- Update the intra socket weight for partitions within single socket as
it is changed to 13 by the driver.
- Use the PCIe function to distinguish the partitions of the same device
such as TPX mode in gfx942.
Change-Id: I8e64023d44e37c2dbb105cbb343441a48021ba7b
[ROCm/clr commit: 1815fc808d]
When CL-GL interop is used, a GL context are used by two or more threads at the same time, which causes race condition.
Solution:
Add lock when accessing GL functions during CL-GL interop.
Change-Id: I3a34da3cbdf74c401111cc4e3a04ad84cc52709e
[ROCm/clr commit: 0c6a952a90]
These are missed for gfx1150/1.
Change-Id: I03d997e451d15a01a961e6597f805f634e5c3ae7
Signed-off-by: Lang Yu <lang.yu@amd.com>
[ROCm/clr commit: a0127c9eea]
Support new comgr unbundling action api to extract codebjects
in compressed and uncompressed modes.
Create HIP_ALWAYS_USE_NEW_COMGR_UNBUNDLING_ACTION ENV to
toggle new path and old path.
If HIP_ALWAYS_USE_NEW_COMGR_UNBUNDLING_ACTION=false(default),
uncompressed codeobject will go old path for better perf,
compressed codeobject will go new path.
If HIP_ALWAYS_USE_NEW_COMGR_UNBUNDLING_ACTION=true,
both uncompressed and compressed codeobjects will go new
path.
Add comgr wrapper for
amd_comgr_action_info_set_bundle_entry_ids()
Change-Id: I79952f132fe21249296685ee12cae05a4f9aec32
[ROCm/clr commit: d0050ce309]
This reverts commit 96e25898c8.
Reason for revert: SWDEV-455075, SWDEV-461507 - This change forces to
use ROCr's copy path. Reintroducing hostBlit copy path for
host-to-host copies.
Change-Id: Ic3c45b49e481c9dcdaa7611f61071778790b7e6c
[ROCm/clr commit: a9f05e22db]
This reverts commit e5b6537315ce9b2688ee0269ba0828a703c3e2c9.
The regressions (SWDEV-459556 and SWDEV-460260) caused by the original patch
has been resolved.
Change-Id: I32344492b4ff88bd7e91ea47983ac15636dc77c1
[ROCm/clr commit: b0930263e5]
* When no GPUs are available, hsa_init fails with HSA_STATUS_ERROR_OUT_OF_RESOURCES, and device and runtime initialization fails. In order for NoGpu tests to pass, true needs to be returned which will cause HIP_INIT_API to return proper error hipErrorNoDevice instead of hipErrorInvalidDevice.
Change-Id: I982d4416c92ed1b36893354d8b10d73df34f2478
[ROCm/clr commit: fdaa7141af]
- Print kernelname for graph launches, its hard to correlate packets
otherwise
- Print correlation_id if any
Change-Id: Ib8db7a00e4e7c98f570e71029e61d86f5dccc2ed
[ROCm/clr commit: 72d23a02c5]
- Gfx12 TCC cacheline size is 256B, Increase to have alignment
compatible. Eventually this needs to be replaced with what the query
returns.
Change-Id: I545929446c4faa3f26872a6290b3a89657888596
[ROCm/clr commit: bb01b4c3b4]
This reverts commit c0ee0ffa1c.
Reason for revert: <INSERT REASONING HERE>
New comgr unbundling action leads to perf drop for uncompressed code object. Will create a new patch to use old path for uncompressed , new unbundling api for compressed .
Change-Id: I41ef53b71fc9f7aaa8cf231d4d70945f1117db52
[ROCm/clr commit: a1350fe8c1]
- Remove Last graph node optimization and instead submit a barrier NOP
packet always. This simplifies the code.
Change-Id: Ied443173ba47a08b6df148ac7e3ead712acda11c
[ROCm/clr commit: badf2b0880]
- No cpu wait is needed when profiler is attached, Doing this changes
the application profile when roctracer is attached.
Change-Id: I2b9cfc48d697cf5ed54bb6a240d8c12bdb079171
[ROCm/clr commit: 51e4368723]
On gfx8, gfx9 devices before MI100 and gfx10.0 or gfx10.1
none of the memory ordering workarounds for device kernel arguments
can be applied. Use host kernel arguments on these devices.
Change-Id: I9be6fbfe4b3986eb7d9f83998334df5f03fd4124
[ROCm/clr commit: 2b746de6de]
hsa_amd_ipc_memory_detach is called with an invalid mapped pointer.
Changed to pass the svm pointer of the owner memory instead.
Change-Id: I8203c6e2d718efb8ca3b028309bc78caff8d4c7d
[ROCm/clr commit: 5bb30d7718]
Switch commands creation to the new suballocator to avoid
frequent expensive OS calls
Change-Id: I3597c811820e577c15708bad8b8a41aa53acc400
[ROCm/clr commit: 5b0bfdcbad]
The Readback and Avoid HDP Flush memory ordering workaround is
used as a fallback solution only when HDP flush register is invalid
Change-Id: Ic284eba1f95ed22b0270d3abeb904fb902015b1a
[ROCm/clr commit: 6cb7b6ec6b]
- Add LOG_TS mask for printing signal times
- Read raw ticks from signals
Change-Id: Ibdd0bf06c790729f6c65083a4784c97a3c3219e0
[ROCm/clr commit: 948ca5a931]
Ioannis Assiouras
Satyanvesh Dittakavi
kjayapra-amd
Saleel Kudchadker
Gu, Wangfeng
Lang Yu
Alex Xie
Tao Sang
German Andryeyev
Ajay
Sourabh Betigeri
Shilei Tian
Payam Ghafari
Brian Sumner
Vladana Stojiljkovic
Rakesh Roy
Maneesh Gupta
Jaydeep Patel