diff options
Diffstat (limited to 'bench/perf_monitoring/gemm/changesets.txt')
| -rw-r--r-- | bench/perf_monitoring/gemm/changesets.txt | 67 |
1 files changed, 35 insertions, 32 deletions
diff --git a/bench/perf_monitoring/gemm/changesets.txt b/bench/perf_monitoring/gemm/changesets.txt index f19b4287d..b379d7bd2 100644 --- a/bench/perf_monitoring/gemm/changesets.txt +++ b/bench/perf_monitoring/gemm/changesets.txt @@ -1,39 +1,42 @@ -3.0.1 -3.1.1 -3.2.0 +#3.0.1 +#3.1.1 +#3.2.0 3.2.4 -5745:37f59e65eb6c -5891:d8652709345d -5893:24b4dc92c6d3 -5895:997c2ef9fc8b -5904:e1eafd14eaa1 -5908:f8ee3c721251 -5921:ca808bb456b0 -5927:8b1001f9e3ac -5937:5a4ca1ad8c53 -5949:f3488f4e45b2 -5969:e09031dccfd9 -5992:4a429f5e0483 +#5745:37f59e65eb6c +5891:d8652709345d # introduce AVX +#5893:24b4dc92c6d3 # merge +5895:997c2ef9fc8b # introduce FMA +#5904:e1eafd14eaa1 # complex and AVX +5908:f8ee3c721251 # improve packing with ptranspose +#5921:ca808bb456b0 # merge +#5927:8b1001f9e3ac +5937:5a4ca1ad8c53 # New gebp kernel handling up to 3 packets x 4 register-level blocks +#5949:f3488f4e45b2 # merge +#5969:e09031dccfd9 # Disable 3pX4 kernel on Altivec +#5992:4a429f5e0483 # merge before-evaluators -6334:f6a45e5b8b7c -6639:c9121c60b5c7 -6655:06f163b5221f -6677:700e023044e7 # FMA has been wrongly disabled -6681:11d31dafb0e3 -6699:5e6e8e10aad1 # merge default to tensors -6726:ff2d2388e7b9 # merge default to tensors -6742:0cbd6195e829 # merge default to tensors -6747:853d2bafeb8f # Generalized the gebp apis +#6334:f6a45e5b8b7c # Implement evaluator for sparse outer products +#6639:c9121c60b5c7 +#6655:06f163b5221f # Properly detect FMA support on ARM +#6677:700e023044e7 # FMA has been wrongly disabled +#6681:11d31dafb0e3 +#6699:5e6e8e10aad1 # merge default to tensors +#6726:ff2d2388e7b9 # merge default to tensors +#6742:0cbd6195e829 # merge default to tensors +#6747:853d2bafeb8f # Generalized the gebp apis 6765:71584fd55762 # Made the blocking computation aware of the l3 cache; Also optimized the blocking parameters to take into account the number of threads used for a computation -6781:9cc5a931b2c6 # generalized gemv -6792:f6e1daab600a # ensured that contractions that can be reduced to a matrix vector product -6844:039efd86b75c # merge tensor +#6781:9cc5a931b2c6 # generalized gemv +#6792:f6e1daab600a # ensured that contractions that can be reduced to a matrix vector product +#6844:039efd86b75c # merge tensor 6845:7333ed40c6ef # change prefetching in gebp -6856:b5be5e10eb7f # merge index conversion -6893:c3a64aba7c70 # clean blocking size computation -6898:6fb31ebe6492 # rotating kernel for ARM +#6856:b5be5e10eb7f # merge index conversion +#6893:c3a64aba7c70 # clean blocking size computation +#6898:6fb31ebe6492 # rotating kernel for ARM 6899:877facace746 # rotating kernel for ARM only -6904:c250623ae9fa # result_of +#6904:c250623ae9fa # result_of 6921:915f1b1fc158 # fix prefetching change for ARM 6923:9ff25f6dacc6 # prefetching -6933:52572e60b5d3 # blocking size strategy
\ No newline at end of file +6933:52572e60b5d3 # blocking size strategy +6937:c8c042f286b2 # avoid redundant pack_rhs +6981:7e5d6f78da59 # dynamic loop swapping +6984:45f26866c091 # rm dynamic loop swapping, adjust lhs's micro panel height to fully exploit L1 cache |