gpu-compute: support in-order data delivery in GM pipe
Review Request #3658 - Created Oct. 10, 2016 and submitted
| Information | |
|---|---|
| Tony Gutierrez | |
| gem5 | |
| default | |
| Reviewers | |
| Default | |
Changeset 11683:e48e281afdd8 --------------------------- gpu-compute: support in-order data delivery in GM pipe this patch adds an ordered response buffer to the GM pipeline to ensure in-order data delivery. the buffer is implemented as a stl ordered map, which sorts the request in program order by using their sequence ID. when requests return to the GM pipeline they are marked as done. only the oldest request may be serviced from the ordered buffer, and only if is marked as done. the FIFO response buffers are kept and used in OoO delivery mode
Posted (Oct. 18, 2016, 3:17 p.m.)
Any comments? I'm planning on shipping this soon.
Neat refactoring! Other than the python arg name, this looks good to me.
-
configs/example/apu_se.py (Diff revision 1) -
Shouldn't we stick to the dash naming style instead of camel case?
-
src/gpu-compute/global_memory_pipeline.hh (Diff revision 1) -
Neat fix! The next two methods should also go away, however that is not something to be considered for this patch.