SoA implementation for float and AVX2 includind the polyexp fix

2026-05-25 12:07:46 +02:00
parent 1d585ffba7
commit f7bea275b3
9 changed files with 31574 additions and 3 deletions
@@ -76,6 +76,13 @@ long long flush_cache() {
 }

 int main(int argc, const char *argv[]) {
+#ifdef __x86_64__
+  // flush denormals to zero via MXCSR. one-time, per thread.
+  // any subnormal in the j-loop chain stalls fma for 100+ cycles, this kills that.
+  _MM_SET_FLUSH_ZERO_MODE(_MM_FLUSH_ZERO_ON);
+  _MM_SET_DENORMALS_ZERO_MODE(_MM_DENORMALS_ZERO_ON);
+#endif
+
  // Check that the correct number of arguments has been passed.
  //
  // Expected usage: