_EXIT	400,532,080	400,532,080	0.0%
_PUSH_FRAME	400,532,080	400,532,080	0.0%
_TIER2_RESUME_CHECK	376,533,960	376,533,960	0.0%
_SEND_GEN_FRAME	376,532,100	376,532,100	0.0%
_GUARD_TYPE_VERSION	112,535,700	112,535,700	0.0%
_CHECK_MANAGED_OBJECT_HAS_VALUES	80,267,340	80,267,340	0.0%
_LOAD_ATTR_INSTANCE_VALUE_0	80,267,340	80,267,340	0.0%
_LOAD_FAST_0	80,267,340	80,267,340	0.0%
_POP_TOP	71,995,180	71,995,180	0.0%
_EXIT_TRACE	56,266,420	56,266,420	0.0%
_RESUME_CHECK	24,000,600	24,000,600	0.0%
_CHECK_PERIODIC	24,000,000	24,000,000	0.0%
_CHECK_VALIDITY_AND_SET_IP	23,999,980	23,999,980	0.0%
_FOR_ITER_GEN_FRAME	23,999,980	23,999,980	0.0%
_CHECK_VALIDITY	23,998,760	23,998,760	0.0%
_GET_YIELD_FROM_ITER	23,998,740	23,998,740	0.0%
_LOAD_CONST_INLINE_BORROW	23,998,740	23,998,740	0.0%
_REPLACE_WITH_TRUE	23,998,740	23,998,740	0.0%
_TO_BOOL_NONE	23,998,040	23,998,040	0.0%
_GUARD_IS_TRUE_POP	15,728,420	15,728,420	0.0%
_GUARD_IS_FALSE_POP	8,270,320	8,270,320	0.0%
_DEOPT	4,420	4,420	0.0%
_GUARD_NOT_EXHAUSTED_RANGE	20	20	0.0%
_ITER_CHECK_RANGE	20	20	0.0%

Pair counts

Pair counts for top 100 Non-JIT uop pairs

Pairs of specialized operations that deoptimize and are then followed by the corresponding unspecialized instruction are not counted as pairs.

Not included in comparative output.

Unsupported opcodes

unsupported opcodes

Optimizer errored out with opcode

Optimization stopped after encountering this opcode

Rare events

Counts of rare/unlikely events

Event	Base Count	Head Count	Change
set class ⓘ Setting an object's class, obj.__class__ = ...	0	0
set bases ⓘ Setting the bases of a class, cls.__bases__ = ...	0	0
set eval frame func ⓘ Setting the PEP 523 frame eval function _PyInterpreterState_SetFrameEvalFunc()	0	0
builtin dict ⓘ Modifying the builtins, __builtins__.__dict__[var] = ...	0	0
func modification ⓘ Modifying a function, e.g. func.__defaults__ = ..., etc.	0	0
watched dict modification ⓘ A watched dict has been modified	0	0
watched globals modification ⓘ A watched globals() dict has been modified	0	0

Meta stats

Meta statistics

	Base Count	Head Count	Change
Number of data files	20	20	0.0%

---

Stats gathered on: 2024-10-25