Bench: GC overhead via bump-allocator comparison

Adds --alloc=<gc|bump> to ail build/run. Bump path links a 256MB
no-free arena C stub instead of libgc; IR is byte-identical except
for the @GC_malloc → @bump_malloc symbol swap. Bench harness times
two allocation-heavy workloads (list cons/sum and balanced tree
build/walk) under both modes.

Numbers (RUNS=5, median of 4):
  bench_list_sum   gc 0.141s  bump 0.048s  +194%
  bench_tree_walk  gc 0.103s  bump 0.041s  +151%

Bucket: large. ~60% of runtime is Boehm on these workloads —
upper bound for any realistic program. Both fixtures hold the
heap fully live, so the cost we're seeing is Boehm's allocate
path itself, not collection work; that fact narrows the design
space for the GC discussion.

- crates/ailang-codegen: AllocStrategy enum, three callsites and
  the IR header parameterised.
- crates/ail/src/main.rs: --alloc flag plumbed; bump runtime
  located + compiled on demand.
- runtime/bump.c: 256MB static arena, abort-on-overflow.
- examples/bench_list_sum, bench_tree_walk: accumulator-form
  fixtures (textbook recursive sum was constructor-blocked).
- bench/run.sh: harness with Python timing helper (Arch's
  /usr/bin/time isn't part of the base install).

No language-level changes; default --alloc=gc, all 141 workspace
tests green, all 5 IR snapshots unchanged, 11 prior fixtures
produce identical stdout.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-05-08 00:06:20 +02:00
parent aee6e9d3bf
commit 65e280bb70
9 changed files with 752 additions and 22 deletions
+1
View File
@@ -0,0 +1 @@
{"defs":[{"ctors":[{"fields":[],"name":"INil"},{"fields":[{"k":"con","name":"Int"},{"k":"con","name":"IntList"}],"name":"ICons"}],"kind":"type","name":"IntList"},{"body":{"cond":{"args":[{"name":"n","t":"var"},{"lit":{"kind":"int","value":0},"t":"lit"}],"fn":{"name":"==","t":"var"},"t":"app"},"else":{"args":[{"args":[{"name":"n","t":"var"},{"lit":{"kind":"int","value":1},"t":"lit"}],"fn":{"name":"-","t":"var"},"t":"app"},{"args":[{"args":[{"name":"n","t":"var"},{"lit":{"kind":"int","value":1},"t":"lit"}],"fn":{"name":"-","t":"var"},"t":"app"},{"name":"acc","t":"var"}],"ctor":"ICons","t":"ctor","type":"IntList"}],"fn":{"name":"cons_n_acc","t":"var"},"t":"app","tail":true},"t":"if","then":{"name":"acc","t":"var"}},"doc":"Tail-recursive list builder. Result = accumulator-prepended list.","kind":"fn","name":"cons_n_acc","params":["n","acc"],"type":{"effects":[],"k":"fn","params":[{"k":"con","name":"Int"},{"k":"con","name":"IntList"}],"ret":{"k":"con","name":"IntList"}}},{"body":{"args":[{"name":"n","t":"var"},{"args":[],"ctor":"INil","t":"ctor","type":"IntList"}],"fn":{"name":"cons_n_acc","t":"var"},"t":"app"},"doc":"Build [0, 1, ..., n-1] :: IntList. Order doesn't matter for sum.","kind":"fn","name":"cons_n","params":["n"],"type":{"effects":[],"k":"fn","params":[{"k":"con","name":"Int"}],"ret":{"k":"con","name":"IntList"}}},{"body":{"arms":[{"body":{"name":"acc","t":"var"},"pat":{"ctor":"INil","fields":[],"p":"ctor"}},{"body":{"args":[{"name":"t","t":"var"},{"args":[{"name":"acc","t":"var"},{"name":"h","t":"var"}],"fn":{"name":"+","t":"var"},"t":"app"}],"fn":{"name":"sum_acc","t":"var"},"t":"app","tail":true},"pat":{"ctor":"ICons","fields":[{"name":"h","p":"var"},{"name":"t","p":"var"}],"p":"ctor"}}],"scrutinee":{"name":"xs","t":"var"},"t":"match"},"doc":"Tail-recursive