aboutsummaryrefslogtreecommitdiffhomepage
path: root/Eigen/src/Core
Commit message (Collapse)AuthorAge
* Fix non-trivial Half constructor for CUDA.Gravatar Antonio Sanchez2021-03-08
| | | | | | | | Both CUDA and HIP require trivial default constructors for types used in shared memory. Otherwise failing with ``` error: initialization is not supported for __shared__ variables. ```
* Revert stack allocation limit change that crept in.Gravatar Antonio Sanchez2021-03-05
| | | | This was accidentally introduced when copying changes between repos.
* Changing the Eigen::half implementation for HIPGravatar Deven Desai2021-03-05
| | | | | | | | | | | | | | | | Currently, when compiling with HIP, Eigen::half is derived from the `__half_raw` struct that is defined within the hip_fp16.h header file. This is true for both the "host" compile phase and the "device" compile phase. This was causing a very hard to detect bug in the ROCm TensorFlow build. In the ROCm Tensorflow build, * files that do not contain ant GPU code get compiled via gcc, and * files that contnain GPU code get compiled via hipcc. In certain case, we have a function that is defined in a file that is compiled by hipcc, and is called in a file that is compiled by gcc. If such a function had Eigen::half has a "pass-by-value" argument, its value was getting corrupted, when received by the function. The reason for this seems to be that for the gcc compile, Eigen::half is derived from a `__half_raw` struct that has `uint16_t` as the data-store, and for hipcc the `__half_raw` implementation uses `_Float16` as the data store. There is some ABI incompatibility between gcc / hipcc (which is essentially latest clang), which results in the Eigen::half value (which is correct at the call-site) getting randomly corrupted when passed to the function. Changing the Eigen::half argument to be "pass by reference" seems to workaround the error. In order to fix it such that we do not run into it again in TF, this commit changes the Eigne::half implementation to use the same `__half_raw` implementation as the non-GPU compile, during host compile phase of the hipcc compile.
* Define EIGEN_CPLUSPLUS and replace most __cplusplus checks.Gravatar Antonio Sanchez2021-03-05
| | | | | | | | | | | | | | | The macro `__cplusplus` is not defined correctly in MSVC unless building with the the `/Zc:__cplusplus` flag. Instead, it defines `_MSVC_LANG` to the specified c++ standard version number. Here we introduce `EIGEN_CPLUSPLUS` which will contain the c++ version number both for MSVC and otherwise. This simplifies checks for supported features. Also replaced most instances of standard version checking via `__cplusplus` with the existing `EIGEN_COMP_CXXVER` macro for better clarity. Fixes: #2170
* Fix rint SSE/NEON again, using optimization barrier.Gravatar Antonio Sanchez2021-03-05
| | | | | | | | | | | | | | | | | | | | This is a new version of !423, which failed for MSVC. Defined `EIGEN_OPTIMIZATION_BARRIER(X)` that uses inline assembly to prevent operations involving `X` from crossing that barrier. Should work on most `GNUC` compatible compilers (MSVC doesn't seem to need this). This is a modified version adapted from what was used in `psincos_float` and tested on more platforms (see #1674, https://godbolt.org/z/73ezTG). Modified `rint` to use the barrier to prevent the add/subtract rounding trick from being optimized away. Also fixed an edge case for large inputs that get bumped up a power of two and ends up rounding away more than just the fractional part. If we are over `2^digits` then just return the input. This edge case was missed in the test since the test was comparing approximate equality, which was still satisfied. Adding a strict equality option catches it.
* Revert "Adds EIGEN_CONSTEXPR and EIGEN_NOEXCEPT to rows(), cols(), ↵Gravatar David Tellenbach2021-03-05
| | | | | | | innerStride(), outerStride(), and size()" This reverts commit 6cbb3038ac48cb5fe17eba4dfbf26e3e798041f1 because it breaks clang-10 builds on x86 and aarch64 when C++11 is enabled.
