git/list[1] front-page[2] threads[3] people[4] search[5] about
 

Re: Why Git is so fast

From
Dmitry Potapov <dpotapov@gmail.com>
Date
May 1, 2009, 10:46 UTC
Message-ID
<20090501104655.GC4863@dpotapov.dyndns.org>
In-Reply-To
<20090501094221.GB13264@glandium.org>
On Fri, May 01, 2009 at 11:42:21AM +0200, Mike Hommey wrote:
Show 10 quoted lines
> On Fri, May 01, 2009 at 09:24:34AM +0400, Dmitry Potapov wrote:
> > 
> > Good compilers can inline memcpy and should produce more efficient code
> > for the target architecture, which can be faster than manually written.
> > On x86_64, memcpy() requires only 3 load/store operations to copy SHA-1
> > while the above code requires 5 operations.
> 
> I guess, though, that some enforced alignment could help produce
> slightly more efficient code on some architectures (most notably sparc,
> which really doesn't like to deal with unaligned words).

Agreed. Enforcing good alignment may be useful. My point was that avoiding memcpy with modern compilers is rather pointless or even harmful because the compiler know more about the target architecture than the author of the code.

Dmitry
Previous: Mike HommeyNext: Shawn O. Pearce
Message 26 of 39 in “Eric Sink's blog - notes on git, dscms and a "whole product" approach”
  1. Martin LanghoffApr 27, 2009
  2. Cross-Platform Version Control (was: Eric Sink's blog - notes on git, dscms and a "whole product" approach)Jakub Narebski, Apr 28, 2009
  3. Robin RosenbergApr 28, 2009
  4. Martin LanghoffApr 29, 2009
  5. Jeff KingApr 29, 2009
  6. Markus HeidelbergApr 29, 2009
  7. Jakub NarebskiApr 29, 2009
  8. Martin LanghoffApr 29, 2009
  9. Jakub NarebskiApr 28, 2009
  10. Sitaram ChamartyApr 29, 2009
  11. Why Git is so fast (was: Re: Eric Sink's blog - notes on git, dscms and a "whole product" approach)Jakub Narebski, Apr 30, 2009
  12. Michael WittenApr 30, 2009
  13. Jakub NarebskiApr 30, 2009
  14. Shawn O. PearceApr 30, 2009
  15. Kjetil BarvikApr 30, 2009
  16. Shawn O. PearceApr 30, 2009
  17. Kjetil BarvikApr 30, 2009
  18. Steven NoonanMay 1, 2009
  19. James PickensMay 1, 2009
  20. Kjetil BarvikMay 1, 2009
  21. Mike HommeyMay 1, 2009
  22. Kjetil BarvikMay 1, 2009
  23. Tony FinchMay 1, 2009
  24. Dmitry PotapovMay 1, 2009
  25. Mike HommeyMay 1, 2009
  26. Dmitry PotapovMay 1, 2009
  27. Shawn O. PearceApr 30, 2009
  28. Jeff KingApr 30, 2009
  29. Linus TorvaldsMay 1, 2009
  30. Jeff KingMay 1, 2009
  31. david@lang.hmMay 1, 2009
  32. Nicolas PitreMay 1, 2009
  33. Daniel BarkalowMay 1, 2009
  34. Linus TorvaldsMay 1, 2009
  35. david@lang.hmMay 1, 2009
  36. Nicolas PitreApr 30, 2009
  37. Alex RiesenApr 30, 2009
  38. Andreas EricssonMay 4, 2009
  39. Jakub NarebskiApr 30, 2009

Read the whole thread, see it on lore, or plain text.

$ cat FOOTERMessages come from the public archive at lore.kernel.org/git, fetched every hour. The front page is chosen and written each morning by an AI editor and can be wrong; the threads themselves are the record. About and API. For agents: an MCP server at https://gitlist.dev/mcp, and any thread, story or person page as Markdown by adding .md to its URL (or sending Accept: text/markdown). Details in /llms.txt.