perf(build): use all cores in host builds — wx lib, test apps, gal-webgl

env.sh exports a docker-safe JOBS=1 default, and every host build silently
inherited it (the docker kicad path dodges it by passing -j explicitly):

- build-wx-wasm.sh: the intended "${JOBS:-nproc}" fallback sat BELOW the
  env.sh source, so it was dead code — full wx builds ran make -j1 on the
  Mac and on CI. Compute the all-cores default before env.sh instead
  (explicit JOBS/PARALLEL_JOBS still wins); also -j the PCRE pre-build.
- build-wasm-test.sh: same default fix, plus fan the post-link
  hoist+asyncify loop out across JOBS with xargs -P. Per-app wasm-opt
  can't feed many cores (small modules), so serial stays ~4min even with
  BINARYEN_CORES=16; fanning across the 74 independent apps is what
  scales. Safe: apply-asyncify is in-place per wasm, injector tmp is
  per-js, HOIST_WASMOPT resolved once up front.
- build-gal-webgl-test.sh: make had no -j at all.

Measured on a 16-core M4 Max, clean test-app build: 15m36s (-j1) → 2m08s,
peak RAM 10.7 GB summed across all build processes (64 GB machine; CI
runners have 120 GB). Core counts are always derived from nproc at
runtime — nothing hardcoded, CI workers differ.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01XeiSRRScdaox5jBueJNcyG

scripts/build-gal-webgl-test.sh

@@ -21,6 +21,10 @@ set -e
 
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 
+# Default to all cores BEFORE env.sh (its docker-safe JOBS=1 default would stick
+# otherwise); an explicit JOBS/PARALLEL_JOBS from the caller still wins.
+JOBS="${JOBS:-$(nproc 2>/dev/null || sysctl -n hw.ncpu 2>/dev/null || echo 4)}"
+
 # Source common environment (sets up local emsdk)
 QUIET=1 source "$SCRIPT_DIR/common/env.sh"
 
@@ -76,9 +80,9 @@ python3 generate_shaders.py
 echo ""
 echo "Building..."
 if [ "$DEBUG_BUILD" = "1" ]; then
-    make DEBUG=1
+    make -j"${JOBS:-1}" DEBUG=1
 else
-    make
+    make -j"${JOBS:-1}"
 fi
 
 echo ""

