Enable register spilling to shared memory#1132
Enable register spilling to shared memory#1132stephenswat wants to merge 1 commit intoacts-project:mainfrom
Conversation
|
|
I'm not 100% certain this works as intended like this, as this pragma is to be attached at the function scope. But we can try. |
|
This is interesting as we are not actively using the shared memory in our finding and fitting kernels. |
stephenswat
force-pushed
the
perf/spill_to_smem
branch
from
13238d6 to
2e6b339
Compare
|
This comment was marked as outdated.
This comment was marked as outdated.
stephenswat
force-pushed
the
perf/spill_to_smem
branch
2 times, most recently
from
d9595e0 to
8c1878e
Compare
CUDA 13.0 enables the PTX assembler to spill registers to shared memory instead of local memory, which should both be much faster, and also reduce the local memory usage of our fitting and finding kernels which are currently bottlenecking our throughput.
stephenswat
force-pushed
the
perf/spill_to_smem
branch
from
8c1878e to
b22a9c4
Compare
|
2 participants
CUDA 13.0 enables the PTX assembler to spill registers to shared memory instead of local memory, which should both be much faster, and also reduce the local memory usage of our fitting and finding kernels which are currently bottlenecking our throughput.