- 15 12月, 2012 1 次提交
-
-
由 Szabolcs Nagy 提交于
with naive exp2l(x*log2e) the last 12bits of the result was incorrect for x with large absolute value with hi + lo = x*log2e is caluclated to 128 bits precision and then expl(x) = exp2l(hi) + exp2l(hi) * f2xm1(lo) this gives <1.5ulp measured error everywhere in nearest rounding mode
-
- 12 12月, 2012 1 次提交
-
-
由 Szabolcs Nagy 提交于
__invtrigl is not needed when acosl, asinl, atanl have asm implementations
-
- 09 8月, 2012 1 次提交
-
-
由 nsz 提交于
exp(inf), exp(-inf), exp(nan) used to raise wrong flags
-
- 08 5月, 2012 1 次提交
-
-
由 Rich Felker 提交于
-
- 05 5月, 2012 1 次提交
-
-
由 nsz 提交于
old: 2*atan2(sqrt(1-x),sqrt(1+x)) new: atan2(fabs(sqrt((1-x)*(1+x))),x) improvements: * all edge cases are fixed (sign of zero in downward rounding) * a bit faster (here a single call is about 131ns vs 162ns) * a bit more precise (at most 1ulp error on 1M uniform random samples in [0,1), the old formula gave some 2ulp errors as well)
-
- 04 4月, 2012 1 次提交
-
-
由 nsz 提交于
use (1-x)*(1+x) instead of (1-x*x) in asin.s the later can be inaccurate with upward rounding when x is close to 1
-
- 29 3月, 2012 1 次提交
-
-
由 nsz 提交于
the int part was wrong when -1 < x <= -0 (+0.0 instead of -0.0) and the size and performace gain of the asm version was negligible
-
- 28 3月, 2012 1 次提交
-
-
由 nsz 提交于
(fldl instruction was used instead of flds and fldt)
-
- 23 3月, 2012 1 次提交
-
-
由 Rich Felker 提交于
special care is made to avoid any inexact computations when either arg is zero (in which case the exact absolute value of the other arg should be returned) and to support the special condition that hypot(±inf,nan) yields inf. hypotl is not yet implemented since avoiding overflow is nontrivial.
-
- 22 3月, 2012 1 次提交
-
-
由 nsz 提交于
the old formula atan2(1,sqrt((1+x)/(1-x))) was faster but could give nan result at x=1 when the rounding mode is FE_DOWNWARD (so 1-1 == -0 and 2/-0 == -inf), the new formula gives -0 at x=+-1 with downward rounding.
-
- 20 3月, 2012 5 次提交
-
-
由 Rich Felker 提交于
the fscale instruction is slow everywhere, probably because it involves a costly and unnecessary integer truncation operation that ends up being a no-op in common usages. instead, construct a floating point scale value with integer arithmetic and simply multiply by it, when possible. for float and double, this is always possible by going to the next-larger type. we use some cheap but effective saturating arithmetic tricks to make sure even very large-magnitude exponents fit. for long double, if the scaling exponent is too large to fit in the exponent of a long double value, we simply fallback to the expensive fscale method. on atom cpu, these changes speed up scalbn by over 30%. (min rdtsc timing dropped from 110 cycles to 70 cycles.)
-
由 Rich Felker 提交于
this is a lot more efficient and also what is generally wanted. perhaps the bit shuffling could be more efficient...
-
由 Rich Felker 提交于
-
由 Rich Felker 提交于
exponents (base 2) near 16383 were broken due to (1) wrong cutoff, and (2) inability to fit the necessary range of scalings into a long double value. as a solution, we fall back to using frndint/fscale for insanely large exponents, and also have to special-case infinities here to avoid inf-inf generating nan. thankfully the costly code never runs in normal usage cases.
-
由 Rich Felker 提交于
-
- 19 3月, 2012 15 次提交
-
-
由 Rich Felker 提交于
-
由 Rich Felker 提交于
-
由 Rich Felker 提交于
this could perhaps use some additional testing for corner cases, but it seems to be correct.
-
由 Rich Felker 提交于
up to 30% faster exp2 by avoiding slow frndint and fscale functions. expm1 also takes a much more direct path for small arguments (the expected usage case).
-
由 Rich Felker 提交于
-
由 Rich Felker 提交于
-
由 Rich Felker 提交于
-
由 Rich Felker 提交于
unlike some implementations, these functions perform the equivalent of gcc's -ffloat-store on the result before returning. this is necessary to raise underflow/overflow/inexact exceptions, perform the correct rounding with denormals, etc.
-
由 Rich Felker 提交于
unlike trig functions, these are easy to do in asm because they do not involve (arbitrary-precision) argument reduction. fpatan automatically takes care of domain issues, and in asin and acos, fsqrt takes care of them for us.
-
由 Rich Felker 提交于
-
由 Rich Felker 提交于
infinities were getting converted into nans. the new code simply tests for infinity and replaces it with a large magnitude value of the same sign. also, the fcomi instruction is apparently not part of the i387 instruction set, so avoid using it.
-
由 Rich Felker 提交于
-
由 Rich Felker 提交于
-
由 Rich Felker 提交于
-
由 Rich Felker 提交于
these are functions that have direct fpu approaches to implementation without problematic exception or rounding issues. x86_64 lacks float/double versions because i'm unfamiliar with the necessary sse code for performing these operations.
-
- 16 3月, 2012 2 次提交
-
-
由 Rich Felker 提交于
a double precision nan, when converted to extended (80-bit) precision, will never end in 0x400, since the corresponding bits do not exist in the original double precision value. thus there's no need to waste time and code size on this check.
-
由 Rich Felker 提交于
-
- 15 3月, 2012 2 次提交
-
-
由 Rich Felker 提交于
-
由 Rich Felker 提交于
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.
-
- 14 3月, 2012 1 次提交
-
-
由 Rich Felker 提交于
-
- 13 3月, 2012 1 次提交
-
-
由 Rich Felker 提交于
thanks to the hard work of Szabolcs Nagy (nsz), identifying the best (from correctness and license standpoint) implementations from freebsd and openbsd and cleaning them up! musl should now fully support c99 float and long double math functions, and has near-complete complex math support. tgmath should also work (fully on gcc-compatible compilers, and mostly on any c99 compiler). based largely on commit 0376d44a890fea261506f1fc63833e7a686dca19 from nsz's libm git repo, with some additions (dummy versions of a few missing long double complex functions, etc.) by me. various cleanups still need to be made, including re-adding (if they're correct) some asm functions that were dropped.
-
- 27 6月, 2011 1 次提交
-
-
由 Rich Felker 提交于
-
- 12 2月, 2011 1 次提交
-
-
由 Rich Felker 提交于
-