devtools/eigen
1
0
Fork 0
mirror of https://gitlab.com/libeigen/eigen.git synced 2026-04-10 11:34:33 +08:00
Code Issues Packages Projects Releases Wiki Activity

Commit Graph

  • bc050ea9f0 Fixed compilation error when sycl is enabled. Benoit Steiner 2017-04-04 09:47:04 -07:00
  • 4910630c96 fix typos in the Tensor readme Gagan Goel 2017-03-31 20:32:16 -04:00
  • c1b3d5ecb6 Restored code compatibility with compilers that dont support c++11 Gated more sycl code under #ifdef sycl Benoit Steiner 2017-03-31 08:31:28 -07:00
  • e2d5d4e7b3 Restore the old constructors to retain compatibility with non c++11 compilers. Benoit Steiner 2017-03-31 08:26:13 -07:00
  • 73fcaa319f Gate the sycl specific code under #ifdef sycl Benoit Steiner 2017-03-31 08:22:25 -07:00
  • bd64ee8555 Fixing TensorArgMaxSycl.h; Removing warning related to the hardcoded type of dims to be int in Argmax. Mehdi Goli 2017-03-28 16:50:34 +01:00
  • a91417a7a5 Introduces align allocator for SYCL buffer Luke Iwanski 2017-03-20 14:48:54 +00:00
  • aae19c70ac update has_ReturnType to be more consistent with other has_ helpers Gael Guennebaud 2017-03-17 17:33:15 +01:00
  • f8a622ef3c Merged eigen/eigen into default Benoit Steiner 2017-03-15 20:06:19 -07:00
  • fd7db52f9b Silenced compilation warning Benoit Steiner 2017-03-15 20:02:39 -07:00
  • 9597d6f6ab Temporary: Disables cxx11_tensor_argmax_sycl test since it is causing zombie thread Luke Iwanski 2017-03-15 19:28:09 +00:00
  • c06861d15e Fixes bug in get_sycl_supported_devices() that was reporting unsupported Intel CPU on AMD platform - causing timeouts in that configuration Luke Iwanski 2017-03-15 19:26:08 +00:00
  • 7f31bb6822 Merged in ilya-biryukov/eigen/fix_clang_cuda_compilation (pull request PR-304) Benoit Steiner 2017-03-15 16:48:52 +00:00
  • 89fd0c3881 better check array index before using it Gael Guennebaud 2017-03-15 15:18:03 +01:00
  • 61160a21d2 ARM prefetch fixes: Implement prefetch on ARM64. Do not clobber cc on ARM32. Benoit Jacob 2017-03-15 06:57:25 -04:00
  • f499fe9496 Adding synchronisation to convolution kernel for sycl backend. Mehdi Goli 2017-03-13 09:18:37 +00:00
  • 1b32a10053 Use name to distinguish name instead of the vendor Luke Iwanski 2017-03-08 18:26:34 +00:00
  • aadb7405a7 Fixing typo in sycl Benchmark. Mehdi Goli 2017-03-08 18:20:06 +00:00
  • 5e9a1e7a7a Adding sycl Benchmarks. Mehdi Goli 2017-03-08 14:17:48 +00:00
  • e2e3f78533 Fixing potential race condition on sycl device. Mehdi Goli 2017-03-07 17:48:15 +00:00
  • f84963ed95 Adding TensorIndexTuple and TensorTupleReduceOP backend (ArgMax/Min) for sycl; fixing the address space issue for const TensorMap; converting all discard_write to write due to data missmatch. Mehdi Goli 2017-03-07 14:27:10 +00:00
  • 1c03d43a5c Fixed compilation with cuda-clang Ilya Biryukov 2017-03-06 12:01:12 +01:00
  • f0f3591118 Made the reduction code compile with cuda-clang Benoit Steiner 2017-03-14 14:16:53 -07:00
  • bfd7bf9c5b Get rid of Init(). Rasmus Munk Larsen 2017-03-10 08:48:20 -08:00
