117 Commity

Autor SHA1 Wiadomość Data
Xianwei Zhang 9c62afb8ba concurrent: enable/fix the related settings
Concurrent profiling relies on the aqlprofile read_api
and tracker. This patch set those options to enable
the concurrent profiling.

Change-Id: Ib97d4d8facfbc11f2684d83109397cd13f117d5e


[ROCm/rocprofiler commit: b445610cd1]
2020-08-26 16:04:57 -04:00
Evgeny a331990ee4 optimization mechanism fix: correct tracker handler; kernel name query on completion;
Change-Id: I14da152b4ac3c7d8fd1af2f54e9d71f834071622


[ROCm/rocprofiler commit: 80747de208]
2020-08-03 23:34:49 -05:00
Evgeny 832ab03e46 kernel name filtering fix - handling [] brakets
Change-Id: I46a62d991a52045694640837393df229cf7a3133


[ROCm/rocprofiler commit: 7364edcc5b]
2020-07-29 18:47:31 -05:00
Xianwei Zhang f95b383dfa pmc: add support of concurrent kernel profiling
The profiling was only enabled in serial mode, i.e., kernels
are serialized in execution, and counters are reset at each
kernel start and read at kernel completion. This patch adds
the concurrent mode, by issuing the process-level start
packet to reset counters, and then reading twice at kernel
start and end time to obtain the counter value difference.
The new concurrent profiling usage needs the integration
with the corresponding augment at aqlprofile side.

Change-Id: I94b4442eadc8c64b8fba51b1e4916fc8b895ad21


[ROCm/rocprofiler commit: 61c9df4631]
2020-07-16 14:39:46 -05:00
Evgeny 3d44ea1a05 counters dumping optimization
Change-Id: I8c694e5380e15179453148dd9ab3a3e51b6db861


[ROCm/rocprofiler commit: 2a7f77b290]
2020-07-15 09:57:41 -05:00
Evgeny d22c364abe cleanup
Change-Id: I518f741d3d3d0bb514936c4db8b727bdc79d9fdc


[ROCm/rocprofiler commit: f214238880]
2020-06-24 12:22:22 -05:00
Evgeny c75faaaa37 concurrent sqtt support
Change-Id: I91391fafabc93aefa5d244d870ef82b96a59dc52


[ROCm/rocprofiler commit: 9f7e936d70]
2020-06-23 20:00:49 -04:00
Evgeny 7d2307424e disabling destruction
Change-Id: I2a7d05a8f597b3bc8bd07bffe7181f9dcace1cbf


[ROCm/rocprofiler commit: 9950b97567]
2020-05-07 03:34:30 -05:00
Evgeny 212aefac7d adding pid for kernel results to support multi-process profiling
Change-Id: I283228a4b4145599c5e637dd6faa771b9f4b6345


[ROCm/rocprofiler commit: 3af87a7423]
2020-05-05 05:35:32 -05:00
Evgeny e3514895c6 toll destruction fix
Change-Id: If069c820526e21a0a4b80ac516f9669a81f34cab


[ROCm/rocprofiler commit: fe70682184]
2020-04-28 03:16:15 -05:00
Evgeny 943b92d4c7 fixing hsa intercept test
Change-Id: I2671dfc6a9bd3e01a0c926aa3ea367b8c7a0279e


[ROCm/rocprofiler commit: 7be9a42ab3]
2020-03-28 17:24:16 -05:00
Evgeny 67e1502ce5 PC sampling bringup
Change-Id: I0d041c4c8c3778f2c328cde38432bc72223706a3

pc sampling integration fix

Change-Id: Ia66ff876d2d99ec4d561daf8320b65d75f5cd2fe


[ROCm/rocprofiler commit: 9df9fddcfb]
2020-03-28 13:07:45 -05:00
Evgeny 0e767e9864 update for gfx9 and 3.1
Change-Id: I0c218f8a2dcdad1c8deb44770d8a64ccd95a92fb


[ROCm/rocprofiler commit: 299a08e4be]
2020-03-24 19:07:11 -05:00
Evgeny 99d4641ee7 dynamic kernel lds size
Change-Id: I051b85550d12ca8662127615be7adfb12c5f9585


[ROCm/rocprofiler commit: 7ecf9ef1e3]
2020-02-27 17:44:22 -06:00
Evgeny d657afa812 adding AgentInfo::lds_block_size
Change-Id: I186893add96dc92570e710ae78b475897ebfe531


[ROCm/rocprofiler commit: 40730e34e4]
2020-02-18 14:00:19 -06:00
Evgeny a40ba7a793 hsa-interept mode enabling in head
Change-Id: I048a975deaae691868034ee361fea71ffb5bdd83


[ROCm/rocprofiler commit: d2324e780f]
2020-02-14 00:22:36 -06:00
Evgeny c1b7e4353a device id/type for submit callback
Change-Id: I69b31bd28850198c8ca44e55bf8f2ff9540d92fc


