Page MenuHomePhabricator

NickGuy (Nicholas Guy)
User

Projects

User does not belong to any projects.

User Details

User Since
Jun 23 2020, 7:14 AM (143 w, 5 d)

Recent Activity

Tue, Mar 14

NickGuy committed rG96615c856df5: [Codegen][ARM][AArch64] Support symmetric operations on complex numbers (authored by NickGuy).
[Codegen][ARM][AArch64] Support symmetric operations on complex numbers
Tue, Mar 14, 5:11 AM · Restricted Project, Restricted Project
NickGuy committed rG49384f14113b: Cleanup of Complex Deinterleaving pass (NFCI) (authored by NickGuy).
Cleanup of Complex Deinterleaving pass (NFCI)
Tue, Mar 14, 5:11 AM · Restricted Project, Restricted Project
NickGuy closed D142482: [Codegen] Support symmetric operations on complex numbers.
Tue, Mar 14, 5:11 AM · Restricted Project, Restricted Project
NickGuy closed D143177: Cleanup of Complex Deinterleaving pass (NFCI).
Tue, Mar 14, 5:11 AM · Restricted Project, Restricted Project

Wed, Mar 8

NickGuy updated the diff for D142482: [Codegen] Support symmetric operations on complex numbers.
Wed, Mar 8, 7:46 AM · Restricted Project, Restricted Project
NickGuy updated the diff for D143177: Cleanup of Complex Deinterleaving pass (NFCI).
Wed, Mar 8, 7:46 AM · Restricted Project, Restricted Project

Feb 6 2023

NickGuy accepted D143382: [ARM] Remove reduce(shuffle) if all the lanes are used.
Feb 6 2023, 8:22 AM · Restricted Project, Restricted Project

Feb 2 2023

NickGuy updated the diff for D142482: [Codegen] Support symmetric operations on complex numbers.

Split out unrelated changes, added more tests, unified the common logic, and renamed Passthrough to Symmetric.

Feb 2 2023, 6:36 AM · Restricted Project, Restricted Project
NickGuy requested review of D143177: Cleanup of Complex Deinterleaving pass (NFCI).
Feb 2 2023, 6:29 AM · Restricted Project, Restricted Project

Feb 1 2023

NickGuy updated the diff for D142482: [Codegen] Support symmetric operations on complex numbers.

I've changed the approach to not be so focused on "complex addition with zero rotation", and instead common operations applied to both sides (dubbed "symmetric operations"). The current implementation doesn't allow for targets to define their own supported operations, but also I'm not sure if there are many (if any at all) operations that wouldn't be common.

Feb 1 2023, 8:07 AM · Restricted Project, Restricted Project

Jan 24 2023

NickGuy requested review of D142482: [Codegen] Support symmetric operations on complex numbers.
Jan 24 2023, 8:49 AM · Restricted Project, Restricted Project

Jan 20 2023

NickGuy committed rG02435a50f22d: [ReleaseNotes] Add mention of complex number support for ARM and AArch64… (authored by NickGuy).
[ReleaseNotes] Add mention of complex number support for ARM and AArch64…
Jan 20 2023, 2:59 AM · Restricted Project, Restricted Project
NickGuy closed D142012: [ReleaseNotes] Adds mention of complex number support for ARM and AArch64 backends..
Jan 20 2023, 2:58 AM · Restricted Project, Restricted Project

Jan 18 2023

NickGuy requested review of D142012: [ReleaseNotes] Adds mention of complex number support for ARM and AArch64 backends..
Jan 18 2023, 6:11 AM · Restricted Project, Restricted Project