  • d56ab01094 Use C++11 ctor forwarding to simplify code a bit. Rasmus Munk Larsen 2017-03-10 08:30:22 -08:00
  • 344c2694a6 Make the non-blocking threadpool more flexible and less wasteful of CPU cycles for high-latency use-cases. Rasmus Munk Larsen 2017-03-09 15:41:03 -08:00
  • 970ff78294 bug #1401: fix compilation of "cond ? x : -x" with x an AutoDiffScalar Gael Guennebaud 2017-03-08 16:16:53 +01:00
  • e5156e4d25 fix typo Gael Guennebaud 2017-03-07 11:25:58 +01:00
  • 5694315fbb remove UTF8 symbol Gael Guennebaud 2017-03-07 10:53:47 +01:00
  • e958c2baac remove UTF8 symbols Gael Guennebaud 2017-03-07 10:47:40 +01:00
  • d967718525 do not include std header within extern C Gael Guennebaud 2017-03-07 10:16:39 +01:00
  • 659087b622 bug #1400: fix stableNorm with EIGEN_DONT_ALIGN_STATICALLY Gael Guennebaud 2017-03-07 10:02:34 +01:00
  • a71943b9a4 Made the Tensor code compile with clang 3.9 Benoit Steiner 2017-03-02 10:47:29 -08:00
  • 09ae0e6586 Adjusted the EIGEN_DEVICE_FUNC qualifiers to make sure that: * they're used consistently between the declaration and the definition of a function * we avoid calling host only methods from host device methods. Benoit Steiner 2017-03-01 11:47:47 -08:00
  • 1e2d046651 Silenced a couple of compilation warnings Benoit Steiner 2017-03-01 10:13:42 -08:00
  • c1d87ec110 Added missing EIGEN_DEVICE_FUNC qualifiers Benoit Steiner 2017-03-01 10:08:50 -08:00
  • 3a3f040baa Added missing EIGEN_DEVICE_FUNC qualifiers Benoit Steiner 2017-02-28 17:06:15 -08:00
  • 7b61944669 Made most of the packet math primitives usable within CUDA kernel when compiling with clang Benoit Steiner 2017-02-28 17:05:28 -08:00
  • c92406d613 Silenced clang compilation warning. Benoit Steiner 2017-02-28 17:03:11 -08:00
  • 857adbbd52 Added missing EIGEN_DEVICE_FUNC qualifiers Benoit Steiner 2017-02-28 16:42:00 -08:00
  • c36bc2d445 Added missing EIGEN_DEVICE_FUNC qualifiers Benoit Steiner 2017-02-28 14:58:45 -08:00
  • 4a7df114c8 Added missing EIGEN_DEVICE_FUNC Benoit Steiner 2017-02-28 14:00:15 -08:00
  • de7b0fdea9 Made the TensorStorage class compile with clang 3.9 Benoit Steiner 2017-02-28 13:52:22 -08:00
  • 765f4cc4b4 Deleted extra: EIGEN_DEVICE_FUNC: the QR and Cholesky code isn't ready to run on GPU yet. Benoit Steiner 2017-02-28 11:57:00 -08:00
  • e993c94f07 Added missing EIGEN_DEVICE_FUNC qualifiers Benoit Steiner 2017-02-28 09:56:45 -08:00
  • 33443ec2b0 Added missing EIGEN_DEVICE_FUNC qualifiers Benoit Steiner 2017-02-28 09:50:10 -08:00
  • f3e9c42876 Added missing EIGEN_DEVICE_FUNC qualifiers Benoit Steiner 2017-02-28 09:46:30 -08:00
  • 8296b87d7b Adding sycl backend for TensorCustomOp; fixing the partial lhs modification issue on sycl when the rhs is TensorContraction, reduction or convolution; Fixing the partial modification for memset when sycl backend is used. Mehdi Goli 2017-02-28 17:16:14 +00:00
  • 4e98a7b2f0 bug #1396: add some missing EIGEN_DEVICE_FUNC Gael Guennebaud 2017-02-28 09:47:38 +01:00
  • 478a9f53be Fix typo. Gael Guennebaud 2017-02-28 09:32:45 +01:00
  • 889c606f8f Added missing EIGEN_DEVICE_FUNC to the SelfCwise binary ops Benoit Steiner 2017-02-27 17:17:47 -08:00
