diff --git a/CHANGELOG.md b/CHANGELOG.md
index edc5da8..b38b189 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -7,6 +7,7 @@
 - Added `hamming_distance` function
 - Added `jaccard_distance` function
 - Added `subvector` function
+- Added CPU dispatching for distance functions on Linux x86-64
 - Updated comparison operators to support vectors with different dimensions
 
 ## 0.6.2 (2024-03-18)
diff --git a/src/vector.c b/src/vector.c
index 2e50fca..065a5aa 100644
--- a/src/vector.c
+++ b/src/vector.c
@@ -33,6 +33,13 @@
 #define STATE_DIMS(x) (ARR_DIMS(x)[0] - 1)
 #define CreateStateDatums(dim) palloc(sizeof(Datum) * (dim + 1))
 
+/* target_clones requires glibc */
+#if defined(__x86_64__) && defined(__gnu_linux__) && defined(__has_attribute) && __has_attribute(target_clones) && !defined(__FMA__)
+#define VECTOR_DISPATCH __attribute__((target_clones("default", "fma")))
+#else
+#define VECTOR_DISPATCH
+#endif
+
 PG_MODULE_MAGIC;
 
 /*
@@ -557,7 +564,7 @@ halfvec_to_vector(PG_FUNCTION_ARGS)
 	PG_RETURN_POINTER(result);
 }
 
-static float
+VECTOR_DISPATCH static float
 VectorL2SquaredDistance(int dim, float *ax, float *bx)
 {
 	float		distance = 0.0;
@@ -604,7 +611,7 @@ vector_l2_squared_distance(PG_FUNCTION_ARGS)
 	PG_RETURN_FLOAT8((double) VectorL2SquaredDistance(a->dim, a->x, b->x));
 }
 
-static float
+VECTOR_DISPATCH static float
 VectorInnerProduct(int dim, float *ax, float *bx)
 {
 	float		distance = 0.0;