Fujitsu Begins Adding A64FX Support To GCC Compiler

The Fujitsu A64FX ARM processor that has 48 cores per node and 32GB of HBM2 memory that currently powers the fastest supercomputer is beginning to see GCC compiler support.

Fujitsu months ago upstreamed A64FX support to the LLVM/Clang compiler. It appears this ARMv8.2-based chip with 512-bit SIMD is using LLVM/Clang as its preferred compiler. But now Fujitsu is also upstreaming GCC support for their high performance A64FX.

This week the start of the Fujitsu A64FX machine model was upstreamed by one of their engineers. At the moment the Fujitsu target of "a64fx" just sets ARMv8.2 and the various extensions supported. The actual tuned machine model and any other optimizations have yet to be upstreamed.

This Fujitsu A64FX support will be part of the GCC 11 release due out in early 2021.