nvprobe 0.1.0__tar.gz

nvprobe-0.1.0/LICENSE

@@ -0,0 +1,199 @@
+                              Apache License
+                        Version 2.0, January 2004
+                     http://www.apache.org/licenses/
+
+TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+1. Definitions.
+
+   "License" shall mean the terms and conditions for use, reproduction,
+   and distribution as defined by Sections 1 through 9 of this document.
+
+   "Licensor" shall mean the copyright owner or entity authorized by
+   the copyright owner that is granting the License.
+
+   "Legal Entity" shall mean the union of the acting entity and all
+   other entities that control, are controlled by, or are under common
+   control with that entity. For the purposes of this definition,
+   "control" means (i) the power, direct or indirect, to cause the
+   direction or management of such entity, whether by contract or
+   otherwise, or (ii) ownership of fifty percent (50%) or more of the
+   outstanding shares, or (iii) beneficial ownership of such entity.
+
+   "You" (or "Your") shall mean an individual or Legal Entity
+   exercising permissions granted by this License.
+
+   "Source" form shall mean the preferred form for making modifications,
+   including but not limited to software source code, documentation
+   source, and configuration files.
+
+   "Object" form shall mean any form resulting from mechanical
+   transformation or translation of a Source form, including but
+   not limited to compiled object code, generated documentation,
+   and conversions to other media types.
+
+   "Work" shall mean the work of authorship, whether in Source or
+   Object form, made available under the License, as indicated by a
+   copyright notice that is included in or attached to the work
+   (an example is provided in the Appendix below).
+
+   "Derivative Works" shall mean any work, whether in Source or Object
+   form, that is based on (or derived from) the Work and for which the
+   editorial revisions, annotations, elaborations, or other modifications
+   represent, as a whole, an original work of authorship. For the purposes
+   of this License, Derivative Works shall not include works that remain
+   separable from, or merely link (or bind by name) to the interfaces of,
+   the Work and Derivative Works thereof.
+
+   "Contribution" shall mean any work of authorship, including
+   the original version of the Work and any modifications or additions
+   to that Work or Derivative Works thereof, that is intentionally
+   submitted to the Licensor for inclusion in the Work by the copyright owner
+   or by an individual or Legal Entity authorized to submit on behalf of
+   the copyright owner. For the purposes of this definition, "submitted"
+   means any form of electronic, verbal, or written communication sent
+   to the Licensor or its representatives, including but not limited to
+   communication on electronic mailing lists, source code control systems,
+   and issue tracking systems that are managed by, or on behalf of, the
+   Licensor for the purpose of discussing and improving the Work, but
+   excluding communication that is conspicuously marked or otherwise
+   designated in writing by the copyright owner as "Not a Contribution."
+
+   "Contributor" shall mean Licensor and any individual or Legal Entity
+   on behalf of whom a Contribution has been received by the Licensor and
+   subsequently incorporated within the Work.
+
+2. Grant of Copyright License. Subject to the terms and conditions of
+   this License, each Contributor hereby grants to You a perpetual,
+   worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+   copyright license to reproduce, prepare Derivative Works of,
+   publicly display, publicly perform, sublicense, and distribute the
+   Work and such Derivative Works in Source or Object form.
+
+3. Grant of Patent License. Subject to the terms and conditions of
+   this License, each Contributor hereby grants to You a perpetual,
+   worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+   (except as stated in this section) patent license to make, have made,
+   use, offer to sell, sell, import, and otherwise transfer the Work,
+   where such license applies only to those patent claims licensable
+   by such Contributor that are necessarily infringed by their
+   Contribution(s) alone or by combination of their Contribution(s)
+   with the Work to which such Contribution(s) was submitted. If You
+   institute patent litigation against any entity (including a
+   cross-claim or counterclaim in a lawsuit) alleging that the Work
+   or a Contribution incorporated within the Work constitutes direct
+   or contributory patent infringement, then any patent licenses
+   granted to You under this License for that Work shall terminate
+   as of the date such litigation is filed.
+
+4. Redistribution. You may reproduce and distribute copies of the
+   Work or Derivative Works thereof in any medium, with or without
+   modifications, and in Source or Object form, provided that You
+   meet the following conditions:
+
+   (a) You must give any other recipients of the Work or
+       Derivative Works a copy of this License; and
