Jake Hemstad

PR https://github.com/NVIDIA/cccl/pull/2205 was a prototypical implementation of a streaming implementation for `DeviceSelect`, which was good enough to gather some performance data but had several limitation: - the number of selected...

Come up with plan for coupling between async_resource and resource concept

2

Today, `async_resource` concept is a strict superset of `resource` which requires an `async_resource` to provide synchronous allocation APIs. This introduces a problem where you have to decide what stream to...

transform_iterator fails with callables whose arguments are passed by non-const l-value ref

3

Minimal reproducer: https://godbolt.org/z/s4oPhqx3W This fails because it cannot deduce the return type of the callable. A workaround is to explicitly define the `result_type` in the callable: https://godbolt.org/z/MTM8b1zW9 However, I believe...

Additional cudax samples

1

We need more samples demonstrating new `cudax::` runtime functionality above and beyond just the vector add. Let's come up with a plan for the next 3 samples that we should...

Our current devcontainer infrastructure and CI scripts are all only built for Linux. We want to have equivalent containers and scripts for running on Windows/msvc. The desired end result is...

Compile times are growing significantly

12

## Feature request As anyone who has built libgdf recently has surely noticed, the time to compile the library from scratch has grown significantly in the last few months. For...