Commit message (Collapse) | Author | Age | ||
---|---|---|---|---|
... | ||||
* | | add support for complex | 2010-07-07 | ||
| | | ||||
* | | add intitial support for the vectorization of complex<float> | 2010-07-05 | ||
| | | ||||
| * | check for !x86 platforms, otherwise the BTL benchmark doesn't compile on ↵ | 2010-07-05 | ||
|/ | | | | arm/powerpc | |||
* | Fix cache computation on old Intel CPUs which do not | 2010-06-27 | ||
| | | | | support the cpuid function 0x4 | |||
* | add the manual Intel's way to query cache info | 2010-06-26 | ||
| | ||||
* | add a utilility to debug cpuid, and makes sure we get 0 if we query an ↵ | 2010-06-26 | ||
| | | | | unsupported cpuid function | |||
* | email change | 2010-06-24 | ||
| | ||||
* | add support for oski | 2010-06-24 | ||
| | ||||
* | btl: add a trmm action and update eigen interface | 2010-06-23 | ||
| | ||||
* | add a spmv mini becnhmark for Eigen, GMM++, ublas, mtl4, and oski | 2010-06-22 | ||
| | ||||
* | slightly optimize computeProductBlockingSizes by explicitely precomputing ↵ | 2010-06-22 | ||
| | | | | what is known at compile time | |||
* | fix in case we don't know how to query the L1/L2 cache sizes | 2010-06-21 | ||
| | ||||
* | simplify and optimize block sizes computation for matrix products. They | 2010-06-21 | ||
| | | | | | are now automatically computed from the L1 and L2 cache sizes which are themselves automatically determined at runtime. | |||
* | make bench_gemm print out the queried cache sizes | 2010-06-21 | ||
| | ||||
* | add the possibility to set the cache size at runtime | 2010-06-18 | ||
| | ||||
* | add runtime API to control multithreading | 2010-06-10 | ||
| | ||||
* | make BenchTimer compatible with 2.0 branch | 2010-06-01 | ||
| | ||||
* | remove USING_PART_OF_NAMESPACE_EIGEN, leaving it in Eigen2Support. | 2010-04-22 | ||
| | | | | improve porting-Eigen2-to-3 docs | |||
* | Fixed line endings. | 2010-03-05 | ||
| | ||||
* | add a small program to bench all combinations of small products | 2010-03-05 | ||
| | ||||
* | clean a bit the bench_gemm files | 2010-03-05 | ||
| | ||||
* | minor cleaning | 2010-03-05 | ||
| | ||||
* | merge with default branch | 2010-03-04 | ||
|\ | ||||
| * | clean #defined tokens, and use clock_gettime for the real time | 2010-03-03 | ||
| | | ||||
| * | BenchTimer: avoid warning about symbol redefinition on win32, and include ↵ | 2010-03-02 | ||
| | | | | | | | | <Eigen/Core> (required to compile) | |||
* | | remove Qt's atomic dependency, I don't know what I was doing wrong... | 2010-03-01 | ||
| | | ||||
* | | make Aron's idea work using Qt's atomic implementation for the synchronisation | 2010-03-01 | ||
| | | ||||
* | | BTL: allow to bench real time | 2010-02-26 | ||
| | | ||||
* | | fix some BTL issues | 2010-02-26 | ||
| | | ||||
* | | implement a smarter parallelization strategy for gemm avoiding multiple | 2010-02-26 | ||
| | | | | | | | | paking of the same data | |||
* | | update BTL (better timer, eigen2 => eigen3, etc) | 2010-02-23 | ||
| | | ||||
| * | merge | 2010-02-22 | ||
| |\ | ||||
| | * | provide default values for CXX, remove duplicate define | 2010-02-22 | ||
| | | | ||||
| | * | ups | 2010-02-22 | ||
| | | | ||||
* | | | fix BTL's eigen interface | 2010-02-22 | ||
| | | | | | | | | | | | | | | | (transplanted from 437f40acc1cbd9ce2f2a2a3f413cae3a5b35f8fb ) | |||
* | | | significant speedup in the matrix-matrix products | 2010-02-23 | ||
| | | | ||||
* | | | oops | 2010-02-22 | ||
| | | | ||||
* | | | Port BenchTimer fix. | 2010-02-22 | ||
| | | | ||||
* | | | merge | 2010-02-22 | ||
|\ \ \ | | |/ | |/| | ||||
| * | | Added getRealTime() for windows. | 2010-02-22 | ||
| | | | ||||
* | | | add a small benchmark to quickly bench/compare SMP support | 2010-02-22 | ||
|/ / | ||||
* | | extend the bench timer to allow benchmarking of parallel code, | 2010-02-22 | ||
| | | | | | | | | improvements are welcome | |||
| * | fix BTL's eigen interface | 2010-02-22 | ||
|/ | ||||
* | merge | 2010-02-16 | ||
|\ | ||||
* | | added benchmark for unscaled and half-spectrum FFTs | 2010-01-21 | ||
| | | ||||
| * | extend sparse product benchmark with ublas | 2010-02-09 | ||
|/ | ||||
* | extend benchmark for sparse products | 2010-01-05 | ||
| | ||||
* | Big renaming: | 2010-01-04 | ||
| | | | | | | start ---> head end ---> tail Much frustration with sed syntax. Need to learn perl some day. | |||
* | * Fix bug #79: ei_alignmentOffset was assuming that ptr is multiple of | 2010-01-02 | ||
| | | | | | | | sizeof(Scalar), and that assumption breaks with double on linux x86-32. * Rename ei_alignmentOffset to ei_first_aligned * Rewrite its documentation and part of its body * The variant taking a MatrixBase doesn't need a separate size argument. | |||
* | add a slerp benchmark (for accuracy and speed)) | 2009-12-04 | ||
| |