[Date Prev][Date Next] [Thread Prev][Thread Next] [Date Index] [Thread Index]

Bug#1013368: ITP: rocm-hipamd -- C++ Runtime API and Kernel Language for AMD and NVIDIA GPUs



Package: wnpp
Severity: wishlist
Owner: Étienne Mollier <emollier@debian.org>
X-Debbugs-Cc: debian-devel@lists.debian.org
X-Debbugs-Cc: debian-ai@lists.debian.org

* Package name    : rocm-hipamd
  Version         : 5.0.0
  Upstream Author : Advanced Micro Devices, Inc
* URL             : https://github.com/rocm-developer-tools/hipamd
* License         : Expat
  Programming Lang: C++
  Description     : C++ Runtime API and Kernel Language for AMD and NVIDIA GPUs

 HIP (Heterogeneous Interface for Portability) is a C++ Runtime API and Kernel
 Language that allows developers to create portable applications for AMD and
 NVIDIA GPUs from single source code.
 .
 Key features include:
 .
  * HIP is very thin and has little or no performance impact over coding
    directly in CUDA mode;
  * HIP allows coding in a single-source C++ programming language including
    features such as templates, C++11 lambdas, classes, namespaces, and more;
  * HIP allows developers to use the "best" development environment and tools
    on each target platform;
  * the HIPify tools automatically convert source from CUDA to HIP;
  * developers can specialize for the platform (CUDA or AMD) to tune for
    performance or handle tricky cases.
 .
 New projects can be developed directly in the portable HIP C++ language and
 can run on either NVIDIA or AMD platforms.  Additionally, HIP provides porting
 tools which make it easy to port existing CUDA codes to the HIP layer, with no
 loss of performance as compared to the original CUDA application.  HIP is not
 intended to be a drop-in replacement for CUDA, and developers should expect to
 do some manual coding and performance tuning work to complete the port.


This package will allow us to begin the deployment of ROCm user
visible libraries, which require the hipcc compiler.  Long term
plan would be to allow various reverse recommends and reverse
dependencies to take advantage of GPU acceleration through the
ROCm stack.

It will be maintained under the Debian Deep Learning Team
<debian-ai@lists.debian.org> umbrella, current work in progress
is available on salsa[1].

[1]: https://salsa.debian.org/rocm-team/rocm-hipamd

Have a nice day,  :)
-- 
Étienne Mollier <emollier@emlwks999.eu>
Fingerprint:  8f91 b227 c7d6 f2b1 948c  8236 793c f67e 8f0d 11da
Sent from /dev/pts/1, please excuse my verbosity.

Attachment: signature.asc
Description: PGP signature


Reply to: