GitLab

- incorrect use of __shfl_down
- fix warp size assumptions
- update unit tests to exit on failure

use __launch_bounds__(1024) for multi_tensor_apply, re-enable skipped tests

* fix warp size in WARP_SHFL* in layernorm

* enable fused_layer_norm tests on ROCm

In this PR, we mainly tried to optimize the performance of Syncatchnorm and also fixed one potential issue in the welford_parallel kernel implementation.

For performance improvement, we batched the mean/var/count all_gather communication together and sent it once in the forward path
We also batch the all_reduce in backward path
We add the contiguous call on the input of welford_parallel kernel.
If there is any standard perf benchmark, I would be happy to run it.

* enable mlp cuda

* add setup changes and tests

* skip the unit tests

* updated conditions for empty array

* removed hip platform conditions

* add device guards to the optimizers

* add untracked file

* set deviceGuard in multi_tensor_apply

* address review comments; fix lamb

* indent

* typo

* Enable sync batchnorm

* enable syncbn properly

* update the unit tests

* update tests

* update conditions for welford_merge_element

* updated conditions based on comments.

* [sync BN]

support non-uniform batch size across process group.

TODO: test should be added once cleaned up.

* updating unit tests

* new unit tests for different inputs

* cleaning

* fix dropout scaling from p to 1/(1-p) (#816)
Co-authored-by: Sukru Eryilmaz <seryilmaz@computelab-dgx1v-32.nvidia.com>

* Improvements to apex.mlp (#804)

* update fused bias relu backward kernel

* adding support for not require first layer dgrad

* fix bug: wrong layer in requires grad

* add infrastructure for optional bias and activation, currently only support no bias and no relu

* make bias and relu optional separately

* add sigmoid activation option

* enable wider load/store for multi_tensor_apply kernels (#763)

* modify MTA axpby for wider load/store

* Make scale/axpby/l2/adam/lamb multi_tensor uses wider load

* Changes to make xentropysoftmax load/store vectorized when possible: (#725)

* Changes to make xentropysoftmax load/store vectorized when possible:
Increase default ILP so that each thread handle 16 Bytes data in one step
Make thread load/store longest vector possible
Make unroll case handle adjacent data instead of strided, so same order compare to vector case

* Add shift for not aligned case. Remove less than 16 bytes aligned access
Co-authored-by: Burc Eryilmaz <sberyilm@gmail.com>
Co-authored-by: Sukru Eryilmaz <seryilmaz@computelab-dgx1v-32.nvidia.com>
Co-authored-by: Deyu Fu <deyuf@nvidia.com>

* modify MTA axpby for wider load/store

* Make scale/axpby/l2/adam/lamb multi_tensor uses wider load

* update fused bias relu backward kernel

* adding support for not require first layer dgrad

* fix bug: wrong layer in requires grad

* add infrastructure for optional bias and activation, currently only support no bias and no relu

* make bias and relu optional separately

* add sigmoid activation option

* Initial commit to hipify all cuda code

* enable multi_tensor_apply extension

* added generatedFileCleaner to handle nested hip files

* NHWC support for multi tensor apply

* compilation fix for version<=1.4

* move previous fused_adam and fp16_optimizer to contrib

* make build contrib.fused_adam optional

* change build option name

* remove unnecessary try import

* Pushing for build tests

* Contrib files

* Removing deprecated checks

correctly not apply bias correction to epsilon(same as recent upstream change)
correctly not apply bias correction to weight decay(consistent with upstream AdamW)
Make adam_w_mode for FusedAdam/LAMB, to do L2 or Weight Decay (Adam vs AdamW)
Correct document reg_inside_moment differently from adam_w_mode in FusedNovoGrad
Removed legacy eps_mode from FusedAdam
Make internal math type float across fused optimizers