Commit-Graf

64521 Incheckningar

Upphovsman SHA1 Meddelande Datum
David Galiffi b3eee295dd Revert "Upgrade ROCm-SMI to AMD SMI (#86)" (#100)
This reverts commit 0c32dfd6bc.
2025-02-07 11:45:26 -05:00
Elwazir, Ammar 5891f34f85 Adding Public Sync GH Action (#10)
Adding Public Sync to ROCProfiler

Co-authored-by: Ammar ELWazir <aelwazir@amd.com>
2025-02-07 09:11:51 -06:00
Elwazir, Ammar 35646e7b05 Adding Public Sync GH Action (#10)
Adding Public Sync to ROCProfiler

Co-authored-by: Ammar ELWazir <aelwazir@amd.com>

[ROCm/rocprofiler commit: 5891f34f85]
2025-02-07 09:11:51 -06:00
taosang2 f84a8e62d3 SWDEV-446880 - Make ocltst MemoryInfo pass in EMU
Make ocltst -m tests/ocltst/liboclruntime.so -t OCLMemoryInfo
pass in emu where GPU memory is very big.

Cherry pick
  https://gerrit-git.amd.com/c/compute/ec/clr/+/1014858

Change-Id: I0228c5e87ce7c366983fd4af71c25e7f8161c2c7


[ROCm/clr commit: de83d7a6ae]
2025-02-07 09:16:24 -05:00
taosang2 de83d7a6ae SWDEV-446880 - Make ocltst MemoryInfo pass in EMU
Make ocltst -m tests/ocltst/liboclruntime.so -t OCLMemoryInfo
pass in emu where GPU memory is very big.

Cherry pick
  https://gerrit-git.amd.com/c/compute/ec/clr/+/1014858

Change-Id: I0228c5e87ce7c366983fd4af71c25e7f8161c2c7
2025-02-07 09:16:24 -05:00
Bhardwaj, Gopesh e228ea8485 SWDEV-510794 Adding MPI usage with rocprofv3 (#183)
* swdev-510794 Adding MPI usage with rocprofv3

* update doc

* Fixed build issues

* updating doc

* doc update

* Fixed Typos

* csv format

* change format to shell

[ROCm/rocprofiler-sdk commit: 7821657d65]
2025-02-07 12:01:31 +05:30
Bhardwaj, Gopesh 7821657d65 SWDEV-510794 Adding MPI usage with rocprofv3 (#183)
* swdev-510794 Adding MPI usage with rocprofv3

* update doc

* Fixed build issues

* updating doc

* doc update

* Fixed Typos

* csv format

* change format to shell
2025-02-07 12:01:31 +05:30
Saleel Kudchadker 890399a7cf rocr: Skip uSleep for non-interrupt signals
- When waiting on non-interrupt signals, do not uSleep. This causes
  regressions compared to interrupt signal usage.
- Cleanup code.

Change-Id: I706bda0b13e64ffec0b607c1915d8380a2ce0dea
2025-02-06 23:48:35 -05:00
Saleel Kudchadker d5f08e6fa8 rocr: Skip uSleep for non-interrupt signals
- When waiting on non-interrupt signals, do not uSleep. This causes
  regressions compared to interrupt signal usage.
- Cleanup code.

Change-Id: I706bda0b13e64ffec0b607c1915d8380a2ce0dea


[ROCm/ROCR-Runtime commit: 890399a7cf]
2025-02-06 23:48:35 -05:00
Satyanvesh Dittakavi 8daab29f7f SWDEV-477584 - hipExtGetLastError should return the immediate previous API error
hipGetLastError should return the error by any of the previous APIs
in the same host thread to match the CUDA behavior, whereas
hipExtGetLastError will return the error by the immediate previous API.
This Ext API was added earlier to facilitate the existing HIP apps which
are following the current behavior of hipGetLastError

Change-Id: I61e95b1fc136cc761e2434e02187b7ed2598b733


[ROCm/clr commit: 4b443f8133]
2025-02-06 23:30:48 -05:00
Satyanvesh Dittakavi 4b443f8133 SWDEV-477584 - hipExtGetLastError should return the immediate previous API error
hipGetLastError should return the error by any of the previous APIs
in the same host thread to match the CUDA behavior, whereas
hipExtGetLastError will return the error by the immediate previous API.
This Ext API was added earlier to facilitate the existing HIP apps which
are following the current behavior of hipGetLastError

Change-Id: I61e95b1fc136cc761e2434e02187b7ed2598b733
2025-02-06 23:30:48 -05:00
Luna Nova 166b08346b rocr: set underlying type of hsa_region
Set underlying type of hsa_region_info_t, hsa_amd_region_info_t
to int.

