@@ -10,6 +10,36 @@
* files/head:/src/aarch64/
*/
+.macro loop_for_copy_128_bytes extra_ops
+ /* pre-get 64 bytes data. */
+ ldp1 A_l, A_h, src, #16
+ ldp1 B_l, B_h, src, #16
+ ldp1 C_l, C_h, src, #16
+ ldp1 D_l, D_h, src, #16
+1:
+ \extra_ops
+ /*
+ * interlace the load of next 64 bytes data block with store of the last
+ * loaded 64 bytes data.
+ */
+ stp1 A_l, A_h, dst, #16
+ ldp1 A_l, A_h, src, #16
+ stp1 B_l, B_h, dst, #16
+ ldp1 B_l, B_h, src, #16
+ stp1 C_l, C_h, dst, #16
+ ldp1 C_l, C_h, src, #16
+ stp1 D_l, D_h, dst, #16
+ ldp1 D_l, D_h, src, #16
+ subs count, count, #64
+ b.ge 1b
+ stp1 A_l, A_h, dst, #16
+ stp1 B_l, B_h, dst, #16
+ stp1 C_l, C_h, dst, #16
+ stp1 D_l, D_h, dst, #16
+
+ tst count, #0x3f
+ b.ne .Ltail63
+.endm
/*
* Copy a buffer from src to dest (alignment handled by the hardware)
@@ -151,31 +181,5 @@ D_h .req x14
*/
.p2align L1_CACHE_SHIFT
.Lcpy_body_large:
- /* pre-get 64 bytes data. */
- ldp1 A_l, A_h, src, #16
- ldp1 B_l, B_h, src, #16
- ldp1 C_l, C_h, src, #16
- ldp1 D_l, D_h, src, #16
-1:
- /*
- * interlace the load of next 64 bytes data block with store of the last
- * loaded 64 bytes data.
- */
- stp1 A_l, A_h, dst, #16
- ldp1 A_l, A_h, src, #16
- stp1 B_l, B_h, dst, #16
- ldp1 B_l, B_h, src, #16
- stp1 C_l, C_h, dst, #16
- ldp1 C_l, C_h, src, #16
- stp1 D_l, D_h, dst, #16
- ldp1 D_l, D_h, src, #16
- subs count, count, #64
- b.ge 1b
- stp1 A_l, A_h, dst, #16
- stp1 B_l, B_h, dst, #16
- stp1 C_l, C_h, dst, #16
- stp1 D_l, D_h, dst, #16
-
- tst count, #0x3f
- b.ne .Ltail63
+ loop_for_copy_128_bytes
.Lexitfunc: