If there is connection between GPU and CPU with weight 13,
KFD_CRAT_INTRA_SOCKET_WEIGHT, then this is AppAPU.
This will be used to skip tests not suitable for AppAPU.
Change-Id: If6fad81528b52afd4ac4cefa508d787b0f6637ca
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
[ROCm/ROCR-Runtime commit: e2df2c21af]
For GC 9.4.0, modifications were made to various shaders since certain
flat_ instructions no longer support glc/slc modifiers (replaced with
nt/sc1/sc0). Instead of repeating conditionals inside various shader
bodies, we can make use of LLVM AMDGCN macros.
This patch modularizes the shader macros into seperated defines. Prior
to the core raw-string literal, each shader now starts with the
SHADER_START literal (".text\n") plus any number of SHADER_MACRO_*
literals. This allows us to seperate the macro definitions logically and
use the pre-processor to only include the required macro groups on a
per-shader basis.
Signed-off-by: Graham Sider <Graham.Sider@amd.com>
Change-Id: I19eb3fd14252a0601bb7509249051b68e7fdb02a
[ROCm/ROCR-Runtime commit: e2435d9e93]
Previously, KFDEvictTest.QueueTest and KFDSVMEvictTest.QueueTest
would create a variable number of wavefronts, one for each 64MB
of memory under test. This ran into limits on the buffers used
by the wavefronts, and may at some point have exceeded the
wavefront limit.
Restrict the number of wavefronts to 512, and adjust the shader
to accomodate a variable buffer size
Signed-off-by: David Francis <David.Francis@amd.com>
Change-Id: I2ec292e2900e2efa62a08313bca3d2f4bdabca8b
[ROCm/ROCR-Runtime commit: 680c8ca5a9]
KFDMemoryTest.DeviceHdpFlush requires device node 0 is large bar to
check VRAM content from CPU, run the test only if device 0 is large
bar GPU.
Change-Id: I874b153219550c50b724625e971e3ed3a84dc652
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
[ROCm/ROCR-Runtime commit: 598e3e8d86]
Nodes with XGMI have no HDP, so DriverHDPFlush should skip.
Signed-off-by: David Francis <David.Francis@amd.com>
Change-Id: If5a87e660712e51d03e750d8e044786036b2e603
[ROCm/ROCR-Runtime commit: e32278a612]
Even with the restriction to only compile on gfx90a, this
shader still fails CompileShaders test.
There don't seem to be any systems that actually use it.
Leave it in the shader store, but remove it otherwise
Signed-off-by: David Francis <David.Francis@amd.com>
Change-Id: I41bec6ba10363d42b163ac101c3a92edaad6d6df
[ROCm/ROCR-Runtime commit: 16c6530330]
A gfx940 code path was erroneously added to this shader.
It's unneccesary; without this path, the shader uses
the scalar store, which works just fine on gfx940 without changes.
Remove it.
Signed-off-by: David Francis <David.Francis@amd.com>
Change-Id: I825cbbebbdb25c4a7c2f16e228c2bea6a6bcc30c
[ROCm/ROCR-Runtime commit: 2a01e5c33b]
gfx940 changed the semantics of the glc and slc coherency options
on vector stores and loads. This means that shaders that use
those bits no longer compile on gfx940.
Add precompilation if statements to those shaders to use the
new coherency bits.
Also add gfx940 to ASMTest so that compilation is tested.
Note: One of the tests enabled by this patch on gfx940,
KFDEvictTest.QueueTest, does not pass on gfx940 emulators.
Signed-off-by: David Francis <David.Francis@amd.com>
Change-Id: I942f9d2536e9eb5510c4d5af30df6ff1a95c8cf7
[ROCm/ROCR-Runtime commit: 30da9a3cf9]
Program ACCUM_OFFSET to match the number of VGPRS used
by the shader as part of Dispatch setup.
Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Change-Id: Icfa1fbe4de2a62f00743de567f3ed382d3378b17
[ROCm/ROCR-Runtime commit: 8994c3ba0e]
Add gfx version for VGPR size per CU calc, add FAMILY_AV to KfdFamilyId,
add blacklist filter to kfdtest.exclude.
