aboutsummaryrefslogtreecommitdiffhomepage
path: root/Eigen/src/Core/arch/Default/BFloat16.h
Commit message (Collapse)AuthorAge
* Eliminate `round_impl` double-promotion warnings for c++03.Gravatar Antonio Sanchez2021-03-25
|
* Make half/bfloat16 constructor take inputs by value, fix powerpc test.Gravatar Antonio Sanchez2021-02-27
| | | | | | | | | | | | Since `numeric_limits<half>::max_exponent` is a static inline constant, it cannot be directly passed by reference. This triggers a linker error in recent versions of `g++-powerpc64le`. Changing `half` to take inputs by value fixes this. Wrapping `max_exponent` with `int(...)` to make an addressable integer also fixes this and may help with other custom `Scalar` types down-the-road. Also eliminated some compile warnings for powerpc.
* Fix some CUDA warnings.Gravatar Antonio Sanchez2021-02-24
| | | | | | | | | | | | | | | | | Added `EIGEN_HAS_STD_HASH` macro, checking for C++11 support and not running on GPU. `std::hash<float>` is not a device function, so cannot be used by `std::hash<bfloat16>`. Removed `EIGEN_DEVICE_FUNC` and only define if `EIGEN_HAS_STD_HASH`. Same for `half`. Added `EIGEN_CUDA_HAS_FP16_ARITHMETIC` to improve readability, eliminate warnings about `EIGEN_CUDA_ARCH` not being defined. Replaced a couple C-style casts with `reinterpret_cast` for aligned loading of `half*` to `half2*`. This eliminates `-Wcast-align` warnings in clang. Although not ideal due to potential type aliasing, this is how CUDA handles these conversions internally.
* Replace M_LOG2E and M_LN2 with custom macros.Gravatar Antonio Sanchez2020-12-11
| | | | | | | | | | For these to exist we would need to define `_USE_MATH_DEFINES` before `cmath` or `math.h` is first included. However, we don't control the include order for projects outside Eigen, so even defining the macro in `Eigen/Core` does not fix the issue for projects that end up including `<cmath>` before Eigen does (explicitly or transitively). To fix this, we define `EIGEN_LOG2E` and `EIGEN_LN2` ourselves.
* Add log2() to Eigen.Gravatar Rasmus Munk Larsen2020-12-04
|
* Revert "Add log2() operator to Eigen"Gravatar Rasmus Munk Larsen2020-12-03
| | | | This reverts commit 4d91519a9be061da5d300079fca17dd0b9328050.
* Add log2() operator to EigenGravatar Rasmus Munk Larsen2020-12-03
|
* Remove explicit casts from Eigen::half and Eigen::bfloat16 to boolGravatar David Tellenbach2020-11-19
| | | | | | | | | Both, Eigen::half and Eigen::Bfloat16 are implicitly convertible to float and can hence be converted to bool via the conversion chain Eigen::{half,bfloat16} -> float -> bool We thus remove the explicit cast operator to bool.
* Add bit_cast for half/bfloat to/from uint16_t, fix TensorRandomGravatar Antonio Sanchez2020-11-18
| | | | | | | | | | The existing `TensorRandom.h` implementation makes the assumption that `half` (`bfloat16`) has a `uint16_t` member `x` (`value`), which is not always true. This currently fails on arm64, where `x` has type `__fp16`. Added `bit_cast` specializations to allow casting to/from `uint16_t` for both `half` and `bfloat16`. Also added tests in `half_float`, `bfloat16_float`, and `cxx11_tensor_random` to catch these errors in the future.
* Replace numext::as_uint with numext::bit_cast<numext::uint32_t>Gravatar David Tellenbach2020-10-29
|
* Revert change from 4e4d3f32d168ed9ce09d950f099a60ddcd11240f that broke ↵Gravatar Rasmus Munk Larsen2020-10-15
| | | | BFloat16.h build with older compilers.
* Clean up packetmath tests and fix various bugs to make bfloat16 pass ↵Gravatar Rasmus Munk Larsen2020-10-09
| | | | (almost) all packetmath tests with SSE, AVX, and AVX512.
