Way hazard on WAR in dual issue processor #219
Unanswered
StefMassin
asked this question in
Q&A
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
In the dual issue processor a way-hazard occurs for example when running the instructions
As far as I can tell this is due to the following lines:
Ripes/src/processors/RISC-V/rv6s_dual/rv6s_dual_waycontrol.h
Lines 142 to 149 in 1a03ff2
Ripes/src/processors/RISC-V/rv6s_dual/rv6s_dual_waycontrol.h
Lines 69 to 88 in 1a03ff2
Here the
rawHazard()
function will look for a RAW, where way1 writes to one of the sources of way2. I get this would cause problems since the instruction in slot 1 has not written its result, yet slot 2 needs it. However at the same time it also looks for a WAR, sincehazard_1
andhazard_2
are or'd in the return value.Is this intended behaviour? Would a WAR hazard cause incorrect behaviour later in the pipeline and if so, where?
Beta Was this translation helpful? Give feedback.
All reactions