[ROCm/rocprofiler commit: 3d4c4d1cce]
2020-02-13 22:00:56 -06:00
Evgeny 988274443a adding agent to device callback data
Change-Id: I7d631e4faae685ce23704ac65308bf2aae0c157a


[ROCm/rocprofiler commit: 4edc6c98cf]
2020-02-13 22:00:56 -06:00
Evgeny 9d2081ceb4 kernel free on executable_destroy
Change-Id: I062e08fd5df94f4d21b443b74494dc6e95201f3d


[ROCm/rocprofiler commit: 304568c1a3]
2020-02-13 22:00:56 -06:00
Evgeny 59bc8da846 adding code object freeze handling, kernel code allocate/device callbacks
Change-Id: I6ec32a0c4e945260cd11f88c1d2a0a7f22d6e10c

documenting comments

Change-Id: I1b7af70d51042c48aef0474d0b6b54275b42c456


[ROCm/rocprofiler commit: 086c29fff1]
2020-02-13 22:00:56 -06:00
Evgeny 3b84973737 adding allocate/device/memcopy/submit callbacks
Change-Id: Ie83ae3cd57cdf5038e83db70891b103439c37d55


[ROCm/rocprofiler commit: f95ed067ba]
2020-02-13 22:00:08 -06:00
Evgeny 67b1e9af0d trace parameters fix
Change-Id: I5cd8c897b9982f9abc9e36c18a4a488bd65fbd30


[ROCm/rocprofiler commit: 389cb50854]
2019-12-10 04:33:29 -06:00
Evgeny 6dd6ea0046 sgpr/vgpr reported sizes in terms of registers; lds size in bytes;
Change-Id: Id527687cc075a4e85ea4d0063ed8f336e34d2454


[ROCm/rocprofiler commit: c8eb0641bf]
2019-11-27 15:19:14 -06:00
Evgeny 9b183d909e code object tracking and v3 code object support
Change-Id: I081ada13f6364ea4401a97a485dedfa9bf8a45fe


[ROCm/rocprofiler commit: 60043d198b]
2019-11-19 20:18:09 -06:00
Evgeny c34655f1ff setting of granulated lds, sgpr, vgpr reserved by HW for the kernel
Change-Id: Ib3e60c0b97787f56f769136480a46a8560e00cc8


[ROCm/rocprofiler commit: dc05345a78]
2019-11-11 18:11:16 -05:00
Evgeny 7bf4ab543d unordered metrics expressions config
Change-Id: I998423046abfd7af45f28071911276cce1c4f3da


[ROCm/rocprofiler commit: e5b938b5fb]
2019-08-25 05:08:55 -05:00
Evgeny Shcherbakov ba57b18464 Merge "build: slightly change files to pass compilation" into amd-master
[ROCm/rocprofiler commit: 4f4e02de7a]
2019-08-23 11:44:44 -04:00
Evgeny 58968594c7 Mem32Bwrites -> MemWrites32B renaming
Change-Id: I86f570b97178caa3d3d5fcbc5ecc716216dad504


[ROCm/rocprofiler commit: aecc7abc76]
2019-08-22 22:34:36 -05:00
Evgeny e5169bf5b3 mi100 metrics fix
Change-Id: I862578a2b7827a88cc6926d636d5eb9a8320a244


[ROCm/rocprofiler commit: dff3256dd5]
2019-08-22 22:30:48 -05:00
Xianwei Zhang 3dce66bd80 build: slightly change files to pass compilation
Compiled using Clang and encountered errors on ambiguous pointer
type, implicit conversion NULL to bool, and unused function, etc.
As a fix, this patch slightly updates the related codes.

Change-Id: I4a73d66293313dda36749036f5c73aaf2a445231


[ROCm/rocprofiler commit: ee917344ff]
2019-08-22 23:29:16 -04:00
Evgeny fc6e208b50 overwriting on inheritance
Change-Id: I6faf79874fc14e898c75972aa2f372e228105f7b


[ROCm/rocprofiler commit: 82ecf9e7a4]
2019-08-08 01:54:29 -05:00
Evgeny 55680ff541 gfx908 events update
Change-Id: Ieb7c72f66b7e5e5dfc29d97650a29722a6276a31


[ROCm/rocprofiler commit: 09eed4f35b]
2019-08-07 19:44:31 -05:00
Evgeny 05f8d9ebca adding gfx908 namespace
Change-Id: Ifd45385777be5066c8bfef23ee24bbabadf4dffa


[ROCm/rocprofiler commit: 855a801ae7]
2019-07-27 03:06:10 -05:00
Xianwei Zhang 62b33801c4 xml: add extra events for gfx906 GPUs
Compard to gfx900, e.g., Vega 10, gfx906 adds extra counter events.
A typical difference is on TCC-EA that gfx906 (e.g., Vega 20) has 2
EAs per TCC, while only one single EA/TCC on gfx900. As such,
additional counters must be profiled to get correct results. This
patch adds one extra events to specifically handle gfx906.

