[Numpy-discussion] Re: [RFC] - numpy/SVML appears to be poorly optimized

2021-11-06 Thread Noah Goldstein
> > Raghuveer > > -Original Message----- > From: Noah Goldstein > Sent: Thursday, November 4, 2021 10:46 AM > To: numpy-discussion@python.org > Subject: [Numpy-discussion] [RFC] - numpy/SVML appears to be poorly optimized > > The numpy SVML library: https://github.com/n

[Numpy-discussion] [RFC] - numpy/SVML appears to be poorly optimized

2021-11-05 Thread Noah Goldstein
The numpy SVML library: https://github.com/numpy/SVML appears to be poorly optimized. Since its just the raw assembly dump this also makes it quite difficult to improve (with either a better compiler or by hand). Some of the glaring issues are: 1. register allocation / spilling 2. rodata layouts