  • 193939d6aa Added missing EIGEN_DEVICE_FUNC qualifiers to several nullary op methods. Benoit Steiner 2017-02-27 17:11:47 -08:00
  • ed4dc9d01a Declared the plset, ploadt_ro, and ploaddup packet primitives as usable within a gpu kernel Benoit Steiner 2017-02-27 16:57:01 -08:00
  • b1fc7c9a09 Added missing EIGEN_DEVICE_FUNC qualifiers. Benoit Steiner 2017-02-27 16:48:30 -08:00
  • 554116bec1 Added EIGEN_DEVICE_FUNC to make the prototype of the EigenBase override match that of DenseBase Benoit Steiner 2017-02-27 16:45:31 -08:00
  • 34d9fce93b Avoid unecessary float to double conversions. Benoit Steiner 2017-02-27 16:33:33 -08:00
  • e0bd6f5738 Merged eigen/eigen into default Benoit Steiner 2017-02-26 10:02:14 -08:00
  • 2fa2b617a9 Adding TensorVolumePatchOP.h for sycl Mehdi Goli 2017-02-24 19:16:24 +00:00
  • 0b7875f137 Converting fixed float type into template type for TensorContraction. Mehdi Goli 2017-02-24 18:13:30 +00:00
  • 89dfd51fae Adding Sycl Backend for TensorGenerator.h. Mehdi Goli 2017-02-22 16:36:24 +00:00
  • 4f07ac16b0 Reducing the number of warnings. Mehdi Goli 2017-02-21 10:09:47 +00:00
  • 76687f385c bug #1394: fix compilation of SelfAdjointEigenSolver<Matrix>(sparse*sparse); Gael Guennebaud 2017-02-20 14:27:26 +01:00
  • d8b1f6cebd bug #1380: for Map<> as input of matrix exponential Gael Guennebaud 2017-02-20 14:06:06 +01:00
  • 6572825703 bug #1395: fix the use of compile-time vectors as inputs of JacobiSVD. Gael Guennebaud 2017-02-20 13:44:37 +01:00
  • 79ebc8f761 Adding Sycl backend for TensorImagePatchOP.h; adding Sycl backend for TensorInflation.h. Mehdi Goli 2017-02-20 12:11:05 +00:00
  • a811a04696 Silent warning. Gael Guennebaud 2017-02-20 10:14:21 +01:00
  • 63798df038 Fix usage of CUDACC_VER Gael Guennebaud 2017-02-20 08:16:36 +01:00
  • deefa54a54 Fix tracking of temporaries in unit tests Gael Guennebaud 2017-02-19 10:32:54 +01:00
  • f8a55cc062 Fix compilation. Gael Guennebaud 2017-02-18 10:08:13 +01:00
  • cbbf88c4d7 Use int32_t instead of int in NEON code. Some platforms with 16 bytes int supports ARM NEON. Gael Guennebaud 2017-02-17 14:39:02 +01:00
  • 582b5e39bf bug #1393: enable Matrix/Array explicit ctor from types with conversion operators (was ok with 3.2) Gael Guennebaud 2017-02-17 14:10:57 +01:00
  • cfa0568ef7 Size indices are signed. Benoit Steiner 2017-02-16 10:13:34 -08:00
  • 91982b91c0 Adding TensorLayoutSwapOp for sycl. Mehdi Goli 2017-02-15 16:28:12 +00:00
  • b1e312edd6 Adding TensorPatch.h for sycl backend. Mehdi Goli 2017-02-15 10:13:01 +00:00
  • 31a25ab226 Merged eigen/eigen into default Benoit Steiner 2017-02-14 15:36:21 -08:00
  • 0d153ded29 Adding TensorChippingOP for sycl backend; fixing the index value in the verification operation for cxx11_tensorChipping.cpp test Mehdi Goli 2017-02-13 17:25:12 +00:00
  • 5937c4ae32 Fall back is_integral to std::is_integral in c++11 Gael Guennebaud 2017-02-13 17:14:26 +01:00
  • 7073430946 Fix overflow and make use of long long in c++11 only. Gael Guennebaud 2017-02-13 17:14:04 +01:00