Dec 12 2022

NickGuy committed rG0c51f9cd8f05: [NFC] Removal of complex deinterleaving i64 test cases (authored by NickGuy).
[NFC] Removal of complex deinterleaving i64 test cases
Dec 12 2022, 4:02 AM · Restricted Project, Restricted Project
NickGuy committed rGa3dc5b534a80: [ARM][CodeGen] Add integer support for complex deinterleaving (authored by NickGuy).
[ARM][CodeGen] Add integer support for complex deinterleaving
Dec 12 2022, 3:43 AM · Restricted Project, Restricted Project
NickGuy closed D139628: [ARM][CodeGen] Add integer support for complex deinterleaving.
Dec 12 2022, 3:43 AM · Restricted Project, Restricted Project

Dec 8 2022

NickGuy requested review of D139628: [ARM][CodeGen] Add integer support for complex deinterleaving.
Dec 8 2022, 6:31 AM · Restricted Project, Restricted Project

Nov 16 2022

NickGuy committed rG41a3f92596a7: [AArch64][CodeGen] Add AArch64 support for complex deinterleaving (authored by NickGuy).
[AArch64][CodeGen] Add AArch64 support for complex deinterleaving
Nov 16 2022, 6:01 AM · Restricted Project, Restricted Project
NickGuy closed D129066: [AArch64][CodeGen] Add AArch64 support for complex deinterleaving.
Nov 16 2022, 6:01 AM · Restricted Project, Restricted Project

Nov 15 2022

NickGuy added inline comments to D129066: [AArch64][CodeGen] Add AArch64 support for complex deinterleaving.
Nov 15 2022, 7:10 AM · Restricted Project, Restricted Project
NickGuy updated the diff for D129066: [AArch64][CodeGen] Add AArch64 support for complex deinterleaving.
Nov 15 2022, 7:10 AM · Restricted Project, Restricted Project
NickGuy updated the diff for D129066: [AArch64][CodeGen] Add AArch64 support for complex deinterleaving.

Addressed comments, and added more tests

Nov 15 2022, 5:47 AM · Restricted Project, Restricted Project

Nov 14 2022

NickGuy added a comment to D114174: [ARM][CodeGen] Add support for complex deinterleaving.

OK great. Thanks for the updates. I think this looks to be in a good state now. We can always do more nitpicking, and but it looks to be in a good state to get into tree. We can get this in now and add AArch64 support on top to increase the test coverage.

Some minor comments below but otherwise LGTM.

Agreed, and thanks for working on this.

Question about AArch64, is that something you are going to work on next?

Nov 14 2022, 8:02 AM · Restricted Project, Restricted Project
NickGuy abandoned D129067: [CodeGen] Complex deinterleaving vector splitting.

This was pushed over to be the responsibility of the target. Therefore this approach is no longer relevant.

Nov 14 2022, 8:01 AM · Restricted Project, Restricted Project
NickGuy committed rG62b00bf1afa7: [NFC] Removal of complex deinterleaving test case complex_mul_v8f64 (authored by NickGuy).
[NFC] Removal of complex deinterleaving test case complex_mul_v8f64
Nov 14 2022, 7:58 AM · Restricted Project, Restricted Project
NickGuy committed rGd52e2839f3b1: [ARM][CodeGen] Add support for complex deinterleaving (authored by NickGuy).
[ARM][CodeGen] Add support for complex deinterleaving
Nov 14 2022, 6:05 AM · Restricted Project, Restricted Project
NickGuy closed D114174: [ARM][CodeGen] Add support for complex deinterleaving.
Nov 14 2022, 6:04 AM · Restricted Project, Restricted Project

Nov 11 2022

NickGuy updated the diff for D114174: [ARM][CodeGen] Add support for complex deinterleaving.
Nov 11 2022, 6:39 AM · Restricted Project, Restricted Project

Nov 8 2022

NickGuy updated the diff for D129066: [AArch64][CodeGen] Add AArch64 support for complex deinterleaving.

