GitLab

Co-authored-by: zhiyi Hu <zhiyihu@U-NYQQMGK0-2250.local>

* Add arg --pressure-test for test_low_latency.py

Add arg --pressure-test for test_low_latency.py
Signed-off-by: Guangguan Wang <guangguan.wang@linux.alibaba.com>

* Export NVSHMEM_QP_DEPTH

Export NVSHMEM_QP_DEPTH
Signed-off-by: Guangguan Wang <guangguan.wang@linux.alibaba.com>

---------
Signed-off-by: Guangguan Wang <guangguan.wang@linux.alibaba.com>

* Remove an outdated todo

* Increase the number of combine forward warps.

* forwarder use TMA.

* Small fix

* Code lint

---------
Co-authored-by: Chenggang Zhao <chenggangz@deepseek.com>

Fix for data error and kernel hung because of inflight rdma channel head update

When dispatch/combine, neither sender nor receiver waits
for the finish of the rdma channel head update, which may
result in the remaining inflight head update wqes even after
the kernel finished. Once the infight wqes arrive after the
rdma channel head buffer cleaning for the next round of
dispatch/combine, the rdma channel head buffer will be re-
written to a none-zero value. The rdma sender can reuse the
data buffer before the rdma receivers consume the date buffer
because of the wrong rdma channel head, cauing date error and
kernel hung.
For performance considering, to overlap the inflight wqes' RTT,
fix this issue by waiting for all previous inflight wqes to
complete before cleaning rdma buffers in the next round of
dispatch/combine.
Signed-off-by: Guangguan Wang <guangguan.wang@linux.alibaba.com>

third-party: Improvements to NVSHMEM Integration

* Fix rdma head movement

* Optimize `cached_notify` by using TMA.

* Fix

* Small fix

Signed-off-by: Seth Howell <sethh@nvidia.com>

correct the wqe_idx in rdma write wqe

correct the wqe_idx in rdma write wqe when num_wqes > 1 in nvshmemi_ibgda_put_nbi_warp.
Signed-off-by: Guangguan <guangguan.wang@linux.alibaba.com>

This enables the CPU-Assisted data path.
Signed-off-by: Seth Howell <sethh@nvidia.com>

Responding to review comments.
Signed-off-by: Seth Howell <sethh@nvidia.com>

Signed-off-by: Seth Howell <sethh@nvidia.com>

Signed-off-by: Seth Howell <sethh@nvidia.com>

This will give consumers an opportunity to update their builds.
Signed-off-by: Seth Howell <sethh@nvidia.com>

* Strengthen the barrier in `cached_notify`

* lint

* Change the timing method

* lint

* feat: low latency combine inplace TMA

* optimize tma pointer with PatternVisitor

* Minor cleanup

* Add `elect_one_sync`

---------
Co-authored-by: Zhean Xu <xza@deepseek.com>
Co-authored-by: Chenggang Zhao <chenggangz@deepseek.com>

Signed-off-by: Seth Howell <sethh@nvidia.com>

This allows users to use NVSHMEM without setting the driver regkey.
Signed-off-by: Seth Howell <sethh@nvidia.com>

NVSHMEM 3.3 and above support the host-side features
in the patch.

Note: Removed recv queue support
Signed-off-by: Seth Howell <sethh@nvidia.com>

ibgda: support non-bond dual-port environments via multi-port config

fix format

* Explicitly destroy the C++ runtime and release resources.

* Small fix

* fix typo

* Add a flag to control whether explicit `destroy()` is required.

* Let forwarders use a dedicated SM

* Shuffle rdma idx

* Sender use TMA.

* Adjust the tuning chunk size.

* Modify NVL chunk layout.

* Update some combine config.

* Small lint

* Minor fix

* Overlap TMA store

---------
Co-authored-by: Chenggang Zhao <chenggangz@deepseek.com>

* Add LogFMT interface

* Update comments

* Add simulated code

* Fix comments

* Change to 128 channels

* Add notes

* Optimize performance

* optimize simulate logfmt 10bit

* Minor fix

* Stronger low latency tests

* Minor fix

* Stronger low latency tests for logfmt

* Optimize logfmt simulate: lg2/ex2 ptx, step_inv

* Minor fix

* Minor fix

* Add non-logfmt bench

* Fix value=0 for logfmt

* Optimize performance

* Refactor tests

---------
Co-authored-by: Zhean Xu <xza@deepseek.com>

Co-authored-by: Zhean Xu <xza@deepseek.com>

* Add TMA buffer allocation

* Use TMA for forwarders and NVL receivers

* Use lane 31 to operate TMA.

* Change rdma buffer layout.

* Use TMA to transfer scales also.

* Increase the NVL recv buffer size.

* Disable early stopping.

* Apply similar optimizations on receiver warps.

* Prevent warp divergence.

* Disable aggressive ptx by default.

* Revert using TMA to transfer scales.

* Format.

* Change the layout of dispatch NVL buffer.

* Move topk transformation to recv warps.

* Use TMA to transfer all data in foward warps

* Use TMA to store scales.

* Code lint

---------
Co-authored-by: Chenggang Zhao <chenggangz@deepseek.com>

* use cli arg for num_processes
Signed-off-by: youkaichao <youkaichao@gmail.com>

* update low-latency
Signed-off-by: youkaichao <youkaichao@gmail.com>

* update intranode
Signed-off-by: youkaichao <youkaichao@gmail.com>

* update internode
Signed-off-by: youkaichao <youkaichao@gmail.com>

---------
Signed-off-by: youkaichao <youkaichao@gmail.com>

* more

* more

* more

* more

* more

* more