* Adds EIGEN_CONSTEXPR and EIGEN_NOEXCEPT to rows(), cols(), innerStride(), ↵Gravatar Steve Bronder2021-03-04
| | | | outerStride(), and size()
* Revert "Fix rint for SSE/NEON."Gravatar Antonio Sánchez2021-03-03
| | | This reverts commit e72dfeb8b9fa5662831b5d0bb9d132521f9173dd
* Fix rint for SSE/NEON.Gravatar Antonio Sanchez2021-03-03
| | | | | | | | | | | | | | It seems *sometimes* with aggressive optimizations the combination `psub(padd(a, b), b)` trick to force rounding is compiled away. Here we replace with inline assembly to prevent this (I tried `volatile`, but that leads to additional loads from memory). Also fixed an edge case for large inputs `a` where adding `b` bumps the value up a power of two and ends up rounding away more than just the fractional part. If we are over `2^digits` then just return the input. This edge case was missed in the test since the test was comparing approximate equality, which was still satisfied. Adding a strict equality option catches it.
* Add print for SSE/NEON, use NEON rounding intrinsics if available.Gravatar Antonio Sanchez2021-02-27
| | | | | | | | | | In SSE, by adding/subtracting 2^MantissaBits, we force rounding according to the current rounding mode. For NEON, we use the provided intrinsics for rint/floor/ceil if available (armv8). Related to #1969.
* 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.
* Remove unused includeGravatar Christoph Hertzberg2021-02-27
|
* clang 10 aggressively warns about precision loss when converting int to ↵Gravatar Christoph Hertzberg2021-02-27
| | | | | | float (or long to double) (cherry picked from commit cd541ad52c8152340469cae210312c0e27829c8d)
* Fixed/masked more implicit copy constructor warningsGravatar Christoph Hertzberg2021-02-27
| | | | (cherry picked from commit 2883e91ce5a99c391fbf28e20160176b70854992)
* Fix double-promotion warningsGravatar Christoph Hertzberg2021-02-27
| | | | (cherry picked from commit c22c103e932e511e96645186831363585a44b7a3)
* Fix NEON sqrt for 32-bit, add prsqrt.Gravatar Antonio Sanchez2021-02-26
| | | | | | | | | | | | With !406, we accidentally broke arm 32-bit NEON builds, since `vsqrt_f32` is only available for 64-bit. Here we add back the `rsqrt` implementation for 32-bit, relying on a `prsqrt` implementation with better handling of edge cases. Note that several of the 32-bit NEON packet tests are currently failing - either due to denormal handling (NEON versions flush to zero, but scalar paths don't) or due to accuracy (e.g. sin/cos).
* Merge branch 'rmlarsen1/eigen-nan_prop'Gravatar Rasmus Munk Larsen2021-02-26
|\
| * Merge branch 'nan_prop' of https://gitlab.com/rmlarsen1/eigen into nan_propGravatar Rasmus Munk Larsen2021-02-26
| |\
| * | Add TODO.Gravatar Rasmus Munk Larsen2021-02-26
| | |
| * | Defer default for minCoeff/maxCoeff to templated variant.Gravatar Rasmus Munk Larsen2021-02-26
| | |
* | | Fix floor/ceil for NEON fp16.Gravatar Antonio Sanchez2021-02-25
| | | | | | | | | | | | Forgot to test this. Fixes bug introduced in !416.
* | | Fix SSE/NEON pfloor/pceil for saturated values.Gravatar Antonio Sanchez2021-02-25
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The original will saturate if the input does not fit into an integer type. Here we fix this, returning the input if it doesn't have enough precision to have a fractional part. Also added `pceil` for NEON. Fixes #1969.
| | * Fix indentation.Gravatar Rasmus Munk Larsen2021-02-25
| | |
| | * Make it possible to specify NaN propagation strategy for maxCoeff/minCoeff ↵Gravatar Rasmus Munk Larsen2021-02-25
| |/ |/| | | | | reductions.
* | Fix clang compile when no MMA flags are set. Simplify MMA compiler detection.Gravatar Chip-Kerchner2021-02-24
| |
| * Fix indentation.Gravatar Rasmus Munk Larsen2021-02-24
| |
| * Make it possible to specify NaN propagation strategy for maxCoeff/minCoeff ↵Gravatar Rasmus Munk Larsen2021-02-25
|/ | | | reductions.
* Remove unused function scalar_cmp_with_cast.Gravatar Rasmus Munk Larsen2021-02-24
|
* Cast anonymous enums to int when used in expressions.Gravatar Rasmus Munk Larsen2021-02-24
|
* Having forward template function declarations in a P10 file causes bad code ↵Gravatar Chip-Kerchner2021-02-24
| | | | in certain situations.
