Now that HsaNodeProperties is passed in to
topology_get_node_props_from_drm, check that pointer instead of the
pointer for MarketingName (which throws a compiler warning)
Signed-off-by: kent.russell@amd.com <kent.russell@amd.com>
Change-Id: If76b24e1bab5a62e514ab440b6316c7b7cd264c1
Add agent info query HSA_AMD_AGENT_INFO_ASIC_FAMILY_ID.
Then we can remove the codes to parse family id.
Signed-off-by: Lang Yu <Lang.Yu@amd.com>
Change-Id: I3ac4746d3015e89b32322ebc0f8a3084f98677a4
Query family id info from drm render node, then
ROCr can query this info directly from Thunk
instead of parsing the info by itself.
Signed-off-by: Lang Yu <Lang.Yu@amd.com>
Change-Id: I030bd27ab2379fbf87f3d787302c3b8613456278
Required due to LLVM retirement of llvm::apply_tuple, instead using
std::apply which was introduced in C++17.
Signed-off-by: Graham Sider <Graham.Sider@amd.com>
Change-Id: I6646ebcca7d71d3e1bcf340ccfa3db2c15a3110a
Failure with new CWSR tests reported for GFX10, for now add to blacklist.
Signed-off-by: Graham Sider <Graham.Sider@amd.com>
Change-Id: I5b2bd9ec61c64ad66e1c34ba2c192bece808f56f
This reverts commit c904cc5856.
The change from using RUNPATH to RPATH was not approved formally.
Reverting this patch until this gets approved.
Change-Id: Ibc1a8f9d5dfa6694adacccfd9e3b0d053660e848
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
The debugger can now request snapshot copies with entry size and
set/clear watchpoints by device.
v3: drop min version check to v10.0
v2: check runtime allowance from v10.3 to 13.x
Signed-off-by: Jonathan Kim <jonathan.kim@amd.com>
Change-Id: I9befefb596201a11591de218db29a9317b41e69b
The allocation logic of the SPI does not take into account compute
user thread management settings for masking CUs with the exception of
skipping fully disabled SEs. This means that occupancy limited
dispatches such as cooperative launch may over allocate onto hardware
resources that are not immediately available, resulting in a potential
barrier logic hang as occupying work groups are waiting on enqueued
work groups to reach the barrier.
Further work will have to be done to get the per-SA CU enablement count
from the KFD in order to correctly clip the cooperative CU limit based
on the CU mask, which will require breaking the current ABI.
For now, report that cooperative launch is not supported while a CU
mask has been applied to prevent potential shader hangs.
Change-Id: I8be4bb47d65ceb62d805f36ef6ef3996d756021f
New environment variable HSA_OVERRIDE_CPU_AFFINITY_DEBUG to
enable/disable overriding CPU affinity.
Default value is enabled(1).
This is a temporary variable and may be removed in the future.
Change-Id: Id6a7c611730471ddc276ca333fde1e57046bf32a
Fix for regression in commit:
8a0fe6a832
When running rocrtstNeg.Queue_Validation_InvalidWorkGroupSize, each
time rocrtst::LoadKernelFromObjFile is called, a new CodeObject is
created and not deleted until end of the whole test. Each CodeObject
keeps an open file descriptor of the kernel file and this can exceed
maximum allowed open files on some systems. Deleting the CodeObjects
after each iteration in the test.
Change-Id: I388e56f95f7b671ecc29d5ecb4eb8ac2d0ddc412
For gfx11 the image type table has some different values compared to
previous asic families (e.g TYPE_SRGB). Creating a new LUT class to
use these new values.
Change-Id: Ifdfc6cd29bfd5f4ec2643c848fcb9986eb874f9e
This library was taken from public MESA library:
https://gitlab.freedesktop.org/mesa/mesa/-/tree/main/src/amd/addrlib
with top commit:
2866ae32da0348caf71ad2d11c353321df626ff4
Removing macros.h as it is no longer used by addrlib
Change-Id: I0fdabfe48b74c259b4d29d81beae89604bbc141a
Non-paged allocation for queue memory necessary for binding wptr to
GART. Required to support usermode queue oversubscription with MES for
GFX11.
Adds AllocateNonPaged entry to MemoryRegion::AllocateEnum for clarity;
aliases AllocateIPC.
Signed-off-by: Graham Sider <Graham.Sider@amd.com>
Change-Id: I1a97a1820da26cf2433d9c237b2e6d2b0b8628b4
Adding new ImageManager class for GFX11 GPUs
ImageManagerGfx11 functions copied from ImageManagerNv.
Register descriptions in resource_gfx11.h updated for gfx11.
Signed-off-by: David Yat Sin <david.yatsin@amd.com>
Change-Id: I48b39f6a633aef14aa829f7240a43fe0feb1c290
GPUs excluded by RVD are not expected to have scratch, memory, trap
handling nor memory regions set up. Now that these GPUs are added to
a new list, early return on agent destruction to prevent bad function
calls on destroy.
Also fix up broken memory releases between the gpu lists and ugly braces.
Change-Id: I52fc6e86ceba0a0383cedc63310eb409515eaf9f
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
The debugger depends on the CWSR area being executable. Set the right
flag when registering SVM memory.
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Tested-by: Laurent Morichetti <Laurent.Morichetti@amd.com>
Change-Id: I7441e214d1a4da8324d775e777976fabd1c81a6f
The current state of hsa-rocr does
NOT requires thunk lib as its dependency.
Its unnecessary pulling thunk package while
installing rocr. This patch corrects
the same
Change-Id: Id98ede8b66ffd9aaf4a47da96ba2f981f4c3da73
Maintainer distribution list field had wrong information.
Adding the newly formed DL by the component team.
Change-Id: I61651e429375cdc512d0fe4b0768f917506b5392
KFDExceptionTest.SdmaQueueException allocates VRAM with host access. This
fails on small-BAR GPUs. This error was incorrectly ignored before
412b24137e ("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
The CMA feature is deprecated and about to be removed from the DKMS
branch. It was never supported upstream. Leave dummy functions in
place for now.
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Change-Id: I9e51403d753cb91630553aff4f19e931af509740
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
hsaKmtMapMemoryToGPU should not try to map VRAM on peer GPUs that don't
have an IO-Link to the memory. The new P2P mapping code in KFD will
fail otherwise.
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Change-Id: I6d59b55651b98756865a0f69eafef3e386372cf3
This allows init_process_apertures to use the whole consistent topoology
instead of taking its own partial snapshot.
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Change-Id: Ia13e7aa7fcd090ea8d6cacd4babb29a27c20207f
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
We should link against numa without hardcoding the path to it.
CMake should determine how to link numa automatically, similar to how rt
and pthread is linked.
Fixes
Change-Id: Ifb9ac30e200c66cbd7f1cf80d25fffef1dcf8d2f
Signed-off-by: Jeremy Newton <Jeremy.Newton@amd.com>
jie1zhan
kent.russell@amd.com
Lang Yu
Graham Sider
David Yat Sin
Jonathan Kim
Yifan Zhang
Jay Cornwall
skhatri
Konstantin Zhuravlyov
Felix Kuehling
Ashutosh Mishra
Sean Keely
Jeremy Newton