simd: implement missing intrinsics from simd/generic-arithmetic-pass.rs #382
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
antoyo
reviewed
Nov 10, 2023
sadlerap
force-pushed
the
impl-generic-arithmetic-pass
branch
from
1ae81e9
to
1d88c5b
Compare
|
I'll do the review soon, hopefully in the next few days. |
|
No worries, take all the time you need. |
antoyo
reviewed
Nov 18, 2023
sadlerap
force-pushed
the
impl-generic-arithmetic-pass
branch
2 times, most recently
from
e4b5828
to
bae699f
Compare
antoyo
reviewed
Nov 23, 2023
src/intrinsic/simd.rs
Outdated
| let shuffled = hi | lo; | ||
| let cast_ty = bx.context.new_vector_type(elem_type, byte_vector_type_size / (elem_size_bytes as u64)); | ||
| let loaded = bx.context.new_bitcast(None, shuffled, cast_ty); | ||
| let elems: Vec<_> = (0..in_len) |
There was a problem hiding this comment.
Do you extract the individual elements instead of casting because you want to truncate the vector?
Please add a comment to explain.
There was a problem hiding this comment.
Yeah, the intention here is to truncate the vector. Is there a more idiomatic way to do this?
There was a problem hiding this comment.
I've added some more documentation for how this particular algorithm is supposed to work in 8d42a82.
sadlerap
force-pushed
the
impl-generic-arithmetic-pass
branch
from
bae699f
to
cee07f5
Compare
|
Apologies on the delay on getting back to your review - last week's holidays made things busy for me, and I couldn't get back to this until now. |
Implements lane-local byte swapping through vector shuffles. While this is more setup than non-vector shuffles, this implementation can shuffle multiple integers concurrently. Signed-off-by: Andy Sadler <[email protected]>
Signed-off-by: Andy Sadler <[email protected]>
The simd intrinsic handler was delegating implementation of `simd_frem` to `Builder::frem`, which wasn't able to handle vector-typed inputs. To fix this, teach this method how to handle vector inputs. Signed-off-by: Andy Sadler <[email protected]>
If we're running against a patched libgccjit, use an algorithm similar to what LLVM uses for this intrinsic. Otherwise, fallback to a per-element bitreverse. Signed-off-by: Andy Sadler <[email protected]>
Signed-off-by: Andy Sadler <[email protected]>
gcc_not would panic upon encountering a vector type, which is not what we want here. Signed-off-by: Andy Sadler <[email protected]>
This test now passes when tested with a patched libgccjit. However, due to [some compiler bugs][1], we can't enable this for non-patched libgccjit yet. [1]: https://github.com/sadlerap/rustc_codegen_gcc/actions/runs/6820180639/job/18548672444#step:15:4375 Signed-off-by: Andy Sadler <[email protected]>
sadlerap
force-pushed
the
impl-generic-arithmetic-pass
branch
from
cee07f5
to
17b2c46
Compare
|
Thanks a lot for your contribution! |
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.
This implements/fixes the following intrinsics:
simd_bswapsimd_fremsimd_bitreversesimd_ctlzsimd_cttzsimd_negThese were the remaining intrinsics from the
simd/generic-arithmetic-pass.rsui test, which should now pass for a patched libgccjit. However, it seems not to compile against a non-patched libgccjit, so leave it disabled there for now.