diff options
| author | Jeff Johnston <jjohnstn@redhat.com> | 2019-01-15 18:36:50 +0300 |
|---|---|---|
| committer | Jeff Johnston <jjohnstn@redhat.com> | 2019-01-15 18:48:08 +0300 |
| commit | 1787e9d033e9e7746ced90bd6d848eb088a5b8ab (patch) | |
| tree | a3db1fce29b3a7bdf497fd1cdc6f31dba1372e45 /newlib/configure.host | |
| parent | 4d2d891b99840e4dc73f8d5f7ec45a5d616db59d (diff) | |
AMD GCN Port contributed by Andrew Stubbs <ams@codesourcery.com>
Add support for the AMD GCN GPU architecture. This is primarily intended for
use with OpenMP and OpenACC offloading. It can also be used for stand-alone
programs, but this is intended mostly for testing the compiler and is not
expected to be useful in general.
The GPU architecture is highly parallel, and therefore Newlib must be
configured to use dynamic re-entrancy, and thread-safe malloc.
The only I/O available is a via a shared-memory interface provided by libgomp
and the gcn-run tool included with GCC. At this time this is limited to
stdout, argc/argv, and the return code.
Diffstat (limited to 'newlib/configure.host')
| -rw-r--r-- | newlib/configure.host | 8 |
1 files changed, 8 insertions, 0 deletions
diff --git a/newlib/configure.host b/newlib/configure.host index 6c49cb750..fa805d61a 100644 --- a/newlib/configure.host +++ b/newlib/configure.host @@ -118,6 +118,10 @@ case "${host_cpu}" in machine_dir=aarch64 libm_machine_dir=aarch64 ;; + amdgcn*) + newlib_cflags="${newlib_cflags} -D__DYNAMIC_REENT__" + machine_dir=amdgcn + ;; arc*) machine_dir=arc ;; @@ -442,6 +446,10 @@ case "${host}" in aarch64*-*-*) newlib_cflags="${newlib_cflags} -D_COMPILING_NEWLIB" ;; + amdgcn*) + sys_dir=amdgcn + have_crt0="no" + ;; arm*-*-*) newlib_cflags="${newlib_cflags} -D_COMPILING_NEWLIB" sys_dir=arm |