You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
This is more of a question than an issue since functionally, all the samples will operate correctly, but I noticed that the invocation to SpdResetAtomicCounter will issue an uncached write on all threads for the last remaining thread group. Is this intentional by any chance? Perhaps because the driver somehow realizes that the value being written is uniform and thus can be coalesced? Or would it have been better to restrict the invocation of SpdResetAtomicCounter to the thread with localInvocationIndex == 0?
The text was updated successfully, but these errors were encountered:
jeremyong
changed the title
SpdResetAtomicCounter issues many 0 writes to the same addressSpdResetAtomicCounter issues many 0-valued uncached writes to the same address
Sep 17, 2023
This is more of a question than an issue since functionally, all the samples will operate correctly, but I noticed that the invocation to
SpdResetAtomicCounter
will issue an uncached write on all threads for the last remaining thread group. Is this intentional by any chance? Perhaps because the driver somehow realizes that the value being written is uniform and thus can be coalesced? Or would it have been better to restrict the invocation ofSpdResetAtomicCounter
to the thread withlocalInvocationIndex == 0
?The text was updated successfully, but these errors were encountered: