Before gfx90a, coherent memory is uncached. So it was reasonable
when environment variable HSA_DISABLE_CACHE is set, memory is mapped
as coherent. On gfx90a, coherent memory can be cached, so mapping
memory as coherent can't guarantee memory is uncached. When
HSA_DISABLE_CACHE is set, we have to map memory as uncached.
Change-Id: Ia5ed4cf0ad6aef5644dc8c9e6632b52d606f06f4
Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
[ROCm/ROCR-Runtime commit: f132fb2cd0]
Refer to commit "Mark buffers accessed by CP as UC"
A+A buffers are mapped as NC. CP (PM4Writes) need ReleaseMem function to
ensure the write go through to the memory
Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Change-Id: I4ee55a6e40fba078f5950d95c8fee7ee076260bf
[ROCm/ROCR-Runtime commit: 57f46b53ec]
Refer to commit: " Mark buffers accessed by CP as UC"
Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Change-Id: I1816e035dbb3178f28f5e34b050c20ecca282060
[ROCm/ROCR-Runtime commit: 0e8500b886]
This change might be redundant if ROCr takes care of it
Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Change-Id: I7b67143a8ad21baa61b7eda7b8e5fe0ac1e33830
[ROCm/ROCR-Runtime commit: 10674916e4]
This change is for the A+A bring-up branch as it needs to made more
generic to handle all ASICs.
For A+A all the system buffers are mapped as NC (non coherent) unless
explicitly marked as UC (uncached). The coherency is then expected to be
handled by shader by explicitly using acquire/release instructions.
However, CP doesn't have same feature. The buffers used by CP thus have
to UC. For now queue buffer and Signal handler memory is marked as UC.
This change shouldn't affect other ASICs since Uncached flag is not used
in those. However, this change still need to be made more generic.
Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Change-Id: I56c37a809913f7f08c94d01b0572d0f4864939aa
[ROCm/ROCR-Runtime commit: 7c05c5240f]
On gfx9, the maximum number of wavefronts per queue is the minimum of
40 waves per compute units, or 512 waves per shader engine. On gfx10,
there can only be 32 waves per compute units.
Signed-off-by: Laurent Morichetti <laurent.morichetti@amd.com>
Change-Id: I148d1a4fe6c07cdbfaa1f77939eb29311c81c008
[ROCm/ROCR-Runtime commit: 4cf11c3a7e]
Reserve some space in the context save area for the debugger's
use. There should be 32 bytes per wave for a given queue.
Change-Id: I65ddb6123d0f6afd3149844617ad19023009101d
[ROCm/ROCR-Runtime commit: a83f9b67ce]
Temporarily blacklist some tests on gfx90a until they are solved.
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
Change-Id: I87cc3a996ea7d55ed8f20f5b4eecfd8bb691effd
[ROCm/ROCR-Runtime commit: e342c9c890]
On every new asic with new stepping, we need to manually relax this
checking. This check is not very helpful. Delete it.
Change-Id: I11f813023ca2566d82f6d11121d4be38c296674b
Signed-off-by: Oak Zeng <Oak.Zeng@amd.com>
[ROCm/ROCR-Runtime commit: 1f05b54dc9]
Due to cache coherence change, the remote vram mapping is changed
to cached, the written value by remote shader will not be read by
local shader. So the test will fail.
Signed-off-by: Eric Huang <jinhuieric.huang@amd.com>
Change-Id: I2b64e8a30bed0066e159bad9bb7febae5ebe84aa
[ROCm/ROCR-Runtime commit: ec7ba38b23]
XNACK API for GPUs that support this mode. This API
makes calls to amdgpu driver to configure xnack mode.
It supports set xnack mode and query the current mode used.
Change-Id: If865fd0e3f900f008243dc49504e1a0694e1791a
Signed-off-by: Alex Sierra <alex.sierra@amd.com>
[ROCm/ROCR-Runtime commit: 3f45f602d4]
Add function definitions to support SVM (shared virtual memory)
and xnack set.
Change-Id: Ia97ad9d0c449d8d500d799f702e1a58e87d65a56
Signed-off-by: Alex Sierra <alex.sierra@amd.com>
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
[ROCm/ROCR-Runtime commit: a352639df5]
Add svm (shared virtual memory) range and xnack mode
APIs.
Change-Id: Ibd8d7fe566dc200730da0c892caa71aad7589ebd
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Signed-off-by: Alex Sierra <alex.sierra@amd.com>
[ROCm/ROCR-Runtime commit: 5ae49f2321]
strlen(src) should not be used as the length in strncpy. Use memcpy
since we know the length of the string, and ensure that we
NULL-terminate regardless of length
Signed-off-by: Kent Russell <kent.russell@amd.com>
Change-Id: I21cc6d106510c69464e7ac9d3fc7da3a1e6d1a68
[ROCm/ROCR-Runtime commit: 731a06c704]
The largebar check will exit exceptionally from test
when destination node is not set.
Signed-off-by: Eric Huang <jinhuieric.huang@amd.com>
Change-Id: I8bf0fed613250cc71468208e645fc562fb1a8757
[ROCm/ROCR-Runtime commit: 18ead8815c]
Update build script and CMakeLists_sp3.txt file as SP3 directory
structure has changed.
The SP3 source code with gfx90a suport is merged into a
new branch mukjoshi/sp3_gfx90a.
Please make sure to checkout this branch before using the
build script to generate the static library.
Change-Id: I2bf0ade8b2d254cd7648cc8a6d69a83ee51344cd
[ROCm/ROCR-Runtime commit: da3abfb0f8]
Add updated SP3 static library with support for gfx90a and
also add initial corresponding changes in kfdtest.
Change-Id: I71bc6404ace7f9bf0dd74e712287136aa2b8a03d
[ROCm/ROCR-Runtime commit: c861873dae]
Given the chance of local memory breakage is so high on emulators, we
should use this simple test to check the local memory function.
Signed-off-by: Yong Zhao <Yong.Zhao@amd.com>
Change-Id: Ifc48c12e11d75cc777ed7ea13e03bf54c2458e12
[ROCm/ROCR-Runtime commit: 690a148427]
PKG_CONFIG_PATH environment variable should be set to
<rocm_path>/lib/pkgconfig, because the *.pc file is located there.
Signed-off-by: Yong Zhao <Yong.Zhao@amd.com>
Change-Id: Iec503b1c2409987e52fd88fea160c70762686a28
[ROCm/ROCR-Runtime commit: 33c34506fa]
It is to provide an option to map specific memory as
uncached on A+A HW platform.
Signed-off-by: Eric Huang <JinhuiEric.Huang@amd.com>
Change-Id: Ib665cb306a0e78aba3ea5ee2f0e46cb62ae139f8
[ROCm/ROCR-Runtime commit: 2464bfc714]
This will give out more info.
Change-Id: I407422b84bebdf39a886c57736093a035ff02118
Signed-off-by: Yong Zhao <Yong.Zhao@amd.com>
[ROCm/ROCR-Runtime commit: 8881075ab2]
Legacy p2p copy path incorrectly transfered in whole pages rather than
the requested size.
Change-Id: I9aa7337754f9e32f587a0cc5305f8ffeb6196f10
[ROCm/ROCR-Runtime commit: 34ac62274a]
Test for HQD preemption during stalled context restore. Added for
regression testing against new microcode.
Change-Id: I13eb7d1c598062390e12cf8a5237e53b6489f232
Signed-off-by: Jay Cornwall <jay.cornwall@amd.com>
[ROCm/ROCR-Runtime commit: 526afa8394]
Replace the stop reasons ttmp11.trap_raised and ttmp11.excp_raised
with ttmp11.wave_stopped which indicates that the trap handler has
halted the wave as the result of an event (trap, single-step or
exception).
If the wave is stopped because of a trap, also record the trap_id in
ttmp11.saved_trap_id[7:0].
Save status.halt in ttmp11.saved_status_halt, so that it can be
restored when resuming a wave (changing a wave's state from stopped to
running or single-stepping).
Change-Id: I7322f59b60e8cc1b92bf5f067dba606a3109ef49
[ROCm/ROCR-Runtime commit: 9ca79d072a]
The purpose of this patch is to add a missing device ID for gfx1030.
The missing ID "0x73A1" is now added to the "topology.c" file.
Signed-off-by: Ori Messinger <Ori.Messinger@amd.com>
Change-Id: I05a8a55e2c46f941a039fa72a6a5e76bf2a52736
[ROCm/ROCR-Runtime commit: 46c94662b7]
This patch is to let ROCr recognize new gfx10.3.3 ISA.
Change-Id: Ied23eee2752e14c19c8c0a6d7789fded9940e31e
Signed-off-by: Huang Rui <ray.huang@amd.com>
[ROCm/ROCR-Runtime commit: feeb2f62e2]
To support single stepping the instruction preceding an s_endpgm,
unwind the PC by 8 bytes and set ttmp11[9] to notify the debugger
that the wave is halted with a modified PC.
Bump the debug r_version for this new trap handler ABI.
Change-Id: I55e4e0d65576f92da14a336266c31c513baab547
[ROCm/ROCR-Runtime commit: 8aec53969f]
Inside Docker, when limit GPU number to one, it may cause node
numIOLinks bigger than total node number.
Signed-off-by: Gang Ba <gaba@amd.com>
Change-Id: Ib84f2f05f8e0c70e48b9043b79aec02b5a214bbe
[ROCm/ROCR-Runtime commit: 7652932c38]
The MMBench issue has fixed by patch:
kfdtest: Take vram size into account when calculate buffer number
So it can remove it from kfdtest blacklist now.
Change-Id: Ib918bca72adf28f4082248fae1e3287d395c32bf
Signed-off-by: changzhu <Changfeng.Zhu@amd.com>
[ROCm/ROCR-Runtime commit: 18d9cca879]
This patch is to add Cezanne/Lucienne support on thunk.
Change-Id: Icd9b9913fa87bbfe6c71b36a2892d6ddb73e3ddd
Signed-off-by: Prike.Liang <Prike.Liang@amd.com>
[ROCm/ROCR-Runtime commit: 7e184ebb3a]
Oak Zeng
Harish Kasiviswanathan
Laurent Morichetti
Amber Lin
Eric Huang
Alex Sierra
Philip Yang
Kent Russell
Jonathan Kim
Mukul Joshi
Yong Zhao
Mike Li
Jason Tang
Sean Keely
Jay Cornwall
Evgeny
Ori Messinger
Huang Rui
Gang Ba
Tony Tye
changzhu
Chris Freehill
Prike.Liang