Spike: localize the mandelbrot 15x floor (jolt-5vsp) (#143)

The jolt-vs-hand-Janet-vs-JVM mandelbrot comparison splits the 15.4x floor
into two layers: a Janet-VM floor (~10.8x JVM, optimal while-loop Janet over
unboxed doubles — only native codegen moves it) plus a ~1.43x jolt loop-
lowering overhead on top. The overhead is entirely the loop/recur -> recursive-
closure-called-per-iteration lowering; hand-Janet written the same way matches
jolt, while a while+var/set version is 1.43x faster. So a cheap backend win
(jolt-v28u) sits above the structural native-codegen lever.

Adds the spike artifacts under bench/ and the results writeup; marks the spike
done in the handoff. No source changes.

Co-authored-by: Yogthos <yogthos@gmail.com>

bench/dump-mandelbrot-emit.janet

@@ -0,0 +1,28 @@
+# Dump the Janet that jolt's backend emits for the mandelbrot hot fns, so we can
+# A/B it against bench/mandelbrot-hand.janet and localize the ~1.43x jolt-over-
+# hand-Janet gap measured in the foundational-runtime spike (jolt-5vsp).
+(import ../src/jolt/api :as api)
+(import ../src/jolt/backend :as backend)
+(import ../src/jolt/reader :as reader)
+
+(def ctx (api/init-cached {:compile? true}))
+(put (ctx :env) :direct-linking? true)
+(put (ctx :env) :inline? true)
+(api/eval-string ctx "(ns mandelbrot)")
+
+(def count-point-src
+  "(defn count-point [cr ci cap] (loop [i 0 zr 0.0 zi 0.0] (if (or (>= i cap) (> (+ (* zr zr) (* zi zi)) 4.0)) i (recur (inc i) (+ (- (* zr zr) (* zi zi)) cr) (+ (* 2.0 (* zr zi)) ci)))))")
+
+(def run-src
+  "(defn run [n] (let [cap 200 nd (* 1.0 n)] (loop [y 0 acc 0] (if (< y n) (let [ci (- (/ (* 2.0 y) nd) 1.0) row (loop [x 0 a 0] (if (< x n) (let [cr (- (/ (* 2.0 x) nd) 1.5)] (recur (inc x) (+ a (count-point cr ci cap)))) a))] (recur (inc y) (+ acc row))) acc))))")
+
+(api/eval-string ctx count-point-src)
+(api/eval-string ctx run-src)
+
+(defn emit [src]
+  (string/format "%p" (backend/emit-ir ctx (backend/analyze-form ctx (reader/parse-string src)))))
+
+(print "===== count-point emitted Janet =====")
+(print (emit count-point-src))
+(print "\n===== run emitted Janet =====")
+(print (emit run-src))

bench/mandelbrot-hand-rec.janet

@@ -0,0 +1,49 @@
+# mandelbrot — hand-written Janet that MIRRORS jolt's loop-lowering: every loop/
+# recur becomes a self-recursive local closure stored in a var and called once
+# per iteration (see bench/dump-mandelbrot-emit.janet). If this lands at jolt's
+# ~219ms (vs the while-loop mandelbrot-hand.janet's ~153ms), the ~1.43x jolt-
+# over-hand-Janet gap is the recursive-closure loop lowering, not anything else.
+#   janet bench/mandelbrot-hand-rec.janet 200
+
+(defn count-point [cr ci cap]
+  (var loopfn nil)
+  (set loopfn (fn [i zr zi]
+    (if (let [t (>= i cap)] (if t t (> (+ (* zr zr) (* zi zi)) 4)))
+      i
+      (loopfn (+ i 1)
+              (+ (- (* zr zr) (* zi zi)) cr)
+              (+ (* 2 (* zr zi)) ci)))))
+  (loopfn 0 0 0))
+
+(defn run [n]
+  (def cap 200)
+  (def nd (* 1 n))
+  (var yloop nil)
+  (set yloop (fn [y acc]
+    (if (< y n)
+      (let [ci (- (/ (* 2 y) nd) 1)
+            row (do
+                  (var xloop nil)
+                  (set xloop (fn [x a]
+                    (if (< x n)
+                      (let [cr (- (/ (* 2 x) nd) 1.5)]
+                        (xloop (+ x 1) (+ a (count-point cr ci cap))))
+                      a)))
+                  (xloop 0 0))]
+        (yloop (+ y 1) (+ acc row)))
+      acc)))
+  (yloop 0 0))
+
+(defn main [& args]
+  (def n (if (> (length args) 1) (scan-number (get args 1)) 1000))
+  (repeat 2 (run (div n 2)))
+  (def times @[])
+  (var last-r 0)
+  (repeat 3
+    (def t0 (os/clock))
+    (def r (run n))
+    (array/push times (* 1000.0 (- (os/clock) t0)))
+    (set last-r r))
+  (printf "mandelbrot n %d result %d" n last-r)
+  (print "runs: " (string/join (map |(string (/ (math/round (* $ 10.0)) 10.0)) times) " "))
+  (printf "mean: %.1f ms" (/ (sum times) 3)))

bench/mandelbrot-hand.janet

@@ -0,0 +1,53 @@
+# mandelbrot — hand-written idiomatic Janet, same nested loop as bench/mandelbrot.clj.
+# This is the "optimal Janet" leg of the foundational-runtime spike (jolt-5vsp):
+# comparing jolt-emitted Janet vs this vs JVM localizes the 15x compute floor —
+# jolt-backend overhead vs the Janet VM's own floor.
+#
+#   janet bench/mandelbrot-hand.janet 200
+
+(defn count-point [cr ci cap]
+  (var i 0)
+  (var zr 0.0)
+  (var zi 0.0)
+  (while (and (< i cap) (<= (+ (* zr zr) (* zi zi)) 4.0))
+    (def nzr (+ (- (* zr zr) (* zi zi)) cr))
+    (def nzi (+ (* 2.0 (* zr zi)) ci))
+    (set zr nzr)
+    (set zi nzi)
+    (++ i))
+  i)
+
+(defn run [n]
+  (def cap 200)
+  (def nd (* 1.0 n))
+  (var acc 0)
+  (var y 0)
+  (while (< y n)
+    (def ci (- (/ (* 2.0 y) nd) 1.0))
+    (var x 0)
+    (var a 0)
+    (while (< x n)
+      (def cr (- (/ (* 2.0 x) nd) 1.5))
+      (set a (+ a (count-point cr ci cap)))
+      (++ x))
+    (set acc (+ acc a))
+    (++ y))
+  acc)
+
+(defn main [& args]
+  (def n (if (> (length args) 1) (scan-number (get args 1)) 1000))
+  # warmup
+  (repeat 2 (run (div n 2)))
+  (def runs 3)
+  (def times @[])
+  (var last-r 0)
+  (repeat runs
+    (def t0 (os/clock))
+    (def r (run n))
+    (def ms (* 1000.0 (- (os/clock) t0)))
+    (set last-r r)
+    (array/push times ms))
+  (def mean (/ (sum times) runs))
+  (printf "mandelbrot n %d result %d" n last-r)
+  (print "runs: " (string/join (map |(string (/ (math/round (* $ 10.0)) 10.0)) times) " "))
+  (printf "mean: %.1f ms" mean))