aboutsummaryrefslogtreecommitdiffhomepage
Commit message (Collapse)AuthorAge
* digits10() needs to return an integerGravatar Christoph Hertzberg2019-05-31
| | | | Problem reported on https://stackoverflow.com/questions/56395899
* Merged in deven-amd/eigen-hip-fix-190524 (pull request PR-649)Gravatar Rasmus Larsen2019-05-24
|\ | | | | | | fix for HIP build errors that were introduced by a commit earlier this week
| * fix for HIP build errors that were introduced by a commit earlier this weekGravatar Deven Desai2019-05-24
| |
* | Use pade for matrix exponential also for complex values.Gravatar Michael Tesch2019-05-08
|/
* GEMV: remove double declaration of constant.Gravatar Gustavo Lima Chaves2019-05-23
| | | | | | | | | | | | | That was hurting users with compilers that would object to proceed with that: """ ./Eigen/src/Core/products/GeneralMatrixVector.h:356:10: error: declaration shadows a static data member of 'general_matrix_vector_product<type-parameter-0-0, type-parameter-0-1, type-parameter-0-2, 1, ConjugateLhs, type-parameter-0-4, type-parameter-0-5, ConjugateRhs, Version>' [-Werror,-Wshadow] LhsPacketSize = Traits::LhsPacketSize, ^ ./Eigen/src/Core/products/GeneralMatrixVector.h:307:22: note: previous declaration is here static const Index LhsPacketSize = Traits::LhsPacketSize; """
* Cast Index to RealScalarGravatar Christoph Hertzberg2019-05-23
| | | | | This fixes compilation issues with RealScalar types that are not implicitly castable from Index (e.g. ceres Jet types). Reported by Peter Anderson-Sprecher via eMail
* Enable support for F16C with Clang. The required intrinsics were added here: ↵Gravatar Rasmus Munk Larsen2019-05-20
| | | | | | https://reviews.llvm.org/D16177 and are part of LLVM 3.8.0.
* Merged in rmlarsen/eigen (pull request PR-643)Gravatar Rasmus Larsen2019-05-20
|\ | | | | | | | | | | Make Eigen build with cuda 10 and clang. Approved-by: Justin Lebar <justin.lebar@gmail.com>
| * MergeGravatar Rasmus Munk Larsen2019-05-20
| |\
* | \ Merged in scramsby/eigen (pull request PR-646)Gravatar Gael Guennebaud2019-05-20
|\ \ \ | | | | | | | | | | | | Eigen: Fix MSVC C++17 language standard detection logic
* | | | Prevent potential division by zero in TensorExecutorGravatar Eugene Zhulenev2019-05-17
| | | |
* | | | Merged in ezhulenev/eigen-01 (pull request PR-644)Gravatar Rasmus Larsen2019-05-17
|\ \ \ \ | | | | | | | | | | | | | | | Always evaluate Tensor expressions with broadcasting via tiled evaluation code path
* \ \ \ \ Merged in glchaves/eigen (pull request PR-635)Gravatar Rasmus Larsen2019-05-17
|\ \ \ \ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Speed up GEMV on AVX-512 builds, just as done for GEBP previously. Approved-by: Rasmus Larsen <rmlarsen@google.com>
| | * | | | Always evaluate Tensor expressions with broadcasting via tiled evaluation ↵Gravatar Eugene Zhulenev2019-05-16
| |/ / / / |/| | | | | | | | | | | | | | code path
| | | * | Make Eigen build with cuda 10 and clang.Gravatar Rasmus Munk Larsen2019-05-15
| |_|/ / |/| | |
| | | * Make Eigen build with cuda 10 and clang.Gravatar Rasmus Munk Larsen2019-05-15
| |_|/ |/| |
* | | Merged in rmlarsen/eigen_threadpool (pull request PR-640)Gravatar Rasmus Larsen2019-05-13
|\ \ \ | | | | | | | | | | | | | | | | | | | | Fix deadlocks in thread pool. Approved-by: Eugene Zhulenev <ezhulenev@google.com>
* | | | Collapsed revision from PR-641Gravatar Christoph Hertzberg2019-05-13
| | | | | | | | | | | | | | | | | | | | * SparseLU.h - corrected example, it didn't compile * Changed encoding back to UTF8
* | | | Removing unused API to fix compile error in TensorFlow due toGravatar Anuj Rawat2019-05-12
| | | | | | | | | | | | | | | | AVX512VL, AVX512BW usage
* | | | bug #1707: Fix deprecation warnings, or disable warnings when testing ↵Gravatar Christoph Hertzberg2019-05-10
| | | | | | | | | | | | | | | | deprecated functions
* | | | Fix build with clang on Windows.Gravatar Rasmus Munk Larsen2019-05-09
| | | |
| * | | A) fix deadlocks in thread pool caused by EventCountGravatar Rasmus Munk Larsen2019-05-08