Signed-off-by: Graham Sider <Graham.Sider@amd.com>
Change-Id: I9b8072e45f4d497e0a8fd3f8f97f1425238e8b42
[ROCm/ROCR-Runtime commit: 6be4461a0d]
See description of previous revert.
This reverts commit 8554f0df14.
Signed-off-by: Graham Sider <Graham.Sider@amd.com>
Change-Id: I969dc6469e62b50cd7ba0595918538602afa7516
[ROCm/ROCR-Runtime commit: 287cb29340]
This patch and the previous made it such that the queue ring buffer was
allocated as non-paged for GFX11+. The queue ring buffer should not be
mapped as non-paged; the non-paged requirement on GFX11 is only needed
for the queue wptr.
This patch was causing issues on various tests, such as intermittent
CP_INTSRC_BAD_OPCODE interrupts.
This reverts commit 92a336d485.
Signed-off-by: Graham Sider <Graham.Sider@amd.com>
Change-Id: I55b64aed73dc3b792f0756ae00daf6e10d93ce10
[ROCm/ROCR-Runtime commit: 0750856d4a]
Get more debug information about user pointers that were registered
through SVM API, and triggered by memory exception events.
A new kfdtest with this use case was also included inside
KFDExceptionTest.
Signed-off-by: Alex Sierra <alex.sierra@amd.com>
Change-Id: I0ef4929afe0625b9b5cbbbebef11ede66dda60ab
[ROCm/ROCR-Runtime commit: 2a1d6ee8b5]
Register and map userptrs through Shared Virtual Memory(SVM) API at
the Kernel level when available. Using this approach, performance
will be improve as register/unregister memory will not trigger any
system call to KFD driver.
Signed-off-by: Alex Sierra <alex.sierra@amd.com>
Change-Id: I3726b4b5e1c6a52a83786fbe0af6322eb29ae7c9
[ROCm/ROCR-Runtime commit: 63c8cf115a]
The MemoryAllocAll test in kfdtests exercises the new KFD memory
availability API by trying to allocate a single buffer object that
exactly fills all of vram. Desired object size is determined using the
memory availility KFD ioctl via libhsakmt, then an object is allocated
slightly larger than that size. If the allocation attempt fails then
the test tries to allocate a slightly smaller object, and continues
trying with smaller sizes until the allocation succeeds. The test
succeeds if the successfully allocated object is within some specified
tolerance of the available memory reported.
There are a number of known issues that can cause the successfully
allocated object to be significantly smaller than reported availability.
Until these issues are addressed, we should not fail the test, but just
log the actual divergence between the size of the object we thought we
could allocate, and what was actually possible.
Signed-off-by: Daniel Phillips <daniel.phillips@amd.com>
Change-Id: I165a30865ffbb2353286dcc896ad8e24af124615
[ROCm/ROCR-Runtime commit: d3bb1ca4af]
Since KFD counts svm allocation as system memory usage,
KFDSVMEvictTest will fail on the case of small system
memory, adding check is to skip test.
Signed-off-by: Eric Huang <jinhuieric.Huang@amd.com>
Change-Id: I040f16f2dd0d4092d069a632cfba9c28293f781b
[ROCm/ROCR-Runtime commit: 3f55ba9fb8]
If the KFD IOCTL version doesn't support available_memory, don't run the
test. Just skip the test
Change-Id: Iebf526d4563ab9f3c054bbfb38c214a1b893fcb5
[ROCm/ROCR-Runtime commit: 64aa9009e1]
KFDTopologyTest.BasicTest duplicates Thunk logic to calculate VGPR size,
meaning it will always be the same, and SGPR size is a constant. Since
no benefit, remove comparisons.
Signed-off-by: Graham Sider <Graham.Sider@amd.com>
Change-Id: I99e7ff6fb69ed07bc0716fdf43946b19c67b9268
[ROCm/ROCR-Runtime commit: 3fb1496fb3]
This reverts commit ea19fbb646.
There are some openMP issues that were introduced after SVM userptr
feature was added.
Signed-off-by: Alex Sierra <Alex.Sierra@amd.com>
Change-Id: I7ef87c5232a3bcbe594c743fa4b4958601845ba5
[ROCm/ROCR-Runtime commit: f2bda56d04]
This reverts commit a89bcd0518.
