Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

More aggressive vectorization of Weighted #11

Merged
merged 8 commits into from
Oct 10, 2022
Merged

More aggressive vectorization of Weighted #11

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
d5a46ff
More aggressive vectorization of UnnormalizedWeighted, using popcnt
sfiligoi Oct 7, 2022
84ad995
Add protection for other platforms
sfiligoi Oct 7, 2022
07fa2fe
Simplify loops to minimize overhead
sfiligoi Oct 7, 2022
0ad9a77
Increase step_size to make better use of vectorization
sfiligoi Oct 7, 2022
cae19a5
Enable AVX on MacOS build and use c++17
sfiligoi Oct 7, 2022
ad8854f
Revert to c++14, since c++17 deprecated std::ptr_fun
sfiligoi Oct 7, 2022
fcaa3a3
Check on AVX not SSE, as popcnt is not part of base SSE
sfiligoi Oct 7, 2022
42460d8
More aggressive vectorization of NormalizedWeighted
sfiligoi Oct 7, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions src/Makefile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -72,9 +72,9 @@ ifneq (,$(findstring pgi,$(COMPILER)))
endif
else
ifeq ($(PERFORMING_CONDA_BUILD),True)
CPPFLAGS += -mtune=generic
CPPFLAGS += -mtune=generic -mavx
else
CPPFLAGS += -mfma -march=native
CPPFLAGS += -mavx -mfma -march=native
endif
endif

Expand All @@ -86,7 +86,7 @@ endif
BLASLIB=-llapacke -lcblas


CPPFLAGS += -Wall -std=c++11 -pedantic -I. $(OPT) -fPIC -L$(PREFIX)/lib
CPPFLAGS += -Wall -std=c++14 -pedantic -I. $(OPT) -fPIC -L$(PREFIX)/lib

all: api main install

Expand Down
Loading