Commits on Jul 11, 2024

1. Speed up kputll. …

   The kputuw function is considerably faster as it encodes 2 digits at a
   time and also utilises __builtin_clz.  This changes kputll to use the
   same 2 digits at a time trick.  I have a __builtin_clzll variant too,
   but with longer numbers it's not the main bottleneck and we fall back
   to kputuw for small numbers.  This avoids complicating the code with
   builtin checks and alternate versions.
   
   An alternative, purely for sam_format1_append would be something like:
   
       static inline int kputll_fast(long long c, kstring_t *s) {
           return c <= INT_MAX && c >= INT_MIN ? kputw(c, s) : kputll(c, s);
       }
       #define kputll kputll_fast
   
   This works as BAM/CRAM only support 32-bit numbers for POS, PNEXT and
   TLEN anyway, so ll vs w is an irrelevant distinction.  However I chose
   to modify the header file so it fixes other callers.
   
   Overall compressed BAM to uncompressed SAM conversion is about 5%
   quicker (tested on 10 million short-read seqs; it'll be minimal on
   long seqs).  This includes decode time and other functions too.  The
   sam_format1_append only component of that is about 15-25% quicker
   depending on compiler and version.

   

   jkbonfield committed Jul 11, 2024
   Configuration menu

   • View commit details
   • Copy full SHA for 6b9d7f1
   • Browse repository at this point

   Copy the full SHA

   6b9d7f1 View commit details

   Browse the repository at this point in the history