#0: Update comment for strided mode sync #52
Merged
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
In order to do pack_untilize we need to set the DEST access mode to strided. The following bits need to be set to enable correct stride amount and proper 32-bit data format handling -
DEST_ACCESS_CFG_remap_addrs_RMW
andDEST_ACCESS_CFG_swizzle_32b_RMW
. Since this is the part of the global CFG, we need to wait for all DEST accesses to finish before changing these bits (as nicely explained here: https://yyz-gitlab.local.tenstorrent.com/tenstorrent/budabackend/-/issues/1849).The sync introduced in
_llk_math_hw_configure_
, intt_metal/third_party/tt_llk_blackhole/llk_lib/llk_math_common.h
allows for our LLK implementation to be in line with the HW design and specification.The fix was introduced to tt-metal as a part of PR#15398 as the mismatch was identified in the issue #14609