+
+   (b) You must cause any modified files to carry prominent notices
+       stating that You changed the files; and
+
+   (c) You must retain, in the Source form of any Derivative Works
+       that You distribute, all copyright, patent, trademark, and
+       attribution notices from the Source form of the Work,
+       excluding those notices that do not pertain to any part of
+       the Derivative Works; and
+
+   (d) If the Work includes a "NOTICE" text file as part of its
+       distribution, then any Derivative Works that You distribute must
+       include a readable copy of the attribution notices contained
+       within such NOTICE file, excluding any notices that do not
+       pertain to any part of the Derivative Works, in at least one
+       of the following places: within a NOTICE text file distributed
+       as part of the Derivative Works; within the Source form or
+       documentation, if provided along with the Derivative Works; or,
+       within a display generated by the Derivative Works, if and
+       wherever such third-party notices normally appear. The contents
+       of the NOTICE file are for informational purposes only and
+       do not modify the License. You may add Your own attribution
+       notices within Derivative Works that You distribute, alongside
+       or as an addendum to the NOTICE text from the Work, provided
+       that such additional attribution notices cannot be construed
+       as modifying the License.
+
+   You may add Your own copyright statement to Your modifications and
+   may provide additional or different license terms and conditions
+   for use, reproduction, or distribution of Your modifications, or
+   for any such Derivative Works as a whole, provided Your use,
+   reproduction, and distribution of the Work otherwise complies with
+   the conditions stated in this License.
+
+5. Submission of Contributions. Unless You explicitly state otherwise,
+   any Contribution intentionally submitted for inclusion in the Work
+   by You to the Licensor shall be under the terms and conditions of
+   this License, without any additional terms or conditions.
+   Notwithstanding the above, nothing herein shall supersede or modify
+   the terms of any separate license agreement you may have executed
+   with Licensor regarding such Contributions.
+
+6. Trademarks. This License does not grant permission to use the trade
+   names, trademarks, service marks, or product names of the Licensor,
+   except as required for reasonable and customary use in describing the
+   origin of the Work and reproducing the content of the NOTICE file.
+
+7. Disclaimer of Warranty. Unless required by applicable law or
+   agreed to in writing, Licensor provides the Work (and each
+   Contributor provides its Contributions) on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+   implied, including, without limitation, any warranties or conditions
+   of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+   PARTICULAR PURPOSE. You are solely responsible for determining the
+   appropriateness of using or redistributing the Work and assume any
+   risks associated with Your exercise of permissions under this License.
+
+8. Limitation of Liability. In no event and under no legal theory,
+   whether in tort (including negligence), contract, or otherwise,
+   unless required by applicable law (such as deliberate and grossly
+   negligent acts) or agreed to in writing, shall any Contributor be
+   liable to You for damages, including any direct, indirect, special,
+   incidental, or consequential damages of any character arising as a
+   result of this License or out of the use or inability to use the
+   Work (including but not limited to damages for loss of goodwill,
+   work stoppage, computer failure or malfunction, or any and all
+   other commercial damages or losses), even if such Contributor
+   has been advised of the possibility of such damages.
+
+9. Accepting Warranty or Additional Liability. While redistributing
+   the Work or Derivative Works thereof, You may choose to offer,
+   and charge a fee for, acceptance of support, warranty, indemnity,
+   or other liability obligations and/or rights consistent with this
+   License. However, in accepting such obligations, You may act only
+   on Your own behalf and on Your sole responsibility, not on behalf
+   of any other Contributor, and only if You agree to indemnify,
+   defend, and hold each Contributor harmless for any liability
+   incurred by, or claims asserted against, such Contributor by reason
+   of your accepting any such warranty or additional liability.
+
+END OF TERMS AND CONDITIONS
+
+APPENDIX: How to apply the Apache License to your work.
+
+   To apply the Apache License to your work, attach the following
+   boilerplate notice, with the fields enclosed by brackets "[]"
+   replaced with your own identifying information. (Don't include
+   the brackets!)  The text should be enclosed in the appropriate
+   comment syntax for the file format. Please also get an original
+   template from http://www.apache.org/licenses/LICENSE-2.0
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

nvprobe-0.1.0/MANIFEST.in

@@ -0,0 +1,4 @@
+include LICENSE
+include NOTICE
+include README.md
+recursive-include nvprobe *.py

nvprobe-0.1.0/NOTICE

@@ -0,0 +1,5 @@
+nvProbe
+Copyright 2026 SergioZ3R0
+
+This product includes software developed by the nvProbe project.
+Licensed under the Apache License, Version 2.0.

nvprobe-0.1.0/PKG-INFO

@@ -0,0 +1,209 @@
+Metadata-Version: 2.4
+Name: nvprobe
+Version: 0.1.0
+Summary: NVIDIA GPU benchmark suite for CUDA workload automation, reporting, and comparison
+Author: SergioZ3R0
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://github.com/SergioZ3R0/nvprobe
+Project-URL: Repository, https://github.com/SergioZ3R0/nvprobe
+Project-URL: Issues, https://github.com/SergioZ3R0/nvprobe/issues
+Keywords: gpu,nvidia,cuda,benchmark,hpc,slurm,mlperf
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: Operating System :: POSIX :: Linux
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: System :: Benchmark
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+License-File: NOTICE
+Requires-Dist: typer>=0.9.0
+Requires-Dist: pyyaml>=6.0
+Requires-Dist: matplotlib>=3.7
+Requires-Dist: jinja2>=3.1
+Requires-Dist: rich>=13.0
+Provides-Extra: cuda
+Requires-Dist: cupy-cuda12x>=13.0; extra == "cuda"
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0; extra == "dev"
+Requires-Dist: ruff>=0.4; extra == "dev"
+Dynamic: license-file
+
+# nvProbe
+
+NVIDIA GPU benchmark suite for CUDA workload automation, reporting, and comparison.
+
+nvProbe runs standardized benchmarks across your GPU fleet, captures environment details, stores results in SQLite, and generates self-contained HTML reports — helping HPC engineers and ML teams make data-driven hardware purchasing decisions.
+
+## Features
+
+- **Benchmark modules**: Bandwidth, custom CUDA kernels (matmul, conv2d, attention), HPL, HPCG, MLPerf
+- **Slurm integration**: Generate and submit sbatch scripts, run across multiple nodes/GPUs
+- **Environment fingerprinting**: Driver version, CUDA version, GPU model, memory, PCI bus ID — captured automatically
+- **SQLite storage**: All results persisted with full query capability
+- **CSV/JSON export**: Raw data for programmatic access
+- **HTML reports**: Self-contained reports with matplotlib charts, sidebar navigation, and comparison views
+- **YAML configs**: Define test matrices (GPU models, precisions, batch sizes) declaratively
+- **Reproducible**: Same config + same hardware = same results
+
+## Quick Start
+
+```bash
+git clone https://github.com/SergioZ3R0/nvprobe.git
+cd nvprobe
+pip install -e .
+```
+
+### Detect GPU environment
+
+```bash
+nvprobe env
+```
+
+### Run benchmarks (dry run)
+
+```bash
+nvprobe run --config configs/default.yaml --dry-run
+```
+
+### Run benchmarks
+
+```bash
+nvprobe run --config configs/default.yaml
+```
+
+### Generate report
+
+```bash
+nvprobe report
+```
+
+### Compare two runs
+
+```bash
+nvprobe compare --a results/run1 --b results/run2
+```
+
+## Configuration
+
+Edit `configs/default.yaml` to define your test matrix:
+
+```yaml
+name: my-benchmark-run
+description: "Comparing L40S vs B200"
+
+gpu:
