proof/: add physics diagnostic/benchmark/pipelining coverage
StarForth_Physics_Diagnostic_Words.thy (physics_diagnostic_words.c): 3 of 4 words are pure-printf identity transitions; PHYSICS-BURN's guard modelled, its arbitrary dynamically-selected func-pointer execution loop is a new class of gap (not reducible to any prior one). StarForth_Physics_Benchmark_Words.thy (physics_benchmark_words.c): hot-words cache is a whole unmodelled subsystem. PHYSICS-RESET-STATS's pipeline_metrics half (3 real vm_state fields) modelled; everything else in the file deferred. StarForth_Physics_Pipelining_Diagnostic_Words.thy (physics_pipelining_diagnostic_words.c): root-cause finding -- `word_transition_metrics` has been a declared record type in StarForth_Base.thy since early in the sweep but was never wired into `dict_entry` as a field, so every word in this file touches state with zero abstract representation. Three no-arg words modelled as identity (with an explicit caveat that this reflects the model's blind spot, not a no-op claim about the C); the three lookup words get only their simplest empty-stack underflow case. Suite now 43 theories, green.
This commit is contained in:
Robert Allan James
@@ -25,6 +25,9 @@ session "StarForth" = "HOL-Library" +
|
||||
StarForth_Transition
|
||||
StarForth_Dictionary_Heat_Diagnostic_Words
|
||||
StarForth_Physics_Freeze_Words
|
||||
StarForth_Physics_Diagnostic_Words
|
||||
StarForth_Physics_Benchmark_Words
|
||||
StarForth_Physics_Pipelining_Diagnostic_Words
|
||||
StarForth_Loop1_Heat
|
||||
StarForth_Loop2_Window
|
||||
StarForth_Loop3_Decay
|
||||
|
||||
@@ -0,0 +1,109 @@
|
||||
theory StarForth_Physics_Benchmark_Words
|
||||
imports StarForth_Base
|
||||
begin
|
||||
|
||||
(* =========================================================================
|
||||
Mirrors: src/word_source/physics_benchmark_words.c
|
||||
Registers: BENCH-DICT-LOOKUP PHYSICS-CACHE-STATS PHYSICS-TOGGLE-CACHE
|
||||
PHYSICS-RESET-STATS PHYSICS-BUILD-INFO PHYSICS-BAYESIAN-REPORT
|
||||
|
||||
── Hot-words cache -- a whole unmodelled subsystem ─────────────────────
|
||||
Every word in this file reads or writes `vm->hotwords_cache` (a
|
||||
`HotwordsCache*`) and/or its nested `HotwordsStats` -- neither has any
|
||||
counterpart in vm_state. This is the same class of gap as the block-
|
||||
window cache StarForth_Block_Words.thy/StarForth_Editor_Words.thy
|
||||
already deferred (own subsystem-modelling project, not a one-word
|
||||
extension), just for a different cache.
|
||||
|
||||
── Scope ─────────────────────────────────────────────────────────────
|
||||
PHYSICS-RESET-STATS is the one partial exception: alongside its
|
||||
unmodelled `hotwords_stats_reset` call, it ALSO resets three
|
||||
`pipeline_metrics` fields that ARE in vm_state
|
||||
(`pm_prefetch_attempts`/`pm_prefetch_hits`/`pm_tuning_checks`). Modelled
|
||||
assuming the (unmodelled) cache-initialized guard is reached -- i.e.
|
||||
this states the word's effect on `pipeline_metrics` conditional on
|
||||
control reaching that point, not the guard itself.
|
||||
|
||||
BENCH-DICT-LOOKUP's guard/pop shape is modelled (same pattern as
|
||||
COMPARE-LOOKUPS/PHYSICS-BURN); its benchmark body is not (timed
|
||||
`vm_find_word` loop, same FIND-family gap, PLUS the hot-words cache
|
||||
gap above).
