mirror of
https://github.com/Motorhead1991/qemu.git
synced 2025-12-17 21:26:13 -07:00
cutils: add avx2 instruction optimization
buffer_find_nonzero_offset() is a hot function during live migration. Now it use SSE2 instructions for optimization. For platform supports AVX2 instructions, use AVX2 instructions for optimization can help to improve the performance of buffer_find_nonzero_offset() about 30% comparing to SSE2. Live migration can be faster with this optimization, the test result shows that for an 8GiB RAM idle guest just boots, this patch can help to shorten the total live migration time about 6%. This patch use the ifunc mechanism to select the proper function when running, for platform supports AVX2, execute the AVX2 instructions, else, execute the original instructions. Signed-off-by: Liang Li <liang.z.li@intel.com> Suggested-by: Paolo Bonzini <pbonzini@redhat.com> Suggested-by: Richard Henderson <rth@twiddle.net> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Message-Id: <1457416397-26671-3-git-send-email-liang.z.li@intel.com> Signed-off-by: Amit Shah <amit.shah@redhat.com>
This commit is contained in:
parent
99f2dbd343
commit
28b90d9c19
2 changed files with 121 additions and 11 deletions
|
|
@ -476,13 +476,7 @@ void qemu_hexdump(const char *buf, FILE *fp, const char *prefix, size_t size);
|
|||
#endif
|
||||
|
||||
#define BUFFER_FIND_NONZERO_OFFSET_UNROLL_FACTOR 8
|
||||
static inline bool
|
||||
can_use_buffer_find_nonzero_offset(const void *buf, size_t len)
|
||||
{
|
||||
return (len % (BUFFER_FIND_NONZERO_OFFSET_UNROLL_FACTOR
|
||||
* sizeof(VECTYPE)) == 0
|
||||
&& ((uintptr_t) buf) % sizeof(VECTYPE) == 0);
|
||||
}
|
||||
bool can_use_buffer_find_nonzero_offset(const void *buf, size_t len);
|
||||
size_t buffer_find_nonzero_offset(const void *buf, size_t len);
|
||||
|
||||
/*
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue