[#41916] Proposal: Bitmap Marking GC — Narihiro Nakamura <authornari@...>

Hi.

18 messages 2012/01/05

[#41941] [ruby-trunk - Bug #5851][Open] make check fails when compiling with GCC 4.7 - *** longjmp causes uninitialized stack frame *** — Vit Ondruch <v.ondruch@...>

12 messages 2012/01/06

[#41979] [ruby-trunk - Bug #5865][Open] Exception#== should return false if the classes differ — Hiro Asari <asari.ruby@...>

10 messages 2012/01/08

[#42003] [ruby-trunk - Bug #5871][Open] regexp \W matches some word characters when inside a case-insensitive character class — Gareth Adams <gareth@...>

14 messages 2012/01/09

[#42016] [ruby-trunk - Feature #5873][Open] Adopt FFI over DL — Heesob Park <phasis@...>

15 messages 2012/01/10

[#42149] [ruby-trunk - Feature #5899][Open] chaining comparsions. — Ondrej Bilka <neleai@...>

12 messages 2012/01/16

[#42164] [ruby-trunk - Feature #5903][Open] Optimize st_table (take 2) — Yura Sokolov <funny.falcon@...>

18 messages 2012/01/17

[ruby-core:41938] Re: Proposal: Bitmap Marking GC

From: Hiroshi Shirosaki <h.shirosaki@...>
Date: 2012-01-06 07:25:13 UTC
List: ruby-core #41938
> I created Bitmap Marking GC for Ruby2.0.
>
> Source code: https://github.com/authorNari/ruby/tree/bitmap_marking
> Patch: https://github.com/authorNari/patch_bag/blob/master/ruby/gc_bitmap_using_alignment_r33786.patch
>

I've tried benchmark against trunk@34217 on Windows XP with mingw32
gcc version 4.5.2 (tdm-1).
I used __mingw_aligned_malloc() cause of build error with
_aligned_[malloc|free].
I also found _aligned_malloc() is usable if #define __MSVCRT_VERSION__ 0x0700.

Result of make benchmark OPTS="-r 5".
https://gist.github.com/1569277

I skipped vm_thread_mutex2 and vm_thread_pass_flood cause of errors.
Some benchmarks are not a little slower on my box. Some benchmarks are
faster. Win7 might have different results.

Here is _aligned_[malloc|free] timing result.
https://gist.github.com/1569002

It's based on Jon Forums's work.
https://github.com/jonforums/tma

_aligned_[malloc|free] looks slower than plain malloc/free.


What do you think of windows implementation?

Thanks,
-- 
Hiroshi Shirosaki

In This Thread