Implement exp10f function correctly rounded to all rounding modes.
Algorithm: perform range reduction to reduce
```
10^x = 2^(hi + mid) * 10^lo
```
where:
```
hi is an integer,
0 <= mid * 2^5 < 2^5
-log10(2) / 2^6 <= lo <= log10(2) / 2^6
```
Then `2^mid` is stored in a table of 32 entries and the product `2^hi * 2^mid` is
performed by adding `hi` into the exponent field of `2^mid`.
`10^lo` is then approximated by a degree-5 minimax polynomials generated by Sollya with:
```
> P = fpminimax((10^x - 1)/x, 4, [|D...|], [-log10(2)/64. log10(2)/64]);
```
Performance benchmark using perf tool from the CORE-MATH project on Ryzen 1700:
```
$ CORE_MATH_PERF_MODE="rdtsc" ./perf.sh exp10f
GNU libc version: 2.35
GNU libc release: stable
CORE-MATH reciprocal throughput : 10.215
System LIBC reciprocal throughput : 7.944
LIBC reciprocal throughput : 38.538
LIBC reciprocal throughput : 12.175 (with `-msse4.2` flag)
LIBC reciprocal throughput : 9.862 (with `-mfma` flag)
$ CORE_MATH_PERF_MODE="rdtsc" ./perf.sh exp10f --latency
GNU libc version: 2.35
GNU libc release: stable
CORE-MATH latency : 40.744
System LIBC latency : 37.546
BEFORE
LIBC latency : 48.989
LIBC latency : 44.486 (with `-msse4.2` flag)
LIBC latency : 40.221 (with `-mfma` flag)
```
This patch relies on https://reviews.llvm.org/D134002
Reviewed By: orex, zimmermann6
Differential Revision: https://reviews.llvm.org/D134104
Implement acosf function correctly rounded for all rounding modes.
We perform range reduction as follows:
- When `|x| < 2^(-10)`, we use cubic Taylor polynomial:
```
acos(x) = pi/2 - asin(x) ~ pi/2 - x - x^3 / 6.
```
- When `2^(-10) <= |x| <= 0.5`, we use the same approximation that is used for `asinf(x)` when `|x| <= 0.5`:
```
acos(x) = pi/2 - asin(x) ~ pi/2 - x - x^3 * P(x^2).
```
- When `0.5 < x <= 1`, we use the double angle formula: `cos(2y) = 1 - 2 * sin^2 (y)` to reduce to:
```
acos(x) = 2 * asin( sqrt( (1 - x)/2 ) )
```
- When `-1 <= x < -0.5`, we reduce to the positive case above using the formula:
```
acos(x) = pi - acos(-x)
```
Performance benchmark using perf tool from the CORE-MATH project on Ryzen 1700:
```
$ CORE_MATH_PERF_MODE="rdtsc" ./perf.sh acosf
GNU libc version: 2.35
GNU libc release: stable
CORE-MATH reciprocal throughput : 28.613
System LIBC reciprocal throughput : 29.204
LIBC reciprocal throughput : 24.271
$ CORE_MATH_PERF_MODE="rdtsc" ./perf.sh asinf --latency
GNU libc version: 2.35
GNU libc release: stable
CORE-MATH latency : 55.554
System LIBC latency : 76.879
LIBC latency : 62.118
```
Reviewed By: orex, zimmermann6
Differential Revision: https://reviews.llvm.org/D133550
The libc.src.__support.FPUtil.fputil target encompassed many unrelated
files, and provided a lot of hidden dependencies. This patch splits out
all of these files into component parts and cleans up the cmake files
that used them. It does not touch any source files for simplicity, but
there may be changes made to them in future patches.
Reviewed By: lntue
Differential Revision: https://reviews.llvm.org/D132980
Performance by core-math (core-math/glibc 2.31/current llvm-14):
10.845/43.174/13.467
The review is done on top of D132809.
Differential Revision: https://reviews.llvm.org/D132811
The FormatSection and the writer functions both previously took a char*
and a length to represent a string. Now they use the StringView class to
represent that more succinctly. This change also required fixing
everywhere these were used, so it touches a lot of files.
Reviewed By: sivachandra
Differential Revision: https://reviews.llvm.org/D131994
To use the FILE data structure, LLVM-libc must be in fullbuild mode
since it expects its own implementation. This means that (f)printf can't
be used without fullbuild, but s(n)printf only uses strings. This patch
adjusts the CMake to allow for this.
