Rasmus Munk Larsen
5226566a14
Speed up pldexp_generic.
2024-04-12 01:32:17 +00:00
Antonio Sánchez
38fcedaf8e
Fix pexp complex test edge-cases.
2024-03-04 17:44:38 +00:00
Antonio Sánchez
6b365e74d6
Fix GPU build for ptanh_float.
2024-02-20 16:08:50 +00:00
Damiano Franzò
be06c9ad51
Implement float pexp_complex
2024-02-17 00:26:57 +00:00
Rasmus Munk Larsen
4d419e2209
Rename generic_fast_tanh_float to ptanh_float and move it to...
2024-02-16 21:27:22 +00:00
Damiano Franzò
7fd7a3f946
Implement plog_complex
2024-01-30 19:06:05 +00:00
Antonio Sánchez
a73970a864
Fix arm32 issues.
2024-01-23 22:04:55 +00:00
Tobias Wood
f38e16c193
Apply clang-format
2023-11-29 11:12:48 +00:00
Antonio Sánchez
6e4d5d4832
Add IWYU private pragmas to internal headers.
2023-08-21 16:25:22 +00:00
Charles Schlosser
387175c258
Fix safe_abs in int_pow
2023-06-23 04:12:41 +00:00
Charles Schlosser
b7151ffaab
Fix unary pow error handling and test
2023-06-06 18:46:55 +00:00
Charles Schlosser
1d80e23186
Optimize scalar_unary_pow_op error handling
2023-06-02 18:53:06 +00:00
Charles Schlosser
29c8e3c754
fix pow for uint32_t, disable pmul<Packet4ul>
2023-04-21 05:47:56 +00:00
Rasmus Munk Larsen
0488b708b4
Vectorize tensor.isnan() by using typed predicates.
2023-03-16 04:04:22 +00:00
Rasmus Munk Larsen
6bcd941ee3
Use pmsub in twoprod. This speeds up pow() on Skylake by ~1%.
2023-02-21 20:09:29 +00:00
Rasmus Munk Larsen
ce62177b5b
Vectorize atanh & add a missing definition and unit test for atan.
2023-02-21 03:14:05 +00:00
Charles Schlosser
71a8e60a7a
Tweak pasin_float, fix psqrt_complex
2023-02-15 01:01:14 +00:00
Charles Schlosser
325e3063d9
Optimize psign
2023-02-09 22:15:26 +00:00
Rasmus Munk Larsen
12ad99ce60
Remove unused variables from GenericPacketMathFunctions.h
2023-01-29 18:10:28 +00:00
Charles Schlosser
0471e61b4c
Optimize various mathematical packet ops
2023-01-28 01:34:26 +00:00
Rasmus Munk Larsen
462758e8a3
Don't use generic sign function for sign(complex) unless it is vectorizable
2022-10-12 16:03:29 +00:00
Rasmus Munk Larsen
72db3f0fa5
Remove references to M_PI_2 and M_PI_4.
2022-10-11 00:27:16 +00:00
Rasmus Munk Larsen
e95c4a837f
Simpler range reduction strategy for atan<float>().
2022-10-04 18:11:00 +00:00
Rasmus Munk Larsen
c475228b28
Vectorize atan() for double.
2022-10-01 01:49:30 +00:00
Antonio Sanchez
3e44f960ed
Reduce compiler warnings for tests.
2022-09-06 18:20:56 +00:00
Rasmus Munk Larsen
bd393e15c3
Vectorize acos, asin, and atan for float.
2022-08-29 19:49:33 +00:00
Charles Schlosser
e5af9f87f2
Vectorize pow for integer base / exponent types
2022-08-29 19:23:54 +00:00
Rasmus Munk Larsen
7064ed1345
Specialize psign<Packet8i> for AVX2, don't vectorize psign<bool>.
2022-08-26 17:02:37 +00:00
Rasmus Munk Larsen
98e51c9e24
Avoid undefined behavior in array_cwise test due to signed integer overflow
2022-08-26 16:19:03 +00:00
Rasmus Munk Larsen
6aad0f821b
Fix psign for unsigned integer types, such as bool.