|/ / / | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This fixed 2 deadlocks caused by sloppiness in the EventCount logic. Both most likely were introduced by cl/236729920 which includes the new EventCount algorithm: https://github.com/eigenteam/eigen-git-mirror/commit/01da8caf003990967e42a2b9dc3869f154569538 bug #1 (Prewait): Prewait must not consume existing signals. Consider the following scenario. There are 2 thread pool threads (1 and 2) and 1 external thread (3). RunQueue is empty. Thread 1 checks the queue, calls Prewait, checks RunQueue again and now is going to call CommitWait. Thread 2 checks the queue and now is going to call Prewait. Thread 3 submits 2 tasks, EventCount signals is set to 1 because only 1 waiter is registered the second signal is discarded). Now thread 2 resumes and calls Prewait and takes away the signal. Thread 1 resumes and calls CommitWait, there are no pending signals anymore, so it blocks. As the result we have 2 tasks, but only 1 thread is running. bug #2 (CancelWait): CancelWait must not take away a signal if it's not sure that the signal was meant for this thread. When one thread blocks and another submits a new task concurrently, the EventCount protocol guarantees only the following properties (similar to the Dekker's algorithm): (a) the registered waiter notices presence of the new task and does not block (b) the signaler notices presence of the waiters and wakes it (c) both the waiter notices presence of the new task and signaler notices presence of the waiter [it's only that both of them do not notice each other must not be possible, because it would lead to a deadlock] CancelWait is called for cases (a) and (c). For case (c) it is OK to take the notification signal away, but it's not OK for (a) because nobody queued a signals for us and we take away a signal meant for somebody else. Consider: Thread 1 calls Prewait, checks RunQueue, it's empty, now it's going to call CommitWait. Thread 3 submits 2 tasks, EventCount signals is set to 1 because only 1 waiter is registered the second signal is discarded). Thread 2 calls Prewait, checks RunQueue, discovers the tasks, calls CancelWait and consumes the pending signal (meant for thread 1). Now Thread 1 resumes and calls CommitWait, since there are no signals it blocks. As the result we have 2 tasks, but only 1 thread is running. Both deadlocks are only a problem if the tasks require parallelism. Most computational tasks do not require parallelism, i.e. a single thread will run task 1, finish it and then dequeue and run task 2. This fix undoes some of the sloppiness in the EventCount that was meant to reduce CPU consumption by idle threads, because we now have more threads running in these corner cases. But we still don't have pthread_yield's and maybe the strictness introduced by this change will actually help to reduce tail latency because we will have threads running when we actually need them running. B) fix deadlock in thread pool caused by RunQueue This fixed a deadlock caused by sloppiness in the RunQueue logic. Most likely this was introduced with the non-blocking thread pool. The deadlock only affects workloads that require parallelism. Most computational tasks don't require parallelism. PopBack must not fail spuriously. If it does, it can effectively lead to single thread consuming several wake up signals. Consider 2 worker threads are blocked. External thread submits a task. One of the threads is woken. It tries to steal the task, but fails due to a spurious failure in PopBack (external thread submits another task and holds the lock). The thread executes blocking protocol again (it won't block because NonEmptyQueueIndex is precise and the thread will discover pending work, but it has called PrepareWait). Now external thread submits another task and signals EventCount again. The signal is consumed by the first thread again. But now we have 2 tasks pending but only 1 worker thread running. It may be possible to fix this in a different way: make EventCount::CancelWait forward wakeup signal to a blocked thread rather then consuming it. But this looks more complex and I am not 100% that it will fix the bug. It's also possible to have 2 versions of PopBack: one will do try_to_lock and another won't. Then worker threads could first opportunistically check all queues with try_to_lock, and only use the blocking version before blocking. But let's first fix the bug with the simpler change.