sum.","kind":"fn","name":"sum_acc","params":["xs","acc"],"type":{"effects":[],"k":"fn","params":[{"k":"con","name":"IntList"},{"k":"con","name":"Int"}],"ret":{"k":"con","name":"Int"}}},{"body":{"args":[{"name":"xs","t":"var"},{"lit":{"kind":"int","value":0},"t":"lit"}],"fn":{"name":"sum_acc","t":"var"},"t":"app"},"doc":"Sum every element. Calls sum_acc with seed 0.","kind":"fn","name":"sum_list","params":["xs"],"type":{"effects":[],"k":"fn","params":[{"k":"con","name":"IntList"}],"ret":{"k":"con","name":"Int"}}},{"body":{"args":[{"args":[{"args":[{"name":"n","t":"var"}],"fn":{"name":"cons_n","t":"var"},"t":"app"}],"fn":{"name":"sum_list","t":"var"},"t":"app"}],"op":"io/print_int","t":"do"},"doc":"Build a list of length n, sum it, print the sum.","kind":"fn","name":"run_one","params":["n"],"type":{"effects":["IO"],"k":"fn","params":[{"k":"con","name":"Int"}],"ret":{"k":"con","name":"Unit"}}},{"body":{"lhs":{"args":[{"lit":{"kind":"int","value":100000},"t":"lit"}],"fn":{"name":"run_one","t":"var"},"t":"app"},"rhs":{"lhs":{"args":[{"lit":{"kind":"int","value":1000000},"t":"lit"}],"fn":{"name":"run_one","t":"var"},"t":"app"},"rhs":{"args":[{"lit":{"kind":"int","value":3000000},"t":"lit"}],"fn":{"name":"run_one","t":"var"},"t":"app"},"t":"seq"},"t":"seq"},"kind":"fn","name":"main","params":[],"type":{"effects":["IO"],"k":"fn","params":[],"ret":{"k":"con","name":"Unit"}}}],"imports":[],"name":"bench_list_sum","schema":"ailang/v0"}
+99
View File
@@ -0,0 +1,99 @@
; Bench fixture (Bench iter): linked-list build + sum.
;
; Drives the heap allocator hard via a recursive Cons spine. Every
; ICons cell is one allocation (24 bytes: tag + Int payload + tail).
; A list of length N therefore costs N allocations. We invoke the
; workload at three different sizes within a single program run to
; cover small / medium / large territory.
;
; Both `cons_n` (build) and `sum_list` (traverse) are written in
; accumulator form so the recursive call sits in tail position and
; can be marked `tail-app`. This is essential at the sizes used here:
; without `musttail`, three million stack frames overflow the default
; thread stack and segfault.
;
; Workload sizes (hardcoded — AILang has no env-var/argv pipeline):
;
; 100_000 * 24 B = 2.4 MB
; 1_000_000 * 24 B = 24 MB
; 3_000_000 * 24 B = 72 MB
;
; (3M was chosen as the largest size that comfortably fits inside the
; bump allocator's 256 MB arena with headroom for closure pairs and
; misc allocations.)
;
; Build is allocation-heavy; sum is pure traversal of already-allocated
; heap (the interesting one for GC pressure / barrier overhead).
;
; Expected stdout (one int per line, the sum 0+1+...+(N-1) = N*(N-1)/2):
; 100_000 -> 4999950000
; 1_000_000 -> 499999500000
; 3_000_000 -> 4499998500000
(module bench_list_sum
(data IntList
(ctor INil)
(ctor ICons (con Int) (con IntList)))
(fn cons_n_acc
(doc "Tail-recursive list builder. Result = accumulator-prepended list.")
(type
(fn-type
(params (con Int) (con IntList))
(ret (con IntList))))
(params n acc)
(body
(if (app == n 0)
acc
(tail-app cons_n_acc
(app - n 1)
(term-ctor IntList ICons (app - n 1) acc)))))
(fn cons_n
(doc "Build [0, 1, ..., n-1] :: IntList. Order doesn't matter for sum.")
