zzh
/
fast-bwa
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
986 Commits
3 Branches
0 Tags
123 MiB
Commit Graph

986 Commits (8f3cb79d6fe58870d7107a77f82a8e592e049638)

Author SHA1 Message Date
zzh 8f3cb79d6f 在avx2中加入了一些特殊判断，保证了和串行的sw结果保持基本一致 2024-03-01 18:45:09 +08:00
zzh 5cd4c10858 减少了频繁开辟释放内存，基本是所有优化手段都加上了，只是simd版本的准确性还有待进一步完善 2024-02-27 16:10:52 +08:00
zzh d51903b923 忽略sam文件 2024-02-22 01:32:18 +08:00
zzh a1a3f4215c 删除调试输出的sam文件 2024-02-22 01:29:42 +08:00
zzh 198fe34ddb 做了一些代码清理，目前结果应该是完全一致的 2024-02-22 01:26:57 +08:00
zzh 57a6ff7b07 解决了sa的bug，现在结果和原版一模一样 2024-02-21 15:21:56 +08:00
zzh c288e1b285 实现了seed过程的所有加速想法，seed部分实现了3倍左右加速比 2024-02-20 01:12:02 +08:00
zzh 95fd6e018b 修改一些注释疏忽的问题 2024-02-16 21:23:55 +08:00
zzh e9022723e6 seed三个步骤，全部用fmt实现，而且结果一致 2024-02-16 20:59:59 +08:00
zzh 980588a9ac 添加了bit过滤，解决了一些bug，现在seed1和seed2都没问题了 2024-02-16 00:18:14 +08:00
zzh 76c32542e7 seed1和seed2结果都正确 2024-02-13 13:37:07 +08:00
zzh 32be32c661 kmer长度变为14，结果正确 2024-02-12 20:54:57 +08:00
zzh 44b7c62715 将smem1函数用fmt结构实现了，结果基本正确 2024-02-07 22:08:51 +08:00
zzh e18e60c0b5 实现了用33bit表示sa，间隔为4，释放内存的时候会崩溃 2023-12-27 10:42:12 +08:00
zzh ed01396d73 添加了运行时间计算代码，用来分析性能 2023-12-25 13:58:15 +08:00
zzh d304f030fb 添加了fmt_idx文件，开始改进seed过程 2023-12-25 11:11:19 +08:00
zzh a37cb500e2 第一次merge 2023-12-24 17:25:55 +08:00
zzh ea9e707238 添加了一些注释 2023-12-24 17:23:14 +08:00
zzh 7807c96882 Initial commit 2023-12-24 17:21:30 +08:00
Heng Li 139f68fc4c
Merge pull request #367 from martin-g/github-actions-linux-aarch64 
Add CI job for Ubuntu 20.04 aarch64
 2022-09-22 19:52:12 -04:00
Martin Tzvetanov Grigorov 94248a8cea
Add CI job for Ubuntu 20.04 aarch64 
Signed-off-by: Martin Tzvetanov Grigorov <mgrigorov@apache.org>
 2022-09-01 10:11:22 +03:00
Heng Li 2e603e4581
Merge pull request #359 from jmarshall/neon 
Add ARM Neon and scalar implementations of SIMD functions
 2022-08-31 09:50:31 -04:00
John Marshall c77ace7059 Use native SSE2 intrinsics on i386 as well as x86-64 
Make the native SSE2 code conditional on __SSE2__, which is defined
by GCC/Clang/etc on x86-64 by default and on i386 with -msse2 etc.
 2022-06-27 14:15:59 +01:00
John Marshall ac612b6f5a On other platforms, emulate SSE2 SIMD calls using scalar code 2022-06-26 19:38:20 +01:00
John Marshall 165e524e5c On ARM, rewrite SSE2 SIMD calls using Neon intrinsics 
Many Intel intrinsics have a corresponding Neon equivalent.
Other cases are more interesting:

* Neon's vmaxvq directly selects the maximum entry in a vector,
  so can be used to implement both the __max_16/__max_8 macros
  and the _mm_movemask_epi8 early loop exit. Introduce additional
  helper macros alongside __max_16/__max_8 so that the early loop
  exit can similarly be implemented differently on the two platforms.

* Full-width shifts can be done via vextq. This is defined close to
  the ksw_u8()/ksw_i16() functions (rather than in neon_sse.h) as it
  implicitly uses one of their local variables.

