aboutsummaryrefslogtreecommitdiff
Commit message (Collapse)AuthorAge
* SSE/AVX: always use unaligned loadsHEADmasterAnton Khirnov2022-11-30
|
* Add support for AVX512.Anton Khirnov2022-08-27
| | | | Largely identical to Intel MIC.
* Convert values to CCTK_REAL explicitlyeschnett2013-08-21
| | | | git-svn-id: https://svn.cct.lsu.edu/repos/numrel/LSUThorns/Vectors/trunk@91 105869f7-3296-0410-a4ea-f4349344b45a
* Correct QPX vector implementationeschnett2013-08-08
| | | | git-svn-id: https://svn.cct.lsu.edu/repos/numrel/LSUThorns/Vectors/trunk@90 105869f7-3296-0410-a4ea-f4349344b45a
* Add stubs for counting floating point and memory operationseschnett2013-08-08
| | | | git-svn-id: https://svn.cct.lsu.edu/repos/numrel/LSUThorns/Vectors/trunk@89 105869f7-3296-0410-a4ea-f4349344b45a
* Correct errors in VSX vectorseschnett2013-08-08
| | | | git-svn-id: https://svn.cct.lsu.edu/repos/numrel/LSUThorns/Vectors/trunk@88 105869f7-3296-0410-a4ea-f4349344b45a
* Indentation changeeschnett2013-08-08
| | | | git-svn-id: https://svn.cct.lsu.edu/repos/numrel/LSUThorns/Vectors/trunk@87 105869f7-3296-0410-a4ea-f4349344b45a
* Correct syntax erroreschnett2013-07-19
| | | | git-svn-id: https://svn.cct.lsu.edu/repos/numrel/LSUThorns/Vectors/trunk@86 105869f7-3296-0410-a4ea-f4349344b45a
* Do not use type punning any moreeschnett2013-07-19
| | | | | | | | | | Do not cast between different pointer types. This is illegal in C/C++, and modern compilers (such as gcc 4.8) then generate wrong code. Instead, use memcpy to re-interpret the bit patterns of values with a different type. git-svn-id: https://svn.cct.lsu.edu/repos/numrel/LSUThorns/Vectors/trunk@85 105869f7-3296-0410-a4ea-f4349344b45a
* Update comment explaining Intel compiler bugeschnett2013-05-06
| | | | git-svn-id: https://svn.cct.lsu.edu/repos/numrel/LSUThorns/Vectors/trunk@82 105869f7-3296-0410-a4ea-f4349344b45a
* Mark file as containing C++ codeeschnett2013-02-26
| | | | git-svn-id: https://svn.cct.lsu.edu/repos/numrel/LSUThorns/Vectors/trunk@81 105869f7-3296-0410-a4ea-f4349344b45a
* Use inline function instead of macro for IfThen for Power7eschnett2013-02-26
| | | | git-svn-id: https://svn.cct.lsu.edu/repos/numrel/LSUThorns/Vectors/trunk@80 105869f7-3296-0410-a4ea-f4349344b45a
* Provide C++ wrapper for madd (multiply-add)eschnett2013-01-18
| | | | git-svn-id: https://svn.cct.lsu.edu/repos/numrel/LSUThorns/Vectors/trunk@78 105869f7-3296-0410-a4ea-f4349344b45a
* Major updateeschnett2013-01-16
| | | | | | | | | | | | | | | | | Disable AVX emulation Set default for streaming stores to "no" Correct QPX vectorisation (IBM Blue Gene/Q) Add MIC vectorisation (Intel Xeon Phi) Convert SSE and AVX vectorisation to using inline functions instead of macros for code clarity Define CCTK_BOOLEAN, CCTK_INTEGER and CCTK_BOOLEAN_VEC, CCTK_INTEGER_VEC to make boolean and integer vectors explicit git-svn-id: https://svn.cct.lsu.edu/repos/numrel/LSUThorns/Vectors/trunk@77 105869f7-3296-0410-a4ea-f4349344b45a
* Many correctionseschnett2012-12-31
| | | | git-svn-id: https://svn.cct.lsu.edu/repos/numrel/LSUThorns/Vectors/trunk@76 105869f7-3296-0410-a4ea-f4349344b45a
* Support 8-element vectorseschnett2012-12-31
| | | | git-svn-id: https://svn.cct.lsu.edu/repos/numrel/LSUThorns/Vectors/trunk@75 105869f7-3296-0410-a4ea-f4349344b45a
* Update commenteschnett2012-11-14
| | | | git-svn-id: https://svn.cct.lsu.edu/repos/numrel/LSUThorns/Vectors/trunk@74 105869f7-3296-0410-a4ea-f4349344b45a
