Current implementations of single precision and double precision
floating point operations operate on bits of the integer type of
same size. The code made use of magic masks which were listed as
literal integer values. This is not possible in the case of long
double type as the mantissa of quad-precision long double type used
on non-x86 architectures is wider that the widest integer type for
which we can list literal values. So, in this patch, to avoid
using magic masks specified with literal values, we use packed
bit-field struct types and let the compiler generate the masks.
This new scheme allows us to implement long double flavors of the
various floating point operations. To keep the size of the patch
small, only the implementations of fabs and trunc have been
switched to the new scheme. In following patches, all exisiting
implementations will be switched to the new scheme.
Reviewers: asteinhauser
Differential Revision: https://reviews.llvm.org/D82036
A new utils library named 'fputil' is added. This library is used in
math tests and the MPFR wrapper. The math implementations will be
modified to use this library in a later round.
Reviewers: phosek
Differential Revision: https://reviews.llvm.org/D79724
Summary:
Math results are compared with MPFR results by checking if they are
within a tolerance level of the MPFR result. The tolerance level is set
using additional bits of precision of the fractional part of a floating
point value. Hence, the actual value of the tolerance depends on not
only the additional bits, but also on the exponent part of the floating
point number.
Previously, the exponent part was not considered in evaluating the
tolerance value. While it was OK for small values less than 1 (hence
sinf, cosf, sincosf tests were OK), it breaks for large values which
functions like exp and friends produce. This change uses the exponent
value also to evaluate the tolerance value. LLVM libc produced results
can now be compared with MPFR produced results for large values also.
Reviewers: abrachet
Differential Revision: https://reviews.llvm.org/D79278
This dramtically reduces the run time of tests. For example,
sincosf_test takes over 25 minutes without this attribute but only 8
seconds with this attribute.
A new test matcher class MPFRMatcher is added along with helper macros
EXPECT|ASSERT_MPFR_MATCH.
New type traits classes RemoveCV and IsFloatingPointType have been
added and used to implement the above class and its helpers.
Reviewers: abrachet, phosek
Differential Revision: https://reviews.llvm.org/D79256
This will fix building the wrapper shared library when
BUILD_SHARED_LIBS is ON.
Reviewers: PaulkaToast
Differential Revision: https://reviews.llvm.org/D78737
NFC intended in the implementaton. Only mechanical changes to fit the LLVM
libc implementation standard have been done.
Math testing infrastructure has been added. This infrastructure compares the
results produced by the libc with the high precision results from MPFR.
Tests making use of this infrastructure have been added for cosf, sinf and
sincosf.
Reviewers: abrachet, phosek
Differential Revision: https://reviews.llvm.org/D76825
Siva Chandra Reddy