powerpc/64: enhance memcmp() with VMX instruction for long bytes comparision
This patch add VMX primitives to do memcmp() in case the compare size
is equal or greater than 4K bytes. KSM feature can benefit from this.
Test result with following test program(replace the "^>" with ""):
------
># cat tools/testing/selftests/powerpc/stringloops/memcmp.c
>#include <malloc.h>
>#include <stdlib.h>
>#include <string.h>
>#include <time.h>
>#include "utils.h"
>#define SIZE (1024 * 1024 * 900)
>#define ITERATIONS 40
int test_memcmp(const void *s1, const void *s2, size_t n);
static int testcase(void)
{
char *s1;
char *s2;
unsigned long i;
s1 = memalign(128, SIZE);
if (!s1) {
perror("memalign");
exit(1);
}
s2 = memalign(128, SIZE);
if (!s2) {
perror("memalign");
exit(1);
}
for (i = 0; i < SIZE; i++) {
s1[i] = i & 0xff;
s2[i] = i & 0xff;
}
for (i = 0; i < ITERATIONS; i++) {
int ret = test_memcmp(s1, s2, SIZE);
if (ret) {
printf("return %d at[%ld]! should have returned zero\n", ret, i);
abort();
}
}
return 0;
}
int main(void)
{
return test_harness(testcase, "memcmp");
}
------
Without this patch (but with the first patch "powerpc/64: Align bytes
before fall back to .Lshort in powerpc64 memcmp()." in the series):
4.726728762 seconds time elapsed ( +- 3.54%)
With VMX patch:
4.234335473 seconds time elapsed ( +- 2.63%)
There is ~+10% improvement.
Testing with unaligned and different offset version (make s1 and s2 shift
random offset within 16 bytes) can archieve higher improvement than 10%..
Signed-off-by: Simon Guo <wei.guo.simon@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
diff --git a/arch/powerpc/lib/memcpy_power7.S b/arch/powerpc/lib/memcpy_power7.S
index df7de9d..070cdf6 100644
--- a/arch/powerpc/lib/memcpy_power7.S
+++ b/arch/powerpc/lib/memcpy_power7.S
@@ -230,7 +230,7 @@
std r5,-STACKFRAMESIZE+STK_REG(R29)(r1)
std r0,16(r1)
stdu r1,-STACKFRAMESIZE(r1)
- bl enter_vmx_copy
+ bl enter_vmx_ops
cmpwi cr1,r3,0
ld r0,STACKFRAMESIZE+16(r1)
ld r3,STK_REG(R31)(r1)
@@ -445,7 +445,7 @@
15: addi r1,r1,STACKFRAMESIZE
ld r3,-STACKFRAMESIZE+STK_REG(R31)(r1)
- b exit_vmx_copy /* tail call optimise */
+ b exit_vmx_ops /* tail call optimise */
.Lvmx_unaligned_copy:
/* Get the destination 16B aligned */
@@ -649,5 +649,5 @@
15: addi r1,r1,STACKFRAMESIZE
ld r3,-STACKFRAMESIZE+STK_REG(R31)(r1)
- b exit_vmx_copy /* tail call optimise */
+ b exit_vmx_ops /* tail call optimise */
#endif /* CONFIG_ALTIVEC */