|
||||
|
||||
PHYSICS-CACHE-STATS, PHYSICS-TOGGLE-CACHE, PHYSICS-BUILD-INFO, and
|
||||
PHYSICS-BAYESIAN-REPORT are entirely reads/writes of the unmodelled
|
||||
cache subsystem (or pure stdout using only compile-time constants) --
|
||||
not modelled at all.
|
||||
======================================================================== *)
|
||||
|
||||
(* ── BENCH-DICT-LOOKUP ( iterations -- ) : guard/pop only ────────────────── *)
|
||||
|
||||
definition forth_bench_dict_lookup_guard :: "vm_state \<Rightarrow> vm_state" where
|
||||
"forth_bench_dict_lookup_guard vm =
|
||||
(case data_stack vm of
|
||||
[] \<Rightarrow> set_error vm
|
||||
| n # xs \<Rightarrow> vm\<lparr>data_stack := xs\<rparr>)"
|
||||
|
||||
lemma bench_dict_lookup_underflow:
|
||||
assumes "data_stack vm = []"
|
||||
shows "vm_error (forth_bench_dict_lookup_guard vm)"
|
||||
by (simp add: forth_bench_dict_lookup_guard_def set_error_def assms)
|
||||
|
||||
lemma bench_dict_lookup_pops_one:
|
||||
assumes "data_stack vm = n # xs"
|
||||
shows "data_stack (forth_bench_dict_lookup_guard vm) = xs"
|
||||
by (simp add: forth_bench_dict_lookup_guard_def assms)
|
||||
|
||||
lemma bench_dict_lookup_body_not_modelled: True
|
||||
\<comment> \<open>iterations \<ge> 1: timed vm_find_word loop over the hot-words cache --
|
||||
both the FIND-family gap and the cache-subsystem gap above.\<close>
|
||||
by simp
|
||||
|
||||
(* ── PHYSICS-RESET-STATS ( -- ) : pipeline_metrics half only ─────────────── *)
|
||||
(* C: guarded by `if (!vm->hotwords_cache) { ...; return; }` (unmodelled);
|
||||
once past that guard: hotwords_stats_reset(...) (unmodelled, cache
|
||||
subsystem) THEN three real vm_state field writes:
|
||||
vm->pipeline_metrics.prefetch_hits = 0
|
||||
vm->pipeline_metrics.prefetch_attempts = 0
|
||||
vm->pipeline_metrics.window_tuning_checks = 0
|
||||
Modelled as the pipeline_metrics update alone, conditional on the guard
|
||||
having been reached (not itself expressed, since "cache initialized"
|
||||
has no vm_state predicate). *)
|
||||
|
||||
definition forth_physics_reset_stats_metrics :: "vm_state \<Rightarrow> vm_state" where
|
||||
"forth_physics_reset_stats_metrics vm =
|
||||
vm\<lparr>pipeline_metrics := (pipeline_metrics vm)
|
||||
\<lparr>pm_prefetch_hits := 0, pm_prefetch_attempts := 0, pm_tuning_checks := 0\<rparr>\<rparr>"
|
||||
|
||||
lemma physics_reset_stats_clears_pipeline_counters:
|
||||
"pm_prefetch_hits (pipeline_metrics (forth_physics_reset_stats_metrics vm)) = 0"
|
||||
"pm_prefetch_attempts (pipeline_metrics (forth_physics_reset_stats_metrics vm)) = 0"
|
||||
"pm_tuning_checks (pipeline_metrics (forth_physics_reset_stats_metrics vm)) = 0"
|
||||
by (simp_all add: forth_physics_reset_stats_metrics_def)
|
||||
|
||||
lemma physics_reset_stats_preserves_other_pipeline_fields:
|
||||
"pm_last_window_size (pipeline_metrics (forth_physics_reset_stats_metrics vm))
|
||||
= pm_last_window_size (pipeline_metrics vm)"
|
||||
"pm_last_accuracy_num (pipeline_metrics (forth_physics_reset_stats_metrics vm))
|
||||
= pm_last_accuracy_num (pipeline_metrics vm)"
|
||||
"pm_last_accuracy_den (pipeline_metrics (forth_physics_reset_stats_metrics vm))
|
||||
= pm_last_accuracy_den (pipeline_metrics vm)"
|
||||
"pm_suggested_next_size (pipeline_metrics (forth_physics_reset_stats_metrics vm))
|
||||
= pm_suggested_next_size (pipeline_metrics vm)"
|
||||
by (simp_all add: forth_physics_reset_stats_metrics_def)
|
||||
|
