In order to accommodate the flaky queue submission under memory
shortage scenarios, BigBufferStressTest has become very much a hack,
undermining its purpose of testing the basic memory related operations.
Therefore, remove the queue submission part. The EvictTest should serve
the purpose of testing the memory and queue submission functionalities
when memory eviction happens.
Change-Id: I3c3603a0e834267eccb72f46efeabe1e053c8fc5
Signed-off-by: Yong Zhao <Yong.Zhao@amd.com>
v2: Remove useless AcquireMem packet after the dispatch
v3: Minimum poll_interval is 4
Change-Id: I352eb21c781ed9e03d62c0febd532da6a9854afa
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
v2: optimize_ace_offload_mode=1, recommended by firmware team
Change-Id: Ia54e37242b4eaaf631c35e61a59f03ee0f85ca35
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
This patch adds the support for gfx90c apu. So far we treat it as "dgpu" and
gfx900. Will update hsa gfxip table while the isa/llvm is implemented on gfx90c.
Change-Id: I6ef164bf3e751fe6dd6287cac212a500dce84b1a
Signed-off-by: Huang Rui <ray.huang@amd.com>
The test actually tested all available SDMA queues, so change the name
to reflect the fact.
Change-Id: Ia23df3e5ac79b692b0b60194b05603ba8dd897a4
Signed-off-by: Yong Zhao <Yong.Zhao@amd.com>
If NUMA system no available memory on node 0, mbind will fail on node
0, so set flag NoNUMABind=1 to bypass mbind for all test cases which use
node 0 and allocate system memory.
Change-Id: I7962938ad2bed5a293ca5e6a8500c7f7e15ff453
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
On NUMA system, allocate queue ctx save restore area on the closest NUMA
node to the GPU which the queue is going to run. This will improve
performance on NUMA system generally by reducing schedule latency and
fix the multi-node rccl-tests unstable performance issue.
If the closest NUMA node has no memory available, set flags NoNUMABind=1
to bypass mbind, to use default NUMA memory policy to allocate system
memory.
Change-Id: Ic62bfa5bb2efbf4f6ae79ff403e9610ddf18d45c
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
This patch adds the non-privileged PMC blocks for GFX10/gfx1010.
Change-Id: I4b98cb2159d71113c12920ca7fd10e45096b4e2c
Signed-off-by: Ori Messinger <Ori.Messinger@amd.com>
This can be used for allocating space in the IB for write-back data
in a NOP-packet with a payload.
Change-Id: I6202b89a455a65326366a15291789004dfdcc0b9
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Useful for allocating space for write-back data in a queue or IB.
Change-Id: I47bd2dcb8537a91410e9a91413979a8a2c1c5f21
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Avoids unnecessary and error-prone duplication of dynamic packet
allocation in many packet classes.
Change-Id: Icec981ae2cd7a3d88cdf9213298940d85627f853
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
FREE_MEMORY_OF_GPU ioctl could fail, e.g., if memory is still mapped
to GPU. Handle this failure by return error in fmm_release/HsaKmtFreeMemory
Change-Id: I5461db39964f733cf97376d50e44906a9b4c0f13
Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
If CPACK_PACKAGING_INSTALL_PREFIX is not set, it's safer to assume it's the
same as CMAKE_INSTALL_PREFIX, incase only the latter is set.
Change-Id: I70727ebbc50f21f8d6e3add10d7f9f2d5e747dee
Signed-off-by: Jeremy Newton <Jeremy.Newton@amd.com>
This will facilitate the need of halting the execution during debugging.
Change-Id: I058c81bbc9f655bbc477b2b542d6b43aa423324c
Signed-off-by: Yong Zhao <Yong.Zhao@amd.com>
The tests are useful to triage the fundamental queue submission
functionality by excluding the packet format variable from the equation.
Change-Id: I2c7fcda811f93bdefc1b62396233559416be44e7
Signed-off-by: Yong Zhao <Yong.Zhao@amd.com>
The class is very useful for triaging complex SDMA issues.
Change-Id: Ib5de729f7fc62f41e894ef98d3967e7e1745d454
Signed-off-by: Yong Zhao <Yong.Zhao@amd.com>
The new filter can be used by "./run_kfdtest.sh -p core_sws".
Change-Id: I1c43669cfc07c09ccafb9fa2e2851932ac59307d
Signed-off-by: Yong Zhao <Yong.Zhao@amd.com>
We are still working on those tests for gfx1010, so disable them
temporarily.
Change-Id: I5d51b4b02bc753137014684859cc033f759b2899
Signed-off-by: Yong Zhao <Yong.Zhao@amd.com>
CMAKE_INSTALL_PREFIX would give incorrect result for packages
build by CPack.
Change-Id: Iaeb4d30eb44080b7924ecf892de011ed6e365f5f
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Without this change, the failure was hard to notice when it happened.
