RIKEN-RCCS · william-dawson · Jul 31, 2026 · Jul 31, 2026 · Jul 31, 2026 · Jul 31, 2026
diff --git a/config/queue.csv b/config/queue.csv
@@ -1,5 +1,5 @@
 queue,submit_cmd,template
-SLURM_RIKYU,sbatch,"-p ${queue_group} -t ${elapse} -N ${nodes} --ntasks-per-node=${numproc_node} --cpus-per-task=${nthreads} --gpus-per-node=${numproc_node}"
+SLURM_RIKYU,sbatch,"-p ${queue_group} --account=${account} -t ${elapse} -N ${nodes} --ntasks-per-node=${numproc_node} --cpus-per-task=${nthreads} --gpus=${proc}"
 FJ,pjsub,"-L rscunit=rscunit_ft01,rscgrp=${queue_group},elapse=${elapse},node=${nodes} --mpi max-proc-per-node=${numproc_node} -x PJM_LLIO_GFSCACHE=/vol0002:/vol0003:/vol0004:/vol0005"
 PJM_GENKAI,pjsub,"-L rscgrp=${queue_group},elapse=${elapse},node=${nodes} --mpi proc=${proc}"
 SLURM_RC,sbatch,"-p ${queue_group} -t ${elapse} -N ${nodes} --ntasks-per-node=${numproc_node} --cpus-per-task=${nthreads}"

diff --git a/config/system.csv b/config/system.csv
@@ -1,9 +1,9 @@
-system,mode,tag_build,tag_run,queue,queue_group
-RIKYU,cross,ai4ss_login,ai4ss_jacamar,SLURM_RIKYU,1n1gpu
+system,mode,tag_build,tag_run,queue,queue_group,account
+RIKYU,cross,ai4ss_login,ai4ss_jacamar,SLURM_RIKYU,gpu,rkp00012
 Fugaku,cross,fugaku_login1,fugaku_jacamar,FJ,small
 FugakuCN,native,,fugaku_jacamar,FJ,small
 RC_GH200,native,,cloud_jacamar,SLURM_RC,qc-gh200
-RC_DGXSP,native,,cloud_jacamar,SLURM_RC,ng-dgx-3h
+RC_DGXSP,native,,cloud_jacamar,SLURM_RC,ng-dgx-m1
 RC_GENOA,native,,cloud_jacamar,SLURM_RC,genoa
 RC_FX700,native,,cloud_jacamar,SLURM_RC,fx700
 MiyabiG,cross,miyabi_g_login,miyabi_g_jacamar,PBS_Miyabi,debug-g

diff --git a/docs/cx/BENCHKIT_SPEC.md b/docs/cx/BENCHKIT_SPEC.md
@@ -251,7 +251,7 @@ BenchKit の system / queue 定義層である。
 - `queue.csv` に scheduler template を持つ
 - app 側の `list.csv` から system 固有事情を切り離す
 
-`system.csv` は system 名、mode、runner tag、queue、queue_group などの正本である。
+`system.csv` は system 名、mode、runner tag、queue、queue_group、scheduler account などの正本である。
 
 This is the system and queue definition layer.
 
@@ -261,7 +261,8 @@ Main roles:
 - `queue.csv` holds scheduler templates
 - system-specific concerns are separated from app-side `list.csv`
 
-`system.csv` is the source of truth for items such as system name, mode, runner tag, queue, and queue_group.
+`system.csv` is the source of truth for items such as system name, mode,
+runner tag, queue, queue_group, and scheduler account.
 
 ### 6.4 ポータル層 / Portal Layer
 

diff --git a/docs/guides/add-site.md b/docs/guides/add-site.md
@@ -547,12 +547,12 @@ command_delay = "30s"
 ### `config/system.csv` にシステムを追加
 
 ```csv
-system,mode,tag_build,tag_run,queue,queue_group
+system,mode,tag_build,tag_run,queue,queue_group,account
 # 既存エントリ...
 # cross モード（ビルドと実行が別ノード）
-NewSystem,cross,newsystem_login,newsystem_jacamar,PBS_NewSystem,default
+NewSystem,cross,newsystem_login,newsystem_jacamar,PBS_NewSystem,default,
 # native モード（同一ノードでビルドと実行）
-NewSystemLN,native,,newsystem_login,none,default
+NewSystemLN,native,,newsystem_login,none,default,
 ```
 
