diff options
author | Kwok Cheung Yeung <kcy@codesourcery.com> | 2022-12-02 23:00:11 +0300 |
---|---|---|
committer | Jeff Johnston <jjohnstn@redhat.com> | 2023-01-18 21:22:58 +0300 |
commit | e18743072bc7fd56ec812e52dcfde5b686d1df8f (patch) | |
tree | 8d8143f9776e614163eae1cb8aa2e2491d51b776 /newlib/configure.host | |
parent | 31302b267b86a9e9190dd260f2ff4f0c74410bf3 (diff) |
amdgcn: Add vectorized math routines
This implements a set of vectorized math routines to be used by the
compiler auto-vectorizer. Versions for vectors with 2 lanes up to
64 lanes (in powers of 2) are provided.
These routines are based on the scalar versions of the math routines in
libm/common, libm/math and libm/mathfp. They make extensive use of the GCC
C vector extensions and GCN-specific builtins in GCC.
Diffstat (limited to 'newlib/configure.host')
-rw-r--r-- | newlib/configure.host | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/newlib/configure.host b/newlib/configure.host index 32d1436ba..7157877ff 100644 --- a/newlib/configure.host +++ b/newlib/configure.host @@ -119,6 +119,7 @@ case "${host_cpu}" in amdgcn*) newlib_cflags="${newlib_cflags} -D__DYNAMIC_REENT__" machine_dir=amdgcn + libm_machine_dir=amdgcn newlib_cv_initfinit_array=yes ;; arc*) |