Make all fp16 routines work with fp32 as input instead of fp64, since that is what...
authorSteinar H. Gunderson <sgunderson@bigfoot.com>
Fri, 15 Jan 2016 23:57:00 +0000 (00:57 +0100)
committerSteinar H. Gunderson <sgunderson@bigfoot.com>
Sat, 16 Jan 2016 00:10:56 +0000 (01:10 +0100)
commit35ab97543afb74f72dd1d4c0d7d3206efe867a5e
tree2485d46212c8c5632281134bc4f0a8b9f58d64d6
parent0830ff087940468a6601b12e6bea8893b722ddcb
Make all fp16 routines work with fp32 as input instead of fp64, since that is what hardware supports anyway.
fft_input.cpp
fft_pass_effect.cpp
fp16.cpp
fp16.h
fp16_test.cpp
resample_effect.cpp
util.cpp