STRICT build of dslash_mdw_fused_* fails with sm_86

[jcosborn]

A STRICT build using sm_86 with MULTIGRID on fails with:
Building CUDA object lib/CMakeFiles/quda.dir/dslash_mdw_fused_ls20.cu.o
ptxas error : Value of threads per SM for entry ZN4quda10raw_kernelINS_18mobius_tensor_core17FusedMobiusDslashENS1_14FusedDslashArgIsLi3EL21QudaReconstructType_s8ELi20ELNS_19MdwfFusedDslashTypeE4ELi32ELi3ELb0EEELb0EEEvT0 is out of range. .minnctapersm will be ignored

[maddyscientist]

@hummingtree can you take a look?

[hummingtree]

@jcosborn This is due to SM 86, 87 and 89 only allow a maximum number of 1536 (as supposed to 2048) per SM. I will have a PR to fix this. Meanwhile you can disable this part of the code by having -D QUDA_MDW_FUSED_LS_LIST="" as part of the cmake parameters, which would decrease your compile time by quite a bit I expect.