ademeure 6cbff5778f Correctly flush L2, as reconstructing the tensors on every iteration effectively put them in the L2, and gave the GPU enough idle time to avoid thermal throttling in a potentially unrealistic way. ... The previous behaviour is potentially representative of some use cases (e.g. previous kernel filling L2 with the data in a very specific way) but not standard benchmarking practice.		2025-03-15 20:46:24 +00:00
..
include/deep_gemm	Add some notes for promotion	2025-03-04 11:42:20 +08:00
jit	Code format	2025-03-11 13:26:10 +08:00
jit_kernels	Merge pull request #65 from Z-NAVY/main	2025-03-14 13:50:08 +08:00
__init__.py	fix typo	2025-02-26 18:37:22 +08:00
utils.py	Correctly flush L2, as reconstructing the tensors on every iteration effectively put them in the L2, and gave the GPU enough idle time to avoid thermal throttling in a potentially unrealistic way.	2025-03-15 20:46:24 +00:00