AI/rocm-systems
2
0
Rozštěpit 0
Zdrojový kód Úkoly Pull requesty Akce Balíčky Projekty Vydání Wiki Aktivita
597 Commity 3 Větve 0 Značky
d42d7e754391fea62c63e27fde2ee7556c44c868
Graf commitů

76 Commity

Autor SHA1 Zpráva Datum
Laurent Morichetti a794247c55 Optimize rotcx markers 
Improve the roctx markers performance when the tracer is not engaged
(the application is not running with rocprof).

The performance of roctx push/pop, measured with:

-----------------------------------------------------------------------
  auto start = std::chrono::steady_clock::now();
  for (int i = 0; i < 10000000; ++i) {
    roctxRangePush ("A");
    roctxRangePop ();
  }
  auto end = std::chrono::steady_clock::now();
  std::cout << "ns = " << std::chrono::nanoseconds(end - start).count()
      / 10000000 << std::endl;
-----------------------------------------------------------------------

w/o rocprof | with rocprof | commit
       92ns |       770ns  | 0d6e132: Cleanup CallbackTable::Get
       28ns |       712ns  | 6421bd5: Cleanup ROCTX's implementation
       20ns |       664ns  | 7f0e5e5: Remove the roctx range message...
        6ns |       665ns  | this commit

Change-Id: Id679dcbd0fb190a3179be98a9b2c1db151efee3d
 2022-05-10 12:08:06 -07:00
Laurent Morichetti 4aeb76f7a8 Cleanup CallbackTable::Get 
Make CallbackTable::Get return the callback_function/user_arg pair
as an actual return value instead of returning it through arguments
pointers.

Change-Id: Ia2dfcdad8c237a09620518ad67af94add47220da
 2022-05-10 08:13:18 -07:00
Laurent Morichetti cd62d841fa Make roctracer_cb_table.h a private header 
Move roctracer_cb_table.h to the src/core directory, as it should not
be exposed as a public header, and rename it callback_table.h

Change-Id: Ib448cbd32a275df0268d53bd8d1da0bdc9201470
 2022-04-20 19:47:43 -07:00
Laurent Morichetti 06a3da7c63 Fix copyright headers 
Change-Id: I380d867fa5fb04e68b5b332e9abf33fbeb1e9418
 2022-04-19 09:30:45 -07:00
Christophe Paquot e5e1258ef8 SWDEV-295205 - Remove KFD domain from roctracer 
Change-Id: I2771cf43aa115bb466531bf887f7cc75e187f2ef
 2021-07-22 10:12:45 -07:00
Rachida Kebichi e5dd1e9b85 SWDEV-284863 Fixed several issues preventing memcpy info dump in csv 
Change-Id: I4c6323311ce8314296e81a9b9b5d8adb485e0aa8
 2021-05-25 11:10:52 -04:00
Rachida Kebichi faada3e569 SWDEV-283958 Workaround for unnamed structs 
CppHeaderParser has limited support for unnamed structs. It leaves the
name empty so this results in classes (a.k.a structs) having trailing '::'
characters, also giving no way to distingush two unnamed structs at the
same level of nesting. An example are the inner structs of
hipExternalSemaphoreSignalParams. The workaround consists in skipping
over these, so they are not generated in the output header file
which lists all ostream ops<<. Only the inner unnamed structs are skipped,
the rest is processed as it should.

