diff options
| author | Rich Felker <dalias@aerifal.cx> | 2012-03-15 01:29:03 -0400 |
|---|---|---|
| committer | Rich Felker <dalias@aerifal.cx> | 2012-03-15 01:29:03 -0400 |
| commit | 809556e60a3359f646946879dd94c4760e5b8e84 (patch) | |
| tree | 23afab7c3cd180406757b99efda0363de99af703 /src | |
| parent | e0a54e6725eaa0b5aeb28e9815c310f70068d308 (diff) | |
| download | musl-809556e60a3359f646946879dd94c4760e5b8e84.tar.gz musl-809556e60a3359f646946879dd94c4760e5b8e84.tar.bz2 musl-809556e60a3359f646946879dd94c4760e5b8e84.tar.xz musl-809556e60a3359f646946879dd94c4760e5b8e84.zip | |
correctly rounded sqrt() asm for x86 (i387)
the fsqrt opcode is correctly rounded, but only in the fpu's selected
precision mode, which is 80-bit extended precision. to get a correctly
rounded double precision output, we check for the only corner cases
where two-step rounding could give different results than one-step
(extended-precision mantissa ending in 0x400) and adjust the mantissa
slightly in the opposite direction of the rounding which the fpu
already did (reported in the c1 flag of the fpu status word).
this should have near-zero cost in the non-corner cases and at worst
very low cost.
note that in order for sqrt() to get used when compiling with gcc, the
broken, non-conformant builtin sqrt must be disabled.
Diffstat (limited to 'src')
| -rw-r--r-- | src/math/i386/sqrt.s | 16 |
1 files changed, 16 insertions, 0 deletions
diff --git a/src/math/i386/sqrt.s b/src/math/i386/sqrt.s index c6e55303..8289d094 100644 --- a/src/math/i386/sqrt.s +++ b/src/math/i386/sqrt.s @@ -2,4 +2,20 @@ .type sqrt,@function sqrt: fldl 4(%esp) fsqrt + fstsw %ax + sub $12,%esp + fld %st(0) + fstpt (%esp) + mov (%esp),%ecx + and $0x7ff,%ecx + cmp $0x400,%ecx + jnz 1f + and $0x200,%eax + sub $0x100,%eax + sub %eax,(%esp) + fstp %st(0) + fldt (%esp) +1: add $12,%esp + fstpl 4(%esp) + fldl 4(%esp) ret |