@@ -23,6 +23,7 @@
# define MEMSET __memset_base64
#endif
+/* To disable DC ZVA, set this threshold to 0. */
#ifndef DC_ZVA_THRESHOLD
# define DC_ZVA_THRESHOLD 512
#endif
@@ -91,11 +92,12 @@ L(set96):
.p2align 4
L(set_long):
stp val, val, [dstin]
+ bic dst, dstin, 15
+#if DC_ZVA_THRESHOLD
cmp count, DC_ZVA_THRESHOLD
ccmp val, 0, 0, cs
- bic dst, dstin, 15
b.eq L(zva_64)
-
+#endif
/* Small-size or non-zero memset does not use DC ZVA. */
sub count, dstend, dst
@@ -105,7 +107,11 @@ L(set_long):
* count is less than 33 bytes, so as to bypass 2 unneccesary stps.
*/
sub count, count, 64+16+1
+
+#if DC_ZVA_THRESHOLD
+ /* Align loop on 16-byte boundary, this might be friendly to i-cache. */
nop
+#endif
1: stp val, val, [dst, 16]
stp val, val, [dst, 32]
@@ -121,6 +127,7 @@ L(set_long):
stp val, val, [dstend, -16]
ret
+#if DC_ZVA_THRESHOLD
.p2align 3
L(zva_64):
stp val, val, [dst, 16]
@@ -173,6 +180,7 @@ L(zva_64):
1: stp val, val, [dstend, -32]
stp val, val, [dstend, -16]
ret
+#endif
END (MEMSET)
libc_hidden_builtin_def (MEMSET)
@@ -21,12 +21,14 @@
# define MEMSET __memset_emag
/*
- * Using dc zva to zero memory does not produce better performance if
+ * Using DC ZVA to zero memory does not produce better performance if
* memory size is not very large, especially when there are multiple
- * processes/threads contending memory/cache. Here we use a somewhat
- * large threshold to trigger usage of dc zva.
-*/
-# define DC_ZVA_THRESHOLD 1024
+ * processes/threads contending memory/cache. Here we set threshold to
+ * zero to disable using DC ZVA, which is good for multi-process/thread
+ * workloads.
+ */
+
+# define DC_ZVA_THRESHOLD 0
# include "./memset_base64.S"
#endif