update operator_range discription in op bench (#30170)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/30170
as title
Test Plan:
```
buck-out/opt/gen/caffe2/benchmarks/operator_benchmark/benchmark_all_other_test.par --tag_filter all --iterations 1 --operator_range ef
...
ValueError: The correct format for operator_range is <start>-<end>, or <point>, <start>-<end>
buck-out/opt/gen/caffe2/benchmarks/operator_benchmark/benchmark_all_other_test.par --tag_filter all --iterations 1 --operator_range a-b
# ----------------------------------------
# PyTorch/Caffe2 Operator Micro-benchmarks
# ----------------------------------------
# Tag : all
# Benchmarking PyTorch: add
# Mode: Eager
# Name: add_M8_N32_K256_cpu
# Input: M: 8, N: 32, K: 256, device: cpu
Forward Execution Time (us) : 60.551
# Benchmarking PyTorch: add
# Mode: Eager
# Name: add_M8_N32_K256_cuda
# Input: M: 8, N: 32, K: 256, device: cuda
Forward Execution Time (us) : 67.716
...
buck-out/opt/gen/caffe2/benchmarks/operator_benchmark/benchmark_all_other_test.par --tag_filter all --iterations 1 --operator_range b,d-f
# ----------------------------------------
# PyTorch/Caffe2 Operator Micro-benchmarks
# ----------------------------------------
# Tag : all
# Benchmarking PyTorch: batchnorm
# Mode: Eager
# Name: batchnorm_M1_N256_K3136_cpu
# Input: M: 1, N: 256, K: 3136, device: cpu
Forward Execution Time (us) : 296.004
...
Reviewed By: hl475
Differential Revision: D18619975
fbshipit-source-id: 08f27ee2aeda47be431385f4b20ef7fbeb797516