+  models: ["L40S", "B200"]
+
+slurm:
+  enabled: true
+  partition: gpu
+  gpus_per_node: 8
+
+precisions:
+  - fp32
+  - fp16
+  - int8
+
+benchmarks:
+  - name: bandwidth
+    enabled: true
+    params:
+      sizes_mb: [1, 4, 16, 64, 256, 1024]
+  - name: custom
+    enabled: true
+    params:
+      kernels: [matmul, conv2d, attention]
+```
+
+## Project Structure
+
+```
+nvprobe/
+├── nvprobe/
+│   ├── cli.py              # CLI entry point
+│   ├── config.py           # YAML config loader
+│   ├── runner.py           # Benchmark orchestration
+│   ├── slurm.py            # Slurm job management
+│   ├── reporter.py         # HTML report generator with charts
+│   ├── db.py               # SQLite storage + CSV/JSON export
+│   └── benchmarks/
+│       ├── base.py         # Base benchmark class
+│       ├── bandwidth.py    # Memory bandwidth tests
+│       ├── custom.py       # Custom CUDA kernels
+│       ├── hpl.py          # HPL wrapper
+│       ├── hpcg.py         # HPCG wrapper
+│       ├── mlperf.py       # MLPerf wrapper
+│       └── _cuda/
+│           ├── bandwidth_test.py   # CUDA bandwidth implementation
+│           ├── custom_kernels.py   # matmul/conv2d/attention
+│           └── utils.py            # Shared GPU utilities
+├── configs/
+│   └── default.yaml        # Default test configuration
+├── reports/                 # Generated HTML reports
+├── results/                 # Benchmark results (SQLite + JSON)
+├── README.md
+└── pyproject.toml
+```
+
+## Roadmap
+
+### v0.1.0 — Project base ✓
+- CLI with Typer (run, report, compare, env, version)
+- YAML config system for test matrices
+- Benchmark module framework (base class + stubs)
+- Runner with nvidia-smi environment detection
+- SQLite storage for results
+- HTML report generator (basic)
+- Default config for L40S/B200 GPUs
+
+### v0.2.0 — CUDA benchmarks ✓
+- Bandwidth test (host↔device, device↔device) via cupy
+- Custom CUDA kernels: matmul, conv2d, attention
+- HPL/HPCG binary wrappers with Slurm script generation
+- MLPerf inference/training wrapper
+- Optional cupy dependency (`pip install nvprobe[cuda]`)
+
+### v0.3.0 — Slurm integration ✓
+- sbatch script generation
+- Job submission and monitoring
+- Multi-GPU parallel execution
+- Result collection from Slurm output
+
+### v0.4.0 — Reporting ✓
+- Matplotlib charts (bandwidth, matmul, attention, GPU comparison)
+- Corporate branding (sidebar, color palette, env cards)
+- Comparison reports (A vs B)
+- CSV/JSON auto-export alongside HTML
+
+### v0.5.0 — Reproducibility ✓
+- Singularity container support (CUDA 12.4 runtime)
+- Makefile for common dev operations
+- Git-tracked configs and results
+- Singularity container support
+- Environment fingerprinting
+- Git-tracked configs and results
+
+## Requirements
+
+- Python 3.10+
+- NVIDIA GPU with CUDA drivers installed
+- Slurm (for multi-node execution)
+- `nvidia-smi` available in PATH
+- Singularity (optional, for containerized execution)
+
+## Container
+
+```bash
+make container-build    # builds nvprobe.sif
+make container-run      # runs with --nv GPU passthrough
+```
+
+## License
+
+[Apache License 2.0](LICENSE)

