benrichard-amd
96803e327c
Fix code formatting
...
Signed-off-by: benrichard-amd <ben.richard@amd.com >
2024-08-09 09:46:42 -04:00
benrichard-amd
c5ea1d0ff0
Set correct number of TCC channels for gfx942
...
Ran into rocprof error:
ROCProfiler: fatal error: input metric'TCC_EA0_RDREQ[16]' not supported on this hardware: gfx942
gfx942 has 16 channels, not 32.
Signed-off-by: benrichard-amd <ben.richard@amd.com >
2024-08-09 09:46:42 -04:00
benrichard-amd
28900f88cb
Remove unused method
...
Signed-off-by: benrichard-amd <ben.richard@amd.com >
2024-08-09 09:46:42 -04:00
benrichard-amd
d77d9f1719
Save accumulate counters to SQ_ files
...
Omniperf analyze expects the accumulate files to be in SQ_*.csv files.
Since these files also contain PMC counters (we are trying to
fit as many counters into each file as possible to minimize runs),
we need to include these SQ_*.csv files in pmc_perf.csv.
Signed-off-by: benrichard-amd <ben.richard@amd.com >
2024-08-09 09:46:42 -04:00
benrichard-amd
241a0949e1
Remove duplicate normal counters
...
Interleve TCC channel counters in putput file e.g. TCC_HIT[0] TCC_ATOMIC[0] ... TCC_HIT[1] TCC_ATOMIC[1]
Signed-off-by: benrichard-amd <ben.richard@amd.com >
2024-08-09 09:46:42 -04:00
benrichard-amd
a4fdee488b
Interleve TCC channel counters
...
Signed-off-by: benrichard-amd <ben.richard@amd.com >
2024-08-09 09:46:42 -04:00
benrichard-amd
c93fead779
Improve perfmon coalescing
...
Signed-off-by: benrichard-amd <ben.richard@amd.com >
2024-08-09 09:46:42 -04:00
coleramos425
7046ea15bd
Comply to formatting
...
Signed-off-by: coleramos425 <colramos@amd.com >
2024-06-03 13:47:45 -05:00
coleramos425
1d19ae9483
Detection of MI308X and hardcode mclk to address bug in rocm-smi
...
Signed-off-by: coleramos425 <colramos@amd.com >
2024-06-03 13:47:45 -05:00
coleramos425
49371cacec
Create dedicated subdirectory in perfmon configs for archs supporting roofline
...
Separate subdirs allows us to target different roofline counters for different archs (i.e. MI300 vs MI200)
Signed-off-by: coleramos425 <colramos@amd.com >
2024-05-31 16:09:58 -05:00
Nicholas Curtis
1f584c1612
handle unspecified case
...
Signed-off-by: Nicholas Curtis <nicurtis@amd.com >
2024-05-28 15:34:00 -05:00
Nick Curtis
5579beeed5
fix formatting
...
Signed-off-by: Nick Curtis <nicholas.curtis@amd.com >
2024-05-28 15:34:00 -05:00
Nick Curtis
989dd3b7ae
Add ability to overide arch when name missing in rocminfo
...
Signed-off-by: Nick Curtis <nicholas.curtis@amd.com >
2024-05-28 15:34:00 -05:00
coleramos425
0fc620ce79
Add TCC_TOO_MANY_EA_WRREQS_STALL to gfx940 input configs ( #349 )
...
Signed-off-by: coleramos425 <colramos@amd.com >
2024-04-25 18:22:00 +00:00
Cole Ramos
f7394bf272
Revert #333 deterministic ordering ( #337 )
...
* Revert "formatting"
This reverts commit e387561791898467371b6219921f10447d3486b3.
* Revert "Implement deterministic ordering of perfmon"
This reverts commit 2a24600a37c8002838145962a957cea447555b0c.
2024-04-01 14:30:21 -05:00
Nicholas Curtis
f6f6165379
formatting
...