Change-Id: Ibf97a025eec6176d8e28af8009e9bd6795ca061f
2025-02-06 16:25:03 -05:00
Luna Nova 9a0f0858fa rocr: set underlying type of hsa_region
Set underlying type of hsa_region_info_t, hsa_amd_region_info_t
to int.

Change-Id: Ibf97a025eec6176d8e28af8009e9bd6795ca061f


[ROCm/ROCR-Runtime commit: 166b08346b]
2025-02-06 16:25:03 -05:00
Madsen, Jonathan e677801859 Undefined behavior warnings caught by ROCPROFILER_DEFAULT_FAIL_REGEX (#23)
* Add regex for undefined behavior to ROCPROFILER_DEFAULT_FAIL_REGEX

- add UBSAN_OPTIONS to setup-sanitizer-env.sh

* Improve ROCPROFILER_DEFAULT_FAIL_REGEX

* Use -fno-sanitize-recover=undefined flag

- this compiler flag causes all undefined behavior errors to exit

* Revert ROCPROFILER_DEFAULT_FAIL_REGEX

* fix for shift overflow

---------

Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>
Co-authored-by: Manjunath-Jakaraddi <manjunath.jakaraddi@amd.com>

[ROCm/rocprofiler-sdk commit: e743bf5a93]
2025-02-06 08:55:57 -06:00
Madsen, Jonathan e743bf5a93 Undefined behavior warnings caught by ROCPROFILER_DEFAULT_FAIL_REGEX (#23)
* Add regex for undefined behavior to ROCPROFILER_DEFAULT_FAIL_REGEX

- add UBSAN_OPTIONS to setup-sanitizer-env.sh

* Improve ROCPROFILER_DEFAULT_FAIL_REGEX

* Use -fno-sanitize-recover=undefined flag

- this compiler flag causes all undefined behavior errors to exit

* Revert ROCPROFILER_DEFAULT_FAIL_REGEX

* fix for shift overflow

---------

Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>
Co-authored-by: Manjunath-Jakaraddi <manjunath.jakaraddi@amd.com>
2025-02-06 08:55:57 -06:00
Welton, Benjamin 6bd6bb1aec Add example for synchronous reading of device counters (#64)
* Add example for synchronous reading of device counters

We already have test cases for this use case but this a sample
such that our collaborators can have a place to quickly pull
code from for use on their end (and to serve as a working example).

* Formatting fix

* Formatting fix

* Minor change for testing

---------

Co-authored-by: Benjamin Welton <ben@amd.com>

[ROCm/rocprofiler-sdk commit: 6c396adf83]
2025-02-06 08:35:55 -06:00
Welton, Benjamin 6c396adf83 Add example for synchronous reading of device counters (#64)
* Add example for synchronous reading of device counters

We already have test cases for this use case but this a sample
such that our collaborators can have a place to quickly pull
code from for use on their end (and to serve as a working example).

* Formatting fix

* Formatting fix

* Minor change for testing

---------

Co-authored-by: Benjamin Welton <ben@amd.com>
2025-02-06 08:35:55 -06:00
Madsen, Jonathan b610b5ff56 SDK: No bg thread if no clients use SDK (#123)
* SDK: No bg thread if no clients use SDK

* Update CHANGELOG

---------

Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>

[ROCm/rocprofiler-sdk commit: 0fbe6cc7b6]
2025-02-06 08:34:56 -06:00
Madsen, Jonathan 0fbe6cc7b6 SDK: No bg thread if no clients use SDK (#123)
* SDK: No bg thread if no clients use SDK

