diff options
| author | Wilson Fung <[email protected]> | 2012-03-29 21:13:54 -0800 |
|---|---|---|
| committer | Andrew Boktor <[email protected]> | 2014-08-14 13:19:05 -0700 |
| commit | 53a2ad0b56960cf22bfe6a89abbcc7c598d79a0e (patch) | |
| tree | 3242fa44d112740469ef53c70be124af233a07e2 | |
| parent | c2235359e7e2dd13372eeb85170a79f0756ed06d (diff) | |
Changing the L1 cache allocation policy to allocation-on-miss.
[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 11828]
| -rw-r--r-- | configs/Fermi/gpgpusim.config | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/configs/Fermi/gpgpusim.config b/configs/Fermi/gpgpusim.config index d8f4d76..b20fe86 100644 --- a/configs/Fermi/gpgpusim.config +++ b/configs/Fermi/gpgpusim.config @@ -25,7 +25,7 @@ # In Fermi, the cache and shared memory can be configured to 16kb:48kb(default) or 48kb:16kb # <nsets>:<bsize>:<assoc>:<rep>:<wr>:<alloc>,<mshr>:<N>:<merge>,<mq> --gpgpu_cache:dl1 32:128:4:L:R:f,A:32:8,8 +-gpgpu_cache:dl1 32:128:4:L:R:m,A:32:8,8 -gpgpu_shmem_size 49152 # The alternative configuration for fermi in case cudaFuncCachePreferL1 is selected |