TL/UCP: adjust barrier radix

[shimmybalsam]

What

Change default radix for TL/UCP barrier to 8

Why ?

Better perf for OOB

[shimmybalsam]

dpu-rock (AMD) 8 nodes:

<style> </style>

	hcoll	ucc oob(radix=4)	ucc radix = 2	ucc radix = 8
ppn=1	3.57	4.06	4.98	3.27
ppn=64	12.43	15.12	14.41	13.58

jazz (Intel) 8 nodes:

<style> </style>

	hcoll	ucc oob(radix=4)	ucc radix = 2	ucc radix = 8
ppn=1	2.13	2.42	3.19	1.78
ppn=64	4.66	5.49	6.45	4.95