* | | Fix AVX512 & GCC 6.3 compilationGravatar Eugene Zhulenev2019-05-07
| | |
* | | Fix stupid shadow-warnings (with old clang versions)Gravatar Christoph Hertzberg2019-05-07
| | |
* | | Restore C++03 compatibilityGravatar Christoph Hertzberg2019-05-07
| | |
* | | Restore C++03 compatibilityGravatar Christoph Hertzberg2019-05-06
| | |
* | | Fix traits for scalar_logistic_op.Gravatar Rasmus Munk Larsen2019-05-03
| | |
| | * Eigen: Fix MSVC C++17 language standard detection logicGravatar Scott Ramsby2019-05-03
| |/ |/| | | | | | | | | | | To detect C++17 support, use _MSVC_LANG macro instead of _MSC_VER. _MSC_VER can indicate whether the current compiler version could support the C++17 language standard, but not whether that standard is actually selected (i.e. via /std:c++17). See these web pages for more details: https://devblogs.microsoft.com/cppblog/msvc-now-correctly-reports-__cplusplus/ https://docs.microsoft.com/en-us/cpp/preprocessor/predefined-macros
* | Add masked_store_available to unpacket_traitsGravatar Eugene Zhulenev2019-05-02
| |
* | Add masked pstoreu for Packet16hGravatar Eugene Zhulenev2019-05-02
| |
* | Add masked pstoreu to AVX and AVX512 PacketMathGravatar Eugene Zhulenev2019-05-02
| |
* | Fix regression in changeset ae33e866c750c6c24ada5c6f7f3ec15815d0e683Gravatar Gael Guennebaud2019-05-02
| |
* | Merged in ezhulenev/eigen-01 (pull request PR-633)Gravatar Rasmus Larsen2019-04-29
|\ \ | | | | | | | | | Check if gpu_assert was overridden in TensorGpuHipCudaDefines
| | * Speed up GEMV on AVX-512 builds, just as done for GEBP previously.Gravatar Gustavo Lima Chaves2019-04-26
| | | | | | | | | | | | | | | | | | We take advantage of smaller SIMD registers as well, in that case. Gains up to 3x for select input sizes.
* | | Fix compilation with PGI version 19Gravatar Andy May2019-04-25
| |/ |/|
* | Merged in ezhulenev/eigen-01 (pull request PR-632)Gravatar Gael Guennebaud2019-04-25
|\ \ | | | | | | | | | Fix doxygen warnings
| | * Check if gpu_assert was overridden in TensorGpuHipCudaDefinesGravatar Eugene Zhulenev2019-04-25
| |/ |/|
| * Fix doxygen warnings to enable statis code analysisGravatar Eugene Zhulenev2019-04-24
| |
* | Get rid of SequentialLinSpacedReturnType deprecation warnings in DenseBase.hGravatar Eugene Zhulenev2019-04-24
|/
* Remove deprecation annotation from typedef Eigen::Index Index, as it would ↵Gravatar Rasmus Munk Larsen2019-04-24
| | | | generate too many build warnings.
