2023 Commits (cd8ac192a901b38980755583faaa35559df7910a)

Author SHA1 Message Date
  Werner Saar 3119def9a7 updated cdot and zdot 10 years ago
  Werner Saar 33b332372a add optimized cdot- and zdot-kernel for sandybridge 10 years ago
  Werner Saar fd838c75bc add optimized cdot- and zdot-kernel for haswell 10 years ago
  Werner Saar b57a60dac8 updated cdot and zdot for piledriver 10 years ago
  Werner Saar 5c51163972 added optimized cdot- and zdot-kernel for steamroller 10 years ago
  Werner Saar 9299d8cfd6 added optimized cdot- and zdot-kernels for bulldozer 10 years ago
  Zhang Xianyi 0a3d3b945d Refs #535. Fix the wrong vector instruction in sgemm sandy bridge kernel. 10 years ago
  Werner Saar 60c6dec6e6 updated some lines for bulldozer 10 years ago
  Werner Saar 47898cca35 added optimized saxpy- and daxpy-kernel for sandybridge 10 years ago
  Werner Saar 53bb924287 added optimized saxpy- and daxpy-kernel for haswell 10 years ago
  Werner Saar a901b065d3 added optimized ddot-kernel for sandybridge 10 years ago
  Werner Saar 3937e2a0a0 add optimized sdot-kernel for sandybridge 10 years ago
  Werner Saar 9707d608d5 removed double definition line 10 years ago
  Werner Saar 701b9d7556 added optimized sdot- and ddot-kernel for HASWELL 10 years ago
  Zhang Xianyi e5b96e55a7 Fix build bug for ARM64. 10 years ago
  Hank Anderson 84d90d6ed8 Fixed some compiler errors/warnings for clang. 10 years ago
  Hank Anderson 518e2424a8 Fixed bad filename for cpuid.S compile. 10 years ago
  Zhang Xianyi ea7f9dacf4 Refs #509. Fixed geadd building bug with DYNAMIC_ARCH=1. 10 years ago
  Hank Anderson 0d8e227ea7 Changed strategy for setting preprocessor definitions. 10 years ago
  Hank Anderson 12d1fb2e40 Fixed incorrect object name in kernel CMakeLists.txt 10 years ago
  Hank Anderson 1b7f427401 Added conj gemv objects for complex build. 10 years ago
  Hank Anderson b2284647a3 More complex objects. 10 years ago
  Hank Anderson a6116e5859 Added some more complex-only objects. 10 years ago
  Hank Anderson 714638c187 Added some TRMM objects for complex types. 10 years ago
  Hank Anderson e27c372e53 Fixed reuse of float_char from parent loop. 10 years ago
  Hank Anderson f3f2b3d768 Added complex and single netlib-lapack fortran sources to lapack.cmake. 10 years ago
  Hank Anderson 9492298048 Added other float types to Makefile.L3. 10 years ago
  Hank Anderson 14fd3d35de Added checks for missing defines in kernel. 10 years ago
  Hank Anderson cebc07cebd ParseMakefileVars now recursively parses included makefiles. 10 years ago
  Hank Anderson 33c5e8db7f Added a helper function for setting the L1 kernel defaults. 10 years ago
  Martin Koehler 39cc6b21d3 Add ATLAS-style ?geadd function 10 years ago
  Hank Anderson 4662a0b13a Changed generate functions to iterate through a list of float types. 10 years ago
  Hank Anderson 162791e30e Added common objects from kernel Makefile. 10 years ago
  Hank Anderson c0624a26be Fixed some dgemm_copy function names. 10 years ago
  Hank Anderson 4bfaf1ce66 Removed some list appends I missed. 10 years ago
  Hank Anderson e8c39138c6 Removed return value from GenerateNamedObjects. 10 years ago
  Hank Anderson f992799226 Added the rest of Makefile.L3. 10 years ago
  Hank Anderson 4c65afcce1 Changed kernel filenames to vars. These will need to be read from KERNEL. 10 years ago
  Hank Anderson 7fa5c4e2fd Fixed some case issues with ARCH. 10 years ago
  Hank Anderson fa0e6a6c93 Added the rest of the L1 kernel makefile. 10 years ago
  Hank Anderson 38681fb1c6 Added more kernel files. 10 years ago
  Hank Anderson 189fadfde0 Started implementing kernel/Makefile in cmake. 10 years ago
  Zhang Xianyi 229ce2ccd1 Add cortex-a9 and cortex-a15 targets. 11 years ago
  Zhang Xianyi 41aad0407f Merge pull request #482 from jeromerobert/develop 11 years ago
  Werner Saar ddf983d643 added optimizations for steamroller 11 years ago
  Werner Saar 4319769b79 added target processor STEAMROLLER 11 years ago
  Jerome Robert e9d9a8eae3 Allow to do gemv and ger buffer allocation on the stack 11 years ago
  Werner Saar 587e16fba3 Ref #458: Backport, sandybrigde uses nehalem zgemm kernel 11 years ago
  Werner Saar 6261342de3 small optimization on dgemm_kernel for N=1 11 years ago
  Werner Saar bc5fff7085 changed inline assembler labels to short form 11 years ago