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

Rationalize compute capability arguments in makefiles #3

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Rationalize compute capability arguments in makefiles #3

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
19 changes: 6 additions & 13 deletions src/Makefile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,20 +15,13 @@ NVCCFLAGS = $(CUDA_INCLUDE) --ptxas-options=-v
# generate code for various compute capabilities
# NVCCFLAGS += --generate-code arch=compute_11,code=sm_11 # CC 1.1, 1.2 and 1.3 GPUs will use this code (1.0 is not possible for mfaktc)
# NVCCFLAGS += --generate-code arch=compute_20,code=sm_20 # CC 2.x GPUs will use this code, one code fits all!
# NVCCFLAGS += --generate-code arch=compute_30,code=sm_30 # all CC 3.x GPUs _COULD_ use this code
# NVCCFLAGS += --generate-code arch=compute_30,code=sm_30 # all CC 3.x GPUs _COULD_ use this code
# NVCCFLAGS += --generate-code arch=compute_35,code=sm_35 # but CC 3.5 (3.2?) _CAN_ use funnel shift which is useful for mfaktc
# NVCCFLAGS += --generate-code arch=compute_50,code=sm_50 # CC 5.x GPUs will use this code
NVCCFLAGS += --generate-code arch=compute_60,code=sm_60
NVCCFLAGS += --generate-code arch=compute_61,code=sm_61
NVCCFLAGS += --generate-code arch=compute_62,code=sm_62
NVCCFLAGS += --generate-code arch=compute_70,code=sm_70
NVCCFLAGS += --generate-code arch=compute_72,code=sm_72
NVCCFLAGS += --generate-code arch=compute_75,code=sm_75
NVCCFLAGS += --generate-code arch=compute_80,code=sm_80
NVCCFLAGS += --generate-code arch=compute_86,code=sm_86
NVCCFLAGS += --generate-code arch=compute_87,code=sm_87
NVCCFLAGS += --generate-code arch=compute_89,code=sm_89
NVCCFLAGS += --generate-code arch=compute_90,code=sm_90
NVCCFLAGS += --generate-code arch=compute_50,code=sm_50 # CC 5.x GPUs will use this code
NVCCFLAGS += --generate-code arch=compute_60,code=sm_60 # CC 6.x GPUs will use this code
NVCCFLAGS += --generate-code arch=compute_70,code=sm_70 # CC 7.x GPUs will use this code
NVCCFLAGS += --generate-code arch=compute_80,code=sm_80 # CC 8.x GPUs will use this code
NVCCFLAGS += --generate-code arch=compute_90,code=sm_90 # CC 9.x GPUs will use this code

# pass some options to the C host compiler (e.g. gcc on Linux)
NVCCFLAGS += --compiler-options=-Wall
Expand Down
21 changes: 10 additions & 11 deletions src/Makefile.win
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,17 +8,16 @@ CUFLAGS = -DWIN64 -Xcompiler /EHsc,/W3,/nologo,/Ox $(NVCCFLAGS)

############################################################

NVCCFLAGS += --generate-code arch=compute_60,code=sm_60
NVCCFLAGS += --generate-code arch=compute_61,code=sm_61
NVCCFLAGS += --generate-code arch=compute_62,code=sm_62
NVCCFLAGS += --generate-code arch=compute_70,code=sm_70
NVCCFLAGS += --generate-code arch=compute_72,code=sm_72
NVCCFLAGS += --generate-code arch=compute_75,code=sm_75
NVCCFLAGS += --generate-code arch=compute_80,code=sm_80
NVCCFLAGS += --generate-code arch=compute_86,code=sm_86
NVCCFLAGS += --generate-code arch=compute_87,code=sm_87
NVCCFLAGS += --generate-code arch=compute_89,code=sm_89
NVCCFLAGS += --generate-code arch=compute_90,code=sm_90
# generate code for various compute capabilities
# NVCCFLAGS += --generate-code arch=compute_11,code=sm_11 # CC 1.1, 1.2 and 1.3 GPUs will use this code (1.0 is not possible for mfaktc)
# NVCCFLAGS += --generate-code arch=compute_20,code=sm_20 # CC 2.x GPUs will use this code, one code fits all!
# NVCCFLAGS += --generate-code arch=compute_30,code=sm_30 # all CC 3.x GPUs _COULD_ use this code
# NVCCFLAGS += --generate-code arch=compute_35,code=sm_35 # but CC 3.5 (3.2?) _CAN_ use funnel shift which is useful for mfaktc
NVCCFLAGS += --generate-code arch=compute_50,code=sm_50 # CC 5.x GPUs will use this code
NVCCFLAGS += --generate-code arch=compute_60,code=sm_60 # CC 6.x GPUs will use this code
NVCCFLAGS += --generate-code arch=compute_70,code=sm_70 # CC 7.x GPUs will use this code
NVCCFLAGS += --generate-code arch=compute_80,code=sm_80 # CC 8.x GPUs will use this code
NVCCFLAGS += --generate-code arch=compute_90,code=sm_90 # CC 9.x GPUs will use this code

############################################################

Expand Down
6 changes: 5 additions & 1 deletion src/Makefile.win32
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,9 +9,13 @@ CUFLAGS = -ccbin="C:\Program Files (x86)\Microsoft Visual Studio 11.0\VC\bin" -X
# generate code for various compute capabilities
NVCCFLAGS += --generate-code arch=compute_11,code=sm_11 # CC 1.1, 1.2 and 1.3 GPUs will use this code (1.0 is not possible for mfaktc)
NVCCFLAGS += --generate-code arch=compute_20,code=sm_20 # CC 2.x GPUs will use this code, one code fits all!
NVCCFLAGS += --generate-code arch=compute_30,code=sm_30 # all CC 3.x GPUs _COULD_ use this code
NVCCFLAGS += --generate-code arch=compute_30,code=sm_30 # all CC 3.x GPUs _COULD_ use this code
NVCCFLAGS += --generate-code arch=compute_35,code=sm_35 # but CC 3.5 (3.2?) _CAN_ use funnel shift which is useful for mfaktc
NVCCFLAGS += --generate-code arch=compute_50,code=sm_50 # CC 5.x GPUs will use this code
# NVCCFLAGS += --generate-code arch=compute_60,code=sm_60 # CC 6.x GPUs will use this code
# NVCCFLAGS += --generate-code arch=compute_70,code=sm_70 # CC 7.x GPUs will use this code
# NVCCFLAGS += --generate-code arch=compute_80,code=sm_80 # CC 8.x GPUs will use this code
# NVCCFLAGS += --generate-code arch=compute_90,code=sm_90 # CC 9.x GPUs will use this code

LINK = link
LFLAGS = /nologo /LTCG #/ltcg:pgo
Expand Down