* Add missing EIGEN_DEPRECATED annotations to deprecated functions and fix few ↵Gravatar Eugene Zhulenev2019-04-23
| | | | other doxygen warnings
* Use packet ops instead of AVX2 intrinsicsGravatar Eugene Zhulenev2019-04-23
|
* Adding lowlevel APIs for optimized RHS packet load in TensorFlowGravatar Anuj Rawat2019-04-20
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | SpatialConvolution Low-level APIs are added in order to optimized packet load in gemm_pack_rhs in TensorFlow SpatialConvolution. The optimization is for scenario when a packet is split across 2 adjacent columns. In this case we read it as two 'partial' packets and then merge these into 1. Currently this only works for Packet16f (AVX512) and Packet8f (AVX2). We plan to add this for other packet types (such as Packet8d) also. This optimization shows significant speedup in SpatialConvolution with certain parameters. Some examples are below. Benchmark parameters are specified as: Batch size, Input dim, Depth, Num of filters, Filter dim Speedup numbers are specified for number of threads 1, 2, 4, 8, 16. AVX512: Parameters | Speedup (Num of threads: 1, 2, 4, 8, 16) ----------------------------|------------------------------------------ 128, 24x24, 3, 64, 5x5 |2.18X, 2.13X, 1.73X, 1.64X, 1.66X 128, 24x24, 1, 64, 8x8 |2.00X, 1.98X, 1.93X, 1.91X, 1.91X 32, 24x24, 3, 64, 5x5 |2.26X, 2.14X, 2.17X, 2.22X, 2.33X 128, 24x24, 3, 64, 3x3 |1.51X, 1.45X, 1.45X, 1.67X, 1.57X 32, 14x14, 24, 64, 5x5 |1.21X, 1.19X, 1.16X, 1.70X, 1.17X 128, 128x128, 3, 96, 11x11 |2.17X, 2.18X, 2.19X, 2.20X, 2.18X AVX2: Parameters | Speedup (Num of threads: 1, 2, 4, 8, 16) ----------------------------|------------------------------------------ 128, 24x24, 3, 64, 5x5 | 1.66X, 1.65X, 1.61X, 1.56X, 1.49X 32, 24x24, 3, 64, 5x5 | 1.71X, 1.63X, 1.77X, 1.58X, 1.68X 128, 24x24, 1, 64, 5x5 | 1.44X, 1.40X, 1.38X, 1.37X, 1.33X 128, 24x24, 3, 64, 3x3 | 1.68X, 1.63X, 1.58X, 1.56X, 1.62X 128, 128x128, 3, 96, 11x11 | 1.36X, 1.36X, 1.37X, 1.37X, 1.37X In the higher level benchmark cifar10, we observe a runtime improvement of around 6% for AVX512 on Intel Skylake server (8 cores). On lower level PackRhs micro-benchmarks specified in TensorFlow tensorflow/core/kernels/eigen_spatial_convolutions_test.cc, we observe the following runtime numbers: AVX512: Parameters | Runtime without patch (ns) | Runtime with patch (ns) | Speedup ---------------------------------------------------------------|----------------------------|-------------------------|--------- BM_RHS_NAME(PackRhs, 128, 24, 24, 3, 64, 5, 5, 1, 1, 256, 56) | 41350 | 15073 | 2.74X BM_RHS_NAME(PackRhs, 32, 64, 64, 32, 64, 5, 5, 1, 1, 256, 56) | 7277 | 7341 | 0.99X BM_RHS_NAME(PackRhs, 32, 64, 64, 32, 64, 5, 5, 2, 2, 256, 56) | 8675 | 8681 | 1.00X BM_RHS_NAME(PackRhs, 32, 64, 