On Fri, Jun 26, 2026 at 02:27:31PM +0530, Surya Kumari Jangala wrote: > Changes from v1: > Fixed formatting issues in changelog. > > This patch depends on: > 1. Support for Dense Math Registers: > https://gcc.gnu.org/pipermail/gcc-patches/2026-April/713352.html > 2. Support for new DMF/MMA+ instructions: > https://gcc.gnu.org/pipermail/gcc-patches/2026-June/721366.html > > This patch adds builtins for the Matrix Multiply Assist Plus (MMA+) > instructions defined in RFC02658. These instructions may or may not be > supported in a future Power processor. Specifically, builtins have been > added for the following instructions: > > 1. Bfloat16 GER operations: > - dmxvbf16gerx2 and its variants (pp, pn, np, nn) > - pmdmxvbf16gerx2 and its variants (pp, pn, np, nn) > > 2. Signed accumulate variant for 8-bit integer GER operations: > - dmxvi8gerx4spp > - pmdmxvi8gerx4spp > > Note, the names of the builtins may change in the future.
This looks ok, once the preceeding patches that add dense math support are added. Obviously, once those patches go in, it may need to be adjusted. -- Michael Meissner, IBM PO Box 98, Ayer, Massachusetts, USA, 01432 email: [email protected]