* Update CHANGELOG

---------

Co-authored-by: Jonathan R. Madsen <jonathanrmadsen@gmail.com>
2025-02-06 08:34:56 -06:00
U, Srihari 908862e45e Initialize extremes to max and min values (#184)
* Initialize extremes to max and min values

* Address review comment

* Adding clang format

[ROCm/rocprofiler-sdk commit: 90ae424c57]
2025-02-06 08:32:37 -06:00
U, Srihari 90ae424c57 Initialize extremes to max and min values (#184)
* Initialize extremes to max and min values

* Address review comment

* Adding clang format
2025-02-06 08:32:37 -06:00
Nagaraj, Sriraksha 4390642c8e remove duplication (#190)
[ROCm/rocprofiler-sdk commit: 03e5a1d9cc]
2025-02-06 08:31:53 -06:00
Nagaraj, Sriraksha 03e5a1d9cc remove duplication (#190) 2025-02-06 08:31:53 -06:00
Elwazir, Ammar 8f99bed27d 6.4 fixes for HSA and HIP (#191)
* Adding support for hsa_amd_signal_wait_all

* Fixes for HIP

---------

Co-authored-by: Ammar ELWazir <aelwazir@amd.com>

[ROCm/rocprofiler-sdk commit: 02a519e84e]
2025-02-06 07:56:08 -06:00
Elwazir, Ammar 02a519e84e 6.4 fixes for HSA and HIP (#191)
* Adding support for hsa_amd_signal_wait_all

* Fixes for HIP

---------

Co-authored-by: Ammar ELWazir <aelwazir@amd.com>
2025-02-06 07:56:08 -06:00
Welton, Benjamin 6cc5501260 [SWDEV-482060] Set execute permission for HSA allocated memory (#7)
Set execute permission for HSA allocated memory

We need execute permission for HSA memory (req for IB buffers).
Enforcement is upcoming which will break counter collection (see ticket).

Change-Id: Id939bbdd8686915407bc60d0dfcd5110b0e91e90

Co-authored-by: Benjamin Welton <bewelton@amd.com>
Co-authored-by: Bhardwaj, Gopesh <Gopesh.Bhardwaj@amd.com>
2025-02-06 07:54:06 -06:00
Welton, Benjamin f9cdc37350 [SWDEV-482060] Set execute permission for HSA allocated memory (#7)
Set execute permission for HSA allocated memory

We need execute permission for HSA memory (req for IB buffers).
Enforcement is upcoming which will break counter collection (see ticket).

Change-Id: Id939bbdd8686915407bc60d0dfcd5110b0e91e90

Co-authored-by: Benjamin Welton <bewelton@amd.com>
Co-authored-by: Bhardwaj, Gopesh <Gopesh.Bhardwaj@amd.com>

[ROCm/rocprofiler commit: 6cc5501260]
2025-02-06 07:54:06 -06:00
Jonathan Luu dbab4d1afb SWDEV-511848 - update readme
Change-Id: Icf590d17f4c1988850f0056e0ec8bc88f921b3be
2025-02-05 18:12:08 -06:00
Jonathan Luu 8442a5f8e2 SWDEV-511848 - update readme
Change-Id: Icf590d17f4c1988850f0056e0ec8bc88f921b3be


[ROCm/rocm-core commit: dbab4d1afb]
2025-02-05 18:12:08 -06:00
Ioannis Assiouras 6a00aa8d61 SWDEV-508435 - Added a fix for double free of hsaImageObject
Change-Id: I9397f7c9dbbad7c249b359155df312cb920eba6c


[ROCm/clr commit: d05ecea253]
2025-02-05 22:21:24 +00:00
Ioannis Assiouras d05ecea253 SWDEV-508435 - Added a fix for double free of hsaImageObject
Change-Id: I9397f7c9dbbad7c249b359155df312cb920eba6c
2025-02-05 22:21:24 +00:00
xuchen-amd 3891342e95 Improve test run time by editing roofline related tests. (#554)
* Improve test run time by editing roofline related tests.

* Fix formatting.

[ROCm/rocprofiler-compute commit: 3396ba3906]
2025-02-05 14:18:59 -05:00
xuchen-amd 3396ba3906 Improve test run time by editing roofline related tests. (#554)
* Improve test run time by editing roofline related tests.

