GitLab

* Unload all loaded modules in HipContext's destructor,
  HIP modules keep file desctriptors opened, but OpenMM never unloads
  modules leaking these file descriptors. This can cause crashinf of
  some scripts like test-openmm-platforms from openmmtools.
* ROCm 6.0 defines operator* for complex types (that are typedefs for
  float2 and double2), they conflict with operators defined for vectors.
  This is fixed in newer ROCm versions.
* Revert HIP_DYNAMIC_SHARED back to extern __shared__ (the macro is
  in the headers).
* Reduce the speed of the HIP platform if there are no HIP devices in
  the system.

* 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.

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>

* Always use nvrtc for compilation

* Install nvrtc on CI

* Workaround for compiler error

* Set empty values for deprecated properties

* Optimized CudaSort for non-uniformly distributed data

* Optimized OpenCLSort for non-uniformly distributed data

* Further tuned distributing elements between buckets

* Copied optimizations over to OpenCL

* Use cuCtxPushCurrent() and cuCtxPopCurrent() for selecting CUDA context

* Fixed errors in amoeba coda

* Fixed more errors in context selection

* Use command line compiler if it is explicitly specified

* Don't set OPENMM_CUDA_COMPILER on Jenkins

Platform specific header files get installed.  This allows plugins to be built with just an OpenMM installation, not a full source tree.

Continuing to implement new CUDA platform: constraints, LangevinIntegrator, BrownianIntegrator, VariableLangevinIntegrator, VariableVerletIntegrator

Moved SFMT into libraries folder, and restructured it to allow multiple independent random number generators

Modified the API for lots of classes so that the number of particles/bonds/etc. need not be specified in the constructor.

Continuing to implement ReferencePlatform (implemented kinetic energy calculation and LangevinIntegrator)

Created a test case for StandardMMForceFieldImpl's findExclusions() method.  Fixed some bugs that it found.  Created a CMake script and configured it for building and running test cases.