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 |
|
Karl W. Schulz
|
d7b6cf81e6
|
update headers for 2024 calendar year
Signed-off-by: Karl W. Schulz <karl.schulz@amd.com>
|
2024-01-24 17:50:31 -06:00 |
|
colramos-amd
|
e5ac5ccf7d
|
Responding to Karls review
Signed-off-by: colramos-amd <colramos@amd.com>
|
2024-01-24 16:30:04 -06:00 |
|
colramos-amd
|
a15857cd1d
|
Add implementation for gfx940 arch
Signed-off-by: colramos-amd <colramos@amd.com>
|
2024-01-24 16:30:04 -06:00 |
|
colramos-amd
|
f229b36277
|
Adding support for Mi300X-A0
Signed-off-by: colramos-amd <colramos@amd.com>
|
2024-01-24 16:30:04 -06:00 |
|
colramos-amd
|
7120f87963
|
Improved --list-metric pretty print
Signed-off-by: colramos-amd <colramos@amd.com>
|
2024-01-24 16:30:04 -06:00 |
|
coleramos425
|
7846a663fd
|
Build out gfx942 SoC class and improve SoC detection
Signed-off-by: coleramos425 <colramos@amd.com>
|
2024-01-24 16:30:04 -06:00 |
|
coleramos425
|
0432f77a7e
|
Add config files for Mi300_A1 and modify run_prof utility to use XCC modes
Co-authored-by: fei.zheng <fei.zheng@amd.com>
Signed-off-by: coleramos425 <colramos@amd.com>
|
2024-01-24 16:30:04 -06:00 |
|
coleramos425
|
4c1e516fb6
|
Improved communication between SoC and profiler classes
Signed-off-by: coleramos425 <colramos@amd.com>
|
2024-01-24 16:30:04 -06:00 |
|
coleramos425
|
1fd91959a2
|
Re-enable TCP_TCC_READ_REQ_LATENCY_sum in mi200
Signed-off-by: coleramos425 <colramos@amd.com>
|
2024-01-24 16:30:04 -06:00 |
|
coleramos425
|
c86334466a
|
Update rocprof config files for counter updates
Co-authored-by: fei.zheng <fei.zheng@amd.com>
Signed-off-by: coleramos425 <colramos@amd.com>
|
2024-01-24 16:30:04 -06:00 |
|
coleramos425
|
19ad88a04e
|
Update config files for new l2 cache per channel structure and general counter updates
Co-authored-by: fei.zheng <fei.zheng@amd.com>
Signed-off-by: coleramos425 <colramos@amd.com>
|
2024-01-24 16:30:04 -06:00 |
|
coleramos425
|
ff09288c83
|
Fix bug in coalescing TCC per channel counters
Signed-off-by: coleramos425 <colramos@amd.com>
|
2024-01-24 16:30:04 -06:00 |
|
colramos-amd
|
d4a649a926
|
Fix bug in profiling for Mi100
Signed-off-by: colramos-amd <colramos@amd.com>
|
2024-01-24 16:30:04 -06:00 |
|
colramos-amd
|
4ffcaa1b4a
|
Separate aggregation of TCC and TCC2 counters
Co-authored-by: fei.zheng <fei.zheng@amd.com>
Signed-off-by: colramos-amd <colramos@amd.com>
|
2024-01-24 16:30:04 -06:00 |
|
colramos-amd
|
a1b5c252e2
|
Optimizations to run_prof() utility
Signed-off-by: colramos-amd <colramos@amd.com>
|
2024-01-24 16:30:04 -06:00 |
|