There are some openMP issues that were introduced after SVM userptr
feature was added.
Signed-off-by: Alex Sierra <Alex.Sierra@amd.com>
Change-Id: I6566c9f0d39d05ecb92f38159880763f432939a5
[ROCm/ROCR-Runtime commit: d9f86ae02b]
Track Test Status in syslog, it will help understand
sys log assoicated with test cases.
Change-Id: I7c0749102db9bc73d6ae3a237ec347a8fefb12e9
Signed-off-by: James Zhu <James.Zhu@amd.com>
[ROCm/ROCR-Runtime commit: 7db29c4797]
Detect under-reporting of available memory by initially attempting to
allocate substantially more than reported available memory, and ensure
that the allocation fails. Continue shrinking the attempted allocation
until it succeeds, then fail the test if the successful allocation is
either too much more than or too much less than reported available.
Signed-off-by: Daniel Phillips <daniel.phillips@amd.com>
Change-Id: Ib418f0aa26e8db80590a6c5f2578da56a4b60f2b
[ROCm/ROCR-Runtime commit: e71eb13784]
Modifier scc is disabled from gfx90a's asm, so remove the
shader for gfx90a A+A and keep it for newer asics with scc
support.
Signed-off-by: Eric Huang <jinhuieric.huang@amd.com>
Change-Id: Iec3c7ccd5156a855adb2b02feb3db0761876aa2f
[ROCm/ROCR-Runtime commit: 8e8aa024fd]
To avoid confusion since this shader has changed to be persistent
(original IterateIsa may be re-used for debugger tests).
Signed-off-by: Graham Sider <Graham.Sider@amd.com>
Change-Id: I4643692765fc7665933257e89d5b922e779ad2e5
[ROCm/ROCR-Runtime commit: 6467664ec7]
Get more debug information about user pointers that were registered
through SVM API, and triggered by memory exception events.
A new kfdtest with this use case was also included inside
KFDExceptionTest.
Signed-off-by: Alex Sierra <alex.sierra@amd.com>
Change-Id: I8e9df3c1c6c3f42d7b9235d12406d80d31746443
[ROCm/ROCR-Runtime commit: 45fad29752]
Register and map userptrs through Shared Virtual Memory(SVM) API at
the Kernel level when available. Using this approach, performance
will be improve as register/unregister memory will not trigger any
system call to KFD driver.
Signed-off-by: Alex Sierra <alex.sierra@amd.com>
Change-Id: I20723cbeb340bf48b95e1115f0102c031397bc14
[ROCm/ROCR-Runtime commit: 178a619b80]
KFDCWSRTest.BasicTest is parameterized to allow an easy method of
tweaking the number of work-items (and save/restores). The input/output
buffers were previously hardcoded to a single page, which would cause a
segmentation fault if the number of work-items specified is greater than
1024 for wave32.
Signed-off-by: Graham Sider <Graham.Sider@amd.com>
Change-Id: Ieefc819a5d81c77cee88081a287fd383e6378e74
[ROCm/ROCR-Runtime commit: 73adbdee2c]
For software trap in GFX11, COMPUTE_PGM_RSRC1 must have PRIV = 1.
Signed-off-by: Graham Sider <Graham.Sider@amd.com>
Change-Id: Id504889c3ca2588b6c8cefdebaec00dcfc217995
[ROCm/ROCR-Runtime commit: 6294ef564b]
On error mmap returns value MAP_FAILED, which is (void *)-1, not NULL
pointer.
Change-Id: I81b187266c943fa0aa4fab21b529d4c2989b12ad
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
[ROCm/ROCR-Runtime commit: 590fd531c0]
IterateIsa had some leftover instructions from when the shader was
getting updated for KFDCWSRTest.BasicTest.
Signed-off-by: Graham Sider <Graham.Sider@amd.com>
Change-Id: I41ae7b7948cbe2aff8bf61b170b9a7d498b836a3
[ROCm/ROCR-Runtime commit: 82a41c7e4d]
This patch restructures the CWSR basic test and allows for
creating parameterized CWSR tests. This patch introduces four
parameterizations. These tests behave as follows:
This test dispatches the IterateIsa shader, which continuously
increments a vgpr for (num_witems / WAVE_SIZE) waves. While this shader
is running, dequeue/requeue requests are sent in a loop to trigger
CWSRs.