* Fix formatting.
2025-02-05 14:18:59 -05:00
Bhardwaj, Gopesh 20415eff0a SWDEV-509568: rocprofiler v1 and v2 API deprecation notice (#5)
* SWDEV-509568: rocprofiler v1 and v2 API deprecation notice

* correcting typo in warning message
2025-02-05 22:50:31 +05:30
Bhardwaj, Gopesh f48bdc2ea6 SWDEV-509568: rocprofiler v1 and v2 API deprecation notice (#5)
* SWDEV-509568: rocprofiler v1 and v2 API deprecation notice

* correcting typo in warning message

[ROCm/rocprofiler commit: 20415eff0a]
2025-02-05 22:50:31 +05:30
Bhardwaj, Gopesh a8a82d7263 Adding ROCTx usage doc (#159)
* Adding Roctx usage doc

* updated CHANGELOG

* dpc update

* Fixing Related Pages issue

* updating doc

* updating docs

* Adding Resource naming section

* Fixed Formatting

* format fix

* format fix

* Fixing build due to incorrect indentation

[ROCm/rocprofiler-sdk commit: 12508b9521]
2025-02-05 11:04:24 -06:00
Bhardwaj, Gopesh 12508b9521 Adding ROCTx usage doc (#159)
* Adding Roctx usage doc

* updated CHANGELOG

* dpc update

* Fixing Related Pages issue

* updating doc

* updating docs

* Adding Resource naming section

* Fixed Formatting

* format fix

* format fix

* Fixing build due to incorrect indentation
2025-02-05 11:04:24 -06:00
Ioannis Assiouras c0b728fcad SWDEV-513323 - Fix for BatchMemOp on devices with no image support
BatchMemop should be positioned before the image support kernels
because the total number of kernels is determined by BlitLinearTotal,
when there is no image support on the device.

Change-Id: I8e53caf744ba54259ac04bad1762eef21806f3f2


[ROCm/clr commit: 3e01da3dac]
2025-02-05 04:45:22 -05:00
Ioannis Assiouras 3e01da3dac SWDEV-513323 - Fix for BatchMemOp on devices with no image support
BatchMemop should be positioned before the image support kernels
because the total number of kernels is determined by BlitLinearTotal,
when there is no image support on the device.

Change-Id: I8e53caf744ba54259ac04bad1762eef21806f3f2
2025-02-05 04:45:22 -05:00
Branislav Brzak b7f9ee2330 SWDEV-447357 - Implement test coverage report integration
Change-Id: I2dd0d375517e421493713106ab436b63222be5d6


[ROCm/hip-tests commit: fc1066ca9f]
2025-02-05 04:17:09 -05:00
Branislav Brzak fc1066ca9f SWDEV-447357 - Implement test coverage report integration
Change-Id: I2dd0d375517e421493713106ab436b63222be5d6
2025-02-05 04:17:09 -05:00
Anusha GodavarthySurya 5535f15104 SWDEV-469422 - hipGraph move to classes from structs
Change-Id: I0f9c8ef1161c0c92ebe0cce6844b2feacfee83f5


[ROCm/clr commit: 32e5b00c30]
2025-02-05 00:33:41 -05:00
Anusha GodavarthySurya 32e5b00c30 SWDEV-469422 - hipGraph move to classes from structs
Change-Id: I0f9c8ef1161c0c92ebe0cce6844b2feacfee83f5
2025-02-05 00:33:41 -05:00
Galantsev, Dmitrii 809ef97d3c Fix warnings on CXX/linker flags (#12)
1) When `clang` is used as system compiler, libraries were built without respecting LDFLAGS. For example, this affected LTO flags, if any (and it only affected clang, not gcc).

