1
0
mirror of https://github.com/paboyle/Grid.git synced 2025-06-13 20:57:06 +01:00
Commit Graph

7746 Commits

Author SHA1 Message Date
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
7d077fe493 Frontier compiel 2023-11-09 13:58:44 -05:00
9cd4128833 fix naik bug 2023-11-03 14:11:38 -06:00
c8b17c9526 Naik to CShift 2023-11-02 12:43:22 -06:00
2ae2a81e85 attempt to fix Naik 2023-10-31 13:54:55 -06:00
69c869d345 fixed stupid typo 2023-10-30 17:41:52 -06:00
df9b958c40 naik now returns separately 2023-10-30 17:40:53 -06:00
3d3376d1a3 LePage works, trying Naik 2023-10-27 16:26:31 -06:00
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
f2648e94b9 getHostPointer added to Lattice 2023-10-23 13:47:41 +02:00
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
21ed6ac0f4 added floating-point support 2023-10-20 13:54:26 -06:00
7bb8ab7000 improve smearing templating 2023-10-20 08:41:02 -06:00