diff options
author | Konsta Holtta <kholtta@nvidia.com> | 2016-09-12 05:37:30 -0400 |
---|---|---|
committer | mobile promotions <svcmobile_promotions@nvidia.com> | 2016-10-17 17:39:00 -0400 |
commit | a8e260bc8dcc0ce9efe622f01ff9a1b2db24f8df (patch) | |
tree | 88c40719282c4d77b00d7514f167a6395cf7075c /drivers/gpu/nvgpu/gm20b | |
parent | 718af968f056cb1bdf5b57e1ce9957720d6053a4 (diff) |
gpu: nvgpu: allow skipping pramin barriers
A wmb() next to each gk20a_mem_wr32() via PRAMIN may be overly careful,
so support not inserting these barriers for performance, in cases where
they are not necessary, where the caller would do an explicit barrier
after a bunch of reads.
Also, move those optional wmb()s to be done at the end of the whole
internally batched write for gk20a_mem_{wr_n,memset} from the per-batch
subloops that may run multiple times.
Jira DNVGPU-23
Change-Id: I61ee65418335863110bca6f036b2e883b048c5c2
Signed-off-by: Konsta Holtta <kholtta@nvidia.com>
Reviewed-on: http://git-master/r/1225149
(cherry picked from commit d2c40327d1995f76e8ab9cb4cd8c76407dabc6de)
Reviewed-on: http://git-master/r/1227474
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Diffstat (limited to 'drivers/gpu/nvgpu/gm20b')
0 files changed, 0 insertions, 0 deletions