Jake Hemstad

[FEA]: Add tests that verify Thrust/CUB algorithms satisfy necessary requirements about how many times they access inputs/outputs

3

### Is this a duplicate? - [X] I confirmed there appear to be no [duplicate issues](https://github.com/NVIDIA/cccl/issues) for this request and that I agree to the [Code of Conduct](CODE_OF_CONDUCT.md) ### Area...

[EPIC]: Thrust/CUB shouldn't invoke user-defined operators on out-of-bounds data

1

### Is this a duplicate? - [X] I confirmed there appear to be no [duplicate issues](https://github.com/NVIDIA/cccl/issues) for this request and that I agree to the [Code of Conduct](CODE_OF_CONDUCT.md) ### Area...

Today, we do a limited form of testing each libcu++ header with a host-only compiler where we just include the header in an otherwise empty file and ensure that compiles....

### Is this a duplicate? - [X] I confirmed there appear to be no [duplicate issues](https://github.com/NVIDIA/cccl/issues) for this request and that I agree to the [Code of Conduct](CODE_OF_CONDUCT.md) ### Area...

[EPIC] std::simd support in libcu++

6

We should add a heterogeneous implementation of [`std::simd`](https://en.cppreference.com/w/cpp/experimental/simd/simd) to libcu++. High-level goals: - Works in host/device code - Replace the need for the CUDA vector types like `int4/double2` - Use...

### Is this a duplicate? - [X] I confirmed there appear to be no [duplicate issues](https://github.com/NVIDIA/cccl/issues) for this request and that I agree to the [Code of Conduct](CODE_OF_CONDUCT.md) ### Area...

```[tasklist] ### Requirements API - [ ] https://github.com/NVIDIA/cccl/issues/1187 ``` ```[tasklist] ### User-defined Tuning API - [ ] Initial investigation and PoC for user-defined tuning APIs - [ ] Investigate productizing...

Setup CI job to automate testing with RAPIDS

1

```[tasklist] ### Tasks - [ ] Add jobs for RMM - [ ] Add jobs for cuDF ```

[EPIC] Consolidate kernels between Thrust and CUB

1

Below is a list of tasks in prioritized order. We should start with algorithms that already exist in CUB. This will allow delivering CUB optimizations into Thrust sooner. ```[tasklist] ###...

[EPIC] Roadmap for cuda/memory_resource

9

`cuda::mr` is intended to be the future of heterogenous memory allocation in CUDA C++. It is inspired heavily by lessons learned in RMM and our experience with the `device_memory_resource*` and...