||||
lemma physics_reset_stats_data_stack_unchanged:
|
||||
"data_stack (forth_physics_reset_stats_metrics vm) = data_stack vm"
|
||||
by (simp add: forth_physics_reset_stats_metrics_def)
|
||||
|
||||
(* ── Everything else -- NOT MODELLED ──────────────────────────────────── *)
|
||||
|
||||
lemma cache_stats_not_modelled: True \<comment> \<open>PHYSICS-CACHE-STATS: reads hotwords_cache subsystem, stdout only.\<close>
|
||||
by simp
|
||||
lemma toggle_cache_not_modelled: True \<comment> \<open>PHYSICS-TOGGLE-CACHE: flips hotwords_cache->enabled -- outside vm_state.\<close>
|
||||
by simp
|
||||
lemma build_info_not_modelled: True \<comment> \<open>PHYSICS-BUILD-INFO: stdout of compile-time constants + hotwords_cache read.\<close>
|
||||
by simp
|
||||
lemma bayesian_report_not_modelled: True \<comment> \<open>PHYSICS-BAYESIAN-REPORT: reads/synthesizes HotwordsStats, stdout only.\<close>
|
||||
by simp
|
||||
|
||||
end
|
||||
@@ -0,0 +1,102 @@
|
||||
theory StarForth_Physics_Diagnostic_Words
|
||||
imports StarForth_Base
|
||||
begin
|
||||
|
||||
(* =========================================================================
|
||||
Mirrors: src/word_source/physics_diagnostic_words.c
|
||||
Registers: PHYSICS-WORD-METRICS PHYSICS-CALC-KNOBS PHYSICS-BURN
|
||||
PHYSICS-SHOW-FEEDBACK
|
||||
|
||||
Interactive stdout demonstrations of the Loop #1 physics feedback loop,
|
||||
built for REPL walkthroughs, not for programmatic use.
|
||||
|
||||
── Scope ─────────────────────────────────────────────────────────────
|
||||
PHYSICS-WORD-METRICS, PHYSICS-CALC-KNOBS, and PHYSICS-SHOW-FEEDBACK are
|
||||
fully modelled: all three share the identical structure of "find the
|
||||
dictionary entry with the largest `physics.last_active_ns` (a linked-
|
||||
list scan via ->link, the same class of raw traversal already flagged
|
||||
not-modelled for FORGET/ALL-HEATS -- but note this scan is READ-ONLY,
|
||||
selecting which entry to print, with no consequence for what state
|
||||
ends up being characterised), then printf a derived report from its
|
||||
fields (`float` thermal-pressure math, purely for display -- not stored
|
||||
anywhere)". None of the three writes to a SINGLE field of `vm_state` or
|
||||
any `dict_entry` -- their entire observable contract, independent of
|
||||
the (unmodelled) linked-list scan, is "no state change". Modelled as
|
||||
identity transitions.
|
||||
|
||||
PHYSICS-BURN is different: its guard conditions are modelled, but its
|
||||
core effect -- calling `target->func(vm)` in a loop, where `target` is
|
||||
whichever word the same last-active-ns scan selects -- is NOT. This is
|
||||
a genuinely new kind of gap for this sweep: every other file's
|
||||
unmodelled dispatch has been either DEFER-style reassignment (function
|
||||
pointer stored then later read) or a call embedded in a fixed
|
||||
C-language control path (DODOES). PHYSICS-BURN calls an ARBITRARY,
|
||||
data-dependent word's `func` directly from within a diagnostic
|
||||
primitive -- there is no way to characterise its effect without first
|
||||
knowing (a) which word gets selected (the unmodelled scan) and (b) what
|
||||
that word's `func` does (the `word_table`/`word_physics_transparent`
|
||||
abstraction StarForth_Transition.thy already provides IS the right tool
|
||||
for word execution in general, but PHYSICS-BURN's selection is dynamic
|
||||
and data-dependent in a way no other call site in this suite is).
