Update status type for EPERM and ENOENT based on feedback from ticket.
Update error output to LOG_ERR.
---------
Signed-off-by: Juan Castillo <juan.castillo@amd.com>
Update status type for EPERM and ENOENT based on feedback from ticket.
Update error output to LOG_ERR.
---------
Signed-off-by: Juan Castillo <juan.castillo@amd.com>
[ROCm/amdsmi commit: 60492e754f]
1. Get the bad pages threshold of a processor.
2. Verify the checksum of RAS EEPROM
Signed-off-by: Meng Li <li.meng@amd.com>
[ROCm/amdsmi commit: dc400d916e]
It consists of two main steps:
1. Generating Bindings with `bindgen`:
- The `build.rs` script uses `bindgen` to generate Rust FFI (Foreign
Function Interface) bindings for the AMD SMI C library. This step
automatically exports all enums, structs, unions, and unsafe functions
from the C library into Rust. This provides a comprehensive low-level
interface to the AMD SMI library.
2. Implementing Safe Rust Wrappers:
- The generated bindings are then wrapped in safe Rust functions. These
safe wrappers handle error checking, resource management, and provide a
more idiomatic Rust interface. This ensures that users of the library
can interact with the AMD SMI functions without dealing with unsafe code
directly.
Change-Id: I7d5e49e59826164fc911ced04ef7ca5706b7cc05
Signed-off-by: Tim Huang <tim.huang@amd.com>
It consists of two main steps:
1. Generating Bindings with `bindgen`:
- The `build.rs` script uses `bindgen` to generate Rust FFI (Foreign
Function Interface) bindings for the AMD SMI C library. This step
automatically exports all enums, structs, unions, and unsafe functions
from the C library into Rust. This provides a comprehensive low-level
interface to the AMD SMI library.
2. Implementing Safe Rust Wrappers:
- The generated bindings are then wrapped in safe Rust functions. These
safe wrappers handle error checking, resource management, and provide a
more idiomatic Rust interface. This ensures that users of the library
can interact with the AMD SMI functions without dealing with unsafe code
directly.
Change-Id: I7d5e49e59826164fc911ced04ef7ca5706b7cc05
Signed-off-by: Tim Huang <tim.huang@amd.com>
[ROCm/amdsmi commit: d32f2a109a]
Error handling was not displaying the missing parameter details in
argument type validator functions. Fixed this by passing param name to
AmdSmiMissingParameterValueException.
Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
Error handling was not displaying the missing parameter details in
argument type validator functions. Fixed this by passing param name to
AmdSmiMissingParameterValueException.
Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
[ROCm/amdsmi commit: 3897670757]
Update wrapper script is not generating the python wrapper properly.
Fixed how the structure names are parsed.
Signed-off-by: Joseph Narlo <joseph.narlo@amd.com>
Update wrapper script is not generating the python wrapper properly.
Fixed how the structure names are parsed.
Signed-off-by: Joseph Narlo <joseph.narlo@amd.com>
[ROCm/amdsmi commit: 84f4d397aa]
Tiny PR to remove occurrences of "Kernel **Fusion** Driver" in
public-facing docs.
Signed-off-by: Peter Park <peter.park@amd.com>
[ROCm/amdsmi commit: d9bba639df]
We can inherit it from gtest, but not in ASAN builds. And we should be
including what we use, instead of hoping to inherit it through other
headers
Change-Id: Id47ab06a57e1c71c88f72da5f21a71f37db8a2f3
Signed-off-by: Kent Russell <kent.russell@amd.com>
We can inherit it from gtest, but not in ASAN builds. And we should be
including what we use, instead of hoping to inherit it through other
headers
Change-Id: Id47ab06a57e1c71c88f72da5f21a71f37db8a2f3
Signed-off-by: Kent Russell <kent.russell@amd.com>
[ROCm/ROCR-Runtime commit: eda54222ea]
- When we use blit(compute) copies, two subsequent copies may read for
the same source buffer, the buffer may get modified by the host in
between and if the src buffer was allocated with non-coherent flag, the
device may simply use stale value from previous cacheline fetch. This is
a corner case.
Change-Id: I2ce261c6f6fa4e5bb608f116548e5cc711ae6f3c
[ROCm/clr commit: b63005d550]
- When we use blit(compute) copies, two subsequent copies may read for
the same source buffer, the buffer may get modified by the host in
between and if the src buffer was allocated with non-coherent flag, the
device may simply use stale value from previous cacheline fetch. This is
a corner case.
Change-Id: I2ce261c6f6fa4e5bb608f116548e5cc711ae6f3c
Network user buffer support for collectives
* Leverage user buffer registration to achieve zero-copy
inter-node communications for Ring, NVLS and Collnet
Add RAS subsystem
* Create a RAS thread keeping track of all NCCL communicators.
* Add a ncclras tool contacting the RAS thread and getting a
report.
Add fp8 support
* Add support for e5m2 and e4m3 8-bit floating point operations.
* Use Tree/PAT algorithms when possible for better numerical
stability.
Add NIC fusion
* Add a NET API to ask the network plugin to fuse a set of
interfaces together.
* Fuse multiple NICs under the same PCI switch as a single,
larger NIC.