 - `system`: システム名（アプリの `list.csv` から参照される）
@@ -561,6 +561,7 @@ NewSystemLN,native,,newsystem_login,none,default
 - `tag_run`: 実行用GitLab Runnerタグ（`native`の場合はbuild_runジョブ用）
 - `queue`: `config/queue.csv` のキュー名（ログインノードは `none`）
 - `queue_group`: キューグループ名
+- `account`: scheduler account/project。不要な拠点では空欄
 
 ### `config/queue.csv` にキューシステムを追加（必要な場合）
 
@@ -571,7 +572,7 @@ queue,submit_cmd,template
 PBS_NewSystem,qsub,"-q ${queue_group} -l select=${nodes} -l walltime=${elapse} -W group_list=your_group"
 ```
 
-テンプレート内で使える変数：`${queue_group}`, `${nodes}`, `${numproc_node}`, `${nthreads}`, `${elapse}`, `${proc}`（`nodes * numproc_node`）, `${cpu_per_node}`, `${gpu_per_node}`, `${cpu_sockets}`（`nodes * cpu_per_node`）, `${gpu_cards}`（`nodes * gpu_per_node`）
+テンプレート内で使える変数：`${queue_group}`, `${account}`, `${nodes}`, `${numproc_node}`, `${nthreads}`, `${elapse}`, `${proc}`（`nodes * numproc_node`）, `${cpu_per_node}`, `${gpu_per_node}`, `${cpu_sockets}`（`nodes * cpu_per_node`）, `${gpu_cards}`（`nodes * gpu_per_node`）
 
 `${cpu_per_node}` と `${gpu_per_node}` は `config/system_info.csv` から取得します。CPU socket 数や GPU card 数を scheduler に明示するサイトでは、`system_info.csv` の値も投入条件に使われます。
 

diff --git a/programs/sbd/README.md b/programs/sbd/README.md
@@ -0,0 +1,78 @@
+# SBD benchmark
+
+This BenchKit application runs the NVIDIA Thrust TPB selected-basis
+diagonalization benchmark from `github.com/r-ccs-cms/sbd`.
+
+The RIKYU recipe uses the H2O cc-pVDZ FCIDUMP with the `1em7` selected alpha
+determinant file (about 628 million product determinants), one MPI rank per
+B200 GPU, and the rank-distributed/index-reordered/NCCL build configuration
+validated in the SubWG2 benchmark study. The inputs are included under
+`programs/sbd/data/h2o/` and can be overridden with `BK_SBD_INPUT_DIR` when a
+project-storage copy is preferred.
+
+The DGX Spark route uses the H2O `1em5` input (about 30.4 million product
+determinants), the Thrust backend with `cc120`, NVHPC/HPC-X CUDA 13 `26.3`,
+and one MPI rank on the single GB10 GPU. The larger `1em7` case reaches about
+98 GB before its first Davidson iteration and is killed by the 128 GB node's
+memory limit. `1em5` retains a substantial GPU workload while leaving enough
+memory headroom and runtime margin for continuous benchmarking. NCCL is disabled
+for the single-GPU case, and all three explicit communicator sizes are one. The
+Rikyu rows retain the `1em7` input and validated `1 x 2 x 2` explicit layout;
+their remaining rank factor becomes SBD's implicit Hamiltonian communicator.
+
+The R-CCS Cloud GH200 route uses the H2O `1em6` input (about 191 million
+product determinants), the Thrust backend with `cc90`, NVHPC/HPC-X CUDA 13
+`26.3`, and one MPI rank on its unified Grace Hopper superchip. No Slurm GPU
+request is made because `qc-gh200` exposes its single GPU as part of the node.
+NCCL is disabled for the single-rank case.
+
+The R-CCS Cloud FX700 route uses the H2O `1em4` input (about 2.38 million
+product determinants) with four MPI ranks and 12 OpenMP threads per rank,
+bound one rank per A64FX NUMA/CMG domain. SBD requires C++17 features missing
+from Fujitsu compiler 4.11.1's bundled libc++, so this route uses the system
+GCC 8.5/MPICH stack with 512-bit SVE enabled. It links Fujitsu's optimized
+LAPACK and its required runtime libraries by absolute path. The absolute paths
