Skip to content

cloud-kernel
cloud-kernel

openanolis / cloud-kernel
接近 2 年 前同步成功

通知 170
Star 36
Fork 7
cloud-kernel
cloud-kernel
切换分支/标签
  1. 18 1月, 2012 1 次提交
  3. 16 1月, 2012 1 次提交
  5. 13 12月, 2011 1 次提交
  7. 05 12月, 2011 2 次提交
  9. 10 10月, 2011 1 次提交
  11. 27 7月, 2011 1 次提交
  13. 22 7月, 2011 1 次提交
  15. 21 7月, 2011 3 次提交
  17. 14 7月, 2011 1 次提交
  19. 04 6月, 2011 1 次提交
  21. 18 5月, 2011 6 次提交
  23. 02 5月, 2011 1 次提交
  25. 28 3月, 2011 1 次提交
  27. 18 3月, 2011 2 次提交
  29. 02 3月, 2011 1 次提交
  31. 01 3月, 2011 3 次提交
  33. 28 2月, 2011 1 次提交
  35. 26 1月, 2011 1 次提交
  37. 04 1月, 2011 1 次提交
  39. 25 9月, 2010 1 次提交
    • M
      x86, mem: Optimize memmove for small size and unaligned cases · 3b4b682b
      由 Ma Ling 提交于 
      movs instruction will combine data to accelerate moving data,
however we need to concern two cases about it.

1. movs instruction need long lantency to startup,
   so here we use general mov instruction to copy data.
2. movs instruction is not good for unaligned case,
   even if src offset is 0x10, dest offset is 0x0,
   we avoid and handle the case by general mov instruction.
Signed-off-by: NMa Ling <ling.ma@intel.com>
LKML-Reference: <1284664360-6138-1-git-send-email-ling.ma@intel.com>
Signed-off-by: NH. Peter Anvin <hpa@zytor.com>
      3b4b682b
  41. 24 8月, 2010 2 次提交
    • M
      x86, mem: Optimize memcpy by avoiding memory false dependece · 59daa706
      由 Ma Ling 提交于 
      All read operations after allocation stage can run speculatively,
all write operation will run in program order, and if addresses are
different read may run before older write operation, otherwise wait
until write commit. However CPU don't check each address bit,
so read could fail to recognize different address even they
are in different page.For example if rsi is 0xf004, rdi is 0xe008,
in following operation there will generate big performance latency.
1. movq (%rsi),	%rax
2. movq %rax,	(%rdi)
3. movq 8(%rsi), %rax
4. movq %rax,	8(%rdi)

If %rsi and rdi were in really the same meory page, there are TRUE
read-after-write dependence because instruction 2 write 0x008 and
instruction 3 read 0x00c, the two address are overlap partially.
Actually there are in different page and no any issues,
but without checking each address bit CPU could think they are
in the same page, and instruction 3 have to wait for instruction 2
to write data into cache from write buffer, then load data from cache,
the cost time read spent is equal to mfence instruction. We may avoid it by
tuning operation sequence as follow.

1. movq 8(%rsi), %rax
2. movq %rax,	8(%rdi)
3. movq (%rsi),	%rax
4. movq %rax,	(%rdi)

Instruction 3 read 0x004, instruction 2 write address 0x010, no any
dependence.  At last on Core2 we gain 1.83x speedup compared with
original instruction sequence.  In this patch we first handle small
size(less 20bytes), then jump to different copy mode. Based on our
micro-benchmark small bytes from 1 to 127 bytes, we got up to 2X
improvement, and up to 1.5X improvement for 1024 bytes on Corei7.  (We
use our micro-benchmark, and will do further test according to your
requirment)
Signed-off-by: NMa Ling <ling.ma@intel.com>
LKML-Reference: <1277753065-18610-1-git-send-email-ling.ma@intel.com>
Signed-off-by: NH. Peter Anvin <hpa@zytor.com>
      59daa706
    • M
      x86, mem: Don't implement forward memmove() as memcpy() · fdf42896
      由 Ma, Ling 提交于 
      memmove() allow source and destination address to be overlap, but
there is no such limitation for memcpy().  Therefore, explicitly
implement memmove() in both the forwards and backward directions, to
give us the ability to optimize memcpy().
Signed-off-by: NMa Ling <ling.ma@intel.com>
LKML-Reference: <C10D3FB0CD45994C8A51FEC1227CE22F0E483AD86A@shsmsx502.ccr.corp.intel.com>
Signed-off-by: NH. Peter Anvin <hpa@linux.intel.com>
      fdf42896
  43. 12 8月, 2010 2 次提交
  45. 29 7月, 2010 2 次提交
  47. 14 7月, 2010 1 次提交
  49. 08 7月, 2010 1 次提交
    • H
      x86, alternatives: Use 16-bit numbers for cpufeature index · 83a7a2ad
      由 H. Peter Anvin 提交于 
      We already have cpufeature indicies above 255, so use a 16-bit number
for the alternatives index.  This consumes a padding field and so
doesn't add any size, but it means that abusing the padding field to
create assembly errors on overflow no longer works.  We can retain the
test simply by redirecting it to the .discard section, however.

[ v3: updated to include open-coded locations ]
Signed-off-by: NH. Peter Anvin <hpa@linux.intel.com>
LKML-Reference: <tip-f88731e3068f9d1392ba71cc9f50f035d26a0d4f@git.kernel.org>
Signed-off-by: NH. Peter Anvin <hpa@zytor.com>
      83a7a2ad
  51. 05 5月, 2010 1 次提交