mirror/eigen
2
0
Fork 0
mirror of https://gitlab.com/libeigen/eigen.git synced 2025-01-06 14:14:46 +08:00
Code Issues Packages Projects Releases Wiki Activity
8,472 Commits 11 Branches 89 Tags 168 MiB
00b2666853
Commit Graph

4884 Commits

Author SHA1 Message Date
Gael Guennebaud
a3f7edf7e7 Biug 1242: fix comma init with empty matrices. 2016-06-23 10:25:04 +02:00
Konstantinos Margaritis
8c34b5a0e3 mostly cleanups and modernizing code 2016-06-19 16:13:17 -03:00
Konstantinos Margaritis
b410d46482 mostly cleanups and modernizing code 2016-06-19 16:12:52 -03:00
Konstantinos Margaritis
b80379bda0 fixed pexp<Packet2d>, was failing tests 2016-06-19 16:11:58 -03:00
Benoit Steiner
b055590e91 Made log1p_impl usable inside a GPU kernel 2016-06-16 11:37:40 -07:00
Gael Guennebaud
67c12531e5 Fix warnings with gcc 2016-06-15 18:11:33 +02:00
Gael Guennebaud
eb91345d64 Move scalar/expr to ArrayBase and fix documentation 2016-06-15 15:22:03 +02:00
Gael Guennebaud
4794834397 Propagate functor to ScalarBinaryOpTraits 2016-06-15 09:58:49 +02:00
Gael Guennebaud
c55035b9c0 Include the cost of stores in unrolling of triangular expressions. 2016-06-15 09:57:33 +02:00
Gael Guennebaud
4e7c3af874 Cleanup useless helper: internal::product_result_scalar 2016-06-15 00:04:10 +02:00
Gael Guennebaud
101ea26f5e Include the cost of stores in unrolling (also fix infinite unrolling with expression costing 0 like Constant) 2016-06-15 00:01:16 +02:00
Gael Guennebaud
76236cdea4 merge 2016-06-14 15:33:47 +02:00
Gael Guennebaud
1004c4df99 Cleanup unused functors. 2016-06-14 15:27:28 +02:00
Gael Guennebaud
70dad84b73 Generalize expr/expr and scalar/expr wrt scalar types. 2016-06-14 15:26:37 +02:00
Gael Guennebaud
62134082aa Update AutoDiffScalar wrt to scalar-multiple. 2016-06-14 15:06:35 +02:00
Gael Guennebaud
396d9cfb6e Generalize expr.pow(scalar), pow(expr,scalar) and pow(scalar,expr). 
Internal: scalar_pow_op (unary) is removed, and scalar_binary_pow_op is renamed scalar_pow_op.
 2016-06-14 14:10:07 +02:00
Gael Guennebaud
a8c08e8b8e Implement expr+scalar, scalar+expr, expr-scalar, and scalar-expr as binary expressions, and generalize supported scalar types. 
The following functors are now deprecated: scalar_add_op, scalar_sub_op, and scalar_rsub_op.
 2016-06-14 12:06:10 +02:00
Gael Guennebaud
756ac4a93d Fix doc. 2016-06-14 12:03:39 +02:00
Gael Guennebaud
bcc0f38f98 Add unittesting plugins to scalar_product_op and scalar_quotient_op to help chaking that types are properly propagated. 2016-06-14 11:31:27 +02:00
Gael Guennebaud
f57fd78e30 Generalize coeff-wise sparse products to support different scalar types 2016-06-14 11:29:54 +02:00
Gael Guennebaud
f5b1c73945 Set cost of constant expression to 0 (the cost should be amortized through the expression) 2016-06-14 11:29:06 +02:00
Gael Guennebaud
deb8306e60 Move MatrixBase::operaotr*(UniformScaling) as a free function in Scaling.h, and fix return type. 2016-06-14 11:28:03 +02:00
Gael Guennebaud
64fcfd314f Implement scalar multiples and division by a scalar as a binary-expression with a constant expression. 
