Enable -tritonintelgpu-optimize-reduction-locality by default

[victor-eds]

After pending issues that will be listed below are merged, this pass can be enabled by default:

• Allow sub-group transpose and shuffles with more than one contiguous row per thread #2749
• Allow scalars as triton_gen.simdblockread and triton_gen.simdblockwrite type arguments #2750
• Avoid bank conflicts on sub-group transposes #2751
• Revamp -tritonintelgpu-optimize-reduction-locality #2752

Speedups after these changes in victor/perf-test (attn benchmark):
Min Speedup: 0.997086
Quartile 1: 1.000324
Median: 1.026954
Quartile 2: 1.121962
Max speedup: 1.181823
Average: 1.064171
Average if improved (>=1.05): 1.131925
#Improved (>=1.05): 12/26
#Worse (>=1.05): 0

[victor-eds]

Blocked: There are some performance regressions after latest optimizations were pushed. Trying alternative approaches.