(type
(fn-type
(params (con Int))
(ret (con IntList))))
(params n)
(body
(app cons_n_acc n (term-ctor IntList INil))))
(fn sum_acc
(doc "Tail-recursive sum.")
(type
(fn-type
(params (con IntList) (con Int))
(ret (con Int))))
(params xs acc)
(body
(match xs
(case (pat-ctor INil) acc)
(case (pat-ctor ICons h t)
(tail-app sum_acc t (app + acc h))))))
(fn sum_list
(doc "Sum every element. Calls sum_acc with seed 0.")
(type
(fn-type
(params (con IntList))
(ret (con Int))))
(params xs)
(body
(app sum_acc xs 0)))
(fn run_one
(doc "Build a list of length n, sum it, print the sum.")
(type (fn-type (params (con Int)) (ret (con Unit)) (effects IO)))
(params n)
(body
(do io/print_int (app sum_list (app cons_n n)))))
(fn main
(type (fn-type (params) (ret (con Unit)) (effects IO)))
(params)
(body
(seq (app run_one 100000)
(seq (app run_one 1000000)
(app run_one 3000000))))))
+1
View File
@@ -0,0 +1 @@
{"defs":[{"ctors":[{"fields":[],"name":"Leaf"},{"fields":[{"k":"con","name":"Int"},{"k":"con","name":"Tree"},{"k":"con","name":"Tree"}],"name":"Node"}],"kind":"type","name":"Tree"},{"body":{"cond":{"args":[{"name":"depth","t":"var"},{"lit":{"kind":"int","value":0},"t":"lit"}],"fn":{"name":"==","t":"var"},"t":"app"},"else":{"args":[{"lit":{"kind":"int","value":1},"t":"lit"},{"args":[{"args":[{"name":"depth","t":"var"},{"lit":{"kind":"int","value":1},"t":"lit"}],"fn":{"name":"-","t":"var"},"t":"app"}],"fn":{"name":"build_tree","t":"var"},"t":"app"},{"args":[{"args":[{"name":"depth","t":"var"},{"lit":{"kind":"int","value":1},"t":"lit"}],"fn":{"name":"-","t":"var"},"t":"app"}],"fn":{"name":"build_tree","t":"var"},"t":"app"}],"ctor":"Node","t":"ctor","type":"Tree"},"t":"if","then":{"args":[],"ctor":"Leaf","t":"ctor","type":"Tree"}},"doc":"Balanced binary tree of given depth, every value = 1.","kind":"fn","name":"build_tree","params":["depth"],"type":{"effects":[],"k":"fn","params":[{"k":"con","name":"Int"}],"ret":{"k":"con","name":"Tree"}}},{"body":{"arms":[{"body":{"lit":{"kind":"int","value":0},"t":"lit"},"pat":{"ctor":"Leaf","fields":[],"p":"ctor"}},{"body":{"args":[{"name":"v","t":"var"},{"args":[{"args":[{"name":"l","t":"var"}],"fn":{"name":"sum_tree","t":"var"},"t":"app"},{"args":[{"name":"r","t":"var"}],"fn":{"name":"sum_tree","t":"var"},"t":"app"}],"fn":{"name":"+","t":"var"},"t":"app"}],"fn":{"name":"+","t":"var"},"t":"app"},"pat":{"ctor":"Node","fields":[{"name":"v","p":"var"},{"name":"l","p":"var"},{"name":"r","p":"var"}],"p":"ctor"}}],"scrutinee":{"name":"t","t":"var"},"t":"match"},"doc":"Sum every Node value via match recursion. Constructor-blocked: not tail-recursive, but recursion depth = tree depth so fits.","kind":"fn","name":"sum_tree","params":["t"],"type":{"effects":[],"k":"fn","params":[{"k":"con","name":"Tree"}],"ret":{"k":"con","name":"Int"}}},{"body":{"args":[{"args":[{"args":[{"name":"depth","t":"var"}],"fn":{"name":"build_tree","t":"var"},"t":"app"}],"fn":{"name":"sum_tree","t":"var"},"t":"app"}],"op":"io/print_int","t":"do"},"doc":"Build a tree of given depth, sum it, print the