64, 30, 64, 5, 5, 1, 1, 256, 56) | 24155 | 16079 | 1.50X BM_RHS_NAME(PackRhs, 32, 64, 64, 30, 64, 5, 5, 2, 2, 256, 56) | 25052 | 17152 | 1.46X BM_RHS_NAME(PackRhs, 32, 256, 256, 4, 16, 8, 8, 1, 1, 256, 56) | 18269 | 18345 | 1.00X BM_RHS_NAME(PackRhs, 32, 256, 256, 4, 16, 8, 8, 2, 4, 256, 56) | 19468 | 19872 | 0.98X BM_RHS_NAME(PackRhs, 32, 64, 64, 4, 16, 3, 3, 1, 1, 36, 432) | 156060 | 42432 | 3.68X BM_RHS_NAME(PackRhs, 32, 64, 64, 4, 16, 3, 3, 2, 2, 36, 432) | 132701 | 36944 | 3.59X AVX2: Parameters | Runtime without patch (ns) | Runtime with patch (ns) | Speedup ---------------------------------------------------------------|----------------------------|-------------------------|--------- BM_RHS_NAME(PackRhs, 128, 24, 24, 3, 64, 5, 5, 1, 1, 256, 56) | 26233 | 12393 | 2.12X BM_RHS_NAME(PackRhs, 32, 64, 64, 32, 64, 5, 5, 1, 1, 256, 56) | 6091 | 6062 | 1.00X BM_RHS_NAME(PackRhs, 32, 64, 64, 32, 64, 5, 5, 2, 2, 256, 56) | 7427 | 7408 | 1.00X BM_RHS_NAME(PackRhs, 32, 64, 64, 30, 64, 5, 5, 1, 1, 256, 56) | 23453 | 20826 | 1.13X BM_RHS_NAME(PackRhs, 32, 64, 64, 30, 64, 5, 5, 2, 2, 256, 56) | 23167 | 22091 | 1.09X BM_RHS_NAME(PackRhs, 32, 256, 256, 4, 16, 8, 8, 1, 1, 256, 56) | 23422 | 23682 | 0.99X BM_RHS_NAME(PackRhs, 32, 256, 256, 4, 16, 8, 8, 2, 4, 256, 56) | 23165 | 23663 | 0.98X BM_RHS_NAME(PackRhs, 32, 64, 64, 4, 16, 3, 3, 1, 1, 36, 432) | 72689 | 44969 | 1.62X BM_RHS_NAME(PackRhs, 32, 64, 64, 4, 16, 3, 3, 2, 2, 36, 432) | 61732 | 39779 | 1.55X All benchmarks on Intel Skylake server with 8 cores.
* Split the implementation of i?amax/min into two. Based on PR-627 by Sameer ↵Gravatar Christoph Hertzberg2019-04-15
| | | | | | Agarwal. Like the Netlib reference implementation, I*AMAX now uses the L1-norm instead of the L2-norm for each element. Changed I*MIN accordingly.
* Tweak cost model for tensor contraction when parallelizing over the inner ↵Gravatar Rasmus Munk Larsen2019-04-12
| | | | | | dimension. https://bitbucket.org/snippets/rmlarsen/MexxLo
* Update TheadPoolDevice example to include ThreadPool creation and passing ↵Gravatar Jonathon Koyle2019-04-10
| | | | pointer into constructor.
* adding EIGEN_DEVICE_FUNC to the recently added TensorContractionKernel ↵Gravatar Deven Desai2019-04-08
| | | | constructor. Not having the EIGEN_DEVICE_FUNC attribute on it was leading to compiler errors when compiling Eigen in the ROCm/HIP path
* Add missing semicolonGravatar Eugene Zhulenev2019-04-02
|
* Add support for custom packed Lhs/Rhs blocks in tensor contractionsGravatar Eugene Zhulenev2019-04-01
|
* bug #1695: fix a numerical robustness issue. Computing the secular equation ↵Gravatar Gael Guennebaud2019-03-27
| | | | at the middle range without a shift might give a wrong sign.
generated by cgit v1.2.3 (git 2.39.1) at 2024-11-26 04:18:01 +0000