- Per-executable contexts should be used from now on
- Global contexts are left as is for now for backwards
compatibility and will be phased out in follow up
patches.
Change-Id: I6291abf865c7ed24ee71f5065e539afc23f5ce64
[ROCm/ROCR-Runtime commit: b983c19729]
This reverts commit 5c520f4544c654e5f18e05cabd1c63d64473cfab.
Reason for revert: This patch is introducing a synchronization related bug in Unit_hipGetSetDevice_MultiThreaded testcase.
Change-Id: I367e4d4f1d75b21658ac1127c58982894a97cedb
[ROCm/ROCR-Runtime commit: 244ad319ac]
The build tree was missing a level of nesting, causing diversions based
on in-tree/out-of-tree use.
KR: Also fixed kfdtest paths
Change-Id: I8638b6d6227daabddd8eaa2aa387ba578b8dfab8
Signed-off-by: Stella Laurenzo <stellaraccident@gmail.com>
Signed-off-by: Kent Russell <kent.russell@amd.com>
[ROCm/ROCR-Runtime commit: a180fea5ad]
Temporary change to set the AllocateGTTAccess flag and node_id
on MES devices.
Change-Id: I22385d11b17b76cfb44278fa0d8a09bc8721cea6
[ROCm/ROCR-Runtime commit: efe455c2fa]
When allocating memory for MES AQL queue structure, the PreferredNode
is set to the device index of GPU to hint the location where the BO
needs to be created. But we need to ignore the device index when calling
bind_mem_to_numa.
Change-Id: Iae69fe02bfd48c5a3bd495319f6f2706d6e8aea2
[ROCm/ROCR-Runtime commit: 541d0dbbae]
The function Init() called by one of the constructors of lazy_ptr is undefined.
Replacing with reset method sets the object to an uninitialized state and assigns a new constructor function
Fix submitted on github by zhoumin2 - https://github.com/ROCm/ROCR-Runtime/pull/184
Change-Id: I7d906d526ce7fe7e2548b01810e6395b13497bf3
[ROCm/ROCR-Runtime commit: 00b63f7452]
Add kfdtest test cases for pc sampling.
Change-Id: I49f4f8ebfa6569803acdc7dec895c1902ce0b280
Signed-off-by: James Zhu <James.Zhu@amd.com>
[ROCm/ROCR-Runtime commit: daf99471a4]
Add pc sampling support.
Change-Id: I08199024ba5a8eb2845c048d499fc8fcd260d2e8
Signed-off-by: David Yat Sin <David.YatSin@amd.com>
Signed-off-by: James Zhu <James.Zhu@amd.com>
[ROCm/ROCR-Runtime commit: f94e2530fb]
Add pc sampling support
Change-Id: I2c472ce00ff8648904cf7e585687e81d3f493049
Signed-off-by: David Yat Sin <David.YatSin@amd.com>
Signed-off-by: James Zhu <James.Zhu@amd.com>
[ROCm/ROCR-Runtime commit: 4f554988b6]
To allocate GTT memory for MES AQL queue structure, KFD will create GART
mapping for the memory to be accessed by MES.
Change-Id: Iae7b33d1e70861109f1551d3a71dc60dfde9de61
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
[ROCm/ROCR-Runtime commit: 9fbe853fea]
The purpose of this patch is to add KFDQMTest.QueueLatency to
kfdtest.exclude file temporarily for the following ASIC filters:
-GFX940
-GFX941
-GFX942
This test is failing due to an issue with the way it was coded,
not due to an issue with the ASICs it is now blacklisted on.
Signed-off-by: Ori Messinger <Ori.Messinger@amd.com>
Change-Id: Ic993629a2400449f598e73fe616a4572a38e2310
[ROCm/ROCR-Runtime commit: 656234abb8]
Reduce test case size if running on emulator.
Also, refactor code as both test cases had more than 80% same code.
Signed-off-by: David Belanger <david.belanger@amd.com>
Change-Id: I5899ee24244a6f0aa6b56fa8a4701b0b1e344b9f
[ROCm/ROCR-Runtime commit: e738648c8f]
Reduce number of iteration for test case to run in reasonable amount of
time.
Signed-off-by: David Belanger <david.belanger@amd.com>
Change-Id: I19a7ec0d5f03c54d6691aae3cf7432754c7481cc
[ROCm/ROCR-Runtime commit: 66e3a09a42]
Was failing to link on AlmaLinux8.
