Rasmus Munk Larsen
0488b708b4
Vectorize tensor.isnan() by using typed predicates.
2023-03-16 04:04:22 +00:00
Rasmus Munk Larsen
d6235d76db
Clean up generic packetmath specializations for various backends with the help of a macro.
2023-03-10 22:02:23 +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
Ryan Senanayake
fe7f527787
Fix guard macros for emulated FP16 operators on GPU
2023-01-06 22:02:51 +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
Antonio Sánchez
80efbfdeda
Unconditionally enable CXX11 math.
2022-10-04 17:37:47 +00:00
Rasmus Munk Larsen
c475228b28
Vectorize atan() for double.
2022-10-01 01:49:30 +00:00
Rasmus Munk Larsen
1e1848fdb1
Add a vectorized implementation of atan2 to Eigen.
2022-09-28 20:46:49 +00:00
Rasmus Munk Larsen
273e0c884e
Revert "Add constexpr, test for C++14 constexpr."
2022-09-16 21:14:29 +00:00
Tobias Schlüter
133498c329
Add constexpr, test for C++14 constexpr.
2022-09-07 03:42:34 +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
Lexi Bromfield
66ea0c09fd
Don't double-define Half functions on aarch64
2022-08-09 20:00:34 +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
Alexander Richardson
b7668c0371
Avoid including <sstream> with EIGEN_NO_IO
2022-07-29 18:02:51 +00:00
Tobias Schlüter
f3ba220c5d
Remove EIGEN_EMPTY_STRUCT_CTOR
2022-04-08 18:27:26 +00:00
Antonio Sánchez
73b2c13bf2
Disable f16c scalar conversions for MSVC.
2022-03-30 18:35:32 +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
Rasmus Munk Larsen
92d0026b7b
Provide a definition for numeric_limits static data members
2022-02-08 20:34:53 +00:00
Antonio Sánchez
6b60bd6754
Fix 32-bit arm int issue.
2022-02-04 21:59:33 +00:00
Rasmus Munk Larsen
96dc37a03b
Some fixes/cleanups for numeric_limits & fix for related bug in psqrt
2022-01-07 01:10:17 +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
Rasmus Munk Larsen
5137a5157a
Make numeric_limits members constexpr as per the newer C++ standards.
...
Author: majnemer@google.com
2021-11-19 15:58:36 +00:00
Antonio Sanchez
e559701981
Fix compile issue for gcc 4.8
2021-10-28 08:23:19 -07:00
Rohit Santhanam
48e40b22bf
Preliminary HIP bfloat16 GPU support.
2021-10-27 18:36:45 +00:00
Kolja Brix
afa616bc9e
Fix some typos found
2021-09-23 15:22:00 +00:00
sciencewhiz
4b6036e276
fix various typos
2021-09-22 16:15:06 +00:00
Alexander Grund
b5eaa42695
Fix alias violation in BFloat16
...
reinterpret_cast between unrelated types is undefined behavior and leads
to misoptimizations on some platforms.
Use the safer (and faster) version via bit_cast
2021-09-20 10:37:50 +02:00
Rasmus Munk Larsen
d7d0bf832d
Issue an error in case of direct inclusion of internal headers.
2021-09-10 19:12:26 +00:00
Gauri Deshpande
e6a5a594a7
remove denormal flushing in fp32tobf16 for avx & avx512
2021-08-09 22:15:21 +00:00
