facebookresearch / DLRM-FlexFlow
Development repository for integrating FlexFlow (A distributed deep learning framework that supports flexible parallelization strategies) with DLRM (Deep Learning Recommendation Model)
Summary
    |
|||
| Main Code: 44,759 LOC (194 files) = CU (39%) + CC (24%) + PY (24%) + H (10%) + CMAKE (<1%) + INC (<1%) + YAML (<1%) + IN (<1%) Secondary code: Test: 2,582 LOC (31); Generated: 0 LOC (0); Build & Deploy: 205 LOC (7); Other: 9,940 LOC (119); |
|||
| Duplication: 45% | |||
| File Size: 28% long (>1000 LOC), 12% short (<= 200 LOC) | |||
| Unit Size: 17% long (>100 LOC), 40% short (<= 10 LOC) | |||
| Conditional Complexity: 13% complex (McCabe index > 50), 56% simple (McCabe index <= 5) | |||
|
|
Logical Component Decomposition: primary (10 components) | ||
|
|
4 years, 5 months old
|
||
|
|
27% of code updated more than 50 times Also see temporal dependencies for files frequently changed in same commits. |
||
| Goals: Keep the system simple and easy to change (4) | |||
|
Features of interest:
TODOs
43 files |
|||
Latest commit date: 2021-06-07
|
0
commits
(30 days)
0
contributors
(30 days) |
|