George Necula 313caba4cb [shape_poly] Add micro-benchmarks for symbolic shape manipulation. ...

In some of the cases when we use many symbolic expressions for shapes, the operations with
symbolic expressions are becoming somewhat costly. These benchmarks help with picking
good internal representations.

PiperOrigin-RevId: 604289958

2024-02-05 05:38:25 -08:00

..

api_benchmark.py

in partial_eval_custom rule for pjit, cache ClosedJaxpr creation

2023-12-21 15:35:45 -08:00

linalg_benchmark.py

Use a Jacobi SVD solver for unbatched SVDs up to 1024x1024 on NVIDIA GPUs.

2023-11-13 12:04:13 -08:00

math_benchmark.py

Update flags to use the ABSL typed flag API.

2023-07-27 12:15:58 -07:00

random_benchmark.py

fast dispatch for functions over typed PRNG key arrays

2023-09-13 09:43:58 -07:00

shape_poly_benchmark.py

[shape_poly] Add micro-benchmarks for symbolic shape manipulation.

2024-02-05 05:38:25 -08:00

sparse_benchmark.py

[jax][benchmark] Added clearing caches for benchmarking compilation time in sparse JAX benchmarks

2023-08-02 10:07:54 -07:00