Commit Graph

64521 Commits

Author SHA1 Message Date
Gopesh Bhardwaj 9b2ece76c3 Fixing installed pacakge tests in CI (#1119)
* Fixing installed pacakge tests in CI

* Formatted rocprofv3.py with black formatter
2024-10-07 20:55:35 +05:30
Satyanvesh Dittakavi 57c5264937 SWDEV-483241 - Add a compile option to avoid including default hiprtc header
Change-Id: Ic23b41395588e6183abac36cb7543da02b0aba29


[ROCm/clr commit: 522ae8ead4]
2024-10-07 07:56:29 -04:00
Satyanvesh Dittakavi 522ae8ead4 SWDEV-483241 - Add a compile option to avoid including default hiprtc header
Change-Id: Ic23b41395588e6183abac36cb7543da02b0aba29
2024-10-07 07:56:29 -04:00
Gopesh Bhardwaj 0b356e16aa updating rocprofv3 help options (#1113)
* updating rocprofv3 help options

* updating CHANGELOG

[ROCm/rocprofiler-sdk commit: f2f267bcc0]
2024-10-05 12:40:27 +05:30
Gopesh Bhardwaj f2f267bcc0 updating rocprofv3 help options (#1113)
* updating rocprofv3 help options

* updating CHANGELOG
2024-10-05 12:40:27 +05:30
Saleel Kudchadker b9497ea70e SWDEV-301667 - Enable ROCr logging
- Use AMD_LOG_LEVEL=5 to dump AQL packets in ROCr

Change-Id: I2c044a5304c4eaf3d3af20e62d1f54c98d4fbaa4


[ROCm/clr commit: e36666e536]
2024-10-04 19:22:12 -04:00
Saleel Kudchadker e36666e536 SWDEV-301667 - Enable ROCr logging
- Use AMD_LOG_LEVEL=5 to dump AQL packets in ROCr

Change-Id: I2c044a5304c4eaf3d3af20e62d1f54c98d4fbaa4
2024-10-04 19:22:12 -04:00
Saleel Kudchadker 375ed9d848 SWDEV-478065 - Revert "SWDEV-478065 - Embed host thread in shared_ptr"
This reverts commit 274fd2628f.

Reason for revert: This blocks multithreaded callbacks

Change-Id: I9944417e4fb63c9eea2b286c828c7dfa621c4fe8


[ROCm/clr commit: d3d0ca5fc6]
2024-10-04 19:19:28 -04:00
Saleel Kudchadker d3d0ca5fc6 SWDEV-478065 - Revert "SWDEV-478065 - Embed host thread in shared_ptr"
This reverts commit 4b03017e8a.

Reason for revert: This blocks multithreaded callbacks

Change-Id: I9944417e4fb63c9eea2b286c828c7dfa621c4fe8
2024-10-04 19:19:28 -04:00
David Yat Sin dbae8da515 rocr: Fix memory leak on non-visible GPUs
Fix memory leak for memory regions objects when GPU is masked using
ROCR_VISIBLE_DEVICES.

Change-Id: I610842a18adbc3cdc854b12650844e271bc00592
2024-10-04 17:40:47 -04:00
David Yat Sin 2445514435 rocr: Fix memory leak on non-visible GPUs
Fix memory leak for memory regions objects when GPU is masked using
ROCR_VISIBLE_DEVICES.

Change-Id: I610842a18adbc3cdc854b12650844e271bc00592


[ROCm/ROCR-Runtime commit: dbae8da515]
2024-10-04 17:40:47 -04:00
Peter Park c444ba6131 Update documentation requirements (#402) (#5)
* Bump rocm-docs-core to 1.8.2

* Remove empty package-ecosystem in dependabot

Co-authored-by: Sam Wu <22262939+samjwu@users.noreply.github.com>

[ROCm/rocprofiler-systems commit: dc63370a1f]
2024-10-04 15:27:02 -04:00
Peter Park dc63370a1f Update documentation requirements (#402) (#5)
* Bump rocm-docs-core to 1.8.2

* Remove empty package-ecosystem in dependabot

Co-authored-by: Sam Wu <22262939+samjwu@users.noreply.github.com>
2024-10-04 15:27:02 -04:00
Branislav Brzak 169423798f SWDEV-476542 - Unable to link to hipGraphExecGetFlags
Change-Id: I572baaeee31c6a73e533f9ef956bf111e9d2e688


