End to end support for bfp16 scl2vec intrinsics #278
Merged
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
niwinanto
requested review from
abhinay-anubola,
abnikant,
andcarminati,
gbossu,
khallouh,
konstantinschwarz,
martien-de-jong,
SagarMaheshwari99 and
stephenneuendorffer
as code owners
| @@ -13,3 +13,4 @@ | |||
|
|
|||
| include "AIEBaseRegisterBanks.td" | |||
| def AccRegBank : RegisterBank<"AccRegBank", [ACC512, ACC1024, ACC2048]>; | |||
| def GPRRegBank : RegisterBank<"GPRRegBank", [eR, eL, eE, EXPVEC64]>; | |||
There was a problem hiding this comment.
Please, include a new line in the end.
There was a problem hiding this comment.
Should not be needed after rebase
| @@ -572,4 +572,10 @@ def int_aie2p_sqrtf : ClangBuiltin<"__builtin_aie2p_sqrtf">, AIE2PNLF; | |||
| // DIVS | |||
| def int_aie2p_divs : AIE2PDIVS; | |||
|
|
|||
| // BFP16 MAC MUL | |||
| class AIE2PSHUFFLEBFP16 | |||
| : Intrinsic<[llvm_v64i8_ty, llvm_v8i8_ty], [llvm_v64i8_ty, llvm_v8i8_ty, llvm_v64i8_ty, llvm_v8i8_ty, llvm_i32_ty], | |||
There was a problem hiding this comment.
Should use DefaultAttrsIntrinsic instead of Intrinsic
khallouh
reviewed
Jan 18, 2025
khallouh
reviewed
Jan 18, 2025
khallouh
reviewed
Jan 18, 2025
khallouh
reviewed
Jan 18, 2025
niwinanto
force-pushed
the
niwin.bfp16.scl2vecIntrinsic
branch
4 times, most recently
from
0f04536 to
487aede
Compare
khallouh
reviewed
Jan 22, 2025
clang/lib/Headers/aie2p_scl2vec.h
Outdated
| } | ||
|
|
||
| INTRINSIC(v64bfp16ebs8) shuffle(v64bfp16ebs8 a, unsigned mode) { | ||
| v64bfp16ebs8 unDef; |
khallouh
reviewed
Jan 22, 2025
clang/lib/Headers/aie2p_scl2vec.h
Outdated
| } | ||
|
|
||
| INTRINSIC(v64bfp16ebs16) shuffle(v64bfp16ebs16 a, unsigned mode) { | ||
| v64bfp16ebs16 unDef; |
khallouh
reviewed
Jan 22, 2025
khallouh
reviewed
Jan 22, 2025
khallouh
reviewed
Jan 22, 2025
| %struct.v64bfp16ebs16 = type <{ <64 x i8>, <8 x i8> }> | ||
|
|
||
| ; Function Attrs: mustprogress nofree norecurse nosync nounwind willreturn memory(none) | ||
| define dso_local noundef <16 x i32> @_Z18test_broadcast_s64Dv2_j(<2 x i32> noundef %b) local_unnamed_addr { |
There was a problem hiding this comment.
This seems unrelated. Didn't we have tests for these broadcasts?
khallouh
reviewed
Jan 22, 2025
| ; CHECK-NEXT: mova r1, #1 // Delay Slot 5 | ||
| ; CHECK-NEXT: lshl r29, r0, r1 // Delay Slot 4 | ||
| ; CHECK-NEXT: or r29, r29, r1; vinsert.32 x0, x2, r29, r2 // Delay Slot 3 | ||
| ; CHECK-NEXT: vinsert.32 x0, x0, r29, r3 // Delay Slot 2 |
There was a problem hiding this comment.
Could you add these tests in a separate commit? as they are unrelated
khallouh
reviewed
Jan 22, 2025
niwinanto
force-pushed
the
niwin.bfp16.scl2vecIntrinsic
branch
from
487aede to
2eec92d
Compare
niwinanto
force-pushed
the
niwin.bfp16.scl2vecIntrinsic
branch
from
2eec92d to
8bc61ad
Compare
niwinanto
force-pushed
the
niwin.bfp16.scl2vecIntrinsic
branch
from
8bc61ad to
39006d5
Compare
khallouh
approved these changes
Jan 24, 2025
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.
TODO:
v128bfp16ebs8 shuffle(v128bfp16ebs8 , unsigned int );
This depends on intrinsics from bfp16
upd_ext