#AdaptiveCpp 25.10 released! Introducing a deployment model (compile once, ship to NVIDIA/AMD/Intel GPUs and CPUs), performance improvements and more! github.com/AdaptiveCpp/...
3
0
0
0
#AdaptiveCpp
Latest posts tagged with #AdaptiveCpp on Bluesky
Trending
Posts tagged #AdaptiveCpp
Cool to see two papers explore #SYCL performance on CPUs at #ISC25. It’s also great to see how much the performance has improved thanks to the commitment to the #oneAPI and #AdaptiveCpp implementations since we evaluated this a few years ago.
1
0
1
0
#AdaptiveCpp 25.02 released! Introducing AdaptiveCpp portable CUDA (PCUDA):direct support for the CUDA and HIP languages in AdaptiveCpp's compiler. Compile CUDA code, obtain single binary that runs on CPU, Intel GPU, NVIDIA GPU, AMD GPU. And perhaps even faster than nvcc. github.com/AdaptiveCpp/...
2
0
0
0
Big news: #AdaptiveCpp can now also compile CUDA or HIP code with its generic JIT compiler - and create a single binary that can offload kernels to CPU/Intel GPU/NVIDIA GPU/AMD GPU. Oh, and you can mix-and-match CUDA/HIP, SYCL and C++ standard parallelism as you like.
github.com/AdaptiveCpp/...
1
0
0
0
#AdaptiveCpp 24.10.0 has just been released! Even more performance and more features, including data parallel SYCL algorithms, group algorithms for the generic JIT compiler, JIT reflection and more! github.com/AdaptiveCpp/...
2
0
0
0