Signed-off-by: Nicholas Curtis <nicurtis@amd.com >
2024-04-01 14:30:21 -05:00
Nicholas Curtis
97af96e435
Implement deterministic ordering of perfmon
...
Signed-off-by: Nicholas Curtis <nicurtis@amd.com >
2024-04-01 14:30:21 -05:00
colramos-amd
6cfdca93b9
Correct typo in Mi100 metric defs for missing SQ_INSTS_VMEM
...
Signed-off-by: colramos-amd <colramos@amd.com >
2024-04-01 14:30:21 -05:00
Nick Curtis
b610e1c27b
fixup MI300 MFMA rate disagreement between SOL and pipeline ( #315 )
...
Signed-off-by: Nicholas Curtis <nicurtis@amd.com >
Co-authored-by: Nicholas Curtis <nicurtis@amd.com >
2024-03-14 10:41:35 -05:00
Karl W Schulz
458087b425
apply formatting
...
Signed-off-by: Karl W Schulz <karl.schulz@amd.com >
2024-03-12 09:09:46 -05:00
Cole Ramos
267f0842ec
Throw error when we cannot read gfx942 details ( #310 )
...
* Throw error when we cannot read gfx942 details
Signed-off-by: colramos-amd <colramos@amd.com >
* Fixing my stupid typo
Signed-off-by: colramos-amd <colramos@amd.com >
---------
Signed-off-by: colramos-amd <colramos@amd.com >
2024-03-11 15:26:26 -05:00
colramos-amd
f2aac37178
Fix python formatting
...
Signed-off-by: colramos-amd <colramos@amd.com >
2024-03-11 14:19:01 -05:00
colramos-amd
5bf38a4fed
All logging should use call new functions
...
Signed-off-by: colramos-amd <colramos@amd.com >
2024-03-11 14:19:01 -05:00
Nick Curtis
525eb3f527
handle case where workload dir is symlink ( #297 )
...
Signed-off-by: Nicholas Curtis <nicurtis@amd.com >
Co-authored-by: Nicholas Curtis <nicurtis@amd.com >
2024-03-06 12:08:16 -06:00
colramos-amd
79260da335
Add rocprofv2 support to Mi200. Closes #295 .
...
Signed-off-by: colramos-amd <colramos@amd.com >
2024-03-04 13:40:52 -06:00
coleramos425
1dc4553091
CMake and Python format
...
Signed-off-by: coleramos425 <colramos@amd.com >
2024-03-01 15:50:42 -06:00
Nick Curtis
04e8395a2a
Fix missing 'and atomic' for write latencies in L2-Fabric section, also simplify these by redundant L2-Fabric ( #289 )
...
Signed-off-by: Nicholas Curtis <nicurtis@amd.com >
Co-authored-by: Nicholas Curtis <nicurtis@amd.com >
2024-03-01 15:50:42 -06:00
coleramos425
1c3e7598a6
Remove hardcoded gfx90a in gen_sysinfo util
...
Signed-off-by: coleramos425 <colramos@amd.com >
2024-03-01 15:50:42 -06:00
colramos-amd
d6f45411eb
Python formatting
...
Signed-off-by: colramos-amd <colramos@amd.com >
2024-03-01 15:50:42 -06:00
Nicholas Curtis
200961ffd9
Re-implement machine-specs to contain documentation, units, etc. Print using tabulate
...
Signed-off-by: Nicholas Curtis <nicurtis@amd.com >
2024-03-01 15:50:42 -06:00
coleramos425
e86741ec6c
Fix outdated function name to set arch
...
Signed-off-by: coleramos425 <colramos@amd.com >
2024-03-01 15:50:42 -06:00
Nicholas Curtis
cdeef4ebb3
minor touchup
...
Signed-off-by: Nicholas Curtis <nicurtis@amd.com >
2024-03-01 15:50:42 -06:00
colramos-amd
09f1455308
Added consistent 'Channel' headers to l2_per_chan, removed hardcoded 32 channels, and removed printed Nones ( #276 )
...
