QOL improvements to float8 gemm benchmark (#596)

Summary:

1. add more options for shape generation, such as
  - square: M == K == N sweeping through powers of 2
  - sweep: M, K, N each sweeping through powers of 2
  - custom: user specifies a single value of M, K, N
2. fix a bug when calling `torch._scaled_mm`, we should create the
   scales outside the benchmark for a less biased result
3. add sweep over `fast_accum` setting
4. add ability to save result to file, for easy analysis later

Test Plan:

```
time python benchmarks/float8/bench_matmul.py --out_filename ~/local/tmp/20240803_f8_gemm_sweep_2.csv --shape_gen_name sweep
// result: https://gist.github.com/vkuzo/1d82e84ddd8aac8166695d819ebc8883
```

Reviewers:

Subscribers:

Tasks:

Tags: