LOAD AND TEST after the COMPARE AND SWAP doesn't make much sense. However, it makes lots of sense when used BEFORE the C&S.
An example — and many other suggested coding nuggets — can be found in Kevin Shum's presentation "IBM z Systems Processor Optimization Primer", available at https://www.ibm.com/developerworks/community/forums/html/topic?id=5cf34211-c8e6-4747-a8c2-f8ff7379150b