* Allow const QPX vectorseschnett2012-11-14
| | | | git-svn-id: https://svn.cct.lsu.edu/repos/numrel/LSUThorns/Vectors/trunk@73 105869f7-3296-0410-a4ea-f4349344b45a
* Correct non-vectorised iftheneschnett2012-11-05
| | | | git-svn-id: https://svn.cct.lsu.edu/repos/numrel/LSUThorns/Vectors/trunk@71 105869f7-3296-0410-a4ea-f4349344b45a
* Use ~0 instead of -1 for intmaxeschnett2012-10-22
| | | | git-svn-id: https://svn.cct.lsu.edu/repos/numrel/LSUThorns/Vectors/trunk@69 105869f7-3296-0410-a4ea-f4349344b45a
* Add std:: prefixeschnett2012-10-22
| | | | git-svn-id: https://svn.cct.lsu.edu/repos/numrel/LSUThorns/Vectors/trunk@68 105869f7-3296-0410-a4ea-f4349344b45a
* Use new C++ isnan calling syntaxeschnett2012-10-22
| | | | git-svn-id: https://svn.cct.lsu.edu/repos/numrel/LSUThorns/Vectors/trunk@67 105869f7-3296-0410-a4ea-f4349344b45a
* Add support for (dynamic) if-then expressionseschnett2012-09-14
| | | | | | | | | | Add types for holding integers and booleans, and vectors thereof. Add if-then expressions. Add floating point comparisons. Update tests. git-svn-id: https://svn.cct.lsu.edu/repos/numrel/LSUThorns/Vectors/trunk@66 105869f7-3296-0410-a4ea-f4349344b45a
* Correct indentationeschnett2012-09-09
| | | | git-svn-id: https://svn.cct.lsu.edu/repos/numrel/LSUThorns/Vectors/trunk@65 105869f7-3296-0410-a4ea-f4349344b45a
* Add dummy kisgn functioneschnett2012-08-16
| | | | git-svn-id: https://svn.cct.lsu.edu/repos/numrel/LSUThorns/Vectors/trunk@64 105869f7-3296-0410-a4ea-f4349344b45a
* Use NOTZERO (~0) instead of IMINeschnett2012-08-16
| | | | git-svn-id: https://svn.cct.lsu.edu/repos/numrel/LSUThorns/Vectors/trunk@63 105869f7-3296-0410-a4ea-f4349344b45a
* Add ksgn function (vectorised version of Kranc's Sign)eschnett2012-08-11
| | | | | | | | | | | All architectures: Add copysign and sgn functions. Remove pos function (which does nothing). Add support for Blue Gene/Q (QPX instructions). Correct errors in AVX instructions. git-svn-id: https://svn.cct.lsu.edu/repos/numrel/LSUThorns/Vectors/trunk@62 105869f7-3296-0410-a4ea-f4349344b45a
* Wrap isnan calls to avoid C++ namespace issueseschnett2012-08-02
| | | | git-svn-id: https://svn.cct.lsu.edu/repos/numrel/LSUThorns/Vectors/trunk@61 105869f7-3296-0410-a4ea-f4349344b45a
* Avoid nans during self-testseschnett2012-05-13
| | | | git-svn-id: https://svn.cct.lsu.edu/repos/numrel/LSUThorns/Vectors/trunk@59 105869f7-3296-0410-a4ea-f4349344b45a
* Support partial stores for the Double Hummer architecture (Blue Gene/P)eschnett2012-05-03
| | | | git-svn-id: https://svn.cct.lsu.edu/repos/numrel/LSUThorns/Vectors/trunk@58 105869f7-3296-0410-a4ea-f4349344b45a
* make sure the test sees an expected nan as a successknarf2012-04-17
| | | | git-svn-id: https://svn.cct.lsu.edu/repos/numrel/LSUThorns/Vectors/trunk@57 105869f7-3296-0410-a4ea-f4349344b45a
* Correct commenteschnett2012-04-02
| | | | git-svn-id: https://svn.cct.lsu.edu/repos/numrel/LSUThorns/Vectors/trunk@56 105869f7-3296-0410-a4ea-f4349344b45a
* Implement asin, sinh, asinh, and friendseschnett2012-04-02
| | | | git-svn-id: https://svn.cct.lsu.edu/repos/numrel/LSUThorns/Vectors/trunk@55 105869f7-3296-0410-a4ea-f4349344b45a
* Add missing casts.barry.wardell2012-03-02
| | | | git-svn-id: https://svn.cct.lsu.edu/repos/numrel/LSUThorns/Vectors/trunk@54 105869f7-3296-0410-a4ea-f4349344b45a
