We measure \lambda _ { R _ { e } } , a proxy for galaxy specific stellar angular momentum within one effective radius , and the ellipticity , \epsilon , for about 2300 galaxies of all morphological types observed with integral field spectroscopy as part of the MaNGA survey , the largest such sample to date .
We use the ( \lambda _ { R _ { e } } , \epsilon ) diagram to separate early-type galaxies into fast and slow rotators .
We also visually classify each galaxy according to its optical morphology and two-dimensional stellar velocity field .
Comparing these classifications to quantitative \lambda _ { R _ { e } } measurements reveals tight relationships between angular momentum and galaxy structure .
In order to account for atmospheric seeing , we use realistic models of galaxy kinematics to derive a general approximate analytic correction for \lambda _ { R _ { e } } .
Thanks to the size of the sample and the large number of massive galaxies , we unambiguously detect a clear bimodality in the ( \lambda _ { R _ { e } } , \epsilon ) diagram which may result from fundamental differences in galaxy assembly history .
There is a sharp secondary density peak inside the region of the diagram with low \lambda _ { R _ { e } } and \epsilon < 0.4 , previously suggested as the definition for slow rotators .
Most of these galaxies are visually classified as non-regular rotators and have high velocity dispersion .
The intrinsic bimodality must be stronger , as it tends to be smoothed by noise and inclination .
The large sample of slow rotators allows us for the first time to unveil a secondary peak at \pm 90 \degree in their distribution of the misalignments between the photometric and kinematic position angles .
We confirm that genuine slow rotators start appearing above a stellar mass of 2 \times 10 ^ { 11 } M _ { \odot } where a significant number of high-mass fast rotators also exist .