hipSetDevice is not used correctly to allocate on multiple devices in mGPU setup.
Due to which hipMalloc was called on the same device on multiple threads leading to out of memory issues on some devices with lesser memory.
Change-Id: I0e5b1bc028b9ecb11bd40c3a5edf715f8bd721ff
[ROCm/clr commit: 6f5e63ebac]
If numa lib is in building system, define ROCCLR_NUMA_SUPPORT to
support numa; otherwise, don't support numa.
Change-Id: I3848d7fdec5a3813ff1edad9b71ff04372dc0b9a
[ROCm/clr commit: 214827defa]
Hip applications assume that hipEventRecord called from multiple
threads will contain exactly the last queued command to the stream.
Change-Id: I1da3259f143d7670d0870d9a47c08e32336b2222
[ROCm/clr commit: 5ef00cf6e9]
Since the introduction of BUILD_SHARED_LIBS there is only one target created : libamdhip64
Which is static ( libamdhip64.a ) or Dynamic ( libamdhip64.so ) depending on whichever it is
being compiled for. After this change we do not have any target libamdhip64_static which is
mentioned in the hipcc for linking. Hence cleaning the same.
Change-Id: Ia45c145e17b111b3f6a32299a11962b10f1cc539
[ROCm/clr commit: 7d3d8c8e6d]
JIRA : SWDEV-234471
With this change compilation of the ibamdhip64 to be decied by arguments to build_hip_on_rocclr.sh file
build_hip_on_rocclr.sh -r (current) shall conitnue to create libamdhip64.so;
build_hip_on_rocclr.sh -r a (new) shall create libamdhip64.a
other options remain the same
Changed the targets according to requirement of stage2 dependencies.
Changed find_lib with find_package
Adpated the review comments
Change-Id: I719918f73ab33cd8031a32db6fe9b8adaa1b4b87
[ROCm/clr commit: a77c7e21be]
Device backend is responsible for memory allocation, including
possible HMM support.
Change-Id: I0e4e5ae3b9551790f4f85f0791cca63196cc896e
[ROCm/clr commit: af1c4a5794]
Tests heq2, hne2, hle2, hge2, hlt2, hgt2 APIs for functionality
and NaN tests
SWDEV-238517 for enhancing hip unit tests
Change-Id: I88a9a8ead0d00a1261f3d650361d655f2f397e48
[ROCm/clr commit: fe3cd6ca27]
Two threads can enqueue to the same HostQueue (HostQueue::enqueue)
and result in last queued command being the first one reachine queue_.enqueue
NOTE: Temporarly make setLastQueuedCommand empty function to pass the build
Change-Id: Id09c3a28d184986f52b2ec86a2f6a18c40df1f0b
[ROCm/clr commit: 3d15a1e291]
Add "BUILD_SHARED_LIBS" flag to cmake file.
To build libamdhip64.so, you don't need change cmake cmd.
To build libamdhip64.a, you need append
-DBUILD_SHARED_LIBS=OFF
to cmake cmd.
Change-Id: Ibc30ed52963314b2b8cc1df73c360fc1ba15780a
[ROCm/clr commit: 4d67856bed]
- amdocl64.icd is renamed to amdocl64_<ROCM_PATCH_VERSION>.icd
- This will enable support for multiple icd for different versions of
ROCm
Signed-off-by: Pruthvi Madugundu <pruthvi.madugundu@amd.com>
Change-Id: I8031b19f8579507ffb6727dedcd2e3fbb4e45de8
[ROCm/clr commit: b88a313eff]
Satyanvesh Dittakavi
Jatin Chaudhary
Tao Sang
Saleel Kudchadker
Matt Arsenault
Rahul Garg
Jason Tang
Chauncey Hui
Aryan Salmanpour
jujiang
Vlad Sytchenko
Sudheer Kumar
German Andryeyev
Ashutosh Mishra
Payam
Christophe Paquot
Evgeny
sushantkumar14
mshivama
Sarbojit Sarkar
kjayapra-amd
agodavar
Pruthvi Madugundu