* Add missing functionality for single precision unvectorised architecture.barry.wardell2012-03-02
| | | | git-svn-id: https://svn.cct.lsu.edu/repos/numrel/LSUThorns/Vectors/trunk@53 105869f7-3296-0410-a4ea-f4349344b45a
* Add tolerance to test caseseschnett2012-02-06
| | | | git-svn-id: https://svn.cct.lsu.edu/repos/numrel/LSUThorns/Vectors/trunk@52 105869f7-3296-0410-a4ea-f4349344b45a
* Implement missing functionalityeschnett2012-02-06
| | | | git-svn-id: https://svn.cct.lsu.edu/repos/numrel/LSUThorns/Vectors/trunk@51 105869f7-3296-0410-a4ea-f4349344b45a
* Make macro arguments safeeschnett2012-02-06
| | | | git-svn-id: https://svn.cct.lsu.edu/repos/numrel/LSUThorns/Vectors/trunk@50 105869f7-3296-0410-a4ea-f4349344b45a
* Correct test case for partial vector storeseschnett2012-02-05
| | | | git-svn-id: https://svn.cct.lsu.edu/repos/numrel/LSUThorns/Vectors/trunk@49 105869f7-3296-0410-a4ea-f4349344b45a
* Correct partial vector storeseschnett2012-02-05
| | | | git-svn-id: https://svn.cct.lsu.edu/repos/numrel/LSUThorns/Vectors/trunk@48 105869f7-3296-0410-a4ea-f4349344b45a
* Various changeseschnett2012-02-05
| | | | | | | | | | | | | | | 1. Implement a simplified partial store interface Implement vec_store_nta_partial, which offers a simpler interface, similar to the one used in OpenCL. 2. Add kifmsg function, and implement kifpos and kifneg in terms of this. 3. Update (and make safer) Kranc-specific code git-svn-id: https://svn.cct.lsu.edu/repos/numrel/LSUThorns/Vectors/trunk@47 105869f7-3296-0410-a4ea-f4349344b45a
* Make building with the Vectors thorn quietereschnett2012-01-04
| | | | git-svn-id: https://svn.cct.lsu.edu/repos/numrel/LSUThorns/Vectors/trunk@46 105869f7-3296-0410-a4ea-f4349344b45a
* Translate Kranc's Pi to M_PIeschnett2012-01-02
| | | | git-svn-id: https://svn.cct.lsu.edu/repos/numrel/LSUThorns/Vectors/trunk@45 105869f7-3296-0410-a4ea-f4349344b45a
* Make vectorisation macros safereschnett2011-12-22
| | | | git-svn-id: https://svn.cct.lsu.edu/repos/numrel/LSUThorns/Vectors/trunk@44 105869f7-3296-0410-a4ea-f4349344b45a
* Output more information in test case failure error messageseschnett2011-12-21
| | | | git-svn-id: https://svn.cct.lsu.edu/repos/numrel/LSUThorns/Vectors/trunk@43 105869f7-3296-0410-a4ea-f4349344b45a
* Simplify setting architecture description stringseschnett2011-12-21
| | | | git-svn-id: https://svn.cct.lsu.edu/repos/numrel/LSUThorns/Vectors/trunk@42 105869f7-3296-0410-a4ea-f4349344b45a
* Implement sqrteschnett2011-12-21
| | | | git-svn-id: https://svn.cct.lsu.edu/repos/numrel/LSUThorns/Vectors/trunk@41 105869f7-3296-0410-a4ea-f4349344b45a
* Don't use <x86intrin.h>; this does not exist everywhereeschnett2011-12-15
| | | | git-svn-id: https://svn.cct.lsu.edu/repos/numrel/LSUThorns/Vectors/trunk@40 105869f7-3296-0410-a4ea-f4349344b45a
* Support FMA4 instructions (AMD's fused multiply-add)eschnett2011-12-14
| | | | git-svn-id: https://svn.cct.lsu.edu/repos/numrel/LSUThorns/Vectors/trunk@39 105869f7-3296-0410-a4ea-f4349344b45a
* LSUThorns/Vectors: Remove pos, add sin/cos/tan functionseschnett2011-12-02
| | | | | | | | | | | | Remove kpos, because it is not used (it is a no-op, i.e. the arithmetic + operator). Add sin, cos, and tan. Begin to implement (still commented out) integer vector operations. git-svn-id: https://svn.cct.lsu.edu/repos/numrel/LSUThorns/Vectors/trunk@38 105869f7-3296-0410-a4ea-f4349344b45a
generated by cgit v1.2.3 (git 2.39.1) at 2024-05-02 05:55:44 +0000