This slightly complexifies the type of the expressions and implies that we now have to distinguish between scalar*expr and expr*scalar to catch scalar-multiple expression (e.g., see BlasUtil.h), but this brings several advantages:
- it makes it clear on each side the scalar is applied,
- it clearly reflects that we are dealing with a binary-expression,
- the complexity of the type is hidden through macros defined at the end of Macros.h,
- distinguishing between "scalar op expr" and "expr op scalar" is important to support non commutative fields (like quaternions)
- "scalar op expr" is now fully equivalent to "ConstantExpr(scalar) op expr"
- scalar_multiple_op, scalar_quotient1_op and scalar_quotient2_op are not used anymore in officially supported modules (still used in Tensor)
 2016-06-14 11:26:57 +02:00
Gael Guennebaud
3c12e24164 Add bind1st_op and bind2nd_op helpers to turn binary functors into unary ones, and implement scalar_multiple2 and scalar_quotient2 on top of them. 2016-06-13 16:18:59 +02:00
Gael Guennebaud
7a9ef7bbb4 Add default template parameters for the second scalar type of binary functors. 
This enhences backward compatibility.
 2016-06-13 16:17:23 +02:00
Gael Guennebaud
4c61f00838 Add missing explicit scalar conversion 2016-06-12 22:42:13 +02:00
Gael Guennebaud
83904a21c1 Make sure T(i+1,i)==0 when diagonalizing T(i:i+1,i:i+1) 2016-06-11 14:41:36 +02:00
Gael Guennebaud
fabae6c9a1 Cleanup 2016-06-10 15:58:33 +02:00
Gael Guennebaud
5fdd703629 Enable mixing types in numext::pow 2016-06-10 15:58:04 +02:00
Gael Guennebaud
2e238bafb6 Big 279: enable mixing types for comparisons, min, and max. 2016-06-10 15:05:43 +02:00
Gael Guennebaud
0028049380 bug #1240: Remove any assumption on NEON vector types. 2016-06-09 23:08:11 +02:00
Gael Guennebaud
2c462f4201 Clean handling for void type in EIGEN_CHECK_BINARY_COMPATIBILIY 2016-06-06 23:11:38 +02:00
Gael Guennebaud
3d71d3918e Disable shortcuts for res ?= prod when the scalar types do not match exactly. 2016-06-06 23:10:55 +02:00
Gael Guennebaud
66e99ab6a1 Relax mixing-type constraints for binary coefficient-wise operators: 
- Replace internal::scalar_product_traits<A,B> by Eigen::ScalarBinaryOpTraits<A,B,OP>
- Remove the "functor_is_product_like" helper (was pretty ugly)
- Currently, OP is not used, but it is available to the user for fine grained tuning
- Currently, only the following operators have been generalized: *,/,+,-,=,*=,/=,+=,-=
- TODO: generalize all other binray operators (comparisons,pow,etc.)
- TODO: handle "scalar op array" operators (currently only * is handled)
- TODO: move the handling of the "void" scalar type to ScalarBinaryOpTraits
 2016-06-06 15:11:41 +02:00
Benoit Steiner
1f1e0b9e30 Silenced compilation warning 2016-06-05 12:59:11 -07:00
Benoit Steiner
5b95b4daf9 Moved static assertions into the class constructor to make the code more portable 2016-06-05 12:57:48 -07:00
Sean Templeton
bd21243821 Fix compile errors initializing packets on ARM DS-5 5.20 
The ARM DS-5 5.20 compiler fails compiling with the following errors:

"src/Core/arch/NEON/PacketMath.h", line 113: Error:  #146: too many initializer values
    Packet4f countdown = EIGEN_INIT_NEON_PACKET4(0, 1, 2, 3);
                         ^
"src/Core/arch/NEON/PacketMath.h", line 118: Error:  #146: too many initializer values
    Packet4i countdown = EIGEN_INIT_NEON_PACKET4(0, 1, 2, 3);
                         ^
"src/Core/arch/NEON/Complex.h", line 30: Error:  #146: too many initializer values
  static uint32x4_t p4ui_CONJ_XOR = EIGEN_INIT_NEON_PACKET4(0x00000000, 0x80000000, 0x00000000, 0x80000000);
                                    ^
"src/Core/arch/NEON/Complex.h", line 31: Error:  #146: too many initializer values
  static uint32x2_t p2ui_CONJ_XOR = EIGEN_INIT_NEON_PACKET2(0x00000000, 0x80000000);
                                    ^

The vectors are implemented as two doubles, hence the too many initializer values error.
Changed the code to use intrinsic load functions which all compilers
implementing NEON should have.
 2016-06-03 10:51:35 -05:00
Gael Guennebaud
1fc2746417 Make Arrays's ctor/assignment noexcept 2016-06-09 22:52:37 +02:00
Gael Guennebaud
2bd59b0e0d Take advantage that T is already diagonal in the extraction of generalized complex eigenvalues. 2016-06-09 17:12:03 +02:00
Gael Guennebaud
c1f9ca9254 Update RealQZ to reduce 2x2 diagonal block of T corresponding to non reduced diagonal block of S to positive diagonal form. 
