- Feb 27, 2019
-
-
Benjamin Cumming authored
Update the installation guide to reflect the latest supported tool, compiler and library versions. Remove the Python docs, because they documented features that have not been implemented yet. The Python docs can be added incrementally as features are implemented. Start work on oupdating the documenetation for hardware interfaces and domain decomposition.
-
- Feb 26, 2019
-
-
* Add SIMD neon implementation for aarch64. * Update unit tests to suit.
-
Allow distinct point processes with the same linear dynamics to be combined if they reside in the same CV after discretization. * Add `linear` flag to `mechinfo` struct. * Add a linearity test to `modcc` that determines if a point process is a suitable candidate for coalescing: state and current updates must be linear, homogeneous functions of the state variables; state change on an event arrival (`net_receive`) must be independent of current state values. * Add `mechanism_state_table()` inquiry function to backend mechanism interface. * Add a field `multiplicity` to `fvm_mechanism_config` that accounts for merged synapse instances, and a corresponding `multiplicity` field in `mechanism::layout`. * Merge linear synapses of the same type in `fvm_build_mechanism_data` if they have the same parameters. * Add global mc_cell property `coalesce_synapses` which enables or disables the merging of linear synapses at run time. * Rename virtual `nrn_init()` interface funct...
-
Update documentation for Python. splits the conceptual model ideas from the C++ docs into their own section has C++ and Python docs for recipes, domain decomposition, etc. fixes #667 Added the following documentation (structure): GETTING STARTED: Installing Arbor/Requirements/Optional Requirements/Python Installing Arbor/Building and Installing Arbor/Python Front End MODEL BASICS: Overview Common Types Recipes Domain Decomposition Simulations PYTHON: Overview Common Types Recipes Domain Decomposition Simulations DEVELOPERS: Python Profiler Python Unit Testing GETTING STARTED has two added sections of optional requirements using python and how to build the python front end. MODEL BASICS describes Arbor's concepts in general (independent of programming language), thus general information on concepts in C++ API was moved here/ added. PYTHON describes Arbor's python frontend in the same structure as MODEL BASICS and C++ API ( needs updates as soon as features are added/changed in new python PR). DEVELOPERS section has two added sections for meter management and unit testing with python front end. Further, some corrections in existing documentation (for obvious errors, e.g. duplicate text, not ending sentences) and referencing sections were done. -
First step towards the Python front end. This commit sets up the structure of the python implementation * directory structure * git submodule for pybind11 * best practices for making bindings with pybind11 * unit testing for the python front end It implements the following features in the Python front end * execution contexts * gpu detection * thread count detection * MPI initialization helpers. Fixes #667.
-
- Feb 25, 2019
-
-
* Bump minimum CMake version to 3.9. Fixes #691.
-
- Feb 18, 2019
-
-
Fixes #683. * Distinguish between per-cell matrix solver and per-'integration domain' state in the FVM back-end, adding new index for FVM back-ends mapping CVs to integration domain index. * Move to one event queue per integration domain, avoiding extra logic for synchronisation of times across gap-junction connected cells. This requires a merging of event lanes in `mc_cell_group` when constructing the staged events in the multi-event queue. * Add synapses to gap junction example.
-
- Feb 06, 2019
-
-
Sam Yates authored
-
Add support for gap junctions in mc_cells, modelled as a conductance between 2 cell CVs. Gap junctions act as additional current sources on the CVs, as opposed to participating in the implicit voltage integration step. Cells connected via gap junctions must be in the same cell group as determined by the provided domain decomposition. * Extend `mc_cell` to hold a list of gap junction locations. * Add `num_gap_junction_sites()` and `gap_junctions_on()` methods to the `recipe` interface. * Add `gather_gids()` collective operation to distributed context interface and implementations. * Extend `partition_load_balance()` functionality to ensure that cells connected by gap junctions are put in the same groups. * Permute cells within `mc_cell_group` so that cells connected by gap junctions are contiguous. * Add gap junction information to `multicore::shared_state` and `gpu::shared_state`, together with `add_gj_current()` method that computes GJ current contributions. * Ad...
-
- Feb 05, 2019
-
-
Sam Yates authored
* Add unit test for event delivery pathing. * Temporarily disable GJ-specific test pending GJ PR.
-
Sam Yates authored
Somewhere along the line, some extensions were made to `cell_member_type` to facilitate some arithmetic on the `gid` field. These operations tend to blur the distinction between a gid and a `cell_member_type` value, and are besides used only in a couple of places. * Remove `cell_member_type` arithmetic with `gid` methods/functions. * Replace usage of these short cuts with explicit use of `gid` field in `dry_run_context_impl` and `symmetric_recipe`.
