russell@unturf.com
661f9a01ec
Folds 76 commits of substance since 2026-04-24 into the whitepaper without losing any of the novel cross-domain glue the language earns its keep on. Additions - §4.3 extended from four scopes to five, with bend as feedback across heterogeneous compute (host ↔ GPU). New diagram diagrams/five-scopes-feedback.png stacks the boundaries. - §11.8 Bend: cross-tier GPU dispatch. Wire modes (S-exp text, BSHK binary), worker hosting per tier, spawn-process-stdio + flush-port cross-tier IPC, worker health heartbeat with VRAM-ranked pick, 6-row catalog of live forms (cuda-shake-fanout, cuda-secp256k1-mul, cuda-bignum-cgbn, cuda-radix-sort, cuda-blake3-tree, cuda-sim-ops-bin). New diagram diagrams/bend-dispatch.png. - §2.1 C-tier bignum: arbitrary-precision integers (Boehm-GC managed), which unblocked the secp256k1 widths the GPU forms need on the host side. - §12.1 post-cycle audit: recv-exact O(n²)→O(n), asm scheme_read overflow, asm gc_sweep page-fault, C-tier JIT cur_code restore across CALL/RETURN. - §13 GPU Phase 1 moved from future to shipped; Phase 2 trampolining and Phase 3 interaction combinators sharpened. - Source repo link (git.unturf.com/engineering/unturf/lumbda) added to the cover page band and the Citation block. Compressions (no novel glue dropped — audited per fox's constraint) - §8.2-§8.5 EML derivation prose collapsed into a single §8.2 derivation chain code block; §8.6 renumbered to §8.3. - §6.6.3 adaptive-meta-GC narrative compressed; result table kept. - §7.4.1 GC-build S-expression portal tightened to two paragraphs; "language is its own wire format" insight kept. Preserved in full per audit - §7.5 portable RNG state across tiers - §7.5.1 one-side kernel entropy + portable bit-identical continuation - §11.7 sendfile + adaptive preload (27 KB asm-gc within 2% of Caddy) - §6.6.1 collaborative arena + mark verifier - §6.6.5 precise block typing - §8.1 + §8.3 Lumbda hosts its own EML proof checker, ~16× faster than Lean cold Net RST: 1622 → 1655 lines.
97 lines
4.4 KiB
Text
97 lines
4.4 KiB
Text
// Bend cross-tier GPU dispatch — 2026-06-07
|
||
// "A diagram is worth 10,000 words." — russell@unturf.com
|
||
//
|
||
// One (bend …) form. The dispatcher picks local vs worker per call.
|
||
// When it goes remote, the wire frame is either S-expression text
|
||
// (small payloads, parser cost dominates) or a 4-byte magic + raw
|
||
// bytes (huge payloads). Workers spawn a leaf CUDA binary via each
|
||
// tier's native process-spawn primitive. CUDA kernel returns bytes
|
||
// back through the same wire frame.
|
||
digraph bend_dispatch {
|
||
rankdir=LR
|
||
splines=true
|
||
nodesep=0.45
|
||
ranksep=0.7
|
||
node [shape=box, style="filled,rounded", fontname="Helvetica", fontsize=11, margin="0.18,0.10"]
|
||
edge [fontname="Helvetica", fontsize=9, arrowsize=0.85]
|
||
label="Bend — one (bend …) form across host, wire, worker, and GPU"
|
||
labelloc=t
|
||
fontsize=14
|
||
fontname="Helvetica Bold"
|
||
|
||
// ─── Caller side ────────────────────────────────────────────────
|
||
subgraph cluster_caller {
|
||
label="Caller tier (any of Python / C / asm)"
|
||
labelloc=t
|
||
style="rounded,filled"
|
||
fillcolor="#e8f4f8"
|
||
color="#0984e3"
|
||
fontname="Helvetica Bold"
|
||
fontsize=11
|
||
fontcolor="#0984e3"
|
||
call [label="(bend! …) form\nin user code" fillcolor="#b3d9e8"]
|
||
cost [label="cost estimator\n(local vs wire)" fillcolor="#d6eaf8"]
|
||
local [label="evaluate locally\n(small payloads)" fillcolor="#aed6f1"]
|
||
call -> cost
|
||
cost -> local [label="cheap" fontcolor="#1f618d"]
|
||
}
|
||
|
||
// ─── Wire ──────────────────────────────────────────────────────
|
||
subgraph cluster_wire {
|
||
label="Wire — port 8320 (BEND)"
|
||
labelloc=t
|
||
style="rounded,filled"
|
||
fillcolor="#fff8e1"
|
||
color="#f57f17"
|
||
fontname="Helvetica Bold"
|
||
fontsize=11
|
||
fontcolor="#f57f17"
|
||
sexp [label="S-expression\n(text)\n— small payloads" fillcolor="#ffe082"]
|
||
bin [label="binary frame\nmagic + raw bytes\n— huge payloads\n(BSHK, BCGB, BSCP,\n BSRT, BSB3, …)" fillcolor="#ffd54f"]
|
||
}
|
||
|
||
cost -> sexp [label="≤ ~1k inputs" fontcolor="#f57f17"]
|
||
cost -> bin [label="≥ ~1k inputs\n(150× over S-exp\n at 1 M)" fontcolor="#f57f17"]
|
||
|
||
// ─── Worker side ───────────────────────────────────────────────
|
||
subgraph cluster_worker {
|
||
label="Worker tier (any of Python / C / asm — listens on :8320)"
|
||
labelloc=t
|
||
style="rounded,filled"
|
||
fillcolor="#e8f5e9"
|
||
color="#2e7d32"
|
||
fontname="Helvetica Bold"
|
||
fontsize=11
|
||
fontcolor="#2e7d32"
|
||
recv [label="gpu-worker\nrecv + dispatch\n+ health" fillcolor="#a5d6a7"]
|
||
spawn [label="spawn-process-stdio\n— Py: subprocess.Popen\n— C: fork + execve\n— asm: pipe2+fork+execve\n (raw syscall, no libc)" fillcolor="#c8e6c9"]
|
||
recv -> spawn
|
||
}
|
||
|
||
sexp -> recv
|
||
bin -> recv
|
||
|
||
// ─── Leaf CUDA binary + GPU ────────────────────────────────────
|
||
subgraph cluster_gpu {
|
||
label="Leaf CUDA binary + RTX 3090"
|
||
labelloc=t
|
||
style="rounded,filled"
|
||
fillcolor="#f3e5f5"
|
||
color="#7b1fa2"
|
||
fontname="Helvetica Bold"
|
||
fontsize=11
|
||
fontcolor="#7b1fa2"
|
||
leaf [label="shake256-fanout /\nsecp256k1-batch-mul /\ncgbn-batch-worker /\nblake3-fanout /\nradix-sort /\ndemo_ops …" fillcolor="#ce93d8"]
|
||
kernel [label="CUDA kernel\n(byte-identical\n vs host reference)" fillcolor="#ba68c8"]
|
||
leaf -> kernel
|
||
}
|
||
|
||
spawn -> leaf [label="stdin / stdout" fontcolor="#7b1fa2"]
|
||
|
||
// ─── Return path ───────────────────────────────────────────────
|
||
kernel -> leaf [label="bytes back" fontcolor="#7b1fa2" style=dashed]
|
||
leaf -> spawn [style=invis]
|
||
spawn -> recv [label="result" style=dashed fontcolor="#2e7d32"]
|
||
recv -> cost [label="wire frame back" style=dashed fontcolor="#f57f17" constraint=false]
|
||
local -> call [label="value" style=dashed fontcolor="#1f618d" constraint=false]
|
||
}
|