[Qemu-devel] [PATCH] migration: vectorize is_dup_page

[Paolo Bonzini]

is_dup_page is already proceeding in 32-bit chunks.  Changing it to 16
bytes using Altivec or SSE is easy, and provides a noticeable improvement.
Pierre Riteau measured 30->25 seconds on a 16GB guest, I measured 4.6->3.9
seconds on a 6GB guest (best of three times for me; dunno for Pierre).
Both of them are approximately a 15% improvement.

I tried playing with non-temporal prefetches, but I did not get any
improvement (though I did get less cache misses, so the patch was doing
its job).

Signed-off-by: Paolo Bonzini <address@hidden>
---
 arch_init.c |   28 ++++++++++++++++++++++------
 1 files changed, 22 insertions(+), 6 deletions(-)

diff --git a/arch_init.c b/arch_init.c
index cdad805..473df2d 100644
--- a/arch_init.c
+++ b/arch_init.c
@@ -94,14 +94,30 @@ const uint32_t arch_type = QEMU_ARCH;
 #define RAM_SAVE_FLAG_EOS      0x10
 #define RAM_SAVE_FLAG_CONTINUE 0x20
 
-static int is_dup_page(uint8_t *page, uint8_t ch)
+#if __ALTIVEC__
+#include <altivec.h>
+#define VECTYPE        vector unsigned char
+#define SPLAT(p)       vec_splat(vec_ld(0, p), 0)
+#define ALL_EQ(v1, v2) vec_all_eq(v1, v2)
+#elif __SSE2__
+#include <emmintrin.h>
+#define VECTYPE        __m128i
+#define SPLAT(p)       _mm_set1_epi8(*(p))
+#define ALL_EQ(v1, v2) (_mm_movemask_epi8(_mm_cmpeq_epi8(v1, v2)) == 0xFFFF)
+#else
+#define VECTYPE        unsigned long
+#define SPLAT(p)       (*(p) * (~0UL / 255))
+#define ALL_EQ(v1, v2) ((v1) == (v2))
+#endif
+
+static int is_dup_page(uint8_t *page)
 {
-    uint32_t val = ch << 24 | ch << 16 | ch << 8 | ch;
-    uint32_t *array = (uint32_t *)page;
+    VECTYPE *p = (VECTYPE *)page;
+    VECTYPE val = SPLAT(p);
     int i;
 
-    for (i = 0; i < (TARGET_PAGE_SIZE / 4); i++) {
-        if (array[i] != val) {
+    for (i = 0; i < TARGET_PAGE_SIZE / sizeof(VECTYPE); i++) {
+        if (!ALL_EQ(val, p[i])) {
             return 0;
         }
     }
@@ -136,7 +152,7 @@ static int ram_save_block(QEMUFile *f)
 
             p = block->host + offset;
 
-            if (is_dup_page(p, *p)) {
+            if (is_dup_page(p)) {
                 qemu_put_be64(f, offset | cont | RAM_SAVE_FLAG_COMPRESS);
                 if (!cont) {
                     qemu_put_byte(f, strlen(block->idstr));
-- 
1.7.7.1