mirror/eigen
2
0
Fork 0
mirror of https://gitlab.com/libeigen/eigen.git synced 2024-12-21 07:19:46 +08:00
Code Issues Packages Projects Releases Wiki Activity
10,576 Commits 11 Branches 89 Tags 162 MiB
e92486b8c3
Commit Graph

10576 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Rasmus Larsen
e92486b8c3 Merged in rmlarsen/eigen (pull request PR-643) 
Make Eigen build with cuda 10 and clang.

Approved-by: Justin Lebar <justin.lebar@gmail.com>
 2019-05-20 17:02:39 +00:00
Rasmus Munk Larsen
fd595d42a7 Merge 2019-05-20 09:39:11 -07:00
Gael Guennebaud
cc7ecbb124 Merged in scramsby/eigen (pull request PR-646) 
Eigen: Fix MSVC C++17 language standard detection logic
 2019-05-20 07:19:10 +00:00
Eugene Zhulenev
01654d97fa Prevent potential division by zero in TensorExecutor 2019-05-17 14:02:25 -07:00
Rasmus Larsen
78d3015722 Merged in ezhulenev/eigen-01 (pull request PR-644) 
Always evaluate Tensor expressions with broadcasting via tiled evaluation code path
 2019-05-17 19:44:25 +00:00
Rasmus Larsen
bf9cbed8d0 Merged in glchaves/eigen (pull request PR-635) 
Speed up GEMV on AVX-512 builds, just as done for GEBP previously.

Approved-by: Rasmus Larsen <rmlarsen@google.com>
 2019-05-17 19:40:50 +00:00
Eugene Zhulenev
96a276803c Always evaluate Tensor expressions with broadcasting via tiled evaluation code path 2019-05-16 16:15:45 -07:00
Rasmus Munk Larsen
ab0a30e429 Make Eigen build with cuda 10 and clang. 2019-05-15 13:32:15 -07:00
Rasmus Munk Larsen
734a50dc60 Make Eigen build with cuda 10 and clang. 2019-05-15 13:32:15 -07:00
Rasmus Larsen
c8d8d5c0fc Merged in rmlarsen/eigen_threadpool (pull request PR-640) 
Fix deadlocks in thread pool.

Approved-by: Eugene Zhulenev <ezhulenev@google.com>
 2019-05-13 20:04:35 +00:00
Christoph Hertzberg
5f32b79edc Collapsed revision from PR-641 
* SparseLU.h - corrected example, it didn't compile
* Changed encoding back to UTF8
 2019-05-13 19:02:30 +02:00
Anuj Rawat
ad372084f5 Removing unused API to fix compile error in TensorFlow due to 
AVX512VL, AVX512BW usage
 2019-05-12 14:43:10 +00:00
Christoph Hertzberg
4ccd1ece92 bug #1707: Fix deprecation warnings, or disable warnings when testing deprecated functions 2019-05-10 14:57:05 +02:00
Rasmus Munk Larsen
d3ef7cf03e Fix build with clang on Windows. 2019-05-09 11:07:04 -07:00
Rasmus Munk Larsen
e5ac8cbd7a A) fix deadlocks in thread pool caused by EventCount 
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:
01da8caf00

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.
 2019-05-08 10:16:46 -07:00
Eugene Zhulenev
45b40d91ca Fix AVX512 & GCC 6.3 compilation 2019-05-07 16:44:55 -07:00
Christoph Hertzberg
e6667a7060 Fix stupid shadow-warnings (with old clang versions) 2019-05-07 18:32:19 +02:00
Christoph Hertzberg
e54dc24d62 Restore C++03 compatibility 2019-05-07 18:30:44 +02:00
Christoph Hertzberg
cca76c272c Restore C++03 compatibility 2019-05-06 16:18:22 +02:00
Rasmus Munk Larsen
8e33844fc7 Fix traits for scalar_logistic_op. 2019-05-03 15:49:09 -07:00
Scott Ramsby
ff06ef7584 Eigen: Fix MSVC C++17 language standard detection logic 
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
 2019-05-03 14:14:09 -07:00
Eugene Zhulenev
e9f0eb8a5e Add masked_store_available to unpacket_traits 2019-05-02 14:52:58 -07:00
Eugene Zhulenev
96e30e936a Add masked pstoreu for Packet16h 2019-05-02 14:11:01 -07:00
Eugene Zhulenev
b4010f02f9 Add masked pstoreu to AVX and AVX512 PacketMath 2019-05-02 13:14:18 -07:00
Gael Guennebaud
578407f42f Fix regression in changeset ae33e866c7 2019-05-02 15:45:21 +02:00
Rasmus Larsen
ac50afaffa Merged in ezhulenev/eigen-01 (pull request PR-633) 
Check if gpu_assert was overridden in TensorGpuHipCudaDefines
 2019-04-29 16:29:35 +00:00
Gustavo Lima Chaves
d4dcb71bcb Speed up GEMV on AVX-512 builds, just as done for GEBP previously. 
We take advantage of smaller SIMD registers as well, in that case.