Addressed comments, and rebased to align with latest revision of D114174 (Diff 16)

Nov 8 2022, 5:40 AM · Restricted Project, Restricted Project
NickGuy added inline comments to D114174: [ARM][CodeGen] Add support for complex deinterleaving.
Nov 8 2022, 4:10 AM · Restricted Project, Restricted Project
NickGuy updated the diff for D114174: [ARM][CodeGen] Add support for complex deinterleaving.
Nov 8 2022, 4:10 AM · Restricted Project, Restricted Project

Oct 21 2022

NickGuy updated the diff for D114174: [ARM][CodeGen] Add support for complex deinterleaving.

Addressed comments

Oct 21 2022, 6:47 AM · Restricted Project, Restricted Project

Oct 12 2022

NickGuy updated the diff for D114174: [ARM][CodeGen] Add support for complex deinterleaving.

Thanks @dmgreen for the extra tests.

Oct 12 2022, 8:38 AM · Restricted Project, Restricted Project

Sep 28 2022

NickGuy updated the diff for D114174: [ARM][CodeGen] Add support for complex deinterleaving.

Added more interesting test cases, covering triangle and diamond multiply cases.

Sep 28 2022, 7:03 AM · Restricted Project, Restricted Project

Sep 21 2022

NickGuy added inline comments to D114174: [ARM][CodeGen] Add support for complex deinterleaving.
Sep 21 2022, 2:51 AM · Restricted Project, Restricted Project
NickGuy updated the diff for D114174: [ARM][CodeGen] Add support for complex deinterleaving.

Addressed comments, and redesigned the lookup list of nodes to now be represented as a graph.

Sep 21 2022, 2:51 AM · Restricted Project, Restricted Project

Sep 12 2022

NickGuy added inline comments to D114174: [ARM][CodeGen] Add support for complex deinterleaving.
Sep 12 2022, 5:58 AM · Restricted Project, Restricted Project
NickGuy updated the diff for D114174: [ARM][CodeGen] Add support for complex deinterleaving.
Sep 12 2022, 5:58 AM · Restricted Project, Restricted Project

Sep 9 2022

NickGuy added a comment to D114174: [ARM][CodeGen] Add support for complex deinterleaving.

Forgot to submit the comments adjoining the patch...

Sep 9 2022, 2:37 AM · Restricted Project, Restricted Project

Sep 7 2022

NickGuy updated the diff for D114174: [ARM][CodeGen] Add support for complex deinterleaving.

Addressed comments

Sep 7 2022, 9:40 AM · Restricted Project, Restricted Project

Sep 5 2022

NickGuy updated the diff for D114174: [ARM][CodeGen] Add support for complex deinterleaving.

Addressed comments and improved case coverage,

Sep 5 2022, 7:32 AM · Restricted Project, Restricted Project

Aug 4 2022

NickGuy updated the diff for D129066: [AArch64][CodeGen] Add AArch64 support for complex deinterleaving.

Addressed comments, cleaned up debug outputs, and implemented vector splitting

Aug 4 2022, 6:16 AM · Restricted Project, Restricted Project
NickGuy added a comment to D114174: [ARM][CodeGen] Add support for complex deinterleaving.

I've pre-committed the tests, and redesigned the core algorthm to operate on pairs of operands, rather than analysing the uses of a given instruction. The vector splitting has also been implemented on the target side

Aug 4 2022, 6:01 AM · Restricted Project, Restricted Project
NickGuy updated the diff for D114174: [ARM][CodeGen] Add support for complex deinterleaving.
Aug 4 2022, 6:00 AM · Restricted Project, Restricted Project

Jul 4 2022

NickGuy added a comment to D129067: [CodeGen] Complex deinterleaving vector splitting.

Looks like I messed up my git-fu somewhere in preparing these patches. There are a few cleanup changes in this patch that should've been in a previous one. I'll try and clean that up when addressing other comments.

Jul 4 2022, 3:45 AM · Restricted Project, Restricted Project
NickGuy added inline comments to D114174: [ARM][CodeGen] Add support for complex deinterleaving.
Jul 4 2022, 3:42 AM · Restricted Project, Restricted Project
NickGuy requested review of D129067: [CodeGen] Complex deinterleaving vector splitting.
Jul 4 2022, 2:58 AM · Restricted Project, Restricted Project
NickGuy updated the diff for D129066: [AArch64][CodeGen] Add AArch64 support for complex deinterleaving.