2) Linker flags are registered as CXX flags, which produces warnings during compilation:
```
clang++: warning: -Wl,-z,noexecstack: 'linker' input unused [-Wunused-command-line-argument]
clang++: warning: -Wl,-znoexecheap: 'linker' input unused [-Wunused-command-line-argument]
clang++: warning: -Wl,-z,relro: 'linker' input unused [-Wunused-command-line-argument]
clang++: warning: -Wl,-z,now: 'linker' input unused [-Wunused-command-line-argument]
```

3) Clang does not support `-Wtrampolines` flag:
```
warning: unknown warning option '-Wtrampolines' [-Wunknown-warning-option]
```

4) No linkers support `noexecheap` anymore. `noexecheap` linker flag was a part of PaX patches to GNU ld, (which were dropped in 2017)[https://www.gentoo.org/support/news-items/2017-08-19-hardened-sources-removal.html]. Now ld/ld.lld/ld.gold don't support it and protection of heap is managed by NX bit. Therefore every compiler produces this warning:
```
ld.lld: warning: unknown -z value: noexecheap
```

Closes #210.

Co-authored-by: Sv. Lockal <lockalsash@gmail.com>

[ROCm/rocm_smi_lib commit: 4dbc2b6d57]
2025-02-04 22:16:57 -06:00
Galantsev, Dmitrii 4dbc2b6d57 Fix warnings on CXX/linker flags (#12)
1) When `clang` is used as system compiler, libraries were built without respecting LDFLAGS. For example, this affected LTO flags, if any (and it only affected clang, not gcc).

2) Linker flags are registered as CXX flags, which produces warnings during compilation:
```
clang++: warning: -Wl,-z,noexecstack: 'linker' input unused [-Wunused-command-line-argument]
clang++: warning: -Wl,-znoexecheap: 'linker' input unused [-Wunused-command-line-argument]
clang++: warning: -Wl,-z,relro: 'linker' input unused [-Wunused-command-line-argument]
clang++: warning: -Wl,-z,now: 'linker' input unused [-Wunused-command-line-argument]
```

3) Clang does not support `-Wtrampolines` flag:
```
warning: unknown warning option '-Wtrampolines' [-Wunknown-warning-option]
```

4) No linkers support `noexecheap` anymore. `noexecheap` linker flag was a part of PaX patches to GNU ld, (which were dropped in 2017)[https://www.gentoo.org/support/news-items/2017-08-19-hardened-sources-removal.html]. Now ld/ld.lld/ld.gold don't support it and protection of heap is managed by NX bit. Therefore every compiler produces this warning:
```
ld.lld: warning: unknown -z value: noexecheap
```

Closes #210.

Co-authored-by: Sv. Lockal <lockalsash@gmail.com>
2025-02-04 22:16:57 -06:00
Jakaraddi, Manjunath 87fe3387c5 SWDEV-506317: Kernel trace failing due to Code object errors (#170)
SWDEV-506317: Kernel trace failing

[ROCm/rocprofiler-sdk commit: 9c89b475b0]
2025-02-04 18:01:42 -06:00
Jakaraddi, Manjunath 9c89b475b0 SWDEV-506317: Kernel trace failing due to Code object errors (#170)
SWDEV-506317: Kernel trace failing
2025-02-04 18:01:42 -06:00
taosang2 27e87ccca6 SWDEV-513458 - Add gfx950 target ID
Add gfx950 target ID

Cherry-picked
https://gerrit-git.amd.com/c/compute/ec/clr/+/997678
https://gerrit-git.amd.com/c/compute/ec/clr/+/1063519

Change-Id: I0228c5e87ceec366983fd4afb1c25e7f8161c2c2


[ROCm/clr commit: 29cc394510]
2025-02-04 18:30:23 -05:00
taosang2 29cc394510 SWDEV-513458 - Add gfx950 target ID
Add gfx950 target ID

Cherry-picked
https://gerrit-git.amd.com/c/compute/ec/clr/+/997678
https://gerrit-git.amd.com/c/compute/ec/clr/+/1063519

Change-Id: I0228c5e87ceec366983fd4afb1c25e7f8161c2c2
2025-02-04 18:30:23 -05:00
Elwazir, Ammar 906b8b507a Support new HIP APIs (#179)
* Adding New HIP APIs

* Format Fix

* Format Fix

* Removing changes from ostream and moving it to format

* Addressing Code Review Comments

* Versioning the new hip calls formatting

---------

Co-authored-by: Ammar ELWazir <aelwazir@amd.com>

[ROCm/rocprofiler-sdk commit: dd5c0ea257]
2025-02-04 15:50:18 -06:00