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
10,644 Commits 11 Branches 89 Tags 162 MiB
6e77f9bef3
Commit Graph

2718 Commits

Author SHA1 Message Date
Eugene Zhulenev
6e77f9bef3 Remove shadow warnings in TensorDeviceThreadPool 2019-08-28 10:32:19 -07:00
Rasmus Larsen
84fefdf321 Merged in ezhulenev/eigen-01 (pull request PR-683) 
Asynchronous parallelFor in Eigen ThreadPoolDevice
 2019-08-26 21:49:17 +00:00
maratek
8b5ab0e4dd Fix get_random_seed on Native Client 
Newlib in Native Client SDK does not provide ::random function.
Implement get_random_seed for NaCl using ::rand, similarly to Windows version.
 2019-08-23 15:25:56 -07:00
Eugene Zhulenev
6901788013 Asynchronous parallelFor in Eigen ThreadPoolDevice 2019-08-22 10:50:51 -07:00
Eugene Zhulenev
071311821e Remove XSMM support from Tensor module 2019-08-19 11:44:25 -07:00
Rasmus Munk Larsen
facc4e4536 Disable tests for contraction with output kernels when using libxsmm, which does not support this. 2019-08-07 14:11:15 -07:00
Rasmus Munk Larsen
eab7e52db2 [Eigen] Vectorize evaluation of coefficient-wise functions over tensor blocks if the strides are known to be 1. Provides up to 20-25% speedup of the TF cross entropy op with AVX. 
A few benchmark numbers:

name                              old time/op             new time/op             delta
BM_Xent_16_10000_cpu              448µs ± 3%              389µs ± 2%  -13.21%
(p=0.008 n=5+5)
BM_Xent_32_10000_cpu              575µs ± 6%              454µs ± 3%  -21.00%          (p=0.008 n=5+5)
BM_Xent_64_10000_cpu              933µs ± 4%              712µs ± 1%  -23.71%          (p=0.008 n=5+5)
 2019-08-07 12:57:42 -07:00
Rasmus Munk Larsen
0987126165 Clean up unnecessary namespace specifiers in TensorBlock.h. 2019-08-07 12:12:52 -07:00
Rasmus Munk Larsen
e2999d4c38 Fix performance regressions due to https://bitbucket.org/eigen/eigen/pull-requests/662. 
The change caused the device struct to be copied for each expression evaluation, and caused, e.g., a 10% regression in the TensorFlow multinomial op on GPU:


Benchmark                       Time(ns)        CPU(ns)     Iterations
----------------------------------------------------------------------
BM_Multinomial_gpu_1_100000_4     128173         231326           2922  1.610G items/s

VS

Benchmark                       Time(ns)        CPU(ns)     Iterations
----------------------------------------------------------------------
BM_Multinomial_gpu_1_100000_4     146683         246914           2719  1.509G items/s
 2019-08-02 11:18:13 -07:00
Eugene Zhulenev
3cd148f983 Fix expression evaluation heuristic for TensorSliceOp 2019-07-09 12:10:26 -07:00
Eugene Zhulenev
6083014594 Add outer/inner chipping optimization for chipping dimension specified at runtime 2019-07-03 11:35:25 -07:00
Deven Desai
7eb2e0a95b adding the EIGEN_DEVICE_FUNC attribute to the constCast routine. 
Not having this attribute results in the following failures in the `--config=rocm` TF build.

```
In file included from tensorflow/core/kernels/cross_op_gpu.cu.cc:20:
In file included from ./tensorflow/core/framework/register_types.h:20:
In file included from ./tensorflow/core/framework/numeric_types.h:20:
In file included from ./third_party/eigen3/unsupported/Eigen/CXX11/Tensor:1:
In file included from external/eigen_archive/unsupported/Eigen/CXX11/Tensor:140:
external/eigen_archive/unsupported/Eigen/CXX11/src/Tensor/TensorChipping.h:356:37: error:  'Eigen::constCast':  no overloaded function has restriction specifiers that are compatible with the ambient context 'data'
    typename Storage::Type result = constCast(m_impl.data());
                                    ^
external/eigen_archive/unsupported/Eigen/CXX11/src/Tensor/TensorChipping.h:356:37: error:  'Eigen::constCast':  no overloaded function has restriction specifiers that are compatible with the ambient context 'data'
external/eigen_archive/unsupported/Eigen/CXX11/src/Tensor/TensorAssign.h:148:56: note: in instantiation of member function 'Eigen::TensorEvaluator<const Eigen::TensorChippingOp<1, Eigen::TensorMap<Eigen::Tensor<int, 2, 1, long>, 16, MakePointer> >, Eigen::Gpu\
Device>::data' requested here
    return m_rightImpl.evalSubExprsIfNeeded(m_leftImpl.data());

