DeepSpeed
Reduction Kernel Utility
#2436
Merged

Reduction Kernel Utility #2436

cmikeh2 merged 10 commits into master from cholmes/reduction-utils
cmikeh2
cmikeh2 Initial reduction_utils.h implementation
4312d089
cmikeh2 cmikeh2 requested a review from jeffra jeffra 2 years ago
cmikeh2 cmikeh2 requested a review from samyam samyam 2 years ago
cmikeh2 cmikeh2 requested a review from tjruwase tjruwase 2 years ago
cmikeh2 cmikeh2 requested a review from ShadenSmith ShadenSmith 2 years ago
cmikeh2 cmikeh2 requested a review from conglongli conglongli 2 years ago
cmikeh2 cmikeh2 requested a review from awan-10 awan-10 2 years ago
cmikeh2 cmikeh2 requested a review from cli99 cli99 2 years ago
cmikeh2 cmikeh2 requested a review from eltonzheng eltonzheng 2 years ago
cmikeh2 cmikeh2 requested a review from minjiaz minjiaz 2 years ago
cmikeh2 cmikeh2 requested a review from RezaYazdaniAminabadi RezaYazdaniAminabadi 2 years ago
cmikeh2 cmikeh2 requested a review from duli2012 duli2012 2 years ago
cmikeh2 cmikeh2 requested a review from mrwyattii mrwyattii 2 years ago
cmikeh2 cmikeh2 requested a review from yaozhewei yaozhewei 2 years ago
cmikeh2 cmikeh2 requested a review from arashb arashb 2 years ago
cmikeh2 cmikeh2 requested a review from xiaoxiawu-microsoft xiaoxiawu-microsoft 2 years ago
cmikeh2 cmikeh2 requested a review from samadejacobs samadejacobs 2 years ago
cmikeh2 cmikeh2 requested a review from GuanhuaWang GuanhuaWang 2 years ago
cmikeh2 Add initialization helper, ensures correct min/max behavior
ce90a56e
cmikeh2 Remove unnecessary warp sync
157b1a93
RezaYazdaniAminabadi
RezaYazdaniAminabadi approved these changes on 2022-10-21
RezaYazdaniAminabadi
cmikeh2
cmikeh2 cmikeh2 enabled auto-merge (squash) 2 years ago
cmikeh2 Merge branch 'master' into cholmes/reduction-utils
08af28fa
cmikeh2 Add element reduction, partioned_block reduction
d5ca7969
cmikeh2 Merge branch 'cholmes/reduction-utils' of github.com:microsoft/DeepSp…
a1884ce2
cmikeh2 Simplify partitioned_block
20ccea78
cmikeh2 Enable subwarp reductions from partitioned_block
0e505b7e
cmikeh2 Fix singleton reduction
a6ec20c7
cmikeh2 Merge branch 'master' into cholmes/reduction-utils
ccbe5d68
cmikeh2 cmikeh2 merged be4ffb82 into master 2 years ago
cmikeh2 cmikeh2 deleted the cholmes/reduction-utils branch 2 years ago

Login to write a write a comment.

Login via GitHub