summaryrefslogtreecommitdiffstats
path: root/vecmathlib.h
Commit message (Expand)AuthorAgeFilesLines
* Add VSX double support for POWER8Timothy Pearson2015-12-211-1/+5
* Initial fixes for POWER8 and GCCTimothy Pearson2015-12-211-1/+1
* Report AVX2 capabilities in capability stringErik Schnetter2015-11-141-1/+6
* Reformat source code with clang-formatErik Schnetter2015-10-161-129/+119
* Rename “automatic” vector types from float/double to float32/float64 for ...Erik Schnetter2013-11-251-12/+12
* Only enable builtin vectors when clang is usedErik Schnetter2013-11-251-1/+3
* Provide vector types implemented via (scalar) compiler builtinsErik Schnetter2013-09-091-2/+1
* SSE: Check whether abs/max/min are available as intrinsics before using themErik Schnetter2013-09-021-1/+6
* Correct auto-detecting VSXErik Schnetter2013-09-021-1/+1
* Provide a string describing the configuration optionsErik Schnetter2013-08-261-1/+71
* Correct detecting ARM NEON intrinsicsErik Schnetter2013-08-201-2/+2
* Provide trivial fallback "best vector" if no "best vector" is availableErik Schnetter2013-08-201-14/+22
* Begin to add MIC supportErik Schnetter2013-08-191-1/+4
* Simplify example, add commentsErik Schnetter2013-07-281-0/+40
* Implement maxval and minval reduction operationsErik Schnetter2013-07-041-1/+0
* Clarify that we won't change rounding modes during optimizationErik Schnetter2013-07-031-1/+1
* Suggest implementing minval and maxval reductionsErik Schnetter2013-07-031-0/+1
* Denormalized numbers are not yer properly supportedErik Schnetter2013-07-031-1/+1
* Turn cpp warnings into TODO itemsErik Schnetter2013-07-031-3/+3
* Choose FP conformance settings automatically depending on fast-mathErik Schnetter2013-07-021-5/+22
* Explain what VML_HAVE_FP_CONTRACT meansErik Schnetter2013-06-201-1/+7
* Explain why vec_builtin doesn't workErik Schnetter2013-06-171-0/+1
* Introduce VML_HAVE_FP_CONTRACT (still unused)Erik Schnetter2013-06-171-0/+1
* Support NEON float32x4_tErik Schnetter2013-06-171-1/+1
* Rename implementation files to indicate vector sizeErik Schnetter2013-06-171-13/+16
* Correct NEON detectionErik Schnetter2013-06-121-1/+1
* Begin to implement ARM NEONErik Schnetter2013-06-121-0/+5
* Suggest some additional vector architecturesErik Schnetter2013-06-121-1/+4
* Initial implementation of QPX (Blue Gene/Q) supportErik Schnetter2013-06-041-0/+4
* Implement VSX supportErik Schnetter2013-06-021-6/+6
* Put url in comment into angle bracketsErik Schnetter2013-06-021-1/+1
* Begin to add Altivec support (work in progress)Erik Schnetter2013-04-201-0/+5
* Correct handling Debian 6.0Erik Schnetter2013-03-231-2/+5
* Re-instate typeinfo work-around for Debian 6.0Erik Schnetter2013-03-221-0/+10
* We handle signed zeros correctlyErik Schnetter2013-03-211-1/+1
* Introduce "builtin" vectors (still disabled)Erik Schnetter2013-03-151-3/+7
* Provide vector types with 8 and 16 bit precisionErik Schnetter2013-02-191-9/+5
* Clean up vector classesErik Schnetter2013-02-141-6/+15
* Introduce VML_NODEBUGErik Schnetter2013-02-141-1/+8
* Activate #defines handling IEEE complianceErik Schnetter2013-02-051-4/+4
* Add flag VML_DEBUGErik Schnetter2013-02-041-4/+16
* Add new template {bool|int|real}pseudovec that scalarizes all operationsErik Schnetter2013-02-031-0/+2
* Add fdim fmax fmin, fma, isfinite isinf isnan isnormalErik Schnetter2012-12-181-0/+5
* Support more SSE and AVX vector typesErik Schnetter2012-12-021-0/+10
* Improve tests, correct errors foundErik Schnetter2012-12-011-0/+1
* Import initial versionErik Schnetter2012-11-301-0/+11
OpenPOWER on IntegriCloud