P3: vectorised nearest-neighbour search; task-driven cloud trials

- fit.py: exact and binned nearest-neighbour searches use one distance
  matrix per searched bin (first-minimum rule kept); fit 2.6 s -> 1.4 s
  per GSA sample, still bit-identical to the oracle
- scripts/validate_p3_large.py: refits 1.2.0 and 1.1.2 transforms for
  every vendor GTC and reports ULP distances per field
- cloud trial runs scripts/cloud/tasks/<TASK>.sh (TASK=p3 default;
  p1p2 = previous validation + ingest)

scripts/cloud/tasks/p1p2.sh

@@ -0,0 +1,12 @@
+#!/bin/bash
+# Phase P1/P2 validation on the 1000 Genomes Omni2.5 set + `simurg ingest` at scale.
+# Args: <data dir with bpm/egt/csv and data/>  <results dir>
+set -uo pipefail
+D=$1; OUT=$2
+.venv/bin/python scripts/validate_p1_large.py --root $D/data --bpm $D/HumanOmni2.5-4v1-Multi_B.bpm \
+  --egt $D/HumanOmni2.5-4v1-Multi_B.egt --csv $D/HumanOmni2.5-4v1_B.csv --out $OUT/summary.json \
+  --workers "$(nproc)" || echo "validation reported differences (see summary.json)"
+/usr/bin/time -v .venv/bin/simurg ingest --bpm $D/HumanOmni2.5-4v1-Multi_B.bpm --idats $D/data \
+  --out /work/ingest --threads "$(nproc)" --quiet 2> $OUT/ingest_time.txt || echo "ingest exit code $?"
+cp /work/ingest/ingest_summary.tsv $OUT/ingest_summary.tsv 2>/dev/null || true
+cp /work/ingest/run_manifest.json $OUT/ingest_run_manifest.json 2>/dev/null || true

scripts/cloud/tasks/p3.sh

@@ -0,0 +1,8 @@
+#!/bin/bash
+# Phase P3: refit normalization transforms (1.2.0 and 1.1.2) for every vendor GTC and compare bit by bit.
+# Args: <data dir with bpm and data/>  <results dir>
+set -uo pipefail
+D=$1; OUT=$2
+/usr/bin/time -v .venv/bin/python scripts/validate_p3_large.py --root $D/data --bpm $D/HumanOmni2.5-4v1-Multi_B.bpm \
+  --out $OUT/summary.json --workers "$(nproc)" 2> $OUT/time.txt || echo "P3 validation reported differences"
+tail -25 $OUT/time.txt

scripts/cloud/trial.sh

@@ -18,6 +18,7 @@ MAX_PRICE=${MAX_PRICE:-0.30}        # USD/hour spot cap (on-demand is 0.6528)
 MAX_MINUTES=${MAX_MINUTES:-360}     # hard cap: 6 hours
 DISK_GB=${DISK_GB:-250}
 BUDGET_USD=${BUDGET_USD:-10}
+TASK=${TASK:-p3}                 # scripts/cloud/tasks/<TASK>.sh
 TAG=simurg-trial
 ACCOUNT=$(aws sts get-caller-identity --query Account --output text)
 BUCKET=simurg-trial-$ACCOUNT
@@ -60,10 +61,12 @@ launch)
   echo "-> packing repository at $(git rev-parse --short HEAD) -> s3://$BUCKET/$RUN/"
   git archive --format=tar.gz -o /tmp/simurg-repo.tar.gz HEAD
   $AWS s3 cp /tmp/simurg-repo.tar.gz "s3://$BUCKET/$RUN/repo.tar.gz" --only-show-errors
-  sed -e "s/__BUCKET__/$BUCKET/" -e "s/__RUN__/$RUN/" -e "s/__MAX_MINUTES__/$MAX_MINUTES/" \
+  [[ -f scripts/cloud/tasks/$TASK.sh ]] || { echo "unknown TASK $TASK"; exit 2; }
+  sed -e "s/__BUCKET__/$BUCKET/" -e "s/__RUN__/$RUN/" -e "s/__MAX_MINUTES__/$MAX_MINUTES/" -e "s/__TASK__/$TASK/g" \
     scripts/cloud/userdata.sh > /tmp/simurg-userdata.sh
   AMI=$($AWS ssm get-parameter --name /aws/service/canonical/ubuntu/server/24.04/stable/current/arm64/hvm/ebs-gp3/ami-id \
     --query Parameter.Value --output text)
+  echo "-> task: $TASK"
   echo "-> launching $TYPE spot (cap \$$MAX_PRICE/h, hard limit ${MAX_MINUTES} min, ${DISK_GB} GB disk deleted on exit)"
   ID=$($AWS ec2 run-instances --image-id "$AMI" --instance-type "$TYPE" --count 1 \
     --iam-instance-profile Name=$ROLE \

scripts/cloud/userdata.sh

@@ -54,20 +54,10 @@ echo "=== streaming 107 GB IDAT+GTC archive (no copy of the .tgz is kept) $(date
 $S3 cp --no-sign-request "$SRC/Omni25_idats_gtcs_2141_samples.tgz" - | pigz -dc | tar -x -C $D/data
 echo "=== extracted $(du -sh $D/data | cut -f1) at $(date -u +%T) ==="
 
-echo "=== validation $(date -u +%T) ==="
+echo "=== unit tests $(date -u +%T) ==="
 .venv/bin/python -m pytest tests/unit -q -p no:cacheprovider || echo "unit tests reported failures (continuing)"
-.venv/bin/python scripts/validate_p1_large.py --root $D/data --bpm $D/HumanOmni2.5-4v1-Multi_B.bpm \
-  --egt $D/HumanOmni2.5-4v1-Multi_B.egt --csv $D/HumanOmni2.5-4v1_B.csv --out /work/summary.json \
-  --workers "$(nproc)" || echo "validation reported differences (see summary.json)"
-$S3 cp /work/summary.json "s3://$BUCKET/$RUN/summary.json" --only-show-errors
-
-echo "=== simurg ingest at scale $(date -u +%T) ==="
-/usr/bin/time -v .venv/bin/simurg ingest --bpm $D/HumanOmni2.5-4v1-Multi_B.bpm --idats $D/data \
-  --out /work/ingest --threads "$(nproc)" --quiet 2> /work/ingest_time.txt || echo "ingest exit code $?"
-tail -25 /work/ingest_time.txt
-for f in ingest_summary.tsv run_manifest.json; do
-  $S3 cp "/work/ingest/$f" "s3://$BUCKET/$RUN/ingest_$f" --only-show-errors || true
-done
-$S3 cp /work/ingest_time.txt "s3://$BUCKET/$RUN/ingest_time.txt" --only-show-errors || true
-echo "ingest output size: $(du -sh /work/ingest | cut -f1)"
+echo "=== task __TASK__ $(date -u +%T) ==="
+mkdir -p /work/results
+bash scripts/cloud/tasks/__TASK__.sh $D /work/results || echo "task exit code $?"
+$S3 cp /work/results "s3://$BUCKET/$RUN/" --recursive --only-show-errors || true
 echo "=== done $(date -u +%T) ==="