+are intentional: adding the Fujitsu library directory with `-L` causes
+MPICH's trailing `-lmpi` to resolve to Fujitsu MPI instead, mixing two MPI
+implementations in one executable.
+
+The input files are copied unchanged from SBD's tracked `data/h2o` directory;
+`data/h2o/README.md` records the upstream revision, checksums, and Apache-2.0
+provenance.
+
+The emitted FOM is SBD's internal Davidson time in seconds. Shell wall time is
+not used because MPI startup and scheduler overhead are substantial on RIKYU.
+The run is accepted only when its energy matches the established reference for
+its selected input within a combined `1e-12 + 1e-11 |E|` tolerance.
+
+The DGX Spark route was validated on `ng-dgx-m2` with NVHPC 26.3. The exact
+energy was `-76.24373504205295 Ha`; the internal Davidson FOM was
+`228.928853 s`, and the complete Slurm job took 4 minutes 9 seconds.
+
+The R-CCS Cloud GH200 route was directly validated on `qc-gh200-01` with
+NVHPC 26.3. The exact energy was `-76.24377593489788 Ha`; the internal
+Davidson FOM was `520.734720 s`, the multiply section was `22.730310 s`, and
+the complete Slurm job took 9 minutes 34 seconds.
+
+The R-CCS Cloud FX700 route was directly validated on `fx29` with GCC 8.5,
+MPICH 4.0, 512-bit SVE, and Fujitsu LAPACK. The exact energy was
+`-76.2429584823075 Ha`; the internal Davidson FOM was `747.636165 s`, the
+multiply section was `33.897903 s`, and the complete Slurm job took 13 minutes
+3 seconds.
+
+The Rikyu route was validated with NVHPC 26.3 on project `rkp00012`. All
+three rows converged to `-76.243776776861 Ha`:
+
+| B200 GPUs | Nodes | Internal Davidson FOM (s) | 4-GPU-relative speedup |
+|---:|---:|---:|---:|
+| 4 | 1 | 565.510 | 1.00x |
+| 8 | 2 | 290.222 | 1.95x |
+| 16 | 4 | 152.144 | 3.72x |
+
+A fresh BenchKit validation rebuilt upstream SBD commit
+`9481f290c2f49d4f8e5df9b0c9c87ea0f7937c2c` through `build.sh`, confirmed the
+effective `cc100` rank-distributed/index-reordered/NCCL configuration, and
+submitted the eight-GPU row through `scripts/test_submit.sh`. The job converged
+to `-76.2437767768609 Ha` with a `290.281226 s` internal Davidson FOM, and
+`scripts/result.sh` produced valid result JSON with source provenance and the
+`mult` timing section.
diff --git a/programs/sbd/build.sh b/programs/sbd/build.sh
@@ -0,0 +1,94 @@
+#!/bin/bash
+set -euo pipefail
+
+system="$1"
+source scripts/bk_functions.sh
+
+REPO_URL="https://github.com/r-ccs-cms/sbd.git"
+REPO_DIR="sbd"
+BUILD_DIR=""
+ARTIFACT_DIR="${PWD}/artifacts"
+
+mkdir -p "${ARTIFACT_DIR}"
+bk_fetch_source "${REPO_URL}" "${REPO_DIR}" "main"
+cd "${REPO_DIR}"
+
+case "${system}" in
+  RIKYU)
+    module purge
+    module load nvhpc/26.3
+    BUILD_DIR="build-rikyu-nvhpc-thrust-rankdist-nccl"
+    nccl_root="/shared/software/hpc_sdk/Linux_aarch64/26.3/comm_libs/13.1/nccl"
+    cmake -S . -B "${BUILD_DIR}" \
+      -DCMAKE_BUILD_TYPE=Release \
+      -DSBD_GPU_BACKEND=thrust \
+      -DSBD_GPU_ARCH=cc100 \
+      -DSBD_THRUST_SAFE_MPI_ALLREDUCE=ON \
+      -DSBD_USE_RANK_DISTRIBUTION=ON \
+      -DSBD_USE_BLOCK_RANK_DISTRIBUTION=ON \
+      -DSBD_REORDER_INDEX_ARRAY=ON \
+      -DSBD_USE_NCCL=ON \
+      -DCMAKE_CXX_FLAGS="-I${nccl_root}/include" \
+      -DCMAKE_EXE_LINKER_FLAGS="-L${nccl_root}/lib -lnccl"
+    cmake --build "${BUILD_DIR}" --parallel