Change-Id: I99c3e8cea0d0cbd3bcfe79069410e6e870e225bf
Signed-off-by: Yong Zhao <Yong.Zhao@amd.com>
When CONFIG_NUMA is not enabled in the kernel config, only one CPU node
presents on the system and /sys/devices/system/node/nodeX directories
don't exist. Read CPU cache information from /sys/devices/system/cpu in
this situation.
Change-Id: I017ff17dd72678a0551edcc77446664501aa42ca
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
When large bar is not available, we can use
xgmi to do p2p tests.
Change-Id: Ib7b59fb8a4d41f605739a0428973f6b2f1a3450f
Signed-off-by: Eric Huang <JinhuiEric.Huang@amd.com>
The debug trap accesses the data0/data1 registers, so we do not
want the userspace to write values to it. We remove the calls to
set the data0/data1 register values.
Change-Id: Iaba842a4c445f339f16a39fe1994526ff78a2f3c
Signed-off-by: Philip Cox <Philip.Cox@amd.com>
Need to check the kfd debugger version of the kernel before
calling kfd debugger tests in kfdtest. If they are out of sync,
the tests may fail.
Change-Id: I1df5e89fb1199304e6fbe8973c60b76062514c03
Signed-off-by: Philip Cox <Philip.Cox@amd.com>
To support adding new features to the kfd debugger, and not break
functionality, we need to be able to check the kfd debugger support
version info from the kernel.
Change-Id: Icd88e4edab8430c35eaed588e62d892c1b5c62ec
Signed-off-by: Philip Cox <Philip.Cox@amd.com>
To check the KFD debugger API support, we need to be able to check
the major/minor version of the kfd debugger version, so we need to
expose this function from the kernel.
Change-Id: I8a3dc617607e2efa9e65306d08b8583b8b1a2172
Signed-off-by: Philip Cox <Philip.Cox@amd.com>
The KFD debugger is only supported on gfx9 platforms, so we need to
restrict it from running on gfx10 platforms until it is supported.
Change-Id: I500f0e20fda71021f2cce70a67fc8d9d042209fe
Signed-off-by: Philip Cox <Philip.Cox@amd.com>
The memory need to be mapped for both local and remote GPU access
Change-Id: I4aeaffc0851b6107fc91e9eaa6150764b06f5ca9
Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
This is some data fabric/vbios issue that causing system hard hang
while running this test. Will enable it after the HW/vibos fix.
Change-Id: Ic0753c2d92e9e4863c310da9a595b2af302f17f8
Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
When fail to get CPU dirs from //sys/devices/system/node/nodeX directory,
the error message should print node_dir, not path.
Change-Id: If76a51918c8dd55fa6605a62f3d29f9efc6fadb3
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
numa_max_node() return the highest node number available on the current
system, number of NUMA nodes should be numa_max_node() + 1.
Change-Id: I20a6c17af071e73e853cb5ea6d0304c8aca52681
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Allocate system memory from node id 0 will fail on NUMA system which has
no memory on node 0. Change to use new flag NoNUMABind to allocate
system memory from NUMA nodes which have free memory.
Change-Id: I8ef9ca28fc2ab5dd31d07a2d3eaf1d5886e798a0
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
on NUMA system, node 0 may have no memory, application pass node id
0 to hsaKmtAllocMemory will fail because mbind to specify the allocation
from node 0 return EINVAL.
Add new flag NoNUMABind for application to pass it to hsaKmtAllocMemory
to skip mbind.
hsaKmtCreateEvent and hsaKmtCreateQueue specify the new flag NoNUMABind
to allocate system memory for event page and CWSR area, don't bind the
system memory to a specific NUMA node.
Change-Id: I854e5a57502c7807c4c5ff2e441d499ae515c309
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Docker seccomp by default blocks mbind system call, so mbind return
failed on docker. thunk should not fail this otherwise application
cannot allocate system memory on docker.
Use pr_warn_once and pr_err_once to avoid duplicate same error messages
Change-Id: I61a7c0e4abaa3dcfe7abf2ea48db90f669f9638a
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
This will emilinate the need of updating the run_kfdtest.sh every time
a new platform is added.
Change-Id: I584d65b462de36a685fa2d29d43962078ba511dc
Signed-off-by: Yong Zhao <Yong.Zhao@amd.com>
Force all the GPUs to a certain type, use the below command:
HSA_FORCE_ASIC_TYPE="10.1.0 1 gfx1010 14"
meaning major.minor.step dgpu asic_name asic_id
This will faciliate the cooperation across the teams for bringing up
ASICs which reuse existing device IDs.
Change-Id: I40fe4c9b46d3ccb3e38ea52250e80e82fb50fb0f
Signed-off-by: Yong Zhao <Yong.Zhao@amd.com>
Yong Zhao
Felix Kuehling
Huang Rui
Philip Cox
Philip Yang
Ori Messinger
Oak Zeng
Jeremy Newton
Amber Lin
Eric Huang
Cole Nelson
shaoyunl