-
- Feb 04, 2019
-
-
Sam Yates authored
Implement a basic glob routine, supporting a subset of POSIX behaviour (e.g. no character classes), as a fallback for platforms such as Android which do not include it in their libc. * Add CMake configuration option `ARB_USE_POSIX_GLOB`, defaults to `ON`, that determines if the fallback implementation is used or not. * Extend `sup::path` functionality to add directory iterators and a couple more path manipulation routines, again following the C++17 `std::filesystem` interface. * Add an NFA pattern matcher `glob_basic_match` and file system `glob_basic` function; the latter is abstracted over a file system provider object, primarily for testing/mocking purposes. * Add unit tests for new `sup::path` functionality and for `glob_basic`. FIxes #181.
-
- Feb 01, 2019
-
-
Remove `sup::spike_emitter` and replace usages in `miniapp` and `brunel-miniapp`. * Replaces instances of `spike_emitter` in `miniapp` and `brunel-miniapp` with a callback that saves spikes to a vector and which is written to a file after the simulation ends. * Remove unused fields from `cl_options` in `brunel-miniapp`, including spike output file components. * Hard code spike output path to `spikes.gdf` in `brunel-miniapp` and write saved spikes after simulation end. * Correctly set 'rank' in `miniapp` (used in spike output paths). * Read spike output options from JSON config in `miniapp` unconditionally. * Make line comments in `miniapp` and `brunel-miniapp` main functions a bit more consistent in formatting. Fixes #677.
-
- Jan 31, 2019
-
-
Make a new installed library `libarborenv.a` covering a subset of the `sup` library functionality, with corresponding installed CMake target `arbor::arborenv`. * Move NVML or CUDA 10 API decision for GPU UUID discovery to top level CMake. * Move affinity, concurrency, MPI init guard, and gpu detection and negotiation functionality out of `sup` and into new library `arborenv`. * Move `include/arbor` in project tree to `arbor/include/arbor` (for consistency across `sup`, `arbor`, and `arborenv` subdirectories.) * Wrangle more explicit library dependency adding CMake code into the installed `arbor-config.cmake`, to help mitigate [CMake issue #18614](https://gitlab.kitware.com/cmake/cmake/issues/18614). * Have `arborenv` code throw `std::runtime_exception` instead of `arb::arbor_error`. (We are still using `arb::mpi_error` though for a failure in `with_mpi`.) * Move `scope_exit` into the `arb::util` namespace. * Merge `affinity.hpp` into `concurrency.hpp`. * Rename `gpu.hpp` to `gpu_env.hpp` in `arborenv` includes. Fixes #647.
-
- Jan 22, 2019
-
-
Benjamin Cumming authored
* Print a `meter-total` value of the accumulated meter values across all checkpoints to the meter `ostream` output. * Add default behavior that prints the mean of a meter across all ranks if the meter type is not one of the known special cases (i.e. not one of time, memory or energy). Fixes #671
-
Sam Yates authored
* Fix bug in optimized (scalar) unconstrained indirect addition. * Fix bug in indirect arithmetic and scatter tests that tested only a subset of the test data.
-
- Jan 18, 2019
-
-
* Optimize "none" index_constraint specialization of compound_indexed_add, so that it only reads/writes each distinct memory index once per vector. Related to issue #637.
-
- Jan 14, 2019
-
-
* Fix incorrect specialization of AVX512 gather in SIMD library. Related to #637. Improves avx512 performance on Intel Xeon Gold 6130.
-
- Dec 18, 2018
-
-
Extend sup library to support assigning unique GPUs to MPI ranks. Fixes #648.
-
Sam Yates authored
* Provide a helper wrapper for use behind the scenes in the implementation of `sup::on_scope_exit` so that we can work around `std::function` not being nothrow move constructible (and maintaining the nothrow move on the `sup::scope_exit` structure). Fixes #664.
-
- Dec 17, 2018
-
-
Events arrive already sorted first by index then by time. * Remove sort by event index. * Replace assertion that events are sorted by time with assertion that they are sorted by index. Assertion that the subrange of events with the same index is sorted by time already exists.
-
- Dec 05, 2018
-
-
Refactoring that moves the logic for determining available concurrency and available GPUs from the core Arbor library to the sup library. This also constitutes work towards providing functionality for allocating GPUs to particular ranks when multiple GPUs are visible per rank. * Move core/thread estimation code to sup library. * Change default resource behaviour to use one thread and no GPU. * Provide an interface in the sup library for: acquiring a default GPU; for coordinating an allocation of GPUs across multiple MPI ranks.