This step involve a real 2x2 SVD problem. The respective routine is thus in src/misc/ to be shared by both EVD and AVD modules.
 2016-06-09 17:11:03 +02:00
Gael Guennebaud
a20d2ec1c0 Fix shadow variable, and indexing. 2016-06-09 16:16:22 +02:00
Abhijit Kundu
0beabb4776 Fixed type conversion from int 2016-06-08 16:12:04 -04:00
Gael Guennebaud
df095cab10 Fixes for PARDISO: warnings, and defaults to metis+ in-core mode. 2016-06-08 18:31:19 +02:00
Gael Guennebaud
9fc8379328 Fix extraction of complex eigenvalue pairs in real generalized eigenvalue problems. 2016-06-08 16:39:11 +02:00
Benoit Steiner
8fd57a97f2 Enable the vectorization of adds and mults of fp16 2016-06-07 18:22:18 -07:00
Benoit Steiner
ea75dba201 Added missing EIGEN_DEVICE_FUNC qualifiers to the unary array ops 2016-06-06 13:32:28 -07:00
Benoit Steiner
33f0340188 Implement result_of for the new ternary functors 2016-06-06 12:06:42 -07:00
Gael Guennebaud
df24f4a01d bug #1201: improve code generation of affine*vec with MSVC 2016-06-06 16:46:46 +02:00
Eugene Brevdo
39baff850c Add TernaryFunctors and the betainc SpecialFunction. 
TernaryFunctors and their executors allow operations on 3-tuples of inputs.
API fully implemented for Arrays and Tensors based on binary functors.

Ported the cephes betainc function (regularized incomplete beta
integral) to Eigen, with support for CPU and GPU, floats, doubles, and
half types.

Added unit tests in array.cpp and cxx11_tensor_cuda.cu


Collapsed revision
* Merged helper methods for betainc across floats and doubles.
* Added TensorGlobalFunctions with betainc().  Removed betainc() from TensorBase.
* Clean up CwiseTernaryOp checks, change igamma_helper to cephes_helper.
* betainc: merge incbcf and incbd into incbeta_cfe.  and more cleanup.
* Update TernaryOp and SpecialFunctions (betainc) based on review comments.
 2016-06-02 17:04:19 -07:00
Gael Guennebaud
8d97ba6b22 bug #725: make move ctor/assignment noexcept. 2016-06-03 14:28:25 +02:00
Gael Guennebaud
fe62c06d9b Fix compilation. 2016-06-03 07:47:38 +02:00
Gael Guennebaud
969b8959a0 Fix compilation: Matrix does not indirectly live in the internal namespace anymore! 2016-06-03 07:44:58 +02:00
Gael Guennebaud
f2c2465acc Fix function dependencies 2016-06-03 07:44:18 +02:00
Gael Guennebaud
53feb73b45 Remove dead code. 2016-06-02 22:19:55 +02:00
Gael Guennebaud
2c00ac0b53 Implement generic scalar*expr and expr*scalar operator based on scalar_product_traits. 
This is especially useful for custom scalar types, e.g., to enable float*expr<multi_prec> without conversion.
 2016-06-02 22:16:37 +02:00
Gael Guennebaud
8b6f53222b bug #1193: fix lpNorm<Infinity> for empty input. 2016-06-02 15:29:59 +02:00
Gael Guennebaud
360e311b66 Doc: add some cross references (also fix empty macro argument warning) 2016-06-01 23:34:09 +02:00
Gael Guennebaud
3c69afca4c Add missing ArrayBase::log1p 2016-06-01 17:08:47 +02:00
Gael Guennebaud
89099b0cf7 Expose log1p to Array. 2016-06-01 17:00:08 +02:00
Gael Guennebaud
afd33539dd Doc: makes the global unary math functions visible to doxygen (and docuement them) 2016-06-01 15:27:13 +02:00
Gael Guennebaud
77e652d8ad Doc: improve documentation of Map<SparseMatrix> 2016-06-01 10:03:32 +02:00
Gael Guennebaud
da4970ead2 Doc: disable inlining of inherited members, workaround Doxygen's limited C++ parsing abilities, and improve doc of MapBase. 2016-06-01 09:38:49 +02:00
Benoit Steiner
099b354ca7 Pulled latest updates from trunk 2016-05-31 10:34:16 -07:00
Benoit Steiner
b6e306f189 Improved support for CUDA 8.0 2016-05-31 09:47:59 -07:00
Gael Guennebaud
1d3b253329 bug #1181: help MSVC inlining. 2016-05-31 17:23:42 +02:00
Gael Guennebaud
d79eee05ef Fix compilation with old icc 2016-05-31 17:13:51 +02:00
Gael Guennebaud
2c1b56f4c1 bug #1238: fix SparseMatrix::sum() overload for un-compressed mode. 2016-05-31 10:56:53 +02:00
Benoit Steiner
c4bd3b1f21 Silenced some compilation warnings triggered by nvcc 8.0 2016-05-27 14:40:49 -07:00
Benoit Steiner
3a5d6a3c38 Disable the use of MMX instructions since the code is broken on many platforms 2016-05-27 09:13:26 -07:00
Gael Guennebaud
e0cb73b46b Fix compilation with old ICC version (use C99 types instead of C++11 ones) 2016-05-27 10:28:09 +02:00
Benoit Steiner
094f4a56c8 Deleted extra namespace 2016-05-26 14:49:51 -07:00
Gael Guennebaud
7ff5fadcc0 Disable usage of MMX with msvc. 2016-05-26 17:58:46 +02:00
Gael Guennebaud
e8cef383b7 bug #1236: fix possible integer overflow in density estimation. 2016-05-26 17:51:04 +02:00
Gael Guennebaud
30d97c03ce Defer the allocation of the working space: 
- it is not always needed,
- and this fixes a long-to-float conversion warning
 2016-05-26 17:39:42 +02:00
Gael Guennebaud
e08f54e9eb Fix copy ctor prototype. 2016-05-26 17:37:25 +02:00
Gael Guennebaud
c7f54b11ec linspaced's divisor for integer is better stored as the underlying scalar type. 2016-05-26 17:36:54 +02:00
Gael Guennebaud
bebc5a2147 Fix/handle some int-to-long conversions. 2016-05-26 17:35:53 +02:00
Gael Guennebaud
00c29c2cae Store permutation's determinant as char. 
This also fixes some long to float conversion warnings
 2016-05-26 17:34:23 +02:00
Gael Guennebaud
2f56d91063 Fix a pointer to integer conversion warning 2016-05-26 17:31:45 +02:00
Gael Guennebaud
2a44a70142 Handle some Index to int conversions in BLAS/LAPACK support. 2016-05-26 17:29:04 +02:00
Gael Guennebaud
f253e19296 Disable some long to float conversion warnings 2016-05-26 17:27:14 +02:00
Gael Guennebaud
37197b602b Remove debuging code. 2016-05-26 11:53:10 +02:00
Gael Guennebaud
27f0434233 Introduce internal's UIntPtr and IntPtr types for pointer to integer conversions. 
This fixes "conversion from pointer to same-sized integral type" warnings by ICC.
Ideally, we would use the std::[u]intptr_t types all the time, but since they are C99/C++11 only,
let's be safe.
 2016-05-26 10:52:12 +02:00
Gael Guennebaud
40e4637d79 Turn off ICC's conversion warning in is_convertible implementation 2016-05-26 10:48:43 +02:00
Gael Guennebaud
cc1ab64f29 Add missing inclusion of mmintrin.h 2016-05-26 09:51:50 +02:00
Benoit Steiner
3585ff585e Silenced a compilation warning 2016-05-25 22:09:19 -07:00
Benoit Steiner
efeb89dcdb Specify the rounding mode in the correct location 2016-05-25 17:53:24 -07:00
Benoit Steiner
0322c66a3f Explicitly specify the rounding mode when converting floats to fp16 2016-05-25 15:56:15 -07:00
Benoit Steiner
ed783872ab Disable the use of MMX instructions on x86_64 since too many compilers only support them in 32bit mode 2016-05-25 08:27:26 -07:00
Benoit Steiner
bcfff64f9e Use numext:: instead of std:: functions. 2016-05-25 08:08:21 -07:00
Gael Guennebaud
bbf9109e25 Fix compilation with ICC. 2016-05-25 10:00:55 +02:00
Gael Guennebaud
2a1bff67fd Fix static/inline order. 2016-05-25 10:00:11 +02:00
Benoit Steiner
d041a528da Cleaned up the fp16 code a little more 2016-05-24 22:43:26 -07:00
Benoit Steiner
cb26784d07 Pulled latest updates from trunk 2016-05-24 18:51:39 -07:00
Benoit Steiner
ff4a289572 Cleaned up the fp16 code 2016-05-24 18:50:09 -07:00
Gael Guennebaud
e68e165a23 bug #256: enable vectorization with unaligned loads/stores. 