[ROCm/clr commit: d29ebea7ac]
2024-10-04 13:39:06 -04:00
Branislav Brzak d29ebea7ac SWDEV-476542 - Unable to link to hipGraphExecGetFlags
Change-Id: I572baaeee31c6a73e533f9ef956bf111e9d2e688
2024-10-04 13:39:06 -04:00
Saleel Kudchadker 5296c77138 SWDEV-301667 - Logging upgrades
- Use AMD_LOG_LEVEL_SIZE in MBs to set log file size truncation, by default its 2048 MB

Change-Id: Ia2f87e8c6b94148e30edfb602b279f93630817c3


[ROCm/clr commit: 35e03ea0d0]
2024-10-04 13:26:25 -04:00
Saleel Kudchadker 35e03ea0d0 SWDEV-301667 - Logging upgrades
- Use AMD_LOG_LEVEL_SIZE in MBs to set log file size truncation, by default its 2048 MB

Change-Id: Ia2f87e8c6b94148e30edfb602b279f93630817c3
2024-10-04 13:26:25 -04:00
Jaydeep Patel 91b343c758 SWDEV-471422 - Free memory being double deducted on APUs due to system_total_alloced var holds local memory.
Change-Id: I3fbbc8f8aaa156881ff95cad6a4f82fd3df651d1


[ROCm/clr commit: 292842ad28]
2024-10-04 04:49:20 -04:00
Jaydeep Patel 292842ad28 SWDEV-471422 - Free memory being double deducted on APUs due to system_total_alloced var holds local memory.
Change-Id: I3fbbc8f8aaa156881ff95cad6a4f82fd3df651d1
2024-10-04 04:49:20 -04:00
Jonathan Kim 0ae064fe2d rocr: Use new extended graphics handle registration call on IPC import
To correctly map to all GPUs after an import, use the new extended
registration call that can import a virtual address without having to
specify a target node.

Change-Id: Ifca8f6f6ee24fa99b2af357dcc3ea1de3ab234f7
2024-10-03 14:06:37 -04:00
Jonathan Kim 2e7b02add9 rocr: Use new extended graphics handle registration call on IPC import
To correctly map to all GPUs after an import, use the new extended
registration call that can import a virtual address without having to
specify a target node.

Change-Id: Ifca8f6f6ee24fa99b2af357dcc3ea1de3ab234f7


[ROCm/ROCR-Runtime commit: 0ae064fe2d]
2024-10-03 14:06:37 -04:00
Jonathan Kim 03463ed2c0 hsakmt: Enable graphics handle registration with a virtual address
Currently registering graphics memory without specifying a target
node will return a memory handle that's not a virtual address.

As a result, ROCr is forced to register with a target node for
IPC usage.

Mapping memory without specifying a target node afterwards will
result in mapping to the target node that was imported because the
previous import call flags this node targeting action to future mapping.

For ROCr IPC usage, ROCr wants to map to all GPU nodes if the target node
is not specified.

Allow the caller to register graphics handles that returns a virtual
address without having to specify the target node so that the caller
can make a subsequent map call to all GPUs.

Change-Id: I5a935092b885cc3568e4f3a5dd951c7ec6c84fca
2024-10-03 14:06:31 -04:00
Jonathan Kim 43ebf5b524 hsakmt: Enable graphics handle registration with a virtual address
Currently registering graphics memory without specifying a target
node will return a memory handle that's not a virtual address.

As a result, ROCr is forced to register with a target node for
IPC usage.

Mapping memory without specifying a target node afterwards will
result in mapping to the target node that was imported because the
previous import call flags this node targeting action to future mapping.

For ROCr IPC usage, ROCr wants to map to all GPU nodes if the target node
is not specified.

Allow the caller to register graphics handles that returns a virtual
address without having to specify the target node so that the caller
can make a subsequent map call to all GPUs.