Socket connection failure retry
* Retry in case of socket connection failure (unreachable host)
* Avoid "Software caused connection abort" errors on retries
QP connection failure retry
* Retry in case of IB QP connection failure during ibv_modify_qp.
NET API improvements
* Allow plugins to force a flush in case data and completion
ordering is not guaranteed.
* Indicate when completion is not needed (e.g. for the LL128
protocol), allowing plugins to skip generating a completion.
* Allow for full offload of allgather operations when using one
GPU per node.
NCCL_ALGO/NCCL_PROTO strict enforcement
* Extend NCCL_ALGO/NCCL_PROTO syntax to be able to specify
ALGO/PROTO filters for each collective operation.
* Strictly enforce the ALGO/PROTO filters, no longer fall back
on the ring algorithm when the filtering leaves no option and
error out instead.
Enable CUMEM host allocations
* Use cumem functions for host memory allocation by default.
Improved profiler plugin API
* Avoid dependencies with NCCL includes.
* Add information on whether the buffer is registered or not
Adjust PAT tuning
* Improve transition between PAT and ring at scale.
Fix hangs when running with different CPU architectures
* Detect when we use a mix of GPU architectures
* Ensure Algo/Proto decisions are made based on that unified
state.
Fix FD leak in UDS
* Fix a leak when mapping buffers intra-node with cumem IPCs.
Fix crash when mixing buffer registration and graph buffer registration.
* Separate local and graph registration to avoid crashes when we free
buffers.
Fix user buffer registration with dmabuf
* Make ncclSend/ncclRecv communication with buffer registration functional
on network plugins relying on dmabuf for buffer registration.
Fix crash in IB code caused by uninitialized fields.
Fix non-blocking ncclSend/ncclRecv
* Fix case where ncclSend/ncclRecv would return ncclSuccess in non-blocking
mode even though the operation was not enqueued onto the stream.
* Issue #1495
Various compiler tweaks and fixes
* PR #758
Fix typo in ncclTopoPrintGraph
* Issue #1468
[ROCm/rccl commit: 6aae379278]
Network user buffer support for collectives
* Leverage user buffer registration to achieve zero-copy
inter-node communications for Ring, NVLS and Collnet
Add RAS subsystem
* Create a RAS thread keeping track of all NCCL communicators.
* Add a ncclras tool contacting the RAS thread and getting a
report.
Add fp8 support
* Add support for e5m2 and e4m3 8-bit floating point operations.
* Use Tree/PAT algorithms when possible for better numerical
stability.
Add NIC fusion
* Add a NET API to ask the network plugin to fuse a set of
interfaces together.
* Fuse multiple NICs under the same PCI switch as a single,
larger NIC.
Socket connection failure retry
* Retry in case of socket connection failure (unreachable host)
* Avoid "Software caused connection abort" errors on retries
QP connection failure retry
* Retry in case of IB QP connection failure during ibv_modify_qp.
NET API improvements
* Allow plugins to force a flush in case data and completion
ordering is not guaranteed.
* Indicate when completion is not needed (e.g. for the LL128
protocol), allowing plugins to skip generating a completion.
* Allow for full offload of allgather operations when using one
GPU per node.
NCCL_ALGO/NCCL_PROTO strict enforcement
* Extend NCCL_ALGO/NCCL_PROTO syntax to be able to specify
ALGO/PROTO filters for each collective operation.
* Strictly enforce the ALGO/PROTO filters, no longer fall back
on the ring algorithm when the filtering leaves no option and
error out instead.
Enable CUMEM host allocations
* Use cumem functions for host memory allocation by default.
Improved profiler plugin API
* Avoid dependencies with NCCL includes.
* Add information on whether the buffer is registered or not
Adjust PAT tuning
* Improve transition between PAT and ring at scale.
Fix hangs when running with different CPU architectures
* Detect when we use a mix of GPU architectures
* Ensure Algo/Proto decisions are made based on that unified
state.
Fix FD leak in UDS
* Fix a leak when mapping buffers intra-node with cumem IPCs.
Fix crash when mixing buffer registration and graph buffer registration.
* Separate local and graph registration to avoid crashes when we free
buffers.
Fix user buffer registration with dmabuf
* Make ncclSend/ncclRecv communication with buffer registration functional
on network plugins relying on dmabuf for buffer registration.
Fix crash in IB code caused by uninitialized fields.
Fix non-blocking ncclSend/ncclRecv
* Fix case where ncclSend/ncclRecv would return ncclSuccess in non-blocking
mode even though the operation was not enqueued onto the stream.
* Issue #1495
Various compiler tweaks and fixes
* PR #758
Fix typo in ncclTopoPrintGraph
* Issue #1468
dependabot[bot]
Castillo, Juan
Williams, Justin
Meng, Li (Jassmine)
Huang, Tim
Kanangot Balakrishnan, Bindhiya
Pham, Gabriel
Narlo, Joseph
Park, Peter
Rahul Manocha
kjayapra-amd
Choudhary, Rahul
Jeffrey Novotny
Kent Russell
Maisam Arif
gobhardw
Saleel Kudchadker
JhaShweta1
Sylvain Jeaugey
stali