SPIRV vector.mask lowering: use 64-bit type.#1093
Merged
Garra1980 merged 1 commit intointel:mainfrom Jul 16, 2025
Merged
Conversation
So far, most of the kernels use 16 or 32 vector sizes. But there is a kernel that returns an i8 tensor and the vector size = 64. So, there was an overflow when computing the mask (1 << valid_elements). This PR updates the data type from 32-bit to 64-bit when computing the mask. It also adds an assert to catch more easily this type of issue.
antonio-cortes-perez
force-pushed
the
dev/aperez/mask_64_upstream
branch
from
835970e to
dbafb63
Compare
antonio-cortes-perez
changed the title
Garra1980
approved these changes
Jul 16, 2025
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
So far, most of the kernels use 16 or 32 vector sizes. But there is a kernel that returns an i8 tensor and the vector size = 64. So, there was an overflow when computing the mask (1 << valid_elements). This PR updates the data type from 32-bit to 64-bit when computing the mask. It also adds an assert to catch more easily this type of issue.