Change-Id: I5a935092b885cc3568e4f3a5dd951c7ec6c84fca


[ROCm/ROCR-Runtime commit: 03463ed2c0]
2024-10-03 14:06:31 -04:00
Giovanni Lenzi Baraldi 9038cfac07 Fixing some accumulate metrics (#1089)
* Fixing some accumulate metrics

* Fixing some more accumulate metrics

---------

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

[ROCm/rocprofiler-sdk commit: fa7fc7ec5d]
2024-10-03 09:44:31 -07:00
Giovanni Lenzi Baraldi fa7fc7ec5d Fixing some accumulate metrics (#1089)
* Fixing some accumulate metrics

* Fixing some more accumulate metrics

---------

Co-authored-by: Benjamin Welton <bewelton@amd.com>
2024-10-03 09:44:31 -07:00
Giovanni Lenzi Baraldi dc85966562 SWDEV-467350: Skipping tool counter iteration for unsupported hardware (#1083)
[ROCm/rocprofiler-sdk commit: 1d6a0b5c80]
2024-10-03 09:04:42 -07:00
Giovanni Lenzi Baraldi 1d6a0b5c80 SWDEV-467350: Skipping tool counter iteration for unsupported hardware (#1083) 2024-10-03 09:04:42 -07:00
Ben Richard 4da8b0dc46 Skip output lines that have UTF8 decoding error (#441)
* Avoid crash if non-UTF8 character is encountered in output

Signed-off-by: benrichard-amd <ben.richard@amd.com>

* Ignore lines with non-UTF-8 characters. Do not print error.

Signed-off-by: benrichard-amd <ben.richard@amd.com>

* Remove trailing whitespace

Signed-off-by: benrichard-amd <ben.richard@amd.com>

---------

Signed-off-by: benrichard-amd <ben.richard@amd.com>

[ROCm/rocprofiler-compute commit: fb210abcd0]
2024-10-03 11:27:55 -04:00
Ben Richard fb210abcd0 Skip output lines that have UTF8 decoding error (#441)
* Avoid crash if non-UTF8 character is encountered in output

Signed-off-by: benrichard-amd <ben.richard@amd.com>

* Ignore lines with non-UTF-8 characters. Do not print error.

Signed-off-by: benrichard-amd <ben.richard@amd.com>

* Remove trailing whitespace

Signed-off-by: benrichard-amd <ben.richard@amd.com>

---------

Signed-off-by: benrichard-amd <ben.richard@amd.com>
2024-10-03 11:27:55 -04:00
pghafari 38ad03660a SWDEV-467263 - Allow hipMalloc to use sys memory
PAL supports allocating from system memory once device memory is used up
or allocation is larger than the device memory.

Change-Id: Iccd3377e95a6cc6d23e45d4738a17af8b9ee32d7


[ROCm/clr commit: b07178618c]
2024-10-03 11:14:08 -04:00
pghafari b07178618c SWDEV-467263 - Allow hipMalloc to use sys memory
PAL supports allocating from system memory once device memory is used up
or allocation is larger than the device memory.

Change-Id: Iccd3377e95a6cc6d23e45d4738a17af8b9ee32d7
2024-10-03 11:14:08 -04:00
AravindanC cbd270ab58 SWDEV-461080 - Remove Hard Coded Install Permission
Change-Id: Idf14ddbd83b304d7a4830467b1f9d14db38dda58


[ROCm/hip-tests commit: 64eed879df]
2024-10-03 06:47:55 -07:00
AravindanC 64eed879df SWDEV-461080 - Remove Hard Coded Install Permission
Change-Id: Idf14ddbd83b304d7a4830467b1f9d14db38dda58
2024-10-03 06:47:55 -07:00
Benjamin Welton 9532bd7032 Update limit for max counter records in rocprof-tool (#1073)
A fixed sized std::array is used to store counter records in rocprofiler SDK. This limit was breached in SWDEV-484742. Upping the limit to 512 to be less likely to reach this limit again.

[ROCm/rocprofiler-sdk commit: a159fb47c7]
2024-10-02 16:56:42 -07:00
Benjamin Welton a159fb47c7 Update limit for max counter records in rocprof-tool (#1073)
A fixed sized std::array is used to store counter records in rocprofiler SDK. This limit was breached in SWDEV-484742. Upping the limit to 512 to be less likely to reach this limit again.
2024-10-02 16:56:42 -07:00
Benjamin Welton ee620bf7dc [SWDEV-484495] Fix int truncation in CSV output (#1098)
CSV output truncates doubles to ints when it shouldn't. Derived metrics
are (mostly) doubles and lose precision (or become worthless) if treated
as an int. Converted these to double to match the format we return from
rocprof-sdk.