This concerns all architectures and all sizes.
This new behavior can be disabled by defining EIGEN_UNALIGNED_VECTORIZE=0
 2016-05-24 21:54:03 +02:00
Gael Guennebaud
78390e4189 Block<> should not disable vectorization based on inner-size, this is the responsibilty of the assignment logic. 2016-05-24 17:14:01 +02:00
Gael Guennebaud
64bb7576eb Clean propagation of Dest/Src alignments. 2016-05-24 17:12:12 +02:00
Benoit Jacob
40a16282c7 Remove now-unused protate PacketMath func 2016-05-24 11:01:18 -04:00
Benoit Jacob
6136f4fdd4 Remove the rotating kernel. It was only useful on some ARM CPUs (Qualcomm Krait) that are not as ubiquitous today as they were when I introduced it. 2016-05-24 10:00:32 -04:00
Benoit Steiner
e617711306 Don't attempt to use MMX instructions with visualstudio since they're only partially supported. 2016-05-24 06:43:58 -07:00
Benoit Steiner
334e76537f Worked around missing clang intrinsic 2016-05-24 00:29:28 -07:00
Benoit Steiner
b517ab349b Use the generic ploadquad intrinsics since it does the job 2016-05-24 00:11:17 -07:00
Benoit Steiner
646872cb3b Worked around missing clang intrinsics 2016-05-24 00:07:08 -07:00
Benoit Steiner
3dfc391a61 Added missing EIGEN_DEVICE_FUNC qualifier 2016-05-23 20:56:59 -07:00
Benoit Steiner
3d0741f027 Include mmintrin.h to make it possible to use mmx instructions when needed. For example, this will enable the definition of a half packet for the Packet4f type. 2016-05-23 20:43:48 -07:00
Benoit Steiner
33a94f5dc7 Use the Index type instead of integers to specify the strides in pgather/pscatter 2016-05-23 20:37:30 -07:00
Benoit Steiner
6bc684ab6a Added missing alignment in the fp16 packet traits 2016-05-23 20:32:30 -07:00
Benoit Steiner
283e33dea4 ptranspose is not a template. 2016-05-23 19:55:55 -07:00
Benoit Steiner
a5a3ba2b80 Avoid unnecessary float to double conversions 2016-05-23 17:16:09 -07:00
Benoit Steiner
5ba0ebe7c9 Avoid unnecessary float to double conversion. 2016-05-23 17:14:31 -07:00
Benoit Steiner
7d980d74e5 Started to vectorize the processing of 16bit floats on CPU. 2016-05-23 15:21:40 -07:00
Benoit Steiner
5d51a7f12c Don't optimize the processing of the last rows of a matrix matrix product in cases that violate the assumptions made by the optimized code path. 2016-05-23 15:13:16 -07:00
Christoph Hertzberg
88654762da Replace multiple constructors of half-type by a generic/templated constructor. This fixes an incompatibility with long double, exposed by the previous commit. 2016-05-23 10:03:03 +02:00
Christoph Hertzberg
718521d5cf Silenced several double-promotion warnings 2016-05-22 18:17:04 +02:00
Gael Guennebaud
ccaace03c9 Make EIGEN_HAS_CONSTEXPR user configurable 2016-05-20 15:10:08 +02:00
Gael Guennebaud
c3410804cd Make EIGEN_HAS_VARIADIC_TEMPLATES user configurable 2016-05-20 15:05:38 +02:00
Gael Guennebaud
abd1c1af7a Make EIGEN_HAS_STD_RESULT_OF user configurable 2016-05-20 15:01:27 +02:00
Gael Guennebaud
1395056fc0 Make EIGEN_HAS_C99_MATH user configurable 2016-05-20 14:58:19 +02:00
Gael Guennebaud
48bf5ec216 Make EIGEN_HAS_RVALUE_REFERENCES user configurable 2016-05-20 14:54:20 +02:00
Gael Guennebaud
f43ae88892 Rename EIGEN_HAVE_RVALUE_REFERENCES to EIGEN_HAS_RVALUE_REFERENCES 2016-05-20 14:48:51 +02:00
Gael Guennebaud
998f2efc58 Add a EIGEN_MAX_CPP_VER option to limit the C++ version to be used. 2016-05-20 14:44:28 +02:00
Gael Guennebaud
