facebookresearch / deepfloat
An exploration of log domain "alternative floating point" for hardware ML/AI accelerators.
Summary
   |
|||
| Main Code: 35,818 LOC (321 files) = SV (73%) + H (10%) + CPP (7%) + CL (4%) + PY (4%) Secondary code: Test: 0 LOC (0); Generated: 0 LOC (0); Build & Deploy: 133 LOC (4); Other: 69 LOC (3); |
|||
| Duplication: 18% | |||
| File Size: 17% long (>1000 LOC), 52% short (<= 200 LOC) | |||
| Unit Size: 8% long (>100 LOC), 71% short (<= 10 LOC) | |||
| Conditional Complexity: 8% complex (McCabe index > 50), 69% simple (McCabe index <= 5) | |||
|
|
Logical Component Decomposition: primary (13 components) | ||
|
|
3 years, 2 months old
|
||
|
|
0% 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
66 files |
|||
Latest commit date: 2018-11-29
|
0
commits
(30 days)
0
contributors
(30 days) |
|