Change-Id: Id7df245f1063c2bebd0f07efc352f1b9017eda0e
Signed-off-by: Stella Laurenzo <stellaraccident@gmail.com>
Signed-off-by: Kent Russell <kent.russell@amd.com>
[ROCm/ROCR-Runtime commit: 7c10e1e4f5]
- hsa_api_trace.h contains C++
- rocprofiler-sdk needs to include the table version number defines (*_MAJOR_VERSION and *_STEP_VERSION) for the HSA API in it's public headers
- rocprofiler-sdk needs it's public headers to be C-compatible so hsa_api_trace_version.h was created
Change-Id: Ieece990b3b7775cb0446b545c9e3391c5f691c61
[ROCm/ROCR-Runtime commit: 5402842d5f]
This allows to build ROCT-Thunk-Interface for Alpine Linux, Gentoo with musl profile and so on.
List of changes:
* Fix redefinition of PAGE_SIZE from limits.h
* Use NAME_MAX from limits.h
Closes#65
Change-Id: Ibdb0ef5668a07b7b403fcc4a44cd2658e00a584a
Signed-off-by: Sv. Lockal <lockalsash@gmail.com>
Signed-off-by: Kent Russell <kent.russell@amd.com>
[ROCm/ROCR-Runtime commit: 9a89997b5f]
When deferring a dmabuf export on an import call, there may be a
failure to export as the GEM object is not referenced by the kernel
mode driver. To get around this, do a non-deferred export and
immediately close the dmabuf FD to keep FD creation to a minimum.
This way, the GEM object will have a kernel mode driver reference
when a deferred export is done.
Also a bad dmabuf FD sent over a socket may not be received by an import
reader and this can cause a hang.
Set a 10 second timer so that importer is not blocking indefinitely.
Change-Id: I11a9b5ec64aa2e16fd6aecdf46c34e4eb56ccfd0
[ROCm/ROCR-Runtime commit: eb2100daad]
Extracts and creates a core dump ELF file from a fault event, using
core dump front end. GFX11 is not supported.
Signed-off-by: Alex Sierra <Alex.Sierra@amd.com>
Change-Id: I5ae154e886f39ab3ce7bbae5803efb27a96c7e2e
[ROCm/ROCR-Runtime commit: cbeddf9eb6]
When inspecting waves on architectures where SPI may not initialize TTMP
registers, the debugger cannot reliably know if the trap handler was
entered and if it saved valuable information in TTMP registers.
This patch uses the status.skip_export bit (unused by the compute
shaders) to indicate that it got executed before halting a wave.
This is done except for gfx940, where ttmp11[31] can be used (as long as
TTMP registers are always initialized by SPI for this architecture). It
could be possible to be more selective as architectures always
initializing TTMP registers do not require this step, but always doing
is makes maintenance simpler.
Change-Id: I5c4148c78062f7ffa049ac7856c2edc82dbc77d1
[ROCm/ROCR-Runtime commit: 5d3f6a63f1]
Work around SDMA hang in non-SPX modes for non-APU devices by disabling
ganging.
Root cause of hang not found.
non-APU xGMI modes have only 1 link between socket devices anyways so
there's likely no real system level gain in ganging intra-socket.
Change-Id: Ia4eda2f85cbf25151d3dbcf50cc45b8b775c60e2
[ROCm/ROCR-Runtime commit: ed462035fa]
Gang items have to wait on dependency signals as well as the leader.
Copies should not start if shaders are still operating on memory
to be copied.
Change-Id: I99703b420045ebcba2c9da39ec64678129dc140f
[ROCm/ROCR-Runtime commit: ed260ea970]
Pass the correct gpu_id to KFD for system memory that is allocated for
the queue and eop buffer
Change-Id: I43bb6333560a7d9d38293c191303161ab1443b5d
Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
[ROCm/ROCR-Runtime commit: 341ecaf1d9]
This allows the VA to be recorded in ROCr so that they are not
treated as an invalid pointer in future API calls.
Change-Id: I8d1d8ef9816a984c89d30a2179b0ce8940fef1da
[ROCm/ROCR-Runtime commit: f2006d6899]
For GTT memory allocation if GPU is provided honour it.
Change-Id: Iea9a26bc44cd3daa2337845f53dc430787b0643b
Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
[ROCm/ROCR-Runtime commit: 858dfd364f]
- add rocprofiler-register to CPACK_DEBIAN_BINARY_PACKAGE_DEPENDS when found
- add rocprofiler-register to CPACK_RPM_BINARY_PACKAGE_REQUIRES when found
- remove report_tool_load_failures_explicit_
- add HSA_TOOLS_DISABLE_REGISTER flag
- add HSA_TOOLS_REPORT_REGISTER_FAILURE
- use HSA_TOOLS_REPORT_REGISTER_FAILURE instead of HSA_TOOLS_REPORT_LOAD_FAILURE
- changed rocprofiler-register message to not include the word "error"
Change-Id: Ib7fd7f14c42758a54c347874018281bb1b5477a6
[ROCm/ROCR-Runtime commit: 7ce263b0e4]
At hsa_shutdown(), scratch_lock_ may be gone. Blit queues don't need it.