+    ;;
+  RC_DGXSP)
+    source /etc/profile.d/modules.sh
+    module purge
+    module load system/ng-dgx nvhpc-hpcx-cuda13/26.3
+    BUILD_DIR="build-dgxsp-nvhpc-thrust-rankdist"
+    cmake -S . -B "${BUILD_DIR}" \
+      -DCMAKE_BUILD_TYPE=Release \
+      -DSBD_GPU_BACKEND=thrust \
+      -DSBD_GPU_ARCH=cc120 \
+      -DSBD_THRUST_SAFE_MPI_ALLREDUCE=ON \
+      -DSBD_USE_RANK_DISTRIBUTION=ON \
+      -DSBD_USE_BLOCK_RANK_DISTRIBUTION=ON \
+      -DSBD_REORDER_INDEX_ARRAY=ON \
+      -DSBD_USE_NCCL=OFF
+    cmake --build "${BUILD_DIR}" --parallel
+    ;;
+  RC_GH200)
+    module purge
+    module load system/qc-gh200 nvhpc-hpcx-cuda13/26.3
+    BUILD_DIR="build-gh200-nvhpc-thrust-rankdist"
+    cmake -S . -B "${BUILD_DIR}" \
+      -DCMAKE_BUILD_TYPE=Release \
+      -DSBD_GPU_BACKEND=thrust \
+      -DSBD_GPU_ARCH=cc90 \
+      -DSBD_THRUST_SAFE_MPI_ALLREDUCE=ON \
+      -DSBD_USE_RANK_DISTRIBUTION=ON \
+      -DSBD_USE_BLOCK_RANK_DISTRIBUTION=ON \
+      -DSBD_REORDER_INDEX_ARRAY=ON \
+      -DSBD_USE_NCCL=OFF
+    cmake --build "${BUILD_DIR}" --parallel
+    ;;
+  RC_FX700)
+    module purge
+    module load system/fx700 mpi/mpich-aarch64
+    BUILD_DIR="build-fx700-gcc-mpich-rankdist"
+    fjlib="/opt/FJSVstclanga/cp-1.0.30.01/lib64"
+    cmake -S . -B "${BUILD_DIR}" \
+      -DCMAKE_BUILD_TYPE=Release \
+      -DCMAKE_CXX_COMPILER=mpicxx \
+      -DCMAKE_CXX_FLAGS="-march=armv8.2-a+sve -msve-vector-bits=512" \
+      -DBLAS_LIBRARIES="${fjlib}/libfjlapack.so" \
+      -DLAPACK_LIBRARIES="${fjlib}/libfjlapack.so" \
+      -DCMAKE_CXX_STANDARD_LIBRARIES="${fjlib}/libfj90i.so ${fjlib}/libfj90f.so ${fjlib}/libfjsrcinfo.so -lelf" \
+      -DSBD_USE_RANK_DISTRIBUTION=ON \
+      -DSBD_USE_BLOCK_RANK_DISTRIBUTION=ON \
+      -DSBD_REORDER_INDEX_ARRAY=ON
+    cmake --build "${BUILD_DIR}" --parallel
+    ;;
+  *)
+    echo "Unknown system: ${system}" >&2
+    exit 1
+    ;;
+esac
+
+binary="${BUILD_DIR}/apps/chemistry_tpb_selected_basis_diagonalization/diag"
+if [[ ! -x "${binary}" ]]; then
+  echo "SBD executable not found: ${binary}" >&2
+  exit 1
+fi
+cp "${binary}" "${ARTIFACT_DIR}/diag"
diff --git a/programs/sbd/data/h2o/README.md b/programs/sbd/data/h2o/README.md
@@ -0,0 +1,24 @@
+# SBD H₂O benchmark inputs
+
+These files are copied unchanged from the SBD repository's tracked
+`data/h2o/` directory:
+
+- Repository: https://github.com/r-ccs-cms/sbd
+- Upstream revision: `02324eee32a49f3203522d230bcbc34ef032a6a6`
+- Files: `fcidump.txt`, `h2o-1em4-alpha.txt`, `h2o-1em5-alpha.txt`,
+  `h2o-1em6-alpha.txt`, `h2o-1em7-alpha.txt`
+
+SHA-256 checksums:
+
+```text
+a3c2302834a33dce7260e8050a3f5180e05dbba1bb748f3e2f6410a7eacbd94d  fcidump.txt
+858c1ef9d430aafe0c325281c7257c2e6cb0e77310a707c1109c55747db02139  h2o-1em4-alpha.txt
+40b29271726daa2be5a5b181535647164e915646710c2641e46dd1ed078a2ee6  h2o-1em5-alpha.txt
+c36920e57507d27dd49d2b729662cbb5a92afce26d61fb0e044e2691599eb804  h2o-1em6-alpha.txt
+1f7af972b56143a9ae6862c02288668656a5bd3fb561337c430e0e478f7cb716  h2o-1em7-alpha.txt
+```
+
+The upstream SBD repository distributes these files under its Apache-2.0
+license (`LICENSE.txt`). They are retained here so the BenchKit application
+can run without private project storage. Set `BK_SBD_INPUT_DIR` to use an
+equivalent project-storage copy instead.