nvprobe-0.1.0/README.md

@@ -0,0 +1,173 @@
+# nvProbe
+
+NVIDIA GPU benchmark suite for CUDA workload automation, reporting, and comparison.
+
+nvProbe runs standardized benchmarks across your GPU fleet, captures environment details, stores results in SQLite, and generates self-contained HTML reports — helping HPC engineers and ML teams make data-driven hardware purchasing decisions.
+
+## Features
+
+- **Benchmark modules**: Bandwidth, custom CUDA kernels (matmul, conv2d, attention), HPL, HPCG, MLPerf
+- **Slurm integration**: Generate and submit sbatch scripts, run across multiple nodes/GPUs
+- **Environment fingerprinting**: Driver version, CUDA version, GPU model, memory, PCI bus ID — captured automatically
+- **SQLite storage**: All results persisted with full query capability
+- **CSV/JSON export**: Raw data for programmatic access
+- **HTML reports**: Self-contained reports with matplotlib charts, sidebar navigation, and comparison views
+- **YAML configs**: Define test matrices (GPU models, precisions, batch sizes) declaratively
+- **Reproducible**: Same config + same hardware = same results
+
+## Quick Start
+
+```bash
+git clone https://github.com/SergioZ3R0/nvprobe.git
+cd nvprobe
+pip install -e .
+```
+
+### Detect GPU environment
+
+```bash
+nvprobe env
+```
+
+### Run benchmarks (dry run)
+
+```bash
+nvprobe run --config configs/default.yaml --dry-run
+```
+
+### Run benchmarks
+
+```bash
+nvprobe run --config configs/default.yaml
+```
+
+### Generate report
+
+```bash
+nvprobe report
+```
+
+### Compare two runs
+
+```bash
+nvprobe compare --a results/run1 --b results/run2
+```
+
+## Configuration
+
+Edit `configs/default.yaml` to define your test matrix:
+
+```yaml
+name: my-benchmark-run
+description: "Comparing L40S vs B200"
+
+gpu:
+  models: ["L40S", "B200"]
+
+slurm:
+  enabled: true
+  partition: gpu
+  gpus_per_node: 8
+
+precisions:
+  - fp32
+  - fp16
+  - int8
+
+benchmarks:
+  - name: bandwidth
+    enabled: true
+    params:
+      sizes_mb: [1, 4, 16, 64, 256, 1024]
+  - name: custom
+    enabled: true
+    params:
+      kernels: [matmul, conv2d, attention]
+```
+
+## Project Structure
+
+```
+nvprobe/
+├── nvprobe/
+│   ├── cli.py              # CLI entry point
+│   ├── config.py           # YAML config loader
+│   ├── runner.py           # Benchmark orchestration
+│   ├── slurm.py            # Slurm job management
+│   ├── reporter.py         # HTML report generator with charts
+│   ├── db.py               # SQLite storage + CSV/JSON export
+│   └── benchmarks/
+│       ├── base.py         # Base benchmark class
+│       ├── bandwidth.py    # Memory bandwidth tests
+│       ├── custom.py       # Custom CUDA kernels
+│       ├── hpl.py          # HPL wrapper
+│       ├── hpcg.py         # HPCG wrapper
+│       ├── mlperf.py       # MLPerf wrapper
+│       └── _cuda/
+│           ├── bandwidth_test.py   # CUDA bandwidth implementation
+│           ├── custom_kernels.py   # matmul/conv2d/attention
+│           └── utils.py            # Shared GPU utilities
+├── configs/
+│   └── default.yaml        # Default test configuration
+├── reports/                 # Generated HTML reports
+├── results/                 # Benchmark results (SQLite + JSON)
+├── README.md
+└── pyproject.toml
+```
+
+## Roadmap
+
+### v0.1.0 — Project base ✓
+- CLI with Typer (run, report, compare, env, version)
+- YAML config system for test matrices
+- Benchmark module framework (base class + stubs)
+- Runner with nvidia-smi environment detection
+- SQLite storage for results
+- HTML report generator (basic)
+- Default config for L40S/B200 GPUs
+
+### v0.2.0 — CUDA benchmarks ✓
+- Bandwidth test (host↔device, device↔device) via cupy
+- Custom CUDA kernels: matmul, conv2d, attention
+- HPL/HPCG binary wrappers with Slurm script generation
+- MLPerf inference/training wrapper
+- Optional cupy dependency (`pip install nvprobe[cuda]`)
+
+### v0.3.0 — Slurm integration ✓
+- sbatch script generation
+- Job submission and monitoring
+- Multi-GPU parallel execution
+- Result collection from Slurm output
+
+### v0.4.0 — Reporting ✓
+- Matplotlib charts (bandwidth, matmul, attention, GPU comparison)
+- Corporate branding (sidebar, color palette, env cards)
+- Comparison reports (A vs B)
+- CSV/JSON auto-export alongside HTML
+
+### v0.5.0 — Reproducibility ✓
+- Singularity container support (CUDA 12.4 runtime)
+- Makefile for common dev operations
+- Git-tracked configs and results
+- Singularity container support
+- Environment fingerprinting
+- Git-tracked configs and results
+
+## Requirements
+
+- Python 3.10+
+- NVIDIA GPU with CUDA drivers installed
+- Slurm (for multi-node execution)
+- `nvidia-smi` available in PATH
+- Singularity (optional, for containerized execution)
+
+## Container
+
+```bash
+make container-build    # builds nvprobe.sif
+make container-run      # runs with --nv GPU passthrough
+```
+
+## License
+
+[Apache License 2.0](LICENSE)

nvprobe-0.1.0/nvprobe/__init__.py

@@ -0,0 +1,3 @@
+"""nvProbe — NVIDIA GPU benchmark suite for CUDA workload automation."""
+
+__version__ = "0.1.0"

nvprobe-0.1.0/nvprobe/benchmarks/__init__.py

@@ -0,0 +1,24 @@
+"""Benchmark modules for nvProbe."""
+
+from nvprobe.benchmarks.bandwidth import BandwidthBenchmark
+from nvprobe.benchmarks.custom import CustomCudaBenchmark
+from nvprobe.benchmarks.hpl import HplBenchmark
+from nvprobe.benchmarks.hpcg import HpcgBenchmark
+from nvprobe.benchmarks.mlperf import MlperfBenchmark
+
+BENCHMARK_REGISTRY: dict[str, type] = {
+    "bandwidth": BandwidthBenchmark,
+    "custom": CustomCudaBenchmark,
+    "hpl": HplBenchmark,
+    "hpcg": HpcgBenchmark,
+    "mlperf": MlperfBenchmark,
+}
+
+__all__ = [
+    "BENCHMARK_REGISTRY",
+    "BandwidthBenchmark",
+    "CustomCudaBenchmark",
+    "HplBenchmark",
+    "HpcgBenchmark",
+    "MlperfBenchmark",
+]

nvprobe-0.1.0/nvprobe/benchmarks/_cuda/__init__.py

@@ -0,0 +1 @@
+"""nvProbe CUDA test modules — called as subprocesses by benchmark runners."""