Move hidden heap creation to the kernel launch to make sure it's
allocated on the actual first usage.
Change-Id: I1b65a82fc06d9129ed45a69765bf14ea3d945b04
[ROCm/clr commit: 4975f69337]
Move StartLateDeviceInit() and FinishDeviceInit() calls in RGP
server to avoid a timeout
Change-Id: Ifd681859c7dc76259d7296aa8cc15305d563c9b2
[ROCm/clr commit: ecea224bcf]
- Memcpy1D node type is not complying with cuda
Signed-off-by: sdashmiz <shadi.dashmiz@amd.com>
Change-Id: If8113f5e699de0c62d98effc4580a2e0fee9a950
[ROCm/clr commit: 13c875eaf0]
Implements hipMemRetainAllocationHandle
HIP layer updates the svmPtr of the amd::memory
ROCCLR just manages the MemObjMap
This is because HIP knows the orignal (generic) address of the
physical memory whereas ROCCLR doesn't keep track of that
Change-Id: Ied26d7f814bc468f5cf586c967020737b9aa9e9f
[ROCm/clr commit: faa7ee48ba]
- make the defualt texref value compatible with cuda
Signed-off-by: sdashmiz <shadi.dashmiz@amd.com>
Change-Id: I2ae980e435f3b0fc15b237741e3f2b97c4257e12
[ROCm/clr commit: 8d93ff521f]
Windows complains about undefined symbol for
hipStreamWrite32/64 and hipStreamWait32/64 -
commit hash 08435a972b
Change-Id: I48b9a6591cab3a05baaedbc26030914dd930fb68
[ROCm/clr commit: de026633c0]
Fixes for hipGraphInstantiate OutofMemory issue and
soft hang of hipStreamSynchronize.
Change-Id: Ic2bb97582c5978ef2e4eb3a1b124483aa412838e
[ROCm/clr commit: c06bfa6bef]
This reverts commit a5b6de5037.
Reason for revert: <Breaking all the staging builds. this is breaking components which are using find_package(HIP)>
Change-Id: Ic7340fb461a5efdd170a0988731e0885538a11d6
[ROCm/clr commit: 43c650cf48]
GNUInstallDirs is used to allow the user to customize the install paths
of HIP, rather than using hardcoded locations.
See documentation for more information:
https://cmake.org/cmake/help/latest/module/GNUInstallDirs.html
Note that libdir must be overriden to "lib" before including
GNUInstallDirs, because by default, cmake tries to detect the libdir
path, but ROCm packaging would like to use lib by default for all
targets. This does not stop the user (or distros) from overriding.
Also note this change does no take into account the changes needed to
non-cmake files, such as perl scripts, so not all paths combinations are
necessarily functional.
Signed-off-by: Jeremy Newton <Jeremy.Newton@amd.com>
Change-Id: Iae80f47c47ea0a74fc1c221b6eea82b557601394
[ROCm/clr commit: bf4df229c9]
Introducing a VirtualMemObj map as it is needed to differentiate
between virtual address ranges and actual physical memory
This is because a whole VA range can have several physical memories
as chunks.
Change-Id: Ie2a972b4faf3f7d552cfa53e77898f80ad75740a
[ROCm/clr commit: 905088e4e7]
1.Keep track of library name in KHRicdVendorRec
2.Check if library with the same name has already been loaded before adding it in ICD list
CL#1760530
Change-Id: I1e0356422c71963788b76019b0d8db5b8542f9ee
[ROCm/clr commit: ed40c24fa3]
hipGraphExecMemcpyNodeSetParamsFromSymbo was not working in functional
case
Change-Id: I2ad04f6f91519efa075c36fe737a695fa1bc127a
[ROCm/clr commit: bb9e52ab9f]
This also fixes the QMCPack staging (SWDEV-335826) test failures related
to hipMemcpyToSymbol
Change-Id: Icc3ff04fb1e17999f5bddf12e1a7266e2289032f
[ROCm/clr commit: 8a333a989b]
haoyuan2
Sourabh Betigeri
German Andryeyev
sdashmiz
Chauncey Hui
Christophe Paquot
agunashe
Aakash Sudhanwa
Satyanvesh Dittakavi
Jeremy Newton
Todd tiantuo Li
Cordell Bloor
Rakesh Roy
pghafari
neqochan
kjayapra-amd
Jason Tang
Maneesh Gupta
Sarbojit Sarkar
Tao Sang