First commit for NEON ISA for `DD`

[manodeep]

Both rpavg and weightavg are wrong and the tests fail locally. The good news is that the number of pairs match

• Edit *

Added a checklist for the PR

• [x] Corrfunc compiles and works correctly on ARM64 platforms with the fallback kernels
• [ ] Add ARM64 kernels for all theory routines
  • [x] DD
  • [ ] DDrppi
  • [ ] DDsmu
  • [ ] wp
  • [ ] xi
  • [ ] vpf
• [ ] Add ARM64 kernels for all mocks routines
  • [ ] DDrppi_mocks
  • [ ] DDsmu_mocks
  • [ ] DDtheta_mocks
  • [ ] vpf_mocks
• [ ] Add tests for all ARM64 kernels
• [ ] Check that the kernels compile and work correctly when installed through python
• [ ] Add notes in the documentation for ARM64 functionality
• [ ] Create new minor Corrfunc release

[lgarrison]

Cool! Will take a look. How's the performance compared to fallback?

[manodeep]

It's a bit of a mixed bag. In single-precision - 3.6s with NEON and 5.8s with FALLBACK, while the times are about the same in double-precision.

[manodeep]

Realised that we have run out of Travis CI build minutes and no tests have run on TravisCI for nearly a year now. Hence, the arm64 tests will have to be done on some other CI -> currently trying out CircleCI

[manodeep]

I am trying out a bunch of new optimisations along side this ARM64 implementation - might take a while to finalise. Will re-open once ready