* ksw_i16() uses saturating *signed* 16-bit operations apart from
  _mm_subs_epu16; presumably the data is effectively still signed but
  we wish to keep it non-negative. The ARM intrinsics are more careful
  about type checking, so this requires an extra U16() helper macro.
 2022-06-20 20:43:17 +01:00
John Marshall ab01ab4490 Make _mm_load_si128() explicit 
The previous code implicitly caused a load; change it so the load
intrinsic is explicitly invoked, as the others are. (This in fact
makes no difference to the generated code.)
 2022-06-17 18:42:07 +01:00
Heng Li b56db22548
Merge pull request #355 from clintval/cv_document_new_XB 
Document that the XB tag now contains the mapping quality too
 2022-06-03 15:01:14 -04:00
clintval 2160a0c7de Document that the XB tag now contains the mapping quality too 2022-05-19 13:43:22 -04:00
Heng Li 2d4272bc82
Merge pull request #263 from jmarshall/std-vars 
Makefile: Use $CPPFLAGS and $LDFLAGS if they are set
 2022-03-07 09:50:23 -05:00
John Marshall ceaaa6d9cb Use $CPPFLAGS and $LDFLAGS if they are set 
The bwa makefile doesn't set these two itself, but the environment
or make command line might set any of CC/CPPFLAGS/CFLAGS/LDFLAGS/LIBS.
Use $(CPPFLAGS) when compiling and $(LDFLAGS) when linking so they can
be used to customise the build. Remove $(DFLAGS) from link commands as
these preprocessor options are irrelevant for linking.
 2022-03-07 10:59:42 +00:00
Heng Li 8c92aef23d Merge branch 'fulcrumgenomics-feature/add-xa-drop-ratio-option' 2022-03-06 18:22:02 -05:00
Heng Li 58e3ed223f Merge branch 'feature/add-xa-drop-ratio-option' of https://github.com/fulcrumgenomics/bwa into fulcrumgenomics-feature/add-xa-drop-ratio-option 2022-03-06 18:21:49 -05:00
Heng Li 41e007868c
Merge pull request #293 from nh13/patch-2 
Output mapping quality with XB
 2022-03-06 18:18:45 -05:00
Heng Li cb7e5dffcf
Merge pull request #292 from nh13/patch-1 
Document "-u"
 2022-03-06 18:16:09 -05:00
Heng Li 40b3aeed56
Merge pull request #297 from nh13/patch-3 
Clarify bwa mem -5 option
 2022-03-06 18:12:09 -05:00
Heng Li 0747fcc09d
Merge pull request #330 from nh13/patch-4 
Add the mate mapping quality tag
 2022-03-06 18:07:01 -05:00
Heng Li ef52b4ac19
Merge pull request #336 from nh13/patch-5 
Add the header line to the output SAM
 2022-03-06 18:06:38 -05:00
Heng Li 760098d1c2
Merge pull request #343 from nh13/patch-7 
Update bwa.1 to remove ancient reference to picard
 2022-03-06 18:05:46 -05:00
Nils Homer 4bf3cdf948
Update bwa.1 2022-02-18 13:36:09 -08:00
Nils Homer 6b18630a62
Add the header line to the output SAM 
In particular, this defines the output SAM to be unsorted BUT also query grouped.  The latter is very important to explicitly define so downstream tools that don't make assumptions know that reads from the same template are grouped.
 2021-12-14 08:02:05 -07:00
Nils Homer d8dd308a1f
Add the mate mapping quality tag 2021-07-21 11:12:27 -07:00
Heng Li 3ddd7b87d4 fixed wrong Markdown format in README 2021-05-10 12:48:45 -04:00
Heng Li fe209ff1ca updated to Github CI status 2021-05-10 12:47:13 -04:00
Heng Li f033d4e4e7
Merge pull request #325 from jmarshall/ci 
Use GitHub Actions instead of Travis CI
 2021-05-10 12:44:43 -04:00
John Marshall 765fac1070 Convert Travis CI to GitHub Actions 
Make an equivalent GitHub Actions workflow that tests compilation
with both GCC and Clang.
 2021-05-09 22:54:58 +01:00
Heng Li fbfffc9031 added code of conduct 2021-04-22 17:35:37 -04:00
Heng Li 34374c5613 Removed the debug output; resolves #320 2021-03-09 08:56:52 -05:00
Heng Li 110bf9b8ed deprecate bwasw 2021-03-09 00:52:20 -05:00
Heng Li f1d1fd7c42 output more memory information 2021-02-23 10:43:41 -05:00
Heng Li b9accf95ad debug flag to measure memory 2021-02-22 23:26:03 -05:00