simplify pimcomp compare workflow

validation/networks/pimcomp_models/README.md

@@ -136,12 +136,11 @@ random placement code occasionally segfaults; an unchanged retry succeeded in
 the observed cases.
 
 The paper's optimizer uses a genetic algorithm with population 200 and up to
-1000 iterations. Select it with `-r=GA` for optimizer studies. The released
-source keeps population 200 but sets `max_iteration = 3`, so reproducing the
-paper's optimization search also requires changing that value in
-`backend/GeneticAlgorithm.h`. GA allocates roughly 32 GB in its fast evaluator;
-use monolith below instead of reducing cores or crossbars when local RAM is
-insufficient.
+1000 iterations. The checked-out PIMCOMP submodule already has both paper
+settings in `backend/GeneticAlgorithm.h`; select them with `-r=GA`. Fitness
+evaluation uses OpenMP and bounded bandwidth timelines. Set `OMP_NUM_THREADS`
+to control its parallelism; otherwise OpenMP uses the available CPUs. The GA
+uses the fixed seed `1`, so repeated serial and parallel runs are reproducible.
 
 ## Compare Raptor and PIMCOMP
 
@@ -150,34 +149,37 @@ compiles both instruction streams, runs both through `pimsim-nn`, validates
 Raptor through the Rust simulator, and writes Markdown and JSON reports.
 PIMCOMP Rust validation also runs when its optional exporter is available.
 
-To reproduce the complete Arch-A latency experiment, use the serial experiment
-runner. It creates an isolated PIMCOMP build with population 200 and 1000 GA
-iterations, runs only the `element`/batch-1 latency pipeline, and invokes the
-comparison driver for one model at a time:
+To reproduce the complete Arch-A latency experiment, use the model-by-model
+runner. It verifies the paper GA settings, builds Raptor and the existing
+`third_party/PIMCOMP-NN/build` tree, then runs the `element`/batch-1 comparison
+for one model at a time:
 
 ```bash
-.venv/bin/python validation/tools/run_pimcomp_paper_latency.py \
-  --out-dir /tmp/raptor-pimcomp-paper-latency
+.venv/bin/python validation/tools/run_pimcomp_paper_latency.py
 ```
 
-Reports are written under `<out-dir>/<model>/comparison_report.{md,json}`.
-Use `--models vgg8` to run one model, `--resume` after an interruption, or
-`--dry-run` to inspect every command. The runner continues after a failed model
-so all reports are produced.
+Each model directory reuses regular validation's ignored `inputs/`, `outputs/`,
+`runner/`, `raptor/`, and `simulation/` paths. PIMCOMP-only artifacts and
+`comparison_report.{md,json}` live under `pimcomp/`. The frontend regenerates
+one isolated `models/JSON/` graph because PIMCOMP requires that relative
+layout; it is removed after a successful backend run and the shared submodule
+model directory is never modified. Models requiring BatchNormalization folding
+also receive a prepared ONNX file; other models use the original ONNX directly.
+PIMCOMP's source tree and build directory remain unchanged at runtime. Use
+`--models vgg8` to run one model, `--resume` after an interruption, `--dry-run`
+to inspect every command, or `--out-dir PATH` to keep results outside
+`validation/`. The runner continues after a failed model so all reports are
+produced.
 
 Arch-A low-latency example:
 
 ```bash
 RAPTOR_ROOT=$PWD
-PIMCOMP="$RAPTOR_ROOT/third_party/PIMCOMP-NN"
-CONFIG_BACKUP=$(mktemp)
-cp "$PIMCOMP/config.json" "$CONFIG_BACKUP"
-trap 'cp "$CONFIG_BACKUP" "$PIMCOMP/config.json"' EXIT
-cp "$RAPTOR_ROOT/validation/pimsim_configs/pimcomp/arch-a/latency_config.json" "$PIMCOMP/config.json"
 
 "$RAPTOR_ROOT/.venv/bin/python" "$RAPTOR_ROOT/validation/tools/compare_raptor_pimcomp.py" \
   --model "$RAPTOR_ROOT/validation/networks/pimcomp_models/resnet34/resnet34-v1-7.onnx" \
-  --out-dir /tmp/compare-resnet34-arch-a-ll \
+  --out-dir "$RAPTOR_ROOT/validation/networks/pimcomp_models/resnet34" \
+  --pimcomp-config "$RAPTOR_ROOT/validation/pimsim_configs/pimcomp/arch-a/latency_config.json" \
   --core-count 168 \
   --crossbar-count 96 \
   --crossbar-size 128 \
@@ -196,11 +198,9 @@ If only semantic and instruction comparison is required, add
 `--skip-pimsim-nn`. A VGG-8 run with the same Arch-A LL settings passed both
 semantic validations with maximum output differences below `5e-10`.
 
-The current PIMCOMP-NN submodule does not include the optional
-`verification/export_to_pim_simulator.py` helper. The driver therefore records
-PIMCOMP Rust semantic validation as skipped, while PIMCOMP compilation,
-instruction reporting, and `pimsim-nn` latency still run. Use
-`--fail-on-error` only when that semantic export helper is available.
+The comparison runner enables `--fail-on-error`, so a failed compiler,
+simulation, or semantic validation makes the command fail while preserving the
+generated report.
 
 Current Raptor status:
 
@@ -247,14 +247,13 @@ python3 -m venv .venv
 .venv/bin/python -m pip install numpy onnx onnxruntime onnxsim colorama
 
 # Run every latency comparison serially.
-.venv/bin/python validation/tools/run_pimcomp_paper_latency.py \
-  --out-dir /tmp/raptor-pimcomp-paper-latency
+.venv/bin/python validation/tools/run_pimcomp_paper_latency.py
 ```
 
 Copy reports back without transferring large compiler artifacts:
 
 ```bash
 rsync -az --include='*/' --include='comparison_report.*' --exclude='*' \
-  monolith:/tmp/raptor-pimcomp-paper-latency/ \
-  /tmp/raptor-pimcomp-paper-latency/
+  "monolith:$REMOTE_REPO/validation/networks/pimcomp_models/" \
+  validation/networks/pimcomp_models/
 ```

validation/networks/pimcomp_models/RESULTS.md

@@ -25,7 +25,6 @@ No throughput experiment was run.
 
 ```bash
 .venv/bin/python validation/tools/run_pimcomp_paper_latency.py \
-  --out-dir /tmp/raptor-pimcomp-paper-latency \
   --models googlenet
 ```