diff mbox

aarch64: Add tunable glibc.memset.dc_zva_threshold

Message ID BYAPR01MB4869818C970E0A2F6FBAD4E9F7D70@BYAPR01MB4869.prod.exchangelabs.com
State Committed
Headers

Commit Message

Feng Xue OS Aug. 8, 2019, 3:56 a.m. UTC 
  This version disable DC ZVA in emag.

Feng
------
    * sysdeps/aarch64/multiarch/memset_base64.S (DC_ZVA_THRESHOLD):
    Disable DC ZVA code if this macro is defined as zero.
    * sysdeps/aarch64/multiarch/memset_emag.S (DC_ZVA_THRESHOLD):
    Change to zero to disable using DC ZVA.
---
 ChangeLog                                 |  7 +++++++
 sysdeps/aarch64/multiarch/memset_base64.S | 12 ++++++++++--
 sysdeps/aarch64/multiarch/memset_emag.S   | 12 +++++++-----
 3 files changed, 24 insertions(+), 7 deletions(-)

--
1.8.3.1
diff mbox

Patch

diff --git a/ChangeLog b/ChangeLog
index dbdb85d..ba27f96 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,10 @@ 
+2019-08-08  Feng Xue  <fxue@os.amperecomputing.com>
+
+       * sysdeps/aarch64/multiarch/memset_base64.S (DC_ZVA_THRESHOLD):
+       Disable DC ZVA code if this macro is defined as zero.
+       * sysdeps/aarch64/multiarch/memset_emag.S (DC_ZVA_THRESHOLD):
+       Change to zero to disable using DC ZVA.
+
 2019-07-25  Florian Weimer  <fweimer@redhat.com>

        [BZ #24677]
diff --git a/sysdeps/aarch64/multiarch/memset_base64.S b/sysdeps/aarch64/multiarch/memset_base64.S
index 9a62325..c0cccba 100644
--- a/sysdeps/aarch64/multiarch/memset_base64.S
+++ b/sysdeps/aarch64/multiarch/memset_base64.S
@@ -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)
diff --git a/sysdeps/aarch64/multiarch/memset_emag.S b/sysdeps/aarch64/multiarch/memset_emag.S
index 1c1fabc..c2aed62 100644
--- a/sysdeps/aarch64/multiarch/memset_emag.S
+++ b/sysdeps/aarch64/multiarch/memset_emag.S
@@ -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