|
||||
======================================================================== *)
|
||||
|
||||
(* ── PHYSICS-WORD-METRICS / PHYSICS-CALC-KNOBS / PHYSICS-SHOW-FEEDBACK ────
|
||||
All three: ( -- ), stdout-only, no vm_state field written. *)
|
||||
|
||||
definition forth_physics_word_metrics :: "vm_state \<Rightarrow> vm_state" where
|
||||
"forth_physics_word_metrics vm = vm"
|
||||
|
||||
definition forth_physics_calc_knobs :: "vm_state \<Rightarrow> vm_state" where
|
||||
"forth_physics_calc_knobs vm = vm"
|
||||
|
||||
definition forth_physics_show_feedback :: "vm_state \<Rightarrow> vm_state" where
|
||||
"forth_physics_show_feedback vm = vm"
|
||||
|
||||
lemma physics_word_metrics_identity:
|
||||
"forth_physics_word_metrics vm = vm"
|
||||
by (simp add: forth_physics_word_metrics_def)
|
||||
|
||||
lemma physics_calc_knobs_identity:
|
||||
"forth_physics_calc_knobs vm = vm"
|
||||
by (simp add: forth_physics_calc_knobs_def)
|
||||
|
||||
lemma physics_show_feedback_identity:
|
||||
"forth_physics_show_feedback vm = vm"
|
||||
by (simp add: forth_physics_show_feedback_def)
|
||||
|
||||
(* ── PHYSICS-BURN ( n -- ) : guards only ──────────────────────────────── *)
|
||||
(* C: error if stack empty; pop burn_count; if burn_count < 1, printf and
|
||||
return (no-op beyond the pop); otherwise scans for a target word (same
|
||||
unmodelled last-active-ns scan as the three words above) and calls its
|
||||
func burn_count times -- NOT modelled, see file header. *)
|
||||
|
||||
definition forth_physics_burn_guard :: "vm_state \<Rightarrow> vm_state" where
|
||||
"forth_physics_burn_guard vm =
|
||||
(case data_stack vm of
|
||||
[] \<Rightarrow> set_error vm
|
||||
| n # xs \<Rightarrow> vm\<lparr>data_stack := xs\<rparr>)"
|
||||
|
||||
lemma physics_burn_underflow:
|
||||
assumes "data_stack vm = []"
|
||||
shows "vm_error (forth_physics_burn_guard vm)"
|
||||
by (simp add: forth_physics_burn_guard_def set_error_def assms)
|
||||
|
||||
lemma physics_burn_pops_one:
|
||||
assumes "data_stack vm = n # xs"
|
||||
shows "data_stack (forth_physics_burn_guard vm) = xs"
|
||||
by (simp add: forth_physics_burn_guard_def assms)
|
||||
|
||||
lemma physics_burn_nonpositive_count_is_pop_only: True
|
||||
\<comment> \<open>C: `if (burn_count < 1) { printf(...); return; }` -- once the
|
||||
underflow guard passes and burn_count < 1, the word's entire
|
||||
remaining effect is the pop already captured by
|
||||
forth_physics_burn_guard.\<close>
|
||||
by simp
|
||||
|
||||
lemma physics_burn_loop_not_modelled: True
|
||||
\<comment> \<open>burn_count \<ge> 1: repeatedly calls an arbitrary, dynamically-selected
|
||||
word's `func` pointer -- see file header for why this is a new class
|
||||
of gap, not reducible to any single already-flagged one.\<close>
|
||||
by simp
|
||||
|
||||
end
|
||||
@@ -0,0 +1,121 @@
|
||||
theory StarForth_Physics_Pipelining_Diagnostic_Words
|
||||
imports StarForth_Base
|
||||
begin
|
||||
|
||||