```

Adding the EIGEN_DEVICE_FUNC attribute resolves those errors
 2019-07-02 20:02:46 +00:00
Gael Guennebaud
ef8aca6a89 Merged in codeplaysoftware/eigen (pull request PR-667) 
[SYCL] :

Approved-by: Gael Guennebaud <g.gael@free.fr>
Approved-by: Rasmus Larsen <rmlarsen@google.com>
 2019-07-02 12:45:23 +00:00
Eugene Zhulenev
4ac93f8edc Allocate non-const scalar buffer for block evaluation with DefaultDevice 2019-07-01 10:55:19 -07:00
Mehdi Goli
9ea490c82c [SYCL] : 
* Modifying TensorDeviceSYCL to use `EIGEN_THROW_X`.
  * Modifying TensorMacro to use `EIGEN_TRY/CATCH(X)` macro.
  * Modifying TensorReverse.h to use `EIGEN_DEVICE_REF` instead of `&`.
  * Fixing the SYCL device macro in SpecialFunctionsImpl.h.
 2019-07-01 16:27:28 +01:00
Eugene Zhulenev
81a03bec75 Fix TensorReverse on GPU with m_stride[i]==0 2019-06-28 15:50:39 -07:00
Rasmus Munk Larsen
74a9dd1102 Fix preprocessor condition to only generate a warning when calling eigen::GpuDevice::synchronize() from device code, but not when calling from a non-GPU compilation unit. 2019-06-28 11:56:21 -07:00
Rasmus Munk Larsen
70d4020ad9 Remove comma causing warning in c++03 mode. 2019-06-28 11:39:45 -07:00
Eugene Zhulenev
6e7c76481a Merge with Eigen head 2019-06-28 11:22:46 -07:00
Eugene Zhulenev
878845cb25 Add block access to TensorReverseOp and make sure that TensorForcedEval uses block access when preferred 2019-06-28 11:13:44 -07:00
Mehdi Goli
7d08fa805a [SYCL] This PR adds the minimum modifications to the Eigen unsupported module required to run it on devices supporting SYCL. 
* Abstracting the pointer type so that both SYCL memory and pointer can be captured.
* Converting SYCL virtual pointer to SYCL device memory in Eigen evaluator class.
* Binding SYCL placeholder accessor to command group handler by using bind method in Eigen evaluator node.
* Adding SYCL macro for controlling loop unrolling.
* Modifying the TensorDeviceSycl.h and SYCL executor method to adopt the above changes.
 2019-06-28 10:08:23 +01:00
Christoph Hertzberg
adec097c61 Remove extra comma (causes warnings in C++03) 2019-06-26 16:14:28 +02:00
Eugene Zhulenev
229db81572 Optimize evaluation strategy for TensorSlicingOp and TensorChippingOp 2019-06-25 15:41:37 -07:00
Rasmus Larsen
c1b0aea653 Merged in Artem-B/eigen (pull request PR-654) 
Minor build improvements

Approved-by: Rasmus Larsen <rmlarsen@google.com>
 2019-05-31 22:27:04 +00:00
Rasmus Munk Larsen
b08527b0c1 Clean up CUDA/NVCC version macros and their use in Eigen, and a few other CUDA build failures. 2019-05-31 15:26:06 -07:00
tra
b4c49bf00e Minor build improvements 
* Allow specifying multiple GPU architectures. E.g.:
  cmake -DEIGEN_CUDA_COMPUTE_ARCH="60;70"
* Pass CUDA SDK path to clang. Without it it will default to /usr/local/cuda
which may not be the right location, if cmake was invoked with
-DCUDA_TOOLKIT_ROOT_DIR=/some/other/CUDA/path
 2019-05-31 14:08:34 -07:00
Michael Tesch
c5019f722b Use pade for matrix exponential also for complex values. 2019-05-08 17:04:55 +02:00
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
Eugene Zhulenev
01654d97fa Prevent potential division by zero in TensorExecutor 2019-05-17 14:02:25 -07:00
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 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
4ccd1ece92 bug #1707: Fix deprecation warnings, or disable warnings when testing deprecated functions 2019-05-10 14:57:05 +02:00
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
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
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
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
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
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
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
Deven Desai
2dbea5510f Merged eigen/eigen into default 2019-03-19 16:52:38 -04:00
David Tellenbach
bd9c2ae3fd Fix include guard comments 2019-03-15 15:29:17 +01:00
Eugene Zhulenev
001f10e3c9 Fix segfaults with cuda compilation 2019-03-11 09:43:33 -07:00