* Add `invoke_result` and eliminate `result_of` warnings for C++17+.Gravatar Antonio Sanchez2021-02-24
| | | | | | | | | | | | | | | | | The `std::result_of` meta struct is deprecated in C++17 and removed in C++20. It was still slipping through due to a faulty definition of `EIGEN_HAS_STD_RESULT_OF`. Added a new macro `EIGEN_HAS_STD_INVOKE_RESULT` and `Eigen::internal::invoke_result` implementation with fallback for pre C++17. Replaces the `result_of` definition with one based on `std::invoke_result` for C++17 and higher. For completeness, added nullary op support for c++03. Fixes #1850.
* Fixes to support old and new versions of the compilers for built-ins. Cast ↵Gravatar Chip-Kerchner2021-02-24
| | | | to non-const when using vector_pair with certain built-ins.
* Fix CUDA device new and delete, and add test.Gravatar Antonio Sanchez2021-02-24
| | | | HIP does not support new/delete on device, so test is skipped.
* Disable fast psqrt for NEON.Gravatar Antonio Sanchez2021-02-23
| | | | | | | Accuracy is too poor - requires at least two Newton iterations, but then it is no longer significantly faster than `vsqrt`. Fixes #2094.
* Fix check if GPU compile phase for std::hashGravatar Antonio Sanchez2021-02-23
|
* 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.
* Accurate pow, part 2. This change adds specializations of log2 and exp2 for ↵Gravatar Rasmus Munk Larsen2021-02-23
| | | | | | | double that make pow<double> accurate the 1 ULP. Speed for AVX-512 is within 0.5% of the currect implementation.
* Fix compilation errors with later versions of GCC and use of MMA.Gravatar Chip-Kerchner2021-02-22
|
* Fixes Bug #1925. Packets should be passed by const reference, even to inline ↵Gravatar Christoph Hertzberg2021-02-20
| | | | functions.
* Revert "add EIGEN_DEVICE_FUNC to EIGEN_MAKE_ALIGNED_OPERATOR_NEW_IF macros ↵Gravatar Antonio Sánchez2021-02-19
| | | | | (only if not HIPCC)." This reverts commit 12fd3dd655e37ba26e7ab236d32163e0aa35da39
* Use the Cephes double subtraction trick in pexp<float> even when FMA is ↵Gravatar Rasmus Munk Larsen2021-02-18
| | | | available. Otherwise the accuracy drops from 1 ulp to 3 ulp.
* add EIGEN_DEVICE_FUNC to EIGEN_MAKE_ALIGNED_OPERATOR_NEW_IF macros (only if ↵Gravatar Masaki Murooka2021-02-17
| | | | not HIPCC).
* Bump to 3.4.99Gravatar David Tellenbach2021-02-17
|
* Define internal::make_unsigned for [unsigned]long long on macOS.Gravatar David Tellenbach2021-02-17
| | | | | | | | | | macOS defines int64_t as long long even for C++03 and therefore expects a template specialization internal::make_unsigned<long long>, for C++03. Since other platforms define int64_t as long for C++03 we cannot add the specialization for all cases.
* Fix uninitialized warning on AVX.Gravatar Antonio Sanchez2021-02-17
|
* Fixed performance issues for VSX and P10 MMA in general_matrix_matrix_productGravatar Chip Kerchner2021-02-17
|
* New accurate algorithm for pow(x,y). This version is accurate to 1.4 ulps ↵Gravatar Rasmus Munk Larsen2021-02-17
| | | | for float, while still being 10x faster than std::pow for AVX512. A future change will introduce a specialization for double.
* Updated pfrexp implementation.Gravatar Antonio Sanchez2021-02-17
| | | | | | The original implementation fails for 0, denormals, inf, and NaN. See #2150
* missing method in packetmath.h void ptranspose(PacketBlock<Packet16uc, 4>& ↵Gravatar Ashutosh Sharma2021-02-16
| | | | kernel)
* Use vrsqrts for rsqrt Newton iterations.Gravatar Antonio Sanchez2021-02-11
| | | | | It's slightly faster and slightly more accurate, allowing our current packetmath tests to pass for sqrt with a single iteration.
generated by cgit v1.2.3 (git 2.39.1) at 2024-07-05 00:00:26 +0000