(* =========================================================================
|
||||
Mirrors: src/word_source/physics_pipelining_diagnostic_words.c
|
||||
Registers (via vm_create_word directly, NOT register_word -- a
|
||||
different registration style from every other file in this sweep, note
|
||||
in case it ever matters for ACL/hot-words-cache interaction):
|
||||
PIPELINING-SHOW-STATS PIPELINING-SHOW-TOP-TRANSITIONS
|
||||
PIPELINING-RESET-ALL PIPELINING-ENABLE PIPELINING-STATS
|
||||
PIPELINING-ANALYZE-WORD
|
||||
|
||||
── Root gap: `transition_metrics` was never wired into `dict_entry` ────
|
||||
Every word in this file reads or writes `entry->transition_metrics`, a
|
||||
`WordTransitionMetrics*` -- StarForth_Base.thy already declares a
|
||||
`word_transition_metrics` RECORD TYPE (Section 3, "Word transition
|
||||
metrics") matching the C struct field-for-field, but `dict_entry`
|
||||
(Section 3, "Dictionary entry") has no field of that type. This looks
|
||||
like an intentional scope decision when `dict_entry` was designed (the
|
||||
comment there only documents omitting a `func` pointer, not
|
||||
transition_metrics), not an oversight noticed until now -- this is the
|
||||
first file in the sweep that actually needs it. Consequence: NOTHING
|
||||
any of these six words reads or writes has a counterpart in the
|
||||
abstract model. This is a materially different situation from every
|
||||
other "not modelled" gap so far (raw pointers, parsing, name lookup) --
|
||||
the underlying DATA doesn't exist in dict_entry at all, only its type
|
||||
declaration does.
|
||||
|
||||
── Scope ─────────────────────────────────────────────────────────────
|
||||
PIPELINING-RESET-ALL / -ENABLE / -STATS take no stack arguments and
|
||||
touch nothing that exists in vm_state (dictionary traversal via ->link
|
||||
is read-only and only reaches the unmodelled transition_metrics field;
|
||||
-ENABLE reads only a compile-time #if). Modelled as identity
|
||||
transitions -- but see the caveat lemma below: this identity is a
|
||||
modelling artifact of the gap above, not a claim that the real C words
|
||||
are no-ops.
|
||||
|
||||
PIPELINING-SHOW-STATS / -ANALYZE-WORD (pop addr, len) and
|
||||
PIPELINING-SHOW-TOP-TRANSITIONS (pop addr, len, top_count) resolve a
|
||||
word by (address, length) via `vm_ptr` + `vm_find_word` -- the same
|
||||
raw-pointer name-resolution gap as physics_freeze_words.c -- then read
|
||||
transition_metrics (root gap above). Only the simplest underflow case
|
||||
(stack already empty before any pop) is modelled; the C's actual
|
||||
guard shape does a real `vm_pop` per argument with an error check
|
||||
between each, so on a single-element stack the first pop succeeds
|
||||
(consuming it) before the second pop discovers the now-empty stack and
|
||||
sets the error -- a genuine partial-pop-then-error path, noted but not
|
||||
mechanised per argument count here given how little of each word's
|
||||
downstream effect is modellable regardless.
