about summary refs log tree commit diff
path: root/src/internal/libc.h
diff options
context:
space:
mode:
authorRich Felker <dalias@aerifal.cx>2012-04-11 14:51:08 -0400
committerRich Felker <dalias@aerifal.cx>2012-04-11 14:51:08 -0400
commit4054da9ba062c694dc4fde5c577fcb6da7743bc9 (patch)
tree9f0e3246c2ac8a76d0e0e568b543de385a138c15 /src/internal/libc.h
parent5837a0bb6b5cf516f79527e837368af0b494d51a (diff)
downloadmusl-4054da9ba062c694dc4fde5c577fcb6da7743bc9.tar.gz
musl-4054da9ba062c694dc4fde5c577fcb6da7743bc9.tar.xz
musl-4054da9ba062c694dc4fde5c577fcb6da7743bc9.zip
optimize floatscan downscaler to skip results that won't be needed
when upscaling, even the very last digit is needed in cases where the
input is exact; no digits can be discarded. but when downscaling, any
digits less significant than the mantissa bits are destined for the
great bitbucket; the only influence they can have is their presence
(being nonzero). thus, we simply throw them away early. the result is
nearly a 4x performance improvement for processing huge values.

the particular threshold LD_B1B_DIG+3 is not chosen sharply; it's
simply a "safe" distance past the significant bits. it would be nice
to replace it with a sharp bound, but i suspect performance will be
comparable (within a few percent) anyway.
Diffstat (limited to 'src/internal/libc.h')
0 files changed, 0 insertions, 0 deletions