* Use EIGEN_USING_STD to fix CUDA compilation error on BFloat16.h.Gravatar Rasmus Munk Larsen2020-10-02
|
* Get rid of initialization logic for blueNorm by making the computed ↵Gravatar Rasmus Munk Larsen2020-09-18
| | | | | | constants static const or constexpr. Move macro definition EIGEN_CONSTEXPR to Core and make all methods in NumTraits constexpr when EIGEN_HASH_CONSTEXPR is 1.
* Make bfloat16(float(-nan)) produce -nan, not nan.Gravatar Tim Shen2020-09-15
|
* Fix clang-tidy warnings in generic bfloat16 implementationGravatar David Tellenbach2020-07-27
| | | | See !172 for related discussions.
* Fix bfloat16 castsGravatar David Tellenbach2020-07-23
| | | | | | | If we have explicit conversion operators available (C++11) we define explicit casts from bfloat16 to other types. If not (C++03), we don't define conversion operators but rely on implicit conversion chains from bfloat16 over float to other types.
* Revert change that made conversion from bfloat16 to {float, double} implicit.Gravatar Rasmus Munk Larsen2020-07-22
| | | | Add roundtrip tests for casting between bfloat16 and complex types.
* Fix cast of blfoat16 to std::complex<T>Gravatar David Tellenbach2020-07-22
| | | | This fixes https://gitlab.com/libeigen/eigen/-/issues/1951
* Make sure we take the little-endian path if __BYTE_ORDER__ is not defined.Gravatar Rasmus Munk Larsen2020-07-22
|
* Faster conversion from integer types to bfloat16Gravatar Niels Dekker2020-07-22
| | | | | | Specialized `bfloat16_impl::float_to_bfloat16_rtne(float)` for normal floating point numbers, infinity and zero, in order to improve the performance of `bfloat16::bfloat16(const T&)` for integer argument types. A reduction of more than 20% of the runtime duration of conversion from int to bfloat16 was observed, using Visual C++ 2019 on Windows 10.
* Avoid undefined behavior by union type punning in float_to_bfloat16_rtneGravatar Niels Dekker2020-07-14
| | | | | | | | Use `numext::as_uint`, instead of union based type punning, to avoid undefined behavior. See also C++ Core Guidelines: "Don't use a union for type punning" https://github.com/isocpp/CppCoreGuidelines/blob/v0.8/CppCoreGuidelines.md#c183-dont-use-a-union-for-type-punning `numext::as_uint` was suggested by David Tellenbach
* AVX path for BF16Gravatar Sheng Yang2020-07-14
|
* Allow implicit conversion from bfloat16 to float and doubleGravatar Niels Dekker2020-07-11
| | | | | | Conversion from `bfloat16` to `float` and `double` is lossless. It seems natural to allow the conversion to be implicit, as the C++ language also support implicit conversion from a smaller to a larger floating point type. Intel's OneDLL bfloat16 implementation also has an implicit `operator float()`: https://github.com/oneapi-src/oneDNN/blob/v1.5/src/common/bfloat16.hpp
* Fix test basic stuffGravatar David Tellenbach2020-07-09
| | | | | | - Guard fundamental types that are not available pre C++11 - Separate subsequent angle brackets >> by spaces - Allow casting of Eigen::half and Eigen::bfloat16 to complex types
* Fix tensor casts for large packets and casts to/from std::complexGravatar Antonio Sanchez2020-06-30
| | | | | | | | | | | | | The original tensor casts were only defined for `SrcCoeffRatio`:`TgtCoeffRatio` 1:1, 1:2, 2:1, 4:1. Here we add the missing 1:N and 8:1. We also add casting `Eigen::half` to/from `std::complex<T>`, which was missing to make it consistent with `Eigen:bfloat16`, and generalize the overload to work for any complex type. Tests were added to `basicstuff`, `packetmath`, and `cxx11_tensor_casts` to test all cast configurations.
* Support BFloat16 in EigenGravatar Teng Lu2020-06-20
generated by cgit v1.2.3 (git 2.39.1) at 2024-06-04 11:55:58 +0000