|
||||
======================================================================== *)
|
||||
|
||||
(* ── PIPELINING-RESET-ALL / -ENABLE / -STATS : identity (see caveat) ────── *)
|
||||
|
||||
definition forth_pipelining_reset_all :: "vm_state \<Rightarrow> vm_state" where
|
||||
"forth_pipelining_reset_all vm = vm"
|
||||
|
||||
definition forth_pipelining_enable :: "vm_state \<Rightarrow> vm_state" where
|
||||
"forth_pipelining_enable vm = vm"
|
||||
|
||||
definition forth_pipelining_stats :: "vm_state \<Rightarrow> vm_state" where
|
||||
"forth_pipelining_stats vm = vm"
|
||||
|
||||
lemma pipelining_reset_all_identity: "forth_pipelining_reset_all vm = vm"
|
||||
by (simp add: forth_pipelining_reset_all_def)
|
||||
|
||||
lemma pipelining_enable_identity: "forth_pipelining_enable vm = vm"
|
||||
by (simp add: forth_pipelining_enable_def)
|
||||
|
||||
lemma pipelining_stats_identity: "forth_pipelining_stats vm = vm"
|
||||
by (simp add: forth_pipelining_stats_def)
|
||||
|
||||
lemma pipelining_identity_is_a_modelling_artifact: True
|
||||
\<comment> \<open>The three identities above hold ONLY because transition_metrics has
|
||||
no vm_state representation (see file header) -- PIPELINING-RESET-ALL
|
||||
genuinely mutates real C heap state (transition_metrics_reset on
|
||||
every instrumented word); this proof suite simply cannot see it.
|
||||
Not evidence of a no-op C implementation.\<close>
|
||||
by simp
|
||||
|
||||
(* ── PIPELINING-SHOW-STATS / -ANALYZE-WORD ( addr len -- ) : empty-stack
|
||||
underflow only ─────────────────────────────────────────────────────── *)
|
||||
|
||||
definition forth_pipelining_show_stats_empty_guard :: "vm_state \<Rightarrow> vm_state" where
|
||||
"forth_pipelining_show_stats_empty_guard vm =
|
||||
(if data_stack vm = [] then set_error vm else vm)"
|
||||
|
||||
lemma pipelining_show_stats_empty_underflow:
|
||||
assumes "data_stack vm = []"
|
||||
shows "vm_error (forth_pipelining_show_stats_empty_guard vm)"
|
||||
by (simp add: forth_pipelining_show_stats_empty_guard_def set_error_def assms)
|
||||
|
||||
definition forth_pipelining_analyze_word_empty_guard :: "vm_state \<Rightarrow> vm_state" where
|
||||
"forth_pipelining_analyze_word_empty_guard vm =
|
||||
(if data_stack vm = [] then set_error vm else vm)"
|
||||
|
||||
lemma pipelining_analyze_word_empty_underflow:
|
||||
assumes "data_stack vm = []"
|
||||
shows "vm_error (forth_pipelining_analyze_word_empty_guard vm)"
|
||||
by (simp add: forth_pipelining_analyze_word_empty_guard_def set_error_def assms)
|
||||
|
||||
(* ── PIPELINING-SHOW-TOP-TRANSITIONS ( addr len top_count -- ) : empty-
|
||||
stack underflow only ───────────────────────────────────────────────── *)
|
||||
|
||||
definition forth_pipelining_show_top_transitions_empty_guard :: "vm_state \<Rightarrow> vm_state" where
|
||||
"forth_pipelining_show_top_transitions_empty_guard vm =
|
||||
(if data_stack vm = [] then set_error vm else vm)"
|
||||
|
||||
lemma pipelining_show_top_transitions_empty_underflow:
|
||||
assumes "data_stack vm = []"
|
||||
shows "vm_error (forth_pipelining_show_top_transitions_empty_guard vm)"
|
||||
by (simp add: forth_pipelining_show_top_transitions_empty_guard_def set_error_def assms)
|
||||
|
||||
lemma pipelining_lookup_words_rest_not_modelled: True
|
||||
\<comment> \<open>Beyond the empty-stack case: partial-pop-then-error on a too-short
|
||||
nonempty stack (see file header), vm_ptr/vm_find_word name resolution
|
||||
(physics_freeze_words.c-class gap), and all transition_metrics reads
|
||||
(root gap) -- none modelled.\<close>
|
||||
by simp
|
||||
|
||||
end
|
||||
Reference in New Issue
Block a user