-
- Nov 29, 2018
-
-
Benjamin Cumming authored
Ensure that all threads use the same GPU, which wasn't the case before. * add `gpu_context::set_gpu()` method that will set all subsequent GPU calls from the calling thread run on the GPU of `gpu_context`. * `fvm_lowered_cell_impl` now calls the `set_gpu` method on construction and `advance`. * Also changed GPU memory allocation errors in `arb::memory` to throw `arb_exception` instead of calling `std::terminate` on error. Now errors due to poor GPU configuration can be caught by the calling application, and unit tests fail gracefully and allow other tests to run. Fixes #655
-
- Nov 27, 2018
-
-
CMake wants to run a device link pass with nvcc despite there being no CUDA seperable compilation enabled anywhere, and then passes on -pthread to that unnecessary nvcc invocation when we use the Threads dependency. The latter, at least, is fixed in CMake 3.13. We used the prefer -pthread option for compatibility with our earlier build configuration; turning it off will hopefully have no consequence. We also enable device linking on the arbor library. Which is not needed, but if they are going to insist on doing it, it should be on the library rather than the executable. CMake then goes and does it on the executable anyway. Great. Fixes #645.
-
- Nov 21, 2018
-
-
* Forward CMAKE_CUDA_TOOLKIT_INCLUDE_DIRECTORIES to compilation of arbor library and unit tests. Fixes #651
-
- Nov 13, 2018
-
-
-
This reverts commit be2a8a9f.
-
Add a new Hines matrix solver implementation for the GPU that can solve a single tree in parallel with multiple threads. It replaces the interleaved solver, which used a single thread to solve each matrix. Branches with the same common root in the tree can be solved independently on each of the forward and backward solution passes. * Add a matrix storage type, `arb::gpu::matrix_state_fine` that stores the branches of multiple trees for efficient backward and forward substitution. * Extend the `arb::tree` data structure to support operations for choosing a new root node and determining a root node which minimises the maximum distance between the root and any of the trees leaves. * Implement code for rebalancing a set of matrix trees, a.k.a. a "forest" of trees. * Add CUDA kernels for efficiently performing matrix assembly and matrix solution steps. * Add CMake option `ARB_WITH_GPU_FINE_MATRIX` for toggling the new solver (default `on`).
-
- Oct 16, 2018
-
-
- Oct 15, 2018
-
-
* Use `Unitful.uconvert` for scalar conversions (Float64 cast apparently does not work at the moment). * Use .+ for scalar/array addition. * Replace `immutable` with `struct`. * Qualify included modules with `Main.` for using statements. * Add informational note to FindJulia as component identification can take a long time as Julia may compile them from source.
-
Benjamin Cumming authored
fixes #627
-
Fixes #622.
-
- Oct 12, 2018
-
-
Sam Yates authored
* Use python3 version of print. * Use dict update method instead of item concatenation, as in Python3 dict.items() no longer returns a list.
-
Sam Yates authored
cf. CMake issue 16716: https://gitlab.kitware.com/cmake/cmake/issues/16716 * Bump version post 0.1 for development. * Read version string from file VERSION. * Strip suffix to make a numerical, CMake-compatible PROJECT_VERSION.
-
Fixes #618 and fixes #617. * Add convenience targets: 'examples' for all examples; 'tests' for all tests. * Add support for component-testing in installed CMake package. * Allow test for MPI support via find_package via component. * Remove REQUIRED specification from `find_dependency()` commands in generated config. * Update `mech_vec.cpp` to match new `fvm_lowered_cell_impl` constructor.
-
- Oct 11, 2018
-
-
Fix potential numeric instabilities in the ring benchmark caused by passing arguments to an event generator in the wrong order.
-
- Oct 10, 2018
-
-
Fixes #612. * Fix issues with permissions on directories created at install time (at least for CMake 3.11+). * Add CMake export guff to various targets and install an `arbor-config.cmake` for consumption by other CMake-based projects.
-
- Oct 04, 2018
-
-
Benjamin Cumming authored
Extend the ring benchmark to have an optional number of synapses attached to each cell, instead of a fixed count of one synapse per cell. This doesn't change the behavior of the model: only the first synapse is used for communication. The other synapses only effect is to increase the per-cell computational overheads, to more effectively mimic real world performance.
-
- Oct 03, 2018
-
-
Fixes an error in vectorized kernels that sees the incorrect index passed to PROCEDURE calls. The loop index variable was being passed, instead of the pack of vector indexes. Fixes #609
-
- Oct 01, 2018
-
-
Add CMake options for V100 support. fixes #605
-