Added context missing from initial patch

Jul 4 2022, 2:57 AM · Restricted Project, Restricted Project
NickGuy requested review of D129066: [AArch64][CodeGen] Add AArch64 support for complex deinterleaving.
Jul 4 2022, 2:56 AM · Restricted Project, Restricted Project
NickGuy updated the diff for D114174: [ARM][CodeGen] Add support for complex deinterleaving.

Addressed comments, and added a file description that attempts to explain what the pass does.

Jul 4 2022, 2:55 AM · Restricted Project, Restricted Project

Jun 22 2022

NickGuy added a comment to D114174: [ARM][CodeGen] Add support for complex deinterleaving.

What happened to the ideas of starting from a shuffle and working through a worklist of pairs of [Real, Imaginary] Values that we match to complex nodes?

While that would work "simply" enough for cases like a * b, more elaborate cases (e.g. (a * b) * c) would result in some ambiguity as to which add(mul, mul) pairs with which sub(mul, mul). This complexity inflates further the more operands are involved. The approach I've implemented here considers each complex node in isolation (with the exception of the accumulator value).

I presume the == 128 can be removed if we teach it how to split the vectors up?I presume the == 128 can be removed if we teach it how to split the vectors up?

Yep, vector splitting is something I decided to push out of this initial patch, and will be implemented in a follow-up. (Due to each node being treated in isolation, the vector splitting from previous iterations got overly complicated and unwieldy). The ideal solution that I can see would be to teach the intrinsic how to split, rather than the pass (somewhere like DAGTypeLegalizer::SplitVectorResult).

Is this cost necessary at the moment, or will it always be profitable for the simple cases?

Complex add has a few cases where I've observed performance regressions, and that's the sort of thing this rudimentary cost-modelling is intended to catch.

Jun 22 2022, 4:02 AM · Restricted Project, Restricted Project

Jun 21 2022

NickGuy updated the diff for D114174: [ARM][CodeGen] Add support for complex deinterleaving.

Since the last patch, I've redesigned the high-level approach; It now crawls through the instruction graph to find opportunities for complex deinterleaving before attempting to perform said deinterleaving. Doing it this way allows us to short-circuit, bailing out and preventing the heavy work from being performed if something isn't supported.
This iteration also implements support for complex operations with multiple steps/operands (e.g. a[i] * b[i] * c[i])

Jun 21 2022, 5:55 AM · Restricted Project, Restricted Project

May 23 2022

NickGuy accepted D126118: [ARM] Fix vcvtb/t.f16 input liveness.

LGTM

May 23 2022, 2:35 AM · Restricted Project, Restricted Project

Apr 8 2022

NickGuy added inline comments to D114174: [ARM][CodeGen] Add support for complex deinterleaving.
Apr 8 2022, 7:24 AM · Restricted Project, Restricted Project
NickGuy updated the diff for D114174: [ARM][CodeGen] Add support for complex deinterleaving.
Apr 8 2022, 7:24 AM · Restricted Project, Restricted Project

Apr 4 2022

NickGuy accepted D123012: [AArch64] Alter mull buildvectors(ext(..)) combine to work on shuffles.

LGTM

Apr 4 2022, 5:20 AM · Restricted Project, Restricted Project
NickGuy added a comment to D123012: [AArch64] Alter mull buildvectors(ext(..)) combine to work on shuffles.