Reviewed By: sivachandra, lntue
Differential Revision: https://reviews.llvm.org/D131913
Previously, the integer_to_string tests used EXPECT_TRUE(.equals)
which doesn't have useful error messages. Now they properly check
equality with the EXPECT_EQ macro, which allows for comparing the
strings more naturally.
Reviewed By: sivachandra
Differential Revision: https://reviews.llvm.org/D131300
Migrating all private STL code to the standard STL case but keeping it under the CPP namespace to avoid confusion. Starting with the type_traits header.
Differential Revision: https://reviews.llvm.org/D130727
The specified rounding mode will be used and restored
to what it was before the test ran.
Additionally, it moves ForceRoundingMode and RoundingMode
out of MPFRUtils to be used in more places.
Differential Revision: https://reviews.llvm.org/D129685
This is a implementation of find remainder fmod function from standard libm.
The underline algorithm is developed by myself, but probably it was first
invented before.
Some features of the implementation:
1. The code is written on more-or-less modern C++.
2. One general implementation for both float and double precision numbers.
3. Spitted platform/architecture dependent and independent code and tests.
4. Tests covers 100% of the code for both float and double numbers. Tests cases with NaN/Inf etc is copied from glibc.
5. The new implementation in general 2-4 times faster for “regular” x,y values. It can be 20 times faster for x/y huge value, but can also be 2 times slower for double denormalized range (according to perf tests provided).
6. Two different implementation of division loop are provided. In some platforms division can be very time consuming operation. Depend on platform it can be 3-10 times slower than multiplication.
Performance tests:
The test is based on core-math project (https://gitlab.inria.fr/core-math/core-math). By Tue Ly suggestion I took hypot function and use it as template for fmod. Preserving all test cases.
`./check.sh <--special|--worst> fmodf` passed.
`CORE_MATH_PERF_MODE=rdtsc ./perf.sh fmodf` results are
```
GNU libc version: 2.35
GNU libc release: stable
21.166 <-- FPU
51.031 <-- current glibc
37.659 <-- this fmod version.
```
This is mostly a mechanical change. In a future pass, all tests from
pthread which create threads will also be converted to integration tests.
Some of thread related features are tightly coupled with the loader. So,
they can only be tested with the in-house loader. Hence, going forward, all
tests which create threads will have to be integration tests.
Reviewed By: lntue
Differential Revision: https://reviews.llvm.org/D128381
They are added as entrypoint object targets. The header-gen
infrastructure has been extended to enable handling standard required
global objects. The libc-api-test has also been extended to verify the
global object declarations.
Reviewed By: lntue
Differential Revision: https://reviews.llvm.org/D126329
Some platforms don't support proper 128 bit integers, but some
algorithms use them, such as any that use long doubles. This patch
modifies the existing UInt class to support the necessary operators.
This does not put this new class into use, that will be in followup
patches.
Reviewed By: sivachandra, lntue
Differential Revision: https://reviews.llvm.org/D124959
The PrintfMatcher depends on printf which is in stdio. Stdio is
currently fullbuild only, but the matcher wasn't, causing failing builds
when fullbuild was off. This patch adds the fullbuild condition to the
PrintfMatcher cmake.
Differential Revision: https://reviews.llvm.org/D124304
This patch changes the printf parser tests to use a more robust matcher.
This allows for better debugging of parsing issues. This does not affect
the actual printf code at all, only the tests.
Reviewed By: sivachandra, lntue
Differential Revision: https://reviews.llvm.org/D124130
All existing loader tests are switched to an integration test added with
the new rule. Also, the getenv test is now enabled as an integration test.
All loader tests have been moved to test/integration. Also, the simple
checker library for the previous loader tests has been moved to a
separate directory of its own.
A follow up change will perform more cleanup of the loader CMake rules
to eliminate now redundent options.
Reviewed By: lntue, michaelrj
Differential Revision: https://reviews.llvm.org/D122266
Previously, the entire support/CPP folder was in one header library,
which meant that a lot of headers were included where they shouldn't be.
This patch splits each header into its own target, as well as adjusting
each place they were included to only include what is used.
Reviewed By: sivachandra, lntue
Differential Revision: https://reviews.llvm.org/D121237
Dominic Chen