Program CWD TPC and SM registers correctly. The old code did not work
when there are more than 4 TPCs.
Change-Id: I18a14a0f76d97b0962607ec0bbd71aafcd768bca
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/1143075
Reviewed-by: Automatic_Commit_Validation_User
GVS: Gerrit_Virtual_Submit
Reviewed-by: Konsta Holtta <kholtta@nvidia.com>