Change-Id: Id6c9d37548a102c80bbfddcfa11e77d20f17431a


[ROCm/rocprofiler commit: ca9a714b77]
2019-07-16 12:56:45 -05:00
Xianwei Zhang f5b54bff3d test: add tests to validate cache/mem blocks
To validate cache and memory blocks profiling, this patch prepares
tests to profile dedicated kernels using specified counters, to
compare the profiled results against expected ones, and further
show the test is a fail or pass.  Tests here are focusing on cache
hit/miss, memory fetch/write size.

Change-Id: Icbc8096a6e15256dec66297597a57c7665a533b8


[ROCm/rocprofiler commit: 8b445d2c00]
2019-07-16 12:39:38 -05:00
Evgeny 4c1a1ce831 adding xml inheritance
Change-Id: Iafbfb8a6fb1936cf1315c1f5215879e99187da77


[ROCm/rocprofiler commit: 46fd670818]
2019-07-16 09:20:53 -07:00
Evgeny 2c091d01d0 adding SPM test
Change-Id: I55dde52e668206e238ea860dd11e0ed5501a582a


[ROCm/rocprofiler commit: 988283533f]
2019-06-04 15:34:21 -05:00
Evgeny 1fecf4774c adding SPM trace support
Change-Id: I07c0d3ec5c4ec51ea00fea539c930c6ed27b1163


[ROCm/rocprofiler commit: 6d6eb2b2d0]
2019-06-04 05:07:19 -05:00
Evgeny 65ea957d1f extending xontext pool API
Change-Id: I56809354a9ea991489479117160f3d4f451f82b3


[ROCm/rocprofiler commit: 8c15ff4bf8]
2019-03-29 11:12:40 -05:00
Evgeny 1ecd03ea5e improving rocprof tracing usage
Change-Id: I4db513c93406a7038b8b681d12a0dc4298975f01


[ROCm/rocprofiler commit: f834529669]
2019-03-12 18:19:17 -05:00
Evgeny 222ef52c5d supporting original hsa api table
Change-Id: Ia98554c137a3ec6433d8234ba17ca4dc2f2be940


[ROCm/rocprofiler commit: df860838a2]
2019-03-06 13:41:54 -06:00
Evgeny 33e8160a54 fix of reported completion signal in th ecase when it is proxied by the tracker
Change-Id: Ic1100fde03bc34e0130405285d32d6b97a031967


[ROCm/rocprofiler commit: 996b64309a]
2019-02-20 19:21:35 -06:00
Evgeny 55664e9ae4 trace input parsing refactoring
Change-Id: Ib5828561249ab7c15c5ed58b932f03839b207295


[ROCm/rocprofiler commit: 20a1db9d6d]
2019-01-18 20:59:29 -06:00
Evgeny a33b1cc58d ctx-wait option
Change-Id: I8a7cf97458f27169774e3a38ee5007b2ca6bf450


[ROCm/rocprofiler commit: 4c0c64493c]
2019-01-17 02:25:08 -06:00
Evgeny 28b8257ef8 fix
Change-Id: I2c13b9610037baf9e5b0db675bac19426fe8239e


[ROCm/rocprofiler commit: 7dd087ebf0]
2019-01-16 19:08:00 -06:00
Evgeny 63150d03e1 hsa memcopy tracking
Change-Id: I61bc4ea01a62b587d5941f9d0e9e358a6ed71b5a


[ROCm/rocprofiler commit: 2b2a279ce9]
2019-01-07 01:53:27 -06:00
Evgeny 2dff8e83f4 adding kernel properties
Change-Id: I5d8672400357d5ef5cbfb5023d82f712fdaf7057


[ROCm/rocprofiler commit: 64e0325a0d]
2018-12-21 18:02:26 -06:00
Evgeny c3c9815c49 minor changes
Change-Id: I16444de8c5d83a9f33392ac870d2fc188978ab54


[ROCm/rocprofiler commit: ea0a1110dc]
2018-12-18 09:51:47 -06:00
Evgeny a4c804a33c cosmetic changes
Change-Id: Ie9c730305c8a882e250f28cc60d640c70d899572


[ROCm/rocprofiler commit: 1d55085060]
2018-11-08 03:54:09 -06:00
Evgeny cde69c4b14 rpl_run data extracting error message; comments for intermediate metrics
Change-Id: I4d9f97ed475d3ec328aafae40f1bc80b6bf69bcc


[ROCm/rocprofiler commit: 812c17ed77]
2018-11-01 13:38:01 -05:00