GitLab

* Compile with -munsafe-fp-atomics to enable fast hardware f32 atomic
  add on global memory on pre-MI100 GPUs;
* Use fixed point charge spreading on other GPUs, otherwise float atomic
  add will be compiled as a slow CAS loop;
* Tune block sizes, use executeKernelFlat;
* Tune launch bounds of PME grid-related kernels: force the compiler to
  use all registers by limiting max waves per EU to 1.

Optimize findBlocksWithInteractions

* Replace volatile shared mem accesses with shuffles;
* Add NUM_TILES_IN_BATCH for processing block1 by multiple warps
  (for small systems);
* Cherry-pick missing changes from .cu;
* Tune MAX_BITS_FOR_PAIRS depending on device and the system size;
* Store single pairs immediately (if there are any), this allows not to
  store flags to shared memory and filter buffer and flagsBuffer after
  saving single pairs;
* Use fma explicitly and sign bit for better device code;
* Use CDNA's MFMA with singe/mixed precision;
* On CDNA the coarse grained stage processes warpSize blocks for
  one block1, the fine grained stage checks atoms of two block2 vs atoms
  of the same block1, singlePairs and interactingAtoms are also stored
  by warps, not half-warps;

Optimize findBlockBounds

* Use shuffles;
* Use executeKernelFlat;
* Process 2 tiles per warp 64 on CDNA;
* Use more uniformly distributed keys when sorting blocks;

Use compareInt2LargeSIMD when tile size < SIMD width

Fix exclusion tiles sorting on AMD CDNA (64 threads per wave)

    The nonbonded kernel uses USE_NEIGHBOR_LIST (useNeighborList)
    so host code also must check it instead of useCutoff.

    See also https://github.com/openmm/openmm/issues/3462

* All AMD GPUs support shuffle, double precision and 64-bit int atomics;
* Remove unused code: !ENABLE_SHUFFLE code paths in nonbonded.hip;
* Use intrinsics in single-precision;
* Use realToFixedPoint (faster float32-to-int64);
* Remove shared atomIndices, use shuffles;
* Check early if atoms are in the cutoff range, sometimes all lanes in
  a warp can skip computations, single pairs can also skip useless
  atomics with zero values;
* Remove volatile skipTiles access, use shuffles;
* Distribute work for warps in a strided order;
* Skip warps that may be still busy in the first loop;
* Unify conditions for excluded atoms with `includeInteraction`;
* Move multiprocessors to HipContext;
* Increase number of warps for computeNonbonded;
* Disable packed math for >=MI200 (it affects performance of some
  kernels like computeGKForces of amoebagk);
* Remove defaultOptimizationOptions and createModule's optimizationFlags
  as they are never used;
* Support -save-temps.

* Compile kernels with max block size of 256 threads:
  The default hipcc behavior since ROCm 4.2 is to compile kernels
  with 1024 threads unless __launch_bounds__ is specified. This
  significantly increases register pressure especially in heavy kernels
  (double precision, for example), requiring register spilling;
* Optimize computeRange by using multiple blocks for reduction;
* Use blocks of 1024 threads for computeBucketPositions - it is executed
  as a single work group so larger block size is faster;
* Sort up-to lenghtNextPow2 instead of blockDim.x (faster for short
  buckets);
* Optimize sortShortList2;
* Optimize sortBuckets with bit instructions;
* Decrease bucket size for non-uniform sorting: too many buckets may
  have sizes too large to sort in shared memory;
* Add more sizes in tests.

* Remove setting of link libraries, include and link dirs and compile
  flags for each target, instead let Cmake deal with them by linking the
  main library to hip::host hiprtc::hiprtc hip::hipfft;
* Fix: custom command without ADD_CUSTOM_TARGET and ADD_DEPENDENCIES is
  executed for both static and shared targets;
* Remove IF(APPLE) parts.

Fix SegFault in HipCalcHippoNonbondedForceKernel

    HipSort was created using a temporary ref. Adding `HipContext& cu`
    field to HipCalcHippoNonbondedForceKernel fixes the issue;

Port changes in CUDA backend to HIP

Fix a warning about arithmetic operations on void* in HipArray::uploadSubArray

Fix "Error Initializing context ROCm 5.3.0"

    https://github.com/StreamHPC/openmm-hip/issues/3


    hipDeviceSetCacheConfig returns hipErrorNotSupported on 5.3
Co-authored-by: Nick Curtis <nicholas.curtis@amd.com>

* Support numpy 2

* Debugging

* Removed debugging code

* Don't require importlib_metadata

* Handle older versions of importlib

* Fix import of netcdf_file for scipy 1.14

* Fix indentation

---------
Co-authored-by: Timothy Palpant <tim@atommapper.com>

* Run Mac tests on ARM and Intel

* Added missing environment file

* Removed obsolete code for M1 runner

* Removed obsolete code for M1 runner

* Debug CI failures

* Debugging

* Debugging

* Debugging

* Debugging

* Debugging

* Debugging

* Debugging

* Debugging

* Removed build that was failing

* Fixed URL that had changed

* addHydrogens() allows specifying exactly what hydrogens to add

* Prevent CI from using numpy 2.0

* Allow multiple registrations of the same atom type if definitions identical

* Different short-circuiting logic

* DrudeForce supports periodic boundary conditions

* Fixed uninitialized memory

Co-authored-by: FloLangenfeld <florent.langenfeld@peptinov.fr>

* added type checking for Simulation.step()

* changed how to check if step is an integer number

* ATMForce reorders inner contexts for better performance

* Fixed obsolete comments

* Avoid overflow in large XTC files

* Also cast box indices to size_t

* Created DebuggingReporter class

* Fixed description

* Update references to "openmmforcefields" project

* Org name, too

* Revised code from installing CUDA on CI

* Debugging

* Debugging

* Debugging

* Debugging

* Debugging

* Debugging

* Debugging

LoongArch is a new architecture, already supported by linux-6.1, gcc-12.
Signed-off-by: Zang Ruochen <zangruochen@loongson.cn>
Co-authored-by: Zang Ruochen <zangruochen@loongson.cn>

* Minor optimization to validating exclusions

* Optimizations to findMoleculeGroups()

* Improved performance of CustomHbondForce on large systems

* Fixed CUDA compilation errors

* Made LangevinIntegrator identical to LangevinMiddleIntegrator

* Removed unused code

* VariableLangevinIntegrator uses LFMiddle

* Can use getPlatform() instead of getPlatformByName()

* More concise arguments for getState()

* Reference platform supports nested virtual sites

* Common platform supports nested virtual sites

* Fixed force distribution from nested virtual sites

* Fixed test failures