Parametrize NumOps by element type instead of SIMD type
#631
Conversation
This file contains 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
robertknight
force-pushed
the
numops-lane-type
branch
from
e2bd298 to
dd02030
Compare
robertknight
force-pushed
the
numops-lane-type
branch
from
dd02030 to
f392636
Compare
robertknight
force-pushed
the
numops-lane-type
branch
from
f392636 to
c4aebf6
Compare
Make the the generic argument to `NumOps` independent of the SIMD ISA. For example `<Avx2Isa as Isa>::f32` now returns an `impl NumOps<f32>` instead of `impl NumOps<float32x4_t`. This in turn will make it possible to add generic methods to get the `NumOps` impl for a given element type, enabling writing `SimdOp`s that are generic over the element type.
robertknight
force-pushed
the
numops-lane-type
branch
from
c4aebf6 to
1201b1e
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Make the generic argument to
NumOpsindependent of the SIMD ISA. For example<Avx2Isa as Isa>::f32now returns animpl NumOps<f32>instead ofimpl NumOps<float32x4_t>. This in turn will make it possible to add generic methods to get theNumOpsimpl for a given element type, enabling writingSimdOps that are generic over the element type.The downside is that a single struct can no longer implement
NumOpsfor two different SIMD vectors with the same element type. This would prevent eg.Avx2Isafrom implementingNumOpsfor both 256 and 128-bit f32 vectors. So far the need to half or quarter-width vectors has been avoided by defining operations in a way that avoids this.