diff --git a/compression/BitShuffleBlock.h b/compression/BitShuffleBlock.h
index b740a4f6a..a4a73f76a 100644
--- a/compression/BitShuffleBlock.h
+++ b/compression/BitShuffleBlock.h
@@ -18,6 +18,9 @@
 //
 // The condition mirrors USEARMNEON in bitshuffle_core.c exactly. With NEON off the classic path
 // falls back to a scalar of its own that is slower than hperf's, so it must not be selected then.
+// It is a preprocessor test rather than a CMake one on purpose: Apple Silicon defines the same two
+// macros as aarch64 Linux, and a macOS universal build compiles this header once per architecture,
+// 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.
diff --git a/tests/FrameTransformationTest.cpp b/tests/FrameTransformationTest.cpp
index 22f997521..3abebda59 100644
--- a/tests/FrameTransformationTest.cpp
+++ b/tests/FrameTransformationTest.cpp
@@ -22,8 +22,10 @@ inline uint64_t read_be64(const void *ptr) {
     return __builtin_bswap64(ptr64[0]);
 }
 
-TEST_CASE("Bshuf_SSE", "[bitshuffle]") {
-    REQUIRE (bshuf_using_SSE2() == 1);
+// The classic bitshuffle runs behind the HDF5 filter everywhere, and on aarch64 it is also the one
+// BitShuffleBlock.h picks, so a build that left it on its scalar path must not go unnoticed.
+TEST_CASE("Bshuf_SIMD", "[bitshuffle]") {
+    REQUIRE ((bshuf_using_SSE2() == 1 || bshuf_using_NEON() == 1));
 }
 
 TEST_CASE("FrameTransformation_Raw_NoCompression" ,"") {