c028d96089 Improve doc of special math functions 2016-05-20 14:18:48 +02:00
Gael Guennebaud
0ba32f99bd Rename UniformRandom to UnitRandom. 2016-05-20 13:21:34 +02:00
Gael Guennebaud
7a9d9cde94 Fix coding practice in Quaternion::UniformRandom 2016-05-20 13:19:52 +02:00
Joseph Mirabel
eb0cc2573a bug #823: add static method to Quaternion for uniform random rotations. 2016-05-20 13:15:40 +02:00
Gael Guennebaud
6761c64d60 zeta and polygamma are not unary functions, but binary ones. 2016-05-19 18:34:16 +02:00
Gael Guennebaud
7a54032408 zeta and digamma do not require C++11/C99 2016-05-19 17:36:47 +02:00
Gael Guennebaud
ce12562710 Add some c++11 flags in documentation 2016-05-19 17:35:30 +02:00
Gael Guennebaud
b6ed8244b4 bug #1201: optimize affine*vector products 2016-05-19 16:09:15 +02:00
Gael Guennebaud
73693b5de6 bug #1221: disable gcc 6 warning: ignoring attributes on template argument 2016-05-19 15:21:53 +02:00
Gael Guennebaud
df9a5e13c6 Fix SelfAdjointEigenSolver for some input expression types, and add new regression unit tests for sparse and selfadjointview inputs. 2016-05-19 13:07:33 +02:00
Gael Guennebaud
6a2916df80 DiagonalWrapper is a vector, so it must expose the LinearAccessBit flag. 2016-05-19 13:06:21 +02:00
Gael Guennebaud
a226f6af6b Add support for SelfAdjointView::diagonal() 2016-05-19 13:05:33 +02:00
Gael Guennebaud
ee7da3c7c5 Fix SelfAdjointView::triangularView for complexes. 2016-05-19 13:01:51 +02:00
Gael Guennebaud
b6b8578a67 bug #1230: add support for SelfadjointView::triangularView. 2016-05-19 11:36:38 +02:00
Gael Guennebaud
84df9142e7 bug #1231: fix compilation regression regarding complex_array/=real_array and add respective unit tests 2016-05-18 23:00:13 +02:00
Gael Guennebaud
21d692d054 Use coeff(i,j) instead of operator(). 2016-05-18 17:09:20 +02:00
Gael Guennebaud
8456bbbadb bug #1224: fix regression in (dense*dense).sparseView() by specializing evaluator<SparseView<Product>> for sparse products only. 2016-05-18 16:53:28 +02:00
Gael Guennebaud
b507b82326 Use default sorting strategy for square products. 2016-05-18 16:51:54 +02:00
Gael Guennebaud
747e3290c0 bug #1213: rename some enums type for consistency. 2016-05-18 13:26:56 +02:00
Rasmus Munk Larsen
0dbd68145f Roll back changes to core. Move include of TensorFunctors.h up to satisfy dependence in TensorCostModel.h. 2016-05-17 10:25:19 -07:00
Rasmus Munk Larsen
e55deb21c5 Improvements to parallelFor. 
Move some scalar functors from TensorFunctors. to Eigen core.
 2016-05-12 14:07:22 -07:00
Benoit Steiner
fae0493f98 Fixed a couple of bugs related to the Pascalfamily of GPUs 
H: Enter commit message.  Lines beginning with 'HG:' are removed.
 2016-05-11 23:02:26 -07:00
Benoit Steiner
b6a517c47d Added the ability to load fp16 using the texture path. 
Improved the performance of some reductions on fp16
 2016-05-11 21:26:48 -07:00
Benoit Steiner
518149e868 Misc fixes for fp16 2016-05-11 20:11:14 -07:00
Benoit Steiner
56a1757d74 Made predux_min and predux_max on fp16 less noisy 2016-05-11 17:37:34 -07:00
Benoit Steiner
9091351dbe __ldg is only available with cuda architectures >= 3.5 2016-05-11 15:22:13 -07:00
Benoit Steiner
02f76dae2d Fixed a typo 2016-05-11 15:08:38 -07:00
Christoph Hertzberg
131e5a1a4a Do not copy for trivial 1x1 case. This also avoids a "maybe-uninitialized" warning in some situations. 2016-05-11 23:50:13 +02:00