diff --git a/arrow-buffer/src/buffer/ops.rs b/arrow-buffer/src/buffer/ops.rs
index c69e5c6deb10..641f3b1af90b 100644
--- a/arrow-buffer/src/buffer/ops.rs
+++ b/arrow-buffer/src/buffer/ops.rs
@@ -71,6 +71,30 @@ pub fn bitwise_bin_op_helper<F>(
 where
     F: FnMut(u64, u64) -> u64,
 {
+    // If the underlying buffers are aligned to u64 we can apply the operation directly on the u64 slices
+    // to improve performance.
+    if left_offset_in_bits == 0 && right_offset_in_bits == 0 {
+        unsafe {
+            let (left_prefix, left_u64s, left_suffix) = left.as_slice().align_to::<u64>();
+            let (right_prefix, right_u64s, right_suffix) = right.as_slice().align_to::<u64>();
+            // if there is no prefix or suffix, both buffers are aligned and we can do the operation directly
+            // on u64s
+            // TODO also handle non empty suffixes by processing them separately
+            if left_prefix.is_empty()
+                && right_prefix.is_empty()
+                && left_suffix.is_empty()
+                && right_suffix.is_empty()
+            {
+                let result_u64s = left_u64s
+                    .iter()
+                    .zip(right_u64s.iter())
+                    .map(|(l, r)| op(*l, *r))
+                    .collect::<Vec<u64>>();
+                return result_u64s.into();
+            }
+        }
+    }
+
     let left_chunks = left.bit_chunks(left_offset_in_bits, len_in_bits);
     let right_chunks = right.bit_chunks(right_offset_in_bits, len_in_bits);
 
@@ -102,6 +126,21 @@ pub fn bitwise_unary_op_helper<F>(
 where
     F: FnMut(u64) -> u64,
 {
+    // If the underlying buffer is aligned to u64, apply the operation directly on the u64 slices
+    // to improve performance.
+    if offset_in_bits == 0 && len_in_bits > 0 {
+        unsafe {
+            let (prefix, u64s, suffix) = left.as_slice().align_to::<u64>();
+            // if there is no prefix or suffix, the buffer is aligned and we can do the operation directly
+            // on u64s
+            // TODO also handle non empty suffixes by processing them separately
+            if prefix.is_empty() && suffix.is_empty() {
+                let result_u64s = u64s.iter().map(|l| op(*l)).collect::<Vec<u64>>();
+                return result_u64s.into();
+            }
+        }
+    }
+
     // reserve capacity and set length so we can get a typed view of u64 chunks
     let mut result =
         MutableBuffer::new(ceil(len_in_bits, 8)).with_bitset(len_in_bits / 64 * 8, false);
diff --git a/arrow-buffer/src/util/bit_chunk_iterator.rs b/arrow-buffer/src/util/bit_chunk_iterator.rs
index e11383f6f3db..afc428ef24c6 100644
--- a/arrow-buffer/src/util/bit_chunk_iterator.rs
+++ b/arrow-buffer/src/util/bit_chunk_iterator.rs
@@ -223,7 +223,8 @@ impl<'a> BitChunks<'a> {
     pub fn new(buffer: &'a [u8], offset: usize, len: usize) -> Self {
         assert!(
             ceil(offset + len, 8) <= buffer.len(),
-            "offset + len out of bounds"
+            "offset + len out of bounds. Buffer length in bits: {}, requested offset: {offset}, len: {len}",
+            buffer.len(),
         );
 
         let byte_offset = offset / 8;