cpu: allow the fetch buffer to be smaller than a cache line
Review Request #1726 - Created Feb. 18, 2013 and submitted
| Information | |
|---|---|
| Tony Gutierrez | |
| gem5 | |
| default | |
| Reviewers | |
| Default | |
Changeset 9821:9e2898b0e9bd --------------------------- cpu: allow the fetch buffer to be smaller than a cache line the current implementation of the fetch buffer in the o3 cpu is only allowed to be the size of a cache line. some architectures, e.g., ARM, have fetch buffers smaller than a cache line, see slide 22 at: http://www.arm.com/files/pdf/at-exploring_the_design_of_the_cortex-a15.pdf this patch allows the fetch buffer to be set to values smaller than a cache line.
ran several of the shorter SPEC CPU2006 benchmarks with test input. icache.overall_accesses::total stat was validated against real cortex A15 hardware, the value is much closer now. regressions pass
Description: |
|
|---|
Summary: |
|
|---|
Testing Done: |
|
|---|
-
src/cpu/o3/O3CPU.py (Diff revision 1) -
(bytes) at the end of the comment would be great
-
src/cpu/o3/fetch.hh (Diff revision 1) -
Would fetchBufferOffset not be a better description? Perhaps I'm misunderstanding the use...but the word Index doesn't seem to describe what is done.
-
src/cpu/o3/fetch_impl.hh (Diff revision 1) -
warn or even fatal?
-
src/cpu/o3/fetch_impl.hh (Diff revision 1) -
Comments please
Summary: |
|
||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Description: |
|
||||||||||||||||||||||||||||||||||||||||||
Diff: |
Revision 2 (+38) |
Summary: |
|
||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Description: |
|
||||||||||||||||||||||||||||||||||||||||||
Diff: |
Revision 3 (+38) |
LGTM. Nice job...on President's day and all :-)
Description: |
|
|||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Diff: |
Revision 4 (+41) |
this seems fine with me. If you set the buffer size to 64, do you see any statistics changes? If not, feel free to commit.
Summary: |
|
||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Description: |
|
||||||||||||||||||||||||||||||||||||||||||
Diff: |
Revision 5 (+73 -50) |
Testing Done: |
|
|---|
LTGM! Thanks!
I'm planning on shipping this today, unless someone has an objection.
I'm planning on shipping this today, unless someone has an objection.