2022-08-22 20:19:35 +00:00
Rasmus Munk Larsen
7c67dc67ae
Use proper double word division algorithm for pow<double>. Gives 11-15% speedup.
2022-08-17 18:36:23 +00:00
Charles Schlosser
76a669fb45
add fixed power unary operation
2022-08-16 21:32:36 +00:00
Rasmus Munk Larsen
97e0784dc6
Vectorize the sign operator in Eigen.
2022-08-09 19:54:57 +00:00
Rasmus Munk Larsen
7a87ed1b6a
Fix code and unit test for a few corner cases in vectorized pow()
2022-08-08 18:48:36 +00:00
Tobias Schlüter
cb1e8228e9
Convert bit calculation to constexpr, avoid casts.
2022-03-13 22:38:36 +09:00
Rasmus Munk Larsen
0e6f4e43f1
Fix a few confusing comments in psincos_float.
2022-03-04 20:41:49 +00:00
Sean McBride
f1b9692d63
Removed EIGEN_UNUSED decorations from many functions that are in fact used
2022-03-03 20:19:33 +00:00
Antonio Sánchez
6b60bd6754
Fix 32-bit arm int issue.
2022-02-04 21:59:33 +00:00
Rasmus Munk Larsen
7b5a8b6bc5
Improve plog: 20% speedup for float + handle denormals
2022-01-05 23:40:31 +00:00
Rasmus Munk Larsen
8eab7b6886
Improve exp<float>(): Don't flush denormal results +4% speedup.
...
1. Speed up exp(x) by reducing the polynomial approximant from degree 7 to
degree 6. With exactly representable coefficients computed by the Sollya tool,
this still gives a maximum relative error of 1 ulp, i.e. faithfully rounded, for
arguments where exp(x) is a normalized float. This change results in a speedup
of about 4% for AVX2.
2. Extend the range where exp(x) returns a non-zero result to from ~[-88;88] to
~[-104;88] i.e. return denormalized values for large negative arguments instead
of zero. Compared to exp<double>(x) the denormalized results gradually decrease
in accuracy down to 0.033 relative error for arguments around x = -104 where
exp(x) is ~std::numeric<float>::denorm_min(). This is expected and acceptable.
2021-12-28 15:00:19 +00:00
Erik Schultheis
dee6428a71
fixed clang warnings about alignment change and floating point precision
2021-12-18 17:18:16 +00:00
Rasmus Munk Larsen
f04fd8b168
Make sure exp(-Inf) is zero for vectorized expressions. This fixes #2385 .
2021-12-08 17:57:23 +00:00
Erik Schultheis
ec2fd0f7ed
Require recent GCC and MSCV and removed EIGEN_HAS_CXX14 and some other feature test macros
2021-12-01 00:48:34 +00:00
Kolja Brix
afa616bc9e
Fix some typos found
2021-09-23 15:22:00 +00:00
Rasmus Munk Larsen
d7d0bf832d
Issue an error in case of direct inclusion of internal headers.
2021-09-10 19:12:26 +00:00
Rasmus Munk Larsen
bbfc4d54cd
Use padd instead of +.
2021-07-02 02:51:48 +00:00
Rasmus Munk Larsen
9312a5bf5c
Implement a generic vectorized version of Smith's algorithms for complex division.
2021-07-01 23:31:12 +00:00
Rasmus Munk Larsen
5aebbe9098
Get rid of redundant pabs instruction in complex square root.
2021-06-29 23:26:15 +00:00
Antonio Sanchez
12e8d57108
Remove pset, replace with ploadu.
...
We can't make guarantees on alignment for existing calls to `pset`,
so we should default to loading unaligned. But in that case, we should
just use `ploadu` directly. For loading constants, this load should hopefully
get optimized away.
This is causing segfaults in Google Maps.
2021-06-16 18:41:17 -07:00
Rasmus Munk Larsen
fc87e2cbaa
Use bit_cast to create -0.0 for floating point types to avoid compiler optimization changing sign with --ffast-math enabled.
2021-06-11 02:35:53 +00:00
