use proper cache-line size variable in work-stealing queue (JuliaLang#53035)

Author: d-netto

src/julia_atomics.h

@@ -56,6 +56,15 @@ enum jl_memory_order {
     jl_memory_order_seq_cst
 };
 
+/**
+ * Cache line size
+*/
+#if defined(_CPU_AARCH64_) && defined(_OS_DARWIN_) // Apple silicon has 128 cache lines
+#define JL_CACHE_BYTE_ALIGNMENT 128
+#else
+#define JL_CACHE_BYTE_ALIGNMENT 64
+#endif
+
 /**
  * Thread synchronization primitives:
  *

src/julia_internal.h

@@ -485,11 +485,6 @@ STATIC_INLINE uint8_t JL_CONST_FUNC jl_gc_szclass_align8(unsigned sz) JL_NOTSAFE
 }
 
 #define JL_SMALL_BYTE_ALIGNMENT 16
-#if defined(_CPU_AARCH64_) && defined(_OS_DARWIN_) // Apple silicon has 128 cache lines
-#define JL_CACHE_BYTE_ALIGNMENT 128
-#else
-#define JL_CACHE_BYTE_ALIGNMENT 64
-#endif
 // JL_HEAP_ALIGNMENT is the maximum alignment that the GC can provide
 #define JL_HEAP_ALIGNMENT JL_SMALL_BYTE_ALIGNMENT
 #define GC_MAX_SZCLASS (2032-sizeof(void*))

src/work-stealing-queue.h

@@ -36,7 +36,7 @@ static inline ws_array_t *create_ws_array(size_t capacity, int32_t eltsz) JL_NOT
 
 typedef struct {
     _Atomic(int64_t) top;
-    char _padding[128 - sizeof(int64_t)];
+    char _padding[JL_CACHE_BYTE_ALIGNMENT - sizeof(_Atomic(int64_t))];
     _Atomic(int64_t) bottom; // put on a separate cache line. conservatively estimate cache line size as 128 bytes
     _Atomic(ws_array_t *) array;
 } ws_queue_t;