Julian Samaroo
Julian Samaroo
Currently we don't do a whole lot to estimate the approximate time cost of a signature on "cold start" (where the signature has never been seen before). Our current approach...
Building on Dagger's unified hashing framework, DaggerMPI.jl allows DAGs to execute efficiently under an MPI cluster. Per-task hashes are used to "color" the DAG, disabling execution of each task on...
musl doesn't have `pthread_attr_setaffinity_np`, so we need to use `pthread_setaffinity_np` on `thread` after `pthread_create`. Note: This is not yet tested on master; it was cherry-picked from my 4.5.2 branch, hence...
I am the maintainer of Julia's AMDGPU computing stack, and was recently upgrading our ROCR-Runtime wrapper package [HSARuntime.jl](https://github.com/jpsamaroo/HSARuntime.jl) to support builds of Julia that use LLVM >= 7. Those versions...
It's unintuitive that you need to set both `BUILD_TESTS=OFF` and `BUILD_TESTING=OFF` to disable building *all* tests. This changes the OpenCL tests to instead just check `BUILD_TESTS`.
Since all accesses to `WeakRef` from Julia code are atomic, we might as well be atomic when accessing their contents from C (even if it may not matter in practice)....
Currently, the intrinsics we expose for `Float16` inputs accept scalar inputs, however, there exists many math intrinsics that take `Tuple{Float16,Float16}`, with the intention to be able to use packed math...
As reported by HSA in CI on master. We should probably switch to a kernel copy for the portions which aren't aligned.
Similar to Julia's `--check-bounds` flag, this flag (used like `@roc boundscheck=false ...`) allows the user to entirely disable boundschecking within their code.