~tslil/ctak

48665b2ab507a5c87ed537dd502f9fe83031b1e9 — tslil clingman 1 year, 1 month ago c2ffe02 master
--fast-math seems saves some time

That i can tell at a glance, the largest relevant change this
introduces is flush-to-zero for floats. Some testing is required to
ensure that the CNN isn't too sensitive to this. Preferable to that
option is to simply train it without relying on subnormal floats in
the first place.
1 files changed, 1 insertions(+), 1 deletions(-)

M Makefile
M Makefile => Makefile +1 -1
@@ 1,6 1,6 @@
IDIR=include
DEFINES=-DDETERMINISTIC
CFLAGS=-O3 -Wall -Wextra -Wpedantic -std=c99 -D_DEFAULT_SOURCE $(DEFINES) -I$(IDIR)
CFLAGS=-O3 --fast-math -Wall -Wextra -Wpedantic -std=c99 -D_DEFAULT_SOURCE $(DEFINES) -I$(IDIR)

CTAK=include/tak.c
CTAK_OBJS=$(CTAK:.c=.o)