141 Commits (d8ba46efdb2ba06ca5f021cda2d49ea60ff0e694)

Author SHA1 Message Date
  wernsaar d8ba46efdb bugfix for bulldozer cgemm-, zgemm- and zgemv-kernel 12 years ago
  wernsaar a15f22a1f6 bugfix for piledriver cgemm-, zgemm- and zgemv-kernel 12 years ago
  wernsaar b94ea89f52 bugfix for haswell cgemm- and zgemm-kernel 12 years ago
  wernsaar 35f668bb14 bugfix for cgemm_kernel_8x2_sandy.S 12 years ago
  wernsaar 365e8de346 added optimized cgemm-kernel for SANDYBRIDGE 12 years ago
  wernsaar 578d1b6219 added DSDOT definition and enabled optimized sdot kernel 12 years ago
  wernsaar dabab2b5f4 added new optimized sgemm kernel for SANDYBRIGE 12 years ago
  wernsaar aa2709c4e0 enabled optimized dgemm kernel for NEHALEM 12 years ago
  wernsaar a13bcc1716 enabled optimized sgemv kernel for barcelona and piledriver 12 years ago
  wernsaar d2c82d7543 enabled optimized sgemv kernel for HASWELL 12 years ago
  wernsaar 0517672dd0 enabled optimized sgemv kernels for nehalem, sandybridge and bulldozer 12 years ago
  wernsaar 23203d52c1 Ref #380: lowered stack usage for haswell kernels 12 years ago
  wernsaar 73545a79cd Ref #380: lowered stack usage for piledriver and bulldozer kernels 12 years ago
  wernsaar 5f3b68b4d4 replaced sgemm and cgemm kernels because lapack bugs 12 years ago
  wernsaar 2424af62fd replaced dgemm-kernel because bug in lapack 12 years ago
  wernsaar 793509a3b5 replaced files for sdot, sgemv_n and sgemv_t for bug #348 12 years ago
  wernsaar 47b22763f8 reduced stack usage on windows to 16K 12 years ago
  Zhang Xianyi 9a557e90da Refs #340. Fixed SEGFAULT bug of dgemv_n on OSX. 12 years ago
  wangqian 2d557eb1e0 Fixed computational error of dgemv_n. 12 years ago
  Zhang Xianyi 05bb391c3a Refs #330. Fixed the compatible issue with clang on Mac OSX. 12 years ago
  Zhang Xianyi 9b5be29886 Refs #310. Fixed Segfault bug on nehalem when Julia calling dgeqrt3 on OSX. 12 years ago
  wernsaar 034a5b2083 modified zsymv 12 years ago
  wernsaar 27d4234d4d merged symv 12 years ago
  wernsaar b3254eecaf Merge remote branch 'origin/haswell' into develop 12 years ago
  wernsaar 0b6e13b689 Merge remote branch 'origin/develop' into haswell 12 years ago
  wernsaar e09dc279a2 Merge remote branch 'origin/develop' into piledriver 12 years ago
  wernsaar 5c648a8984 Merge remote branch 'origin/develop' into haswell 12 years ago
  wernsaar c44dc4dd3c Merge remote branch 'origin/develop' into piledriver 12 years ago
  wernsaar f1db386211 changes for compatibility with Pathscale compiler 12 years ago
  wernsaar 6da558d2ab changes for compatibility with Pathscale compiler 12 years ago
  Zhang Xianyi 2f5fdd2000 Refs #314. Fixed clang compiling bug on OSX. 12 years ago
  wernsaar 5118a7f4d1 small optimizations on dgemm_kernel for Piledriver 12 years ago
  wernsaar e172b70ea2 added cgemm_kernel for Piledriver 12 years ago
  wernsaar 1cf4b974b2 added zgemm_kernel for Piledriver 12 years ago
  wernsaar 7bccff1512 added sgemm_kernel for PILEDRIVER 12 years ago
  wernsaar afe44b0241 tests and code cleanup of gemm_kernels for HASWELL 12 years ago
  wernsaar a77c71eaf5 added highly optimized dgemm_kernel for HASWELL 12 years ago
  wernsaar fe8c5666f9 optimized dgemm_kernel for HASWELL 12 years ago
  wernsaar f6b50057e2 corrected and testet FMA3 Code 12 years ago
  wernsaar 2840d56aeb added dgemm_kernel for Piledriver 12 years ago
  wangqian beffee7d91 Fixed buffer overflow bug in kernel/x86_64/dgemv_t.S file. 12 years ago
  Zhang Xianyi 6c4a7d0828 Import AMD Piledriver DGEMM kernel generated by AUGEM. 12 years ago
  wernsaar 067e8417fd removed unnessesary instructions from zgemm_kernel_2x2_bulldozer.S 12 years ago
  wernsaar a82da3d069 removed unnessesary instructions 12 years ago
  Zhang Xianyi 1569bf14f8 Refs #282. Fixed zgemv_n typo bug on Win64. 12 years ago
  Zhang Xianyi f51a849d91 Merge pull request #278 from wernsaar/haswell 12 years ago
  wernsaar 44ef70420c added cgemm_kernel_8x2_haswell.S 12 years ago
  wernsaar d488b1b1aa added zgemm_kernel_4x2_haswell.S 12 years ago
  wernsaar 2b8ab8f55b sgemm_kernel_16x4_haswell.S minor changes 12 years ago
  wernsaar 1cb9579cd0 added zgemm_kernel_4x2_haswell.S and fixed a bug in sgemm_kernel_16x4_haswell.S 12 years ago