Loop Blocking for fn GPU Backend #1382

Job	Run time
perftests (gcc-8, release)	1m 29s
perftests (gcc-9, release)	1m 31s
perftests (gcc-10, release)	1m 38s
perftests (gcc-11, release)	1m 40s
perftests (gcc-12, debug)	2m 9s
perftests (gcc-12, release)	1m 39s
perftests (gcc-13, debug)	2m 10s
perftests (gcc-13, release)	1m 38s
perftests (clang-11, debug)	1m 59s
perftests (clang-11, release)	1m 54s
perftests (clang-12, debug)	1m 55s
perftests (clang-12, release)	1m 53s
perftests (clang-13, release)	1m 55s
perftests (clang-14, release)	2m 5s
perftests (clang-15, debug)	1m 47s
perftests (clang-15, release)	1m 56s
perftests (clang-16, debug)	1m 54s
perftests (clang-16, release)	1m 56s
perftests (clang-14-cuda-11, debug)	5m 54s
perftests (clang-14-cuda-11, release)	5m 17s
perftests (gcc-10-cuda-11.8, debug)	5m 49s
perftests (gcc-10-cuda-11.8, release)	5m 17s
perftests (gcc-11-cuda-12.0, debug)	5m 41s
perftests (gcc-11-cuda-12.0, release)	5m 4s
perftests (gcc-12-cuda-12.3, debug)	6m 0s
perftests (gcc-12-cuda-12.3, release)	5m 10s
perftests (gcc-12-cuda-12.4, debug)	5m 51s
perftests (gcc-12-cuda-12.4, release)	5m 4s
perftests (base-hip, debug)	7m 27s
perftests (base-hip, release)	6m 23s
perftests (gcc-10-hpx, release)	3m 25s
perftests (nvhpc-23.3, debug)	9m 13s
perftests (nvhpc-23.3, release)	10m 2s
perftests (nvhpc-23.9, debug)	8m 45s
perftests (nvhpc-23.9, release)	9m 55s
	2h 23m 25s

Provide feedback