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

[ROCm/rocprofiler-sdk commit: 4f05850efd]
2024-10-02 16:55:00 -07:00
Benjamin Welton 4f05850efd [SWDEV-484495] Fix int truncation in CSV output (#1098)
CSV output truncates doubles to ints when it shouldn't. Derived metrics
are (mostly) doubles and lose precision (or become worthless) if treated
as an int. Converted these to double to match the format we return from
rocprof-sdk.

Co-authored-by: Benjamin Welton <ben@amd.com>
2024-10-02 16:55:00 -07:00
Ioannis Assiouras 3a07931ad4 SWDEV-483134 - Deprecate hipHostMalloc and hipHostFree APIs
Change-Id: I55432d34ea7e9357e6528089cf38addcb5b22ddf


[ROCm/hip commit: d8906fa045]
2024-10-02 12:36:23 -04:00
Ioannis Assiouras d8906fa045 SWDEV-483134 - Deprecate hipHostMalloc and hipHostFree APIs
Change-Id: I55432d34ea7e9357e6528089cf38addcb5b22ddf
2024-10-02 12:36:23 -04:00
Julia Jiang 8977f07def SWDEV-488771 - Adding build dependency on LLVM
Change-Id: I63c381a406ee4b0211a4f5a6c9c519eb7313b6c1


[ROCm/hip commit: cda9c38b8f]
2024-10-02 11:03:41 -04:00
Julia Jiang cda9c38b8f SWDEV-488771 - Adding build dependency on LLVM
Change-Id: I63c381a406ee4b0211a4f5a6c9c519eb7313b6c1
2024-10-02 11:03:41 -04:00
Aravindan Cheruvally 9e559345d2 Revert "SWDEV-342167, SWDEV-461080 - Remove Hard Coded Install Permission"
This reverts commit e495390b7f.

Reason for revert: Observing issue SWDEV-488249 due to catch test permission settings. 

Change-Id: Ifdc55e4eb3938c9bc0b9af0a4e9dc9ba366614b3


[ROCm/hip-tests commit: c2671515df]
2024-10-02 10:33:03 -04:00
Aravindan Cheruvally c2671515df Revert "SWDEV-342167, SWDEV-461080 - Remove Hard Coded Install Permission"
This reverts commit 38eedf86cf.

Reason for revert: Observing issue SWDEV-488249 due to catch test permission settings. 

Change-Id: Ifdc55e4eb3938c9bc0b9af0a4e9dc9ba366614b3
2024-10-02 10:33:03 -04:00
Ioannis Assiouras 00cb623a67 SWDEV-488851 - Correctly remove the queue from the active set on windows
Change-Id: I4d21743ecf7a44636121f85566f898e62ff61e97


[ROCm/clr commit: 07bcc283f9]
2024-10-02 12:06:59 +01:00
Ioannis Assiouras 07bcc283f9 SWDEV-488851 - Correctly remove the queue from the active set on windows
Change-Id: I4d21743ecf7a44636121f85566f898e62ff61e97
2024-10-02 12:06:59 +01:00
Ranjith Ramakrishnan f27ae44b8c cmake component grouping should not be ignored
In static build, the dev and binary components are grouped to generate static package
Removed the line that was ignoring the component grouping

Change-Id: Ie0ca9db109f2002891260985634f2e6b1ea7f236
2024-10-01 14:22:21 -07:00
Ranjith Ramakrishnan 7b21e011d2 cmake component grouping should not be ignored
In static build, the dev and binary components are grouped to generate static package
Removed the line that was ignoring the component grouping

Change-Id: Ie0ca9db109f2002891260985634f2e6b1ea7f236


[ROCm/ROCR-Runtime commit: f27ae44b8c]
2024-10-01 14:22:21 -07:00
Cole Ramos 83de3f34ae Add smart name and notes to triggered releases (#438)
Signed-off-by: coleramos425 <colramos@amd.com>

[ROCm/rocprofiler-compute commit: c8a1add54b]
2024-10-01 14:59:38 -05:00
Cole Ramos c8a1add54b Add smart name and notes to triggered releases (#438)
Signed-off-by: coleramos425 <colramos@amd.com>
2024-10-01 14:59:38 -05:00
Ioannis Assiouras 6221aee0af SWDEV-478295 - Set CXX as the project language in 23_cmake_hiprtc
Change-Id: I40c01191e9de1790bbdd42896bdf70c046a70e34


[ROCm/hip-tests commit: 8e62770f50]
2024-10-01 10:57:16 -04:00