[PATCH] D88929: [OpenMP] Change CMake Configuration to Build for Highest CUDA Architecture by Default

Ye Luo via Phabricator via cfe-commits cfe-commits at lists.llvm.org
Tue Oct 6 17:07:09 PDT 2020


ye-luo added a comment.

In D88929#2315640 <https://reviews.llvm.org/D88929#2315640>, @JonChesterfield wrote:

> An alternative approach is to build the deviceRTL for multiple cuda versions and then pick whichever one is the best fit when compiling application code. That has advantages when building the deviceRTL libraries on a different machine to the one that intends to use it.
>
> Cmake isn't my thing, but I see that my trunk build only has libomptarget-nvptx-sm_35.bc when the local card is a sm_50. The downstream amd toolchain builds lots of this library, my install dir has fifteen of them (including sm_50).

You can build multiple deviceRTL today with LIBOMPTARGET_NVPTX_COMPUTE_CAPABILITIES=50,61,70. This patch tries to add the high arch automatically.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D88929/new/

https://reviews.llvm.org/D88929



More information about the cfe-commits mailing list