Project

General

Profile

Integration planning for GROMACS 2020 GPU features » History » Version 11

Alan Gray, 09/10/2019 10:30 AM

1 1 Mark Abraham
h1. Integration planning for GROMACS 2020 GPU features
2 1 Mark Abraham
3 1 Mark Abraham
We have a set of target functionality to integrate by 9/16. (TODO record that)
4 1 Mark Abraham
5 1 Mark Abraham
Due 8/30
6 1 Mark Abraham
7 1 Mark Abraham
* GPU halo-exchange for positions. Coding assigned to Alan. Review assigned to Mark and Berk.
8 5 Mark Abraham
  Status - code in gerrit, class+file+method naming input given, can merge when revised accordingly
9 1 Mark Abraham
10 1 Mark Abraham
Due 9/2
11 1 Mark Abraham
12 1 Mark Abraham
* pp-pme exchange class. Coding assigned to Alan. Review assigned to Mark, Berk.
13 8 Alan Gray
  Status - https://gerrit.gromacs.org/c/gromacs/+/12783 awaiting further review/merge.
14 1 Mark Abraham
* simulation flags structs. Coding assigned to Szilard. Review assigned to Mark, Berk, Paul, Erik.
15 1 Mark Abraham
  Status - WIP at https://gerrit.gromacs.org/c/gromacs/+/11622, would benefit from FTF discussion on how to describe lifetime and intent for this initial patch, whose form is understood to be unlike what we want in the long term
16 8 Alan Gray
* -Question: Does multi-domain GPU-halo-exchange force handling support adding extra CPU forces?- Alan's answer: I believe it should do (if an H2D copy of CPU forces is placed before the halo exchange), since the non-local part from the remote GPU wil be accumulated into the local part of the force buffer.   
17 1 Mark Abraham
18 1 Mark Abraham
Due 9/3
19 1 Mark Abraham
20 1 Mark Abraham
* LF pressure-coupling support for GPU-based update. Coding assigned to Artem. Review assigned to TODO.
21 1 Mark Abraham
  Status - P-R is plus2 on gerrit at https://gerrit.gromacs.org/c/gromacs/+/12477. Berendsen support easy to add in a future patch?
22 1 Mark Abraham
* tests covering .mdp nst* flags, in particular for well chosen co-prime cases to prevent unexpected behavior changes. Also can we test e.g. forces with FEP on non-output steps. Coding assigned to Mark. Review assigned to TODO.
23 1 Mark Abraham
  Status - start work Monday afternoon
24 7 Artem Zhmurov
* Make GPU version of StatePropagatorData. Coding assigned to Artem. Review assigned to Erik, Mark.
25 7 Artem Zhmurov
  Status - awaiting patch from Artem. Naming decision recorded at https://gerrit.gromacs.org/c/gromacs/+/11986
26 1 Mark Abraham
27 1 Mark Abraham
Due 9/5
28 1 Mark Abraham
29 1 Mark Abraham
* Clean up to make a PP-rank "PME force receiver". Coding assigned to Mark. Review assigned to Alan, Paul, Berk.
30 1 Mark Abraham
  Status: awaiting pp-pme exchange class stabilizing. Also review of clfft init change https://gerrit.gromacs.org/c/gromacs/+/12897.
31 10 Alan Gray
* Code to receive PME-rank forces on PP-rank GPU buffers (avoiding CPU). Coding assigned to Alan. Review assigned to Szilard, Berk, Mark.
32 10 Alan Gray
  Status: Code at https://gerrit.gromacs.org/c/gromacs/+/12980 awaiting review.
33 10 Alan Gray
  
34 1 Mark Abraham
35 1 Mark Abraham
Due 9/6
36 1 Mark Abraham
37 9 Alan Gray
* Halo-exchange class for force. Coding assigned to Alan. Review assigned to Szilard, Mark, Berk.
38 9 Alan Gray
  Status: Code in Gerrit at https://gerrit.gromacs.org/c/gromacs/+/12943. Awaiting review.
39 1 Mark Abraham
* Stitching together high-level single-GPU logic to achieve performance. Coding assigned to Artem. Review assigned to Erik, Mark.
40 3 Mark Abraham
  Status: Awaiting progress on GPU StatePropagatorData patch
41 3 Mark Abraham
* Lift cr->duty assignment out of init_domain_decomposition(). Coding assigned to Berk. Review assigned to Mark, Paul, Szilard.
42 1 Mark Abraham
43 1 Mark Abraham
Due 9/9
44 1 Mark Abraham
45 4 Alan Gray
* Class containing Pme-pp exchange for coordinate buffers. Coding Assigned to Alan. Review assigned to Szilard, Berk, Mark.
46 11 Alan Gray
  Status: Code at https://gerrit.gromacs.org/c/gromacs/+/13043 awaiting review.
47 1 Mark Abraham
* refinement of simulation flag structs. Coding assigned to Szilard. Review assigned to Mark, Berk, Paul, Erik.
48 1 Mark Abraham
  Status: awaiting submission of earlier patch
49 1 Mark Abraham
50 1 Mark Abraham
Due 9/12 
51 1 Mark Abraham
52 1 Mark Abraham
* Stitching together high-level multi-GPU logic to achieve performance. Coding assigned to TODO. Will need input from many people
53 1 Mark Abraham
  Status: not started yet
54 1 Mark Abraham
55 1 Mark Abraham
Due 9/14
56 1 Mark Abraham
57 1 Mark Abraham
* mdrun user interface + choices of defaults. Coding assigned to Paul. Review assigned to Alan, Artem, Mark.
58 1 Mark Abraham
  Status: not started yet
59 1 Mark Abraham
60 1 Mark Abraham
Due last minute
61 1 Mark Abraham
62 1 Mark Abraham
* Link task assignment to simulation flags and high-level GPU logic. Coding assigned to TODO. Will need input from many people.
63 3 Mark Abraham
  Status: clfft init patch needing review https://gerrit.gromacs.org/c/gromacs/+/12897. That prepares for a patch to manage GPU streams at high level and pass handles into individual modules that need to collaborate on the ~5 streams we identified, namely nonlocal, local, pme work, pp-pme xfer, update). Waiting on Berk's patch to pull cr->duty assignment out of init_domain_decomposition(), so we can rearrange order of operations in runner so that GPU device info is available earlier, so that GPU streams can be set up before init_domain_decomposition() and init_forcerec()