Signed-off-by: colramos-amd <colramos@amd.com >
2024-03-01 15:50:42 -06:00
Nicholas Curtis
20d93703fc
correct small negatives in remote read/write traffic due to running in different passes
...
Signed-off-by: Nicholas Curtis <nicurtis@amd.com >
2024-03-01 15:50:42 -06:00
colramos-amd
17a4d92c63
Remove mean for avg header in inst cache panel
...
Signed-off-by: colramos-amd <colramos@amd.com >
2024-03-01 15:50:42 -06:00
colramos-amd
a70dc4999d
Hide L2Banks in sysinfo and update roofline module
...
Signed-off-by: colramos-amd <colramos@amd.com >
2024-03-01 15:50:42 -06:00
colramos-amd
3e59c928e0
Fixing misc Mi300 typos
...
Signed-off-by: colramos-amd <colramos@amd.com >
2024-03-01 15:50:42 -06:00
colramos-amd
bd794abb12
Fix Mi300 clk timings using GRBM_GUI_ACTIVE from #255
...
Co-authored-by: Nick Curtis <nicholas.curtis@amd.com >
Signed-off-by: colramos-amd <colramos@amd.com >
2024-03-01 15:50:42 -06:00
colramos-amd
2001908fd8
Carry over fixed numSQCs calc from #247
...
Co-authored-by: Nick Curtis <nicholas.curtis@amd.com >
Signed-off-by: colramos-amd <colramos@amd.com >
2024-03-01 15:50:42 -06:00
colramos-amd
3ce140d04b
Including remaining metric fixes from #251
...
Co-authored-by: Nick Curtis <nicholas.curtis@amd.com >
Signed-off-by: colramos-amd <colramos@amd.com >
2024-03-01 15:50:42 -06:00
colramos-amd
86b6c8e848
Renaming global spec vars. Replacing L2Banks with total_l2_chan ( #251 )
...
Signed-off-by: colramos-amd <colramos@amd.com >
2024-03-01 15:50:42 -06:00
colramos-amd
3b1b8d7b5b
Reorganize the specs module to reduce duplicate code
...
Signed-off-by: colramos-amd <colramos@amd.com >
2024-03-01 15:50:42 -06:00
Karl W Schulz
79b877d679
code formatting updates
...
Signed-off-by: Karl W Schulz <karl.schulz@amd.com >
2024-02-22 16:02:25 -06:00
colramos-amd
b7d5d3b64b
Modify yaml configs to reflect new combined Top Stats
...
Signed-off-by: colramos-amd <colramos@amd.com >
2024-02-13 19:56:46 -06:00
colramos-amd
3b8e08f589
Add numPipes field and omit 'non-functional' counters from configs
...
Signed-off-by: colramos-amd <colramos@amd.com >
2024-02-06 16:19:40 -06:00
colramos-amd
4c9a638e2d
Standardize syntax across all metric configs
...
Signed-off-by: colramos-amd <colramos@amd.com >
2024-02-06 16:19:40 -06:00
colramos-amd
f4053bc0a2
Update perfmon config for tcc
...
Co-authored-by: Nick Curtis <nicholas.curtis>
Signed-off-by: colramos-amd <colramos@amd.com >
2024-02-06 16:19:40 -06:00
colramos-amd
d16f58b797
Add numPipes built-in-var for updated metrics
...
Co-authored-by: Nick Curtis <nicholas.curtis@amd.com >
Signed-off-by: colramos-amd <colramos@amd.com >
2024-02-06 16:19:40 -06:00
colramos-amd
deef37d5a9
Update metrics, handling merge conflicts in L2 cache per channel
...
Co-authored-by: Nick Curtis <nicholas.curtis@amd.com >
Signed-off-by: colramos-amd <colramos@amd.com >
2024-02-06 16:19:40 -06:00
colramos-amd
4174788e59
Update metric configs incorrectly using legacy rocprof headers
...
Signed-off-by: colramos-amd <colramos@amd.com >
2024-02-01 16:22:44 -06:00