Change-Id: I17439c46095469b7adb7aee0b0f0b3d234aabc11
 2021-05-07 15:57:30 -04:00
Rachida Kebichi 06271806d4 SWDEV-255637 support for hsa_amd_memory_async_copy_rect 
Change-Id: I5db6484c30427712c56b59862e748118a3f079c2
 2021-03-31 10:02:06 -04:00
Rachida Kebichi ad5b463912 SWDEV-271503 Fixed core dump 
Change-Id: Ia582a27482581c3b81c42da0add9f6743898da6c
 2021-03-30 14:06:56 -04:00
Evgeny bb5f2231a1 calling python3 explictely 
Change-Id: I3dda55865bafa41cc6670e414b213f13a2a2a7ac
 2020-12-16 14:29:12 -05:00
Rachida Kebichi ef36218286 SWDEV-255938 NEW - added regex and depth support to ostream ops 
Change-Id: I292255adab3a70fa00a1dd5685b788521687f35b
 2020-11-18 16:48:50 -05:00
Evgeny 9562675382 SWDEV-251491 : gen_ostream_ops.py porting to python3 
Change-Id: I7081b6ad21b038040267067bd73d8a44df46e4ff
 2020-10-01 00:52:23 -05:00
Rachida Kebichi 29da9a744d Fix for trace checker 
Change-Id: Ib8a0df7b7bb0da2e68b5b4d99ce8025de169f317
 2020-09-11 14:26:47 -04:00
Evgeny Shcherbakov 361f099847 Merge "build normalizing - generating under build directory" into amd-staging 2020-09-11 09:42:28 -04:00
Evgeny c9ed0f067d gen_ostream_ops.py fix - ostream operators as inline static 
Change-Id: I9688236b06dd167960662b8eecf1a07c93b43fff
 2020-09-09 01:46:23 -05:00
Evgeny ed1f1b66ac build normalizing - generating under build directory 
Change-Id: Id9203aec7800024bd749059a415fb29b8051005a
 2020-09-07 15:24:58 -05:00
Evgeny e9b8de644e Format ostream ops 
Change-Id: I8c609b1ef82e02f3547541c2cc47dec3a4f1c7b3
 2020-08-28 11:30:18 -05:00
Evgeny ac59f349d4 enabling hipIpcEventHandle_t 
Change-Id: Iaf973567298d5ef8450e14e869b5f837e0620022
 2020-08-03 13:04:05 -05:00
Evgeny Shcherbakov de338b02e6 Merge "Added hsa ostream ops generation" into amd-master 2020-07-30 11:24:32 -04:00
Rachida Kebichi bac4bae41c Added hsa ostream ops generation 
Change-Id: Icc68e136d22b05b35d6adaff56e090272633d760
 2020-07-29 10:41:32 -04:00
Rachida Kebichi 0502f196d9 more verbosity in trace diffs 
Change-Id: I1e3f6c8ee126ca4470f0846aabab19d18397dd64
 2020-07-29 03:00:16 -05:00
Evgeny 264e3d816d fixing ostreams linking as inline static 
Change-Id: Idbfac3e5220acd62500cd4c204a5bd9a9461c8fc
 2020-06-19 12:54:12 -05:00
Evgeny 9d4a58f6da disabling kernel name printing for kernel launches by func pointer and ostream operator template 
Change-Id: Icbcedafb1812a1be03837f6cb47283eb0d382ad2
 2020-05-27 05:23:29 -04:00
Rachida Kebichi 8cece61689 Added check trace with config. 
Change-Id: I1c71793c4c6f512288e92f70105f428c3f8671c4
 2020-05-19 09:47:19 -05:00
Evgeny 074306d997 SWDEV-236864 : packaging of generated headers 
Change-Id: Ifda69eecf3697f6b69c978b3c4c2ffe9835edeb8
 2020-05-18 18:08:06 -05:00
Rachida Kebichi 72b0d25ea4 Added generation of hip ostream operators 
Change-Id: I5d07ea07cdd94097cb44619c29d9deba54e5d6a5

ostream ops code cleanup

Change-Id: Ia4e287de1e1953f5d323a0066c29aa6056442139
 2020-05-01 16:15:01 -04:00
Evgeny 5e5fe9917d normalizing trace comparison mechanism 2020-03-27 00:32:18 -05:00
Evgeny aaecb3dbbb cleanup 2020-03-26 11:51:56 -05:00
eshcherb 7b8b39b495 Merge branch 'amd-master' into rkebichi-trace-compare 2020-03-25 19:27:49 -05:00
rkebichi afd562dd94 Update check_trace.py 2020-03-25 15:27:20 -04:00
rkebichi 1d46509af4 Update check_trace.py 2020-03-23 17:29:38 -04:00
rkebichi d108cca320 Delete parse_trace.py 
Not needed (replaced by check_trace.py)
 2020-03-23 17:19:03 -04:00
rkebichi ebf78e2a43 Delete check_trace.sh 
Not needed (replaced by check_trace.py)
 2020-03-23 17:16:27 -04:00
rkebichi e100e6d87d Create check_trace.py 2020-03-23 17:12:13 -04:00
rkebichi a342265a30 Create check_trace.sh 2020-03-17 12:22:10 -04:00
rkebichi 90912231e7 Update parse_trace.py 2020-03-17 12:20:25 -04:00
Evgeny 1be273a1b4 enable tool reloading 2020-03-14 00:13:22 -05:00
Evgeny 8b63135ced PC sampling initial bringup 2020-02-28 14:01:40 -06:00
rkebichi 70274c3692 Update parse_trace.py 2020-02-10 15:29:49 -05:00
rkebichi e28dde64b3 Update parse_trace.py 2020-02-07 17:00:50 -05:00
rkebichi 20051e559e Update parse_trace.py 2020-02-03 17:25:28 -05:00
rkebichi 941622e6b9 Create parse_trace.py 
script to parse roctracer .txt trace files
 2020-01-31 11:01:11 -05:00
eshcherb 8c41ac3a10 Merge branch 'amd-master' into rkebichi-patch-2 2020-01-28 14:14:31 -06:00
rkebichi 2901da60a5 Update gen_ostream_ops.py 2020-01-24 10:19:09 -05:00
rkebichi fff5d9833f Update gen_ostream_ops.py 2020-01-22 14:06:58 -05:00
rkebichi 547b36f9f6 Update gen_ostream_ops.py 2020-01-17 11:23:01 -05:00
Evgeny b82a21056e normalizing C API: HSA domain 2019-12-30 20:09:41 -06:00
Evgeny 077f8ec6b6 normalizing C API 2019-12-29 03:06:11 -06:00
rkebichi dd69b522c3 Update gen_ostream_ops.py 2019-12-27 12:14:27 -05:00
Evgeny 8475e25e7a kfd trace fix: disbale recursive callback; disable open/close API tracing; 2019-12-03 09:43:50 -06:00