sum.","kind":"fn","name":"run_one","params":["depth"],"type":{"effects":["IO"],"k":"fn","params":[{"k":"con","name":"Int"}],"ret":{"k":"con","name":"Unit"}}},{"body":{"lhs":{"args":[{"lit":{"kind":"int","value":16},"t":"lit"}],"fn":{"name":"run_one","t":"var"},"t":"app"},"rhs":{"lhs":{"args":[{"lit":{"kind":"int","value":18},"t":"lit"}],"fn":{"name":"run_one","t":"var"},"t":"app"},"rhs":{"args":[{"lit":{"kind":"int","value":20},"t":"lit"}],"fn":{"name":"run_one","t":"var"},"t":"app"},"t":"seq"},"t":"seq"},"kind":"fn","name":"main","params":[],"type":{"effects":["IO"],"k":"fn","params":[],"ret":{"k":"con","name":"Unit"}}}],"imports":[],"name":"bench_tree_walk","schema":"ailang/v0"}
+78
View File
@@ -0,0 +1,78 @@
; Bench fixture (Bench iter): balanced-tree build + sum.
;
; Allocates a balanced binary tree of `Node value left right` cells,
; then walks it summing the value field. Distinct from
; `bench_list_sum` in two ways:
; 1. Each tree node has an additional pointer field versus a list
; cell — 32-byte alloc instead of 24-byte. The branching shape
; means the recursion structure is genuinely tree-shaped: the
; build cannot be made tail-recursive without explicit
; continuation passing, so this fixture is constrained to depths
; where the recursion stack fits.
; 2. The traversal pattern hits two children per node, exercising
; the GC's mark-phase pointer-chasing heuristics differently from
; a plain linked-list walk.
;
; Depth picked: 20 -> 2^20 - 1 = 1_048_575 nodes -> 32 MB heap usage.
; Recursion depth in `build_tree` and `sum_tree` matches `depth`,
; which fits comfortably in the default 8 MB system stack.
;
; Hardcoded multi-call form: build/sum the same tree thrice for
; signal averaging. The depths are different per call so the GC has
; to deal with three independent live-set sizes.
;
; Expected stdout (one int per line):
; depth 16: 2^16 - 1 = 65535 nodes, sum = 65535
; depth 18: 2^18 - 1 = 262143 nodes, sum = 262143
; depth 20: 2^20 - 1 = 1048575 nodes, sum = 1048575
;
; (Each node stores literal `1`; sum is therefore node count.)
(module bench_tree_walk
(data Tree
(ctor Leaf)
(ctor Node (con Int) (con Tree) (con Tree)))
(fn build_tree
(doc "Balanced binary tree of given depth, every value = 1.")
(type
(fn-type
(params (con Int))
(ret (con Tree))))
(params depth)
(body
(if (app == depth 0)
(term-ctor Tree Leaf)
(term-ctor Tree Node
1
(app build_tree (app - depth 1))
(app build_tree (app - depth 1))))))
(fn sum_tree
(doc "Sum every Node value via match recursion. Constructor-blocked: not tail-recursive, but recursion depth = tree depth so fits.")
(type
(fn-type
(params (con Tree))
(ret (con Int))))
(params t)
(body
(match t
(case (pat-ctor Leaf) 0)
(case (pat-ctor Node v l r)
(app + v (app + (app sum_tree l) (app sum_tree r)))))))
(fn run_one
(doc "Build a tree of given depth, sum it, print the sum.")
(type (fn-type (params (con Int)) (ret (con Unit)) (effects IO)))
(params depth)
(body
(do io/print_int (app sum_tree (app build_tree depth)))))
(fn main
(type (fn-type (params) (ret (con Unit)) (effects IO)))
(params)
(body
(seq (app run_one 16)
(seq (app run_one 18)
(app run_one 20))))))