diff --git a/compression/BitShuffleBlock.h b/compression/BitShuffleBlock.h
index a4a73f76a..0f053b16d 100644
--- a/compression/BitShuffleBlock.h
+++ b/compression/BitShuffleBlock.h
@@ -23,13 +23,24 @@
 // which a single configure-time answer could not follow.
 #if (defined(__ARM_NEON__) || (__ARM_NEON)) && defined(__aarch64__)
 
-// The classic entry points allocate their own block-sized scratch, so the caller's goes unused.
+// The two stages of bshuf_untrans_bit_elem_NEON, which bitshuffle_core.c defines but no header
+// declares. Calling them directly lets the decode use the caller's scratch instead of the block-sized
+// buffer the classic entry point mallocs and frees for every block.
+extern "C" {
+    int64_t bshuf_trans_byte_bitrow_NEON(const void *in, void *out, size_t size, size_t elem_size);
+    int64_t bshuf_shuffle_bit_eightelem_NEON(const void *in, void *out, size_t size, size_t elem_size);
+}
+
+// The classic encode entry point allocates its own block-sized scratch, so the caller's goes unused.
 inline int64_t JFJochBitShuffleBlock(char *out, const char *in, char *, size_t size, size_t elem_size) {
     return bshuf_trans_bit_elem(in, out, size, elem_size);
 }
 
-inline int64_t JFJochBitUnshuffleBlock(char *out, const char *in, char *, size_t size, size_t elem_size) {
-    return bshuf_untrans_bit_elem(in, out, size, elem_size);
+inline int64_t JFJochBitUnshuffleBlock(char *out, const char *in, char *scratch, size_t size, size_t elem_size) {
+    const int64_t count = bshuf_trans_byte_bitrow_NEON(in, scratch, size, elem_size);
+    if (count < 0)
+        return count;
+    return bshuf_shuffle_bit_eightelem_NEON(scratch, out, size, elem_size);
 }
 
 #else