Current test has 4 processes, each process allocate and access 512
buffers, this requires 2048 waves to access 2048 buffers at same time to
finish the test. For CPX compute partition mode, each compute node has
less waves and cause random test failure. Change test to 2 processes to
use 1024 waves to access 1024 buffers with the increased buffer size.
Add waves_num check to avoid the test failure on new ASICs or simulator,
skip test if the available waves is less than 1024.
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Change-Id: I64b5f9172b62cf38f62fbb0b48a801b8a11401c0
Current test has 4 processes, each process allocate and access 512
buffers, this requires 2048 waves to access 2048 buffers at same time to
finish the test. For CPX compute partition mode, each compute node has
less waves and cause random test failure. Change test to 2 processes to
use 1024 waves to access 1024 buffers with the increased buffer size.
Add waves_num check to avoid the test failure on new ASICs or simulator,
skip test if the available waves is less than 1024.
Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Change-Id: I64b5f9172b62cf38f62fbb0b48a801b8a11401c0
[ROCm/ROCR-Runtime commit: e6d4a32c42]
Ensure that ncclstringtotype iterates only over data types known to
nccl-tests (as indicated by test_typenum), not over a potentially larger
set of all NCCL types.
[ROCm/rccl-tests commit: 34d6d53910]
Ensure that ncclstringtotype iterates only over data types known to
nccl-tests (as indicated by test_typenum), not over a potentially larger
set of all NCCL types.
Using set as-is doesn't allow the user to set their own rocm path.
This is useful for community packagers or debugging.
Signed-off-by: Jeremy Newton <Jeremy.Newton@amd.com>
[ROCm/rocdecode commit: 07ecb5e7d6]
Using set as-is doesn't allow the user to set their own rocm path.
This is useful for community packagers or debugging.
Signed-off-by: Jeremy Newton <Jeremy.Newton@amd.com>
if the number of elements to be used in the allreduce operation is not
exact multiple of the work-array buffer size and number of pe's, we need
to adjust the algorithm to:
- initially perform a ring_allreduce on n_segments * chunk_size (which
is the integer division of the number of elements and the work-buffer
size, i.e. will not cover the entire buffer)
- perform another ring_allreduce where chunk_size is reduced to match
the remaining elements
- if the remaining elements from the previous step cannot evenly be
divded by the number of pe's, we need to perform a direct_allreduce on
the outstanding number of elements.
[ROCm/rocshmem commit: a4b4281f50]
if the number of elements to be used in the allreduce operation is not
exact multiple of the work-array buffer size and number of pe's, we need
to adjust the algorithm to:
- initially perform a ring_allreduce on n_segments * chunk_size (which
is the integer division of the number of elements and the work-buffer
size, i.e. will not cover the entire buffer)
- perform another ring_allreduce where chunk_size is reduced to match
the remaining elements
- if the remaining elements from the previous step cannot evenly be
divded by the number of pe's, we need to perform a direct_allreduce on
the outstanding number of elements.
Changes:
- Corrected max speed users can sample from FW/driver
is 100 ms
- Added warning to amdsmi_get_violation_status()
call on delay required 100ms to sample
- Removed guest support, this API will not be supported
- Updated CLI `amd-smi metric --throttle` outputs from
XXX_active -> XXX_status
XXX_percent -> XXX_activity
to align with host
- Changelog updated
Change-Id: Ib30dd35dcc04ff67904ca82c86a55a16689df226
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
Changes:
- Corrected max speed users can sample from FW/driver
is 100 ms
- Added warning to amdsmi_get_violation_status()
call on delay required 100ms to sample
- Removed guest support, this API will not be supported
- Updated CLI `amd-smi metric --throttle` outputs from
XXX_active -> XXX_status
XXX_percent -> XXX_activity
to align with host
- Changelog updated
Change-Id: Ib30dd35dcc04ff67904ca82c86a55a16689df226
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
[ROCm/amdsmi commit: 0ceca28f41]
ROCM_LIBPATCH_VERSION will be set in ENV and should be using that for setting library patch version. Fixing the bug as the patch version was not taken from ENV
Change-Id: I020e48ce5169c17b916be99311623198da1cabf7
ROCM_LIBPATCH_VERSION will be set in ENV and should be using that for setting library patch version. Fixing the bug as the patch version was not taken from ENV
Change-Id: I020e48ce5169c17b916be99311623198da1cabf7
[ROCm/rocm-core commit: 58d9a05f95]
USE $RPM_INSTALL_PREFIX0 rather than hard coded paths in the post/pre install scripts for rpm use case
Change-Id: I56c66f0befd5502fd2a4218f0b661661259436ed
USE $RPM_INSTALL_PREFIX0 rather than hard coded paths in the post/pre install scripts for rpm use case
Change-Id: I56c66f0befd5502fd2a4218f0b661661259436ed
[ROCm/rocm-core commit: f2208f6452]
Philip Yang
Yiltan Temucin
Kamil Iskra
jeffqjiangNew
AravindanC
Jeremy Newton
Julia Jiang
Edgar Gabriel
Aryan Salmanpour
gilbertlee-amd
Brandon Potter
Zhang Ava
Branislav Brzak
Gopesh Bhardwaj
Avinash Kethineedi
Chao Fei
Charis Poag
Nirmal Unnikrishnan
Ranjith Ramakrishnan