This test defines a CWSR threshold. Once the number of CWSRs triggered
reaches the threshold, a known-value is filled into the inputBuf to
signal the shader to exit.
4 parameterized tests are defined:
KFDCWSRTest.BasicTest/0
KFDCWSRTest.BasicTest/1
KFDCWSRTest.BasicTest/2
KFDCWSRTest.BasicTest/3
0: 1 work-item, CWSR threshold of 10
1: 256 work-items, CWSR threshold of 50
2: 512 work-items, CWSR threshold of 100
3: 1024 work-items, CWSR threshold of 1000
Tuple Format: (num_witems, cwsr_thresh)
num_witems: Defines the number of work-items.
cwsr_thresh: Defines the number of CWSRs to trigger.
Signed-off-by: Graham Sider <Graham.Sider@amd.com>
Change-Id: I639eb7bd75b14ee70e190b4bd19dcf34096fc7bf
[ROCm/ROCR-Runtime commit: 0dbac97b75]
This didn't return anything, so add a "return 0" at the end, since the
function expects to return an int value
Change-Id: I17c398e431b2ce4571e6ca4abe6d567f110ea2a7
[ROCm/ROCR-Runtime commit: 90ada94141]
: The kernel driver will do align VRAM allocations to 2MB, instead of 4KB.
Change-Id: Iea9d8c0f02999b9ea5fd931da82240a33f7bcc69
[ROCm/ROCR-Runtime commit: 17fb40f1f6]
KFDExceptionTest.SdmaQueueException allocates VRAM with host access. This
fails on small-BAR GPUs. This error was incorrectly ignored before
7ccda4ba26 ("kfdtest: Full TearDown and SetUp in child process").
The test doesn't really need host access to the memory. Therefore the fix
is to disable the HostAccess flag.
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Change-Id: Ifec279eeb6c1ecb1160db9b692e6dc8816d761a3
[ROCm/ROCR-Runtime commit: 9d33827a84]
The CMA feature is deprecated and about to be removed from the DKMS
branch. It was never supported upstream.
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Change-Id: I64b6213eb3adbdc550542e51181cd8ba6ca4cb45
[ROCm/ROCR-Runtime commit: cdaaf8236a]
With the next patch, child processes need to fully reinitialize the
topology in order to recreate the process apertures. Just calling
hsaKmtOpenKFD is no longer sufficient. Tests based on
KFDMultiProcessTest already did this correctly (KFDHWSTest, eviction
tests). This patch fixes KFDExceptionTest and KFDIPCTest.
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Change-Id: Iaad24e88ddd29c1105bf791a77891cc55a6072ff
[ROCm/ROCR-Runtime commit: 412b24137e]
LoopIsa is a shader that performs a variety of intensive
calculations in a loop. It is used by tests such as
KFDQMTest.QueuePriorityOn*
It contained a scalar load, despite not having any buffer to
read from. This load causes page faults on GFX11. It is
unclear why it did not cause page faults on earlier ASICs.
Remove the load.
Signed-off-by: David Francis <David.Francis@amd.com>
Change-Id: I7426d0db48e933f3bb870467ea88476f7a283040
[ROCm/ROCR-Runtime commit: 39e8a85aac]
When the shaders were moved to ShaderStore,
KFDQMTest.EmptyDispatch was erroneously
changed to use LoopIsa instead of NoopIsa.
Change it back.
Signed-off-by: David Francis <David.Francis@amd.com>
Change-Id: Iaf7d0d107e3bf3bd8b7d616b137a1740e309cf91
[ROCm/ROCR-Runtime commit: 4b8c74bf04]
Philip Yang
Graham Sider
David Francis
Mukul Joshi
Alex Sierra
Daniel Phillips
Eric Huang
Yifan Zhang
Felix Kuehling
kent.russell@amd.com
James Zhu
Ramesh Errabolu
Daniel Phillips
jie1zhan