Project

General

Profile

2020-rc1

Due in 11 days (12/17/2019)

first release candidate of GROMACS 2020

1%

29 issues   (0 closed — 29 open)

Issues by
Bug

0/10
Feature

0/3
Task

0/16
Related issues
Bug #2722: gmxapi may over-manage RPATH
Bug #2737: AMD OpenCl failes release build in complex tests
Bug #2958: Compiling master (to become 2020) using CUDA 9.0
Bug #2990: ARM neon SIMD4 error
Bug #3017: ddBalanceRegionHandler triggers need fixing
Bug #3125: OpenCL on Volta and Turing borken
Bug #3136: gmxapi.operation data flow topology unclear or incomplete
Bug #3163: gpuupdate / task assignment stabilization
Bug #3226: Regression tests segfault with GPU update and DD
Bug #3230: mdrun-test -ntmpi 2 deadlock in calculateForces in density fitting
Feature #2817: GPU X/F buffer ops
Feature #3029: GPU force buffer ops + reduction
Feature #3168: GPU update release notes
Task #2756: gmxapi integration testing
Task #2979: Reconsider default 1 OpenMP thread per thread-MPI rank
Task #3010: upgrade OpenCL stack on bs-gpu01
Task #3037: add missing cylcle counters related to buffer ops/reduction launches
Task #3093: rework GPU direct halo-exchange related force reduction complexities
Task #3130: Interim handling of gmxapi data references.
Task #3131: support ccache with clang-tidy
Task #3159: eliminate regression due to moving gmx_pme_send_coordinates()
Task #3167: GPU update path user documentation
Task #3171: schedule CPU H2D force contribution in separate stream
Task #3183: enable bonded interactions on GPU
Task #3189: implement heuristics for switching between different spread/gather kernel layouts
Task #3205: address Debian experimental issues
Task #3207: Add cycle counting to StatePropagatorDataGpu
Task #3220: change rolling pruning scheduling with GPU update
Task #3221: fix the x D2H overlap limitation with GPU update