scripts/build-wasm-test.sh

@@ -3,6 +3,10 @@
 
 # Redirect all output to a log file (re-execs script with redirection)
 source "$(dirname "$0")/common/logging.sh"
+# Default to all cores BEFORE env.sh (its docker-safe JOBS=1 default would stick
+# otherwise); an explicit JOBS/PARALLEL_JOBS from the caller still wins. Measured
+# 2026-07-02 (16-core M4 Max): clean build 15m36s at -j1 → ~2min, peak RAM ~11 GB.
+JOBS="${JOBS:-$(nproc 2>/dev/null || sysctl -n hw.ncpu 2>/dev/null || echo 4)}"
 source "$(dirname "$0")/common/env.sh"
 # This script creates library symlinks and builds the test apps
 #
@@ -136,19 +140,30 @@ fi
 # so re-running it here is safe. The .wasm gets post-link hoist + asyncify first.
 _eh_restore_wasmopt; trap - EXIT
 echo ""
-echo "=== Post-link --hoist-cpp-catches + --asyncify ==="
+echo "=== Post-link --hoist-cpp-catches + --asyncify (${JOBS:-1}-wide) ==="
-while IFS= read -r w; do
+# The apps are independent here too (apply-asyncify rewrites each wasm in place; the shim
-    "$SCRIPT_DIR/common/apply-asyncify.sh" --no-removelist "$w"
+# injector's temp file is per-js), so fan the post-link out across JOBS like the make phase.
-    js="${w%.wasm}.js"
+# This dominates the build: per-app wasm-opt can't feed many cores (small modules, serial
-    if [ -f "$js" ]; then
+# parse/write), so parallelism must come from running apps side by side — serial 3m52s even
-        ( cd "$(dirname "$js")" && "$SCRIPT_DIR/common/inject-dyncall-shims.sh" "$(basename "$js")" )
+# with BINARYEN_CORES=16, vs 2m08s fanned out at ~11 GB peak RAM. HOIST_WASMOPT is resolved
-    fi
+# once above, so workers skip the binaryen ninja check. xargs fails the build (exit 123) if
+# any app's post-link fails.
+export SCRIPT_DIR
 # Match EVERY freshly-linked app wasm, not just standalone/*/*_test.wasm: the main demo
 # (apps/minimal_test.wasm) is at the apps/ root, and the coroutine-pthread repros + wxpt app
 # are *_repro*.wasm / *_wxpt.wasm. The old '*_test.wasm under standalone' filter silently
 # skipped all of those, so under native wasm-EH they never got hoist+asyncify and crashed at
 # runtime with "asyncify_start_unwind not found".
-done < <(find "$WASM_APP_DIR" -name '*.wasm' -newer "$EH_MARKER")
+find "$WASM_APP_DIR" -name '*.wasm' -newer "$EH_MARKER" -print0 \
+  | xargs -0 -n1 -P "${JOBS:-1}" bash -c '
+    set -eo pipefail
+    w="$1"
+    "$SCRIPT_DIR/common/apply-asyncify.sh" --no-removelist "$w"
+    js="${w%.wasm}.js"
+    if [ -f "$js" ]; then
+        ( cd "$(dirname "$js")" && "$SCRIPT_DIR/common/inject-dyncall-shims.sh" "$(basename "$js")" )
+    fi
+' _
 rm -f "$EH_MARKER"
 
 echo ""

scripts/build-wx-wasm.sh

@@ -5,6 +5,13 @@
 # Redirect all output to a log file (re-execs script with redirection)
 source "$(dirname "$0")/common/logging.sh"
 
+# Default to all cores BEFORE sourcing env.sh — env.sh exports a docker-safe
+# JOBS=1 when unset, which would make the "${JOBS:-nproc}" fallback below it
+# dead code (this build ran make -j1 everywhere for that reason). An explicit
+# JOBS/PARALLEL_JOBS from the caller still wins (e.g. the docker pipeline's -j
+# via build-kicad-target.sh).
+JOBS="${JOBS:-$(nproc 2>/dev/null || sysctl -n hw.ncpu 2>/dev/null || echo 4)}"
+
 # Source common environment (sets up local emsdk)
 source "$(dirname "$0")/common/env.sh"
 # Build-progress markers (parsed by scripts/build-monitor.sh).
@@ -53,9 +60,6 @@ export CONFIG_SHELL="$SCRIPT_DIR/config/config-sub-wrapper.sh"
 # Disable autom4te cache to keep submodules clean
 export AUTOM4TE="$SCRIPT_DIR/config/autom4te-wrapper.sh"
 
-# Use JOBS from env.sh if set, otherwise use all available cores
-JOBS="${JOBS:-$(nproc 2>/dev/null || sysctl -n hw.ncpu 2>/dev/null || echo 4)}"
-
 echo "=== Building wxWidgets for WASM ==="
 echo "Project root: $PROJECT_ROOT"
 echo "Build dir: $BUILD_DIR"
@@ -187,7 +191,8 @@ if [ $NEEDS_CONFIGURE -eq 1 ]; then
     # PCRE headers (pcre2.h) must be generated before regex.cpp compiles
     echo ""
     echo "=== Building PCRE first (dependency) ==="
-    emmake make -C 3rdparty/pcre
+    # Serial relative to the main build (it fully completes first); parallel inside.
+    emmake make -j${JOBS} -C 3rdparty/pcre
 fi
 
 # Ensure the Emscripten zlib port exists before compiling. We configure with