Gains up to 3x for select input sizes.
 2019-04-26 14:12:39 -07:00
Andy May
ae33e866c7 Fix compilation with PGI version 19 2019-04-25 21:23:19 +01:00
Gael Guennebaud
665ac22cc6 Merged in ezhulenev/eigen-01 (pull request PR-632) 
Fix doxygen warnings
 2019-04-25 20:02:20 +00:00
Eugene Zhulenev
01d7e6ee9b Check if gpu_assert was overridden in TensorGpuHipCudaDefines 2019-04-25 11:19:17 -07:00
Eugene Zhulenev
8ead5bb3d8 Fix doxygen warnings to enable statis code analysis 2019-04-24 12:42:28 -07:00
Eugene Zhulenev
07355d47c6 Get rid of SequentialLinSpacedReturnType deprecation warnings in DenseBase.h 2019-04-24 11:01:35 -07:00
Rasmus Munk Larsen
144ca33321 Remove deprecation annotation from typedef Eigen::Index Index, as it would generate too many build warnings. 2019-04-24 08:50:07 -07:00
Eugene Zhulenev
a7b7f3ca8a Add missing EIGEN_DEPRECATED annotations to deprecated functions and fix few other doxygen warnings 2019-04-23 17:23:19 -07:00
Eugene Zhulenev
68a2a8c445 Use packet ops instead of AVX2 intrinsics 2019-04-23 11:41:02 -07:00
Anuj Rawat
8c7a6feb8e Adding lowlevel APIs for optimized RHS packet load in TensorFlow 
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.
 2019-04-20 06:46:43 +00:00
Christoph Hertzberg
4270c62812 Split the implementation of i?amax/min into two. Based on PR-627 by Sameer 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.
 2019-04-15 17:18:03 +02:00
Rasmus Munk Larsen
039ee52125 Tweak cost model for tensor contraction when parallelizing over the inner dimension. 
https://bitbucket.org/snippets/rmlarsen/MexxLo
 2019-04-12 13:35:10 -07:00
Jonathon Koyle
9a3f06d836 Update TheadPoolDevice example to include ThreadPool creation and passing pointer into constructor. 2019-04-10 10:02:33 -06:00
Deven Desai
66a885b61e adding EIGEN_DEVICE_FUNC to the recently added TensorContractionKernel constructor. Not having the EIGEN_DEVICE_FUNC attribute on it was leading to compiler errors when compiling Eigen in the ROCm/HIP path 2019-04-08 13:45:08 +00:00
Eugene Zhulenev
629ddebd15 Add missing semicolon 2019-04-02 15:04:26 -07:00
Eugene Zhulenev
4e2f6de1a8 Add support for custom packed Lhs/Rhs blocks in tensor contractions 2019-04-01 11:47:31 -07:00
Gael Guennebaud
45e65fbb77 bug #1695: fix a numerical robustness issue. Computing the secular equation at the middle range without a shift might give a wrong sign. 2019-03-27 20:16:58 +01:00
William D. Irons
8de66719f9 Collapsed revision from PR-619 
* Add support for pcmp_eq in AltiVec/Complex.h
* Fixed implementation of pcmp_eq for double

The new logic is based on the logic from NEON for double.
 2019-03-26 18:14:49 +00:00
Gael Guennebaud
f11364290e ICC does not support -fno-unsafe-math-optimizations 2019-03-22 09:26:24 +01:00
Deven Desai
51e399fc15 updates requested in the PR feedback. Also droping coded within #ifdef EIGEN_HAS_OLD_HIP_FP16 2019-03-19 21:45:25 +00:00
Deven Desai
2dbea5510f Merged eigen/eigen into default 2019-03-19 16:52:38 -04:00
Rasmus Larsen
5c93b38c5f Merged in rmlarsen/eigen (pull request PR-618) 
Make clipping outside [-18:18] consistent for vectorized and non-vectorized paths of scalar_logistic_op<float>.

Approved-by: Gael Guennebaud <g.gael@free.fr>
 2019-03-18 15:51:55 +00:00
Gael Guennebaud
48898a988a fix unit test in c++03: c++03 does not allow passing local or anonymous enum as template param 2019-03-18 11:38:36 +01:00
Gael Guennebaud
cf7e2e277f bug #1692: enable enum as sizes of Matrix and Array 2019-03-17 21:59:30 +01:00