  • 3453b00a1e Fix vector indexing with uint64_t Jonathan Hseu 2017-02-11 21:45:32 -08:00
  • e7ebe52bfb bug #1391: include IO.h before DenseBase to enable its usage in DenseBase plugins. Gael Guennebaud 2017-02-13 09:46:20 +01:00
  • b3750990d5 Workaround some gcc 4.7 warnings Gael Guennebaud 2017-02-11 23:24:06 +01:00
  • c16ee72b20 bug #1392: fix #include <Eigen/Sparse> with mpl2-only Gael Guennebaud 2017-02-11 10:35:01 +01:00
  • e43016367a Forgot to include a file in previous commit Gael Guennebaud 2017-02-11 10:34:18 +01:00
  • 6486d4fc95 Worakound gcc 4.7 issue in c++11. Gael Guennebaud 2017-02-11 10:29:10 +01:00
  • 4a4a72951f Fix previous commits: disbale only problematic indexed view methods for old compilers instead of disabling everything. Tested with gcc 4.7 (c++03) and gcc 4.8 (c++03 & c++11) Gael Guennebaud 2017-02-11 10:28:44 +01:00
  • fad776492f Merged eigen/eigen into default Benoit Steiner 2017-02-10 14:27:43 -08:00
  • 1ef30b8090 Fixed bug introduced in previous commit Benoit Steiner 2017-02-10 13:35:10 -08:00
  • 769208a17f Pulled latest updates from upstream Benoit Steiner 2017-02-10 13:11:40 -08:00
  • 8b3cc54c42 Added a new EIGEN_HAS_INDEXED_VIEW define that set to 0 for older compilers that are known to fail to compile the indexed views (I used the define from the indexed_views.cpp test). Only include the indexed view methods when the compiler supports the code. This makes it possible to use Eigen again in complex code bases such as TensorFlow and older compilers such as gcc 4.8 Benoit Steiner 2017-02-10 13:08:49 -08:00
  • a1ff24f96a Fix prunning in (sparse*sparse).pruned() when the result is nearly dense. Gael Guennebaud 2017-02-10 13:59:32 +01:00
  • 0256c52359 Include clang in the list of non strict MSVC (just to be sure) Gael Guennebaud 2017-02-10 13:41:52 +01:00
  • dd58462e63 fixed inlining issue with clang-cl on visual studio (grafted from 7962ac1a58 ) Alexander Neumann 2017-02-08 23:50:38 +01:00
  • fc8fd5fd24 Improve multi-threading heuristic for matrix products with a small number of columns. Gael Guennebaud 2017-02-07 17:19:59 +01:00
  • 0ee97b60c2 Adding mean to TensorReductionSycl.h Mehdi Goli 2017-02-07 15:43:17 +00:00
  • 42bd5c4e7b Fixing TensorReductionSycl for min and max. Mehdi Goli 2017-02-06 18:05:23 +00:00
  • 4254b3eda3 bug #1389: MSVC's std containers do not properly align in 64 bits mode if the requested alignment is larger than 16 bytes (e.g., with AVX) Gael Guennebaud 2017-02-03 15:22:35 +01:00
  • bc128f9f3b Reducing the warnings in Sycl backend. Mehdi Goli 2017-02-02 10:43:47 +00:00
  • 442e9cbb30 Silenced several compilation warnings Benoit Steiner 2017-02-01 15:50:58 -08:00
  • 2db75c07a6 fixed the ordering of the template and EIGEN_DEVICE_FUNC keywords in a few more places to get more of the Eigen codebase to compile with nvcc again. Benoit Steiner 2017-02-01 15:41:29 -08:00
  • fcd257039b Replaced EIGEN_DEVICE_FUNC template<foo> with template<foo> EIGEN_DEVICE_FUNC to make the code compile with nvcc8. Benoit Steiner 2017-02-01 15:30:49 -08:00