Change-Id: Ic132ac8a6be31fb2f0623137115608b0b222f077
[ROCm/ROCR-Runtime commit: 24633c7a85]
If two attach requests to the same piece of shared memory occur,
a double export or premature dmabuf fd close can occur since the export
and close on demand calls are not atomic.
Use a reference counter on shared memory dmabuf FDs that have
already been opened to avoid this problem.
Change-Id: I14a59209c0385e32582af42a57b33b1c6838a9b1
[ROCm/ROCR-Runtime commit: 1f63ea3476]
Add rocrtst to test mapping non-contiguous memory to a
single VA range
Change-Id: Id2e57f83512f8b482456b2b1925586951ada7400
[ROCm/ROCR-Runtime commit: b77ade9c64]
Add test to verify whether GPU shaders can read memory created using VMM
APIs.
Split VMM rocrtst to two separate groups: Basic and Access tests
Change-Id: Iead8d46125580c71ccd582e967c8e2e891e75c5e
[ROCm/ROCR-Runtime commit: 99e31e43aa]
The wavefront size is currently only exposed as an agent level
attribute. This is not correctyl, because while the agent has a default
wave front size that is usually correct, it can easily be overridden via
options like -mwavefrontsize64 on various ISAs. The wavefrontsize
attribute is actually more of a calling convention that is consistent
within a callgraph. Because the root of each call graph is a kernel in
this architecture, we need to be able to query this on a per-kernel
basis. This information is already avialable in the kernel descriptor
packet, but it wasn't exported.
This patch adds HSA_CODE_SYMBOL_INFO_KERNEL_WAVEFRONT_SIZE as a new
option to query on the executable symbol.
Change-Id: I744815c89cc9d4c82f25479bdd48ae1f32e859ff
[ROCm/ROCR-Runtime commit: 9e26cbac14]
Instead of caching shared memory fds for export on the exporter side,
only export the FD in the async handler when requested.
The importer should request export fd closure once import is done.
Change-Id: I469e0cd1749beeb9c506c8a6461745fb039d9c3b
[ROCm/ROCR-Runtime commit: e911335cee]
ToolsApiTable's version was incorrectly default initialized to 0.
Fixes error in commit fc889669
Change-Id: I41e9301a9c33b119ee50f6164d21ddf11dc188c4
[ROCm/ROCR-Runtime commit: 8e312471dc]
Prevents OOM-Killer trigger,if all physical and swap mem gets fully used
Change-Id: I70d558fa9c06fe6217e62d57e11aec6a089aa0bb
[ROCm/ROCR-Runtime commit: 13800cc6d5]
Adjust code to allow the use of non-contiguous chunks of memory to be
mapped within a single VA range.
Change-Id: Ida21ba202927229347b3a32d9b7106df10819cf5
[ROCm/ROCR-Runtime commit: f7de85082e]
Add tests to catch whether ROCr breaks ABI compatibility with the
hsa_amd_pointer_info API in case the hsa_amd_pointer_info struct is
extended.
Change-Id: I4e69bf30db9791e59f895b2798b87985c41242e5
[ROCm/ROCR-Runtime commit: 776da1a3f7]
Add new tools table and functions to notify in case of an event
Change-Id: I47f0c2f3c8e02d7bcb74d649903eb4f86721c154
[ROCm/ROCR-Runtime commit: a67af3807f]
Currently, the definition of hsa_amd_memory_fault_reason_t tries to
set a constant of 0x8000_0000 by using the definition "1 << 31".
However, the 1 in this definition is a signed integer by C++ rules.
On our architectures, shifting a signed integer by 31 results in
signed integer overflow. Signed integer overflow results in
undefined behavior.
Forcing the 1 to be unsigned avoids this.
Change-Id: I860431eeede4eff29598f646abf3c1337b048d71
[ROCm/ROCR-Runtime commit: 1d6691e06b]
Konstantin Zhuravlyov
Shweta Khatri
Stella Laurenzo
David Yat Sin
Mihai Preda
James Zhu
Philip Yang
Ori Messinger
David Belanger
Xinmudotmoe
pvanhout
Jonathan R. Madsen
Sv. Lockal
Jonathan Kim
Alex Sierra
Lancelot SIX
Harish Kasiviswanathan
Joseph Huber
Mythreya
Joseph Greathouse