Codex/add bboplace 2 0

2.0/README.md

@@ -34,3 +34,21 @@ This variant keeps the same SIFT1M-scale service contract and recall target as
 `vector_db_ann`, but reduces the load/index-build penalty by 10x so stronger
 offline indexing strategies are more viable. Its problem ID is
 `vector_db_ann_relaxed`.
+
+## BBOPlace ISPD2005
+
+This VLSI placement problem asks agents to generate macro placement candidates
+for the ISPD2005 benchmarks used by BBOPlace-Bench. Its problem ID is
+`bboplace_ispd2005`. The public iterative feedback path evaluates the first
+benchmark only, while the final verifier reruns the best iterative artifact and
+the final submission across the full ISPD2005 suite. Scoring minimizes MP-HPWL
+against relaxed MGO baselines and clips negative scores to zero. The task is
+CPU-only and does not require DREAMPlace, GPU execution, or Ray.
+
+## BBOPlace ICCAD2015
+
+This VLSI placement problem uses the ICCAD2015 benchmark suite from
+BBOPlace-Bench. Its problem ID is `bboplace_iccad2015`. It follows the same
+candidate format, CPU-only evaluator, MP-HPWL metric, relaxed MGO baselines,
+and quick-versus-final evaluation flow as `bboplace_ispd2005`, but scores the
+ICCAD2015 benchmark set.

2.0/problems/bboplace_iccad2015/config.yaml

@@ -0,0 +1,15 @@
+tag: optimization
+runtime:
+  language: python
+  timeout_seconds: 10800
+  environment: "Python solution returning BBOPlace MGO placement candidates; hidden ICCAD2015 judge data"
+  apt_packages:
+    - python3-numpy
+  docker:
+    image: ubuntu:24.04
+    judge_image: ghcr.io/frontiercs/frontiercs-bboplace-data:2026-06-ispd-iccad
+environment:
+  cpus: 8
+  memory_mb: 16384
+  storage_mb: 8192
+  build_timeout_seconds: 3600

2.0/problems/bboplace_iccad2015/evaluate.sh

@@ -0,0 +1,12 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+SCRIPT_DIR=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)
+SOLUTION="/work/execution_env/solution_env/solution.py"
+
+if [[ ! -f "$SOLUTION" ]]; then
+  echo "Error: Missing $SOLUTION" >&2
+  exit 1
+fi
+
+python "$SCRIPT_DIR/evaluator.py" "$SOLUTION"