diff options
author | Szabolcs Nagy <nsz@port70.net> | 2019-09-16 20:33:11 +0000 |
---|---|---|
committer | Rich Felker <dalias@aerifal.cx> | 2019-09-27 11:18:59 -0400 |
commit | ca577951138127dcf4190a2eb3c7148b2ad6d779 (patch) | |
tree | c8f2686823505275503dd12f38ab0c96bdb41fbf /src/ldso/aarch64/tlsdesc.s | |
parent | 604f8d3d8b08ee4f548de193050ef93a7753c2e0 (diff) | |
download | musl-ca577951138127dcf4190a2eb3c7148b2ad6d779.tar.gz musl-ca577951138127dcf4190a2eb3c7148b2ad6d779.tar.xz musl-ca577951138127dcf4190a2eb3c7148b2ad6d779.zip |
math: optimize lrint on 32bit targets
lrint in (LONG_MAX, 1/DBL_EPSILON) and in (-1/DBL_EPSILON, LONG_MIN) is not trivial: rounding to int may be inexact, but the conversion to int may overflow and then the inexact flag must not be raised. (the overflow threshold is rounding mode dependent). this matters on 32bit targets (without single instruction lrint or rint), so the common case (when there is no overflow) is optimized by inlining the lrint logic, otherwise the old code is kept as a fallback. on my laptop an i486 lrint call is asm:10ns, old c:30ns, new c:21ns on a smaller arm core: old c:71ns, new c:34ns on a bigger arm core: old c:27ns, new c:19ns
Diffstat (limited to 'src/ldso/aarch64/tlsdesc.s')
0 files changed, 0 insertions, 0 deletions