Oleksandr Pavlyk debde4f4b2 Lazy-load nvbench-compare bulk timing data ...

Store JSON-bin sample time and frequency metadata in GpuTimingData instead of
reading the binary files during summary extraction.

Add Float32BinarySource and lazy cached accessors for samples and frequencies.
Use np.fromfile by default, but allow tests and alternate callers to inject a
float32 reader returning any buffer-compatible object convertable to "<f4" data
type.

Treat optional bulk-data failures as unavailable evidence instead of aborting
comparison: unreadable files, invalid buffers, count mismatches, and mismatched
sample/frequency metadata now emit RuntimeWarning and return None.

Update nvbench_compare tests to verify lazy loading, cache reuse, injected
reader behavior, warning-based degradation, and count mismatch handling.

2026-06-02 15:55:02 -05:00

..

run_1.py

Correct Python API signature of State.get_axis_values_as_strings (#346)

2026-05-04 08:40:29 -05:00

stubs.py

Add python api for cold warmup parameters (#363)

2026-05-18 10:56:44 -05:00

test_benchmark_result.py

Provide BenchmarkResult class for parsing JSON output of NVBench-instrumented benchmarks (#356)

2026-05-13 13:23:58 -05:00

test_cuda_bench.py

Add python api for cold warmup parameters (#363)

2026-05-18 10:56:44 -05:00

test_nvbench_compare.py

Lazy-load nvbench-compare bulk timing data

2026-06-02 15:55:02 -05:00

test_nvbench_json_summary.py

Provide BenchmarkResult class for parsing JSON output of NVBench-instrumented benchmarks (#356)

2026-05-13 13:23:58 -05:00