af_scaletempo2: use gcc vectors to speed up inner loop

This brings my scaletempo2 benchmark down from ~22s to ~7s on my machine
(-march=native), and down to ~11s with a generic compile.

Guarded behind an appropriate #ifdef to avoid being ableist against
people who have the clinical need to run obscure platforms.

Closes #8848

1 files changed, 4 insertions, 0 deletions

diff --git a/wscript b/wscript
index e9f4d53002..1a5ff5aa65 100644
--- a/wscript
+++ b/wscript
@@ -117,6 +117,10 @@ build_options = [
         'default': 'enable',
         'func': check_true,
     }, {
+        'name': '--vector',
+        'desc': 'GCC vector instructions',
+        'func': check_statement([], 'float v __attribute__((vector_size(32)))'),
+    }, {
         'name': '--clang-database',
         'desc': 'generate a clang compilation database',
         'func': check_true,