1
0
mirror of https://github.com/paboyle/Grid.git synced 2025-06-11 03:46:55 +01:00
Commit Graph

7539 Commits

Author SHA1 Message Date
a294bc3c5b Relax constraints for multiRHS 2023-11-23 18:20:42 -05:00
b302ad3d49 multiRHS test in place, passes Yay! 2023-11-23 18:20:15 -05:00
82fc4b1e94 Finalise 2023-11-23 18:19:41 -05:00
b4f1740380 Finalise message 2023-11-23 18:19:16 -05:00
031f85247c multRHS initial support -- needs optimisation for multi project/promote.
Bug fix in freeing intermediate grids to stop double free
2023-11-23 18:18:35 -05:00
639cc6f73a better support for multiRHS coarse space
Still to add restriction of domain of last loop to interior of padded cell (expect about 4.5x on test volume on Crusher)
2023-11-23 18:16:26 -05:00
09946cf1ba Improved, works on 48^3 moving to multiRHS optimisations 2023-11-15 18:03:05 -05:00
f4fa95e7cb Use 5.3.0 2023-11-15 18:01:38 -05:00
100e29e35e Allow expression as argument to norm2 2023-11-15 18:00:44 -05:00
4cbe471a83 devVector 2023-11-15 18:00:07 -05:00
8bece1f861 Faster to transpose the matrix and apply with column major order 2023-11-15 17:58:38 -05:00
a3ca71ec01 Lots more setup options, still working on them 2023-11-15 17:58:04 -05:00
e0543e8af5 Implement flexible preconditioned CG 2023-11-15 17:57:39 -05:00
c1eb80d01a Print which have converged 2023-11-15 17:57:08 -05:00
a26121d97b Better printing 2023-11-15 17:56:45 -05:00
043031a757 Report resid on failed convergence 2023-11-15 17:56:22 -05:00
807aeebe4c Resize tol in constructor 2023-11-15 17:55:57 -05:00
8aa1a37aad For Mirs preconditioner solver 2023-11-15 17:55:32 -05:00
4efa042f50 C++17 change 2023-10-24 10:57:50 -04:00
c7cb37e970 c++17 accepted 2023-10-24 10:57:24 -04:00
d34b207eab Avoid HIP warnings 2023-10-24 10:57:04 -04:00
0e6fa6f6b8 DOn't need the Cshift for the period optimisation 2023-10-24 10:56:31 -04:00
38b87de53f This works around a stacksize limit on AMD GPU 2023-10-24 10:56:07 -04:00
aa5047a9e4 Faster blockProject blockPromote 2023-10-24 10:49:55 -04:00
24b6ee0df9 M4 file 2023-10-24 10:36:48 -04:00
1e79cc9cbe Avoid compiler error 2023-10-24 10:36:09 -04:00
b3925df9c3 Verbose on CPU-GPU xfer, remove performance by default 2023-10-24 10:25:01 -04:00
351795ac3a Better messaging 2023-10-20 19:33:04 -04:00
9c9c42d0df Tests on frontier with real speed up . 3.5x on 16^3 at mq=0.01 2023-10-20 19:27:13 -04:00
b6ad1bafc7 Normal memory SendToRecvFrom asynchronous for use in general stencil
code
2023-10-20 19:27:13 -04:00
a5ca40f446 Better verbose -- track CPU GPU motion under --log Memory, others go to
debug output stream
2023-10-20 19:27:13 -04:00
9ab54c5565 Overlap comms & data copy/buffer assembly in Ghost zone exchange 2023-10-20 19:27:13 -04:00
4341d96bde Massively sped up coarse grid mult, comms
Save 3ms spend (60% of time !) on cudaMalloc !!
2023-10-20 19:27:13 -04:00
5fac47a26d Faster halo exchange 2023-10-20 19:27:13 -04:00
e064f17346 Faster halo exchange 2023-10-20 19:27:13 -04:00
afe10ba2a2 More digits 2023-10-20 19:27:13 -04:00
7cc3435ba8 Imporved General coarsened matrix 2023-10-20 19:27:13 -04:00
541772313c Verbosity 2023-10-20 19:27:13 -04:00
3747494a09 Notify delet public 2023-10-20 19:27:13 -04:00
f2b98d0dcc Const safety 2023-10-20 19:27:13 -04:00
80471bf762 Alternate implementation involving face operations 2023-10-20 19:27:13 -04:00
a06f63c110 Improved I/O and non-lexico option exposed to SciDAC format 2023-10-20 19:27:13 -04:00
0ae4478cd9 Checkpoint the subspace and ldop 2023-10-20 19:27:13 -04:00
ae4e705e09 Use random vec as easier for debug 2023-10-20 19:27:13 -04:00
f5dcea9dbf Updates for Frontier 2023-10-20 19:27:12 -04:00
2207309f8a Spack rules 2023-10-16 18:38:24 -04:00
2111e7ab5f Run at physical mass 2023-10-06 21:20:21 -04:00
d29abfdcaf Transfer code to Frontier now 2023-10-06 21:03:34 -04:00
a751c42cc5 Checkpoint restore the setup 2023-10-06 21:03:08 -04:00
6a3bc9865e Verbose change 2023-10-06 21:02:04 -04:00