Wrapper header files
Soft link to libraries and binaries
rocm_smi.py and rsmiBindings.py installed in libexec/rocm_smi
Binaries, libraries and header files installed as per File Reorg folder structure
Change-Id: I3166ab67f89c2ae4aafbc87bb00c9a5233221ade
[ROCm/rocm_smi_lib commit: f1da5591b5]
Wrapper header files
Soft link to libraries and binaries
rocm_smi.py and rsmiBindings.py installed in libexec/rocm_smi
Binaries, libraries and header files installed as per File Reorg folder structure
Change-Id: I3166ab67f89c2ae4aafbc87bb00c9a5233221ade
Wrapper header files
Soft link to libraries and binaries
rocm_smi.py and rsmiBindings.py installed in libexec/rocm_smi
Binaries, libraries and header files installed as per File Reorg folder structure
Change-Id: I3166ab67f89c2ae4aafbc87bb00c9a5233221ade
[ROCm/amdsmi commit: f1da5591b5]
grpc v1.44.0 needs to link to library absl_synchronization. The
CMakeLists.txt is changed to link to that library if available.
Change-Id: I92f7247473a70e7a83416b9744e788e45d104565
grpc v1.44.0 needs to link to library absl_synchronization. The
CMakeLists.txt is changed to link to that library if available.
Change-Id: I92f7247473a70e7a83416b9744e788e45d104565
[ROCm/rdc commit: 2a46ee2ab2]
readlink() does not append a null byte to buffer. Initialize the
tpath to prevent stack buffer overflow.
Change-Id: I17895dc3576b080a0c35bd0528a5b83223ec1c1b
[ROCm/rocm_smi_lib commit: 4b65b0307f]
readlink() does not append a null byte to buffer. Initialize the
tpath to prevent stack buffer overflow.
Change-Id: I17895dc3576b080a0c35bd0528a5b83223ec1c1b
readlink() does not append a null byte to buffer. Initialize the
tpath to prevent stack buffer overflow.
Change-Id: I17895dc3576b080a0c35bd0528a5b83223ec1c1b
[ROCm/amdsmi commit: 4b65b0307f]
Excessive scratch allocations can normally trigger occupancy
reduction. This breaks cooperative groups so if occupancy
reduction is required on a cooperative dispatch fail with OOM.
Change-Id: I64612a2e38bf1286f3b74c1c2a68ab0c85452771
Excessive scratch allocations can normally trigger occupancy
reduction. This breaks cooperative groups so if occupancy
reduction is required on a cooperative dispatch fail with OOM.
Change-Id: I64612a2e38bf1286f3b74c1c2a68ab0c85452771
[ROCm/ROCR-Runtime commit: 8a6954c63c]
With asym. harvest hw does not issue groups equally to each SE,
occasionally hw will skip an SE so that the distribution reflects
each SE's CU count. Scratch resources must be allocated to reflect
this asymmetric distribution of groups.
Change-Id: I65e26206500483ea18e6e8796e65ecba5354b029
With asym. harvest hw does not issue groups equally to each SE,
occasionally hw will skip an SE so that the distribution reflects
each SE's CU count. Scratch resources must be allocated to reflect
this asymmetric distribution of groups.
Change-Id: I65e26206500483ea18e6e8796e65ecba5354b029
[ROCm/ROCR-Runtime commit: 552dcead93]
HW does not ignore low bits of the scratch wave count and will
stride beyond the end of the allocation if the wave count is
ever indivisible by SE count. Rather than returning the allocation
size for cached large scratch allocations, use the requested
scratch size in scratch setup. Scratch cache will retain the
cached allocation's size.
Change-Id: I0129ddc99a8940d01d8fbcd0b02d5061f31f456d
HW does not ignore low bits of the scratch wave count and will
stride beyond the end of the allocation if the wave count is
ever indivisible by SE count. Rather than returning the allocation
size for cached large scratch allocations, use the requested
scratch size in scratch setup. Scratch cache will retain the
cached allocation's size.
Change-Id: I0129ddc99a8940d01d8fbcd0b02d5061f31f456d
[ROCm/ROCR-Runtime commit: cedc3e80a8]
Always choose fing grain memory pool for hipHostMalloc
Choose coarse grain only if hipHostMallocNonCoherent is passed.
Change-Id: I9a67ba77335d4f373d32fea4ecd7848c77f9c190
[ROCm/clr commit: 0da908ec79]
Always choose fing grain memory pool for hipHostMalloc
Choose coarse grain only if hipHostMallocNonCoherent is passed.
Change-Id: I9a67ba77335d4f373d32fea4ecd7848c77f9c190
Currently, context save area size passed to KFD includes the
size of the debug area. Change this to report the actual size
of the context save area to KFD.
Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Change-Id: I5d440ae802255a97ade046775f6a000bae79d5d5
Currently, context save area size passed to KFD includes the
size of the debug area. Change this to report the actual size
of the context save area to KFD.
Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Change-Id: I5d440ae802255a97ade046775f6a000bae79d5d5
[ROCm/ROCR-Runtime commit: b8dc875b3c]
Add network communication through another GPU connected with NVLink
(PXN).
Add aggregation of messages coming from different local GPUs through
PXN and going to the same destination.
Add new v5 plugin API with grouped receives and tags.
Add compat for v4 plugins.
Add naming of NCCL threads to help debugging.
Fix NVLink detection and avoid data corruption when some NVLinks are
down.
Add support for Relaxed Ordering for IB.
Add profiling and timing infrastructure.
[ROCm/rccl commit: 3c223c105a]
Add network communication through another GPU connected with NVLink
(PXN).
Add aggregation of messages coming from different local GPUs through
PXN and going to the same destination.
Add new v5 plugin API with grouped receives and tags.
Add compat for v4 plugins.
Add naming of NCCL threads to help debugging.
Fix NVLink detection and avoid data corruption when some NVLinks are
down.
Add support for Relaxed Ordering for IB.
Add profiling and timing infrastructure.
gilbertlee-amd
Ranjith Ramakrishnan
Bill(Shuzhou) Liu
Ajay
Maneesh Gupta
Hao Zhou
Saleel Kudchadker
cjatin
Sean Keely
Sourabh Betigeri
Julia Jiang
ROCm CI Service Account
akolliasAMD
Mukul Joshi
Sylvain Jeaugey
Chauncey Hui
Mark Laws