Code looks good to me, but a small nitpick on the function name

Apr 4 2022, 12:43 AM · Restricted Project, Restricted Project

Mar 31 2022

NickGuy committed rG7d676714fbf2: [AArch64] Set MaxBytesForLoopAlignment for more targets (authored by NickGuy).
[AArch64] Set MaxBytesForLoopAlignment for more targets
Mar 31 2022, 3:37 AM · Restricted Project, Restricted Project
NickGuy closed D122566: [AArch64] Set MaxBytesForLoopAlignment for more targets.
Mar 31 2022, 3:37 AM · Restricted Project, Restricted Project

Mar 29 2022

NickGuy added inline comments to D122566: [AArch64] Set MaxBytesForLoopAlignment for more targets.
Mar 29 2022, 9:24 AM · Restricted Project, Restricted Project
NickGuy updated the diff for D122566: [AArch64] Set MaxBytesForLoopAlignment for more targets.
Mar 29 2022, 9:23 AM · Restricted Project, Restricted Project

Mar 28 2022

NickGuy updated the diff for D122566: [AArch64] Set MaxBytesForLoopAlignment for more targets.
Mar 28 2022, 6:45 AM · Restricted Project, Restricted Project
NickGuy requested review of D122566: [AArch64] Set MaxBytesForLoopAlignment for more targets.
Mar 28 2022, 2:29 AM · Restricted Project, Restricted Project

Mar 21 2022

NickGuy updated the diff for D114174: [ARM][CodeGen] Add support for complex deinterleaving.

It's been longer than I would've liked before I've gotten back to this, but I've;

Mar 21 2022, 6:55 AM · Restricted Project, Restricted Project

Feb 17 2022

NickGuy accepted D120018: [AArch64] Alter mull shuffle(ext(..)) combine to work on buildvectors.

I wasn't aware of the implicit truncation. In that case, LGTM

Feb 17 2022, 5:53 AM · Restricted Project
NickGuy added a comment to D120018: [AArch64] Alter mull shuffle(ext(..)) combine to work on buildvectors.

Looks good overall, with potential wins in both performance and codesize. Just 1 minor thing (and a nitpick about a comment).

Feb 17 2022, 2:36 AM · Restricted Project

Feb 10 2022

NickGuy added a comment to D114174: [ARM][CodeGen] Add support for complex deinterleaving.

Thanks all for the comments so far (And thanks Dave for taking on the evening shift, as it were)

Feb 10 2022, 2:18 AM · Restricted Project, Restricted Project

Feb 9 2022

NickGuy added a comment to D114174: [ARM][CodeGen] Add support for complex deinterleaving.

...
I'm not exactly sure why to do target specific pattern matching here. We could simply add generic complex intrinsics and the different patterns could be matched at each archs ISEL, no? I do agree that it should check in the backend if it should generate a complex operation of a given vector type.
...
Is there any strong reason to create target specific intrinsics instead of having generic intrinsics with polymorphism? Such as llvm.complex.add.v2f32?

Feb 9 2022, 3:31 AM · Restricted Project, Restricted Project

Feb 8 2022

NickGuy added a comment to D114174: [ARM][CodeGen] Add support for complex deinterleaving.

The supportsComplexArithmetic method doesn't add a lot on its own. It would probably be better to represent it in terms of asking the backend if it has certain patterns of certain types available. An f32 fcadd, for example, or a i16 fcmul_with_rotate (I'm not sure what to name them).
The ComplexArithmeticGraph seems like internal details to the pass. It would be best not to pass it over the TTI interface boundary if we can. The backend just needs to create the correct intrinsics of the correct type.
Equally I would keep all the matching logic in the pass, not through matchComplexArithmeticIR. That would be similar to, for example, the MachineCombiner pass which has its own enum of a set of patterns.

Unfortunately, not all architectures/intrinsics follow the same patterns, so this was done to provide a way for architecture-specific stuff to be handled as needed. The MVE halving complex add (which I only now realise was included in this patch) is a good example of this; It only works on integers, and requires some extra instructions to be matched. This instruction is only in MVE, it is not part of NEON in any way.
The intrinsics that are common are also constructed differently; While the NEON intrinsics are separated out by their rotations (aarch64_neon_vcmla_rot0, aarch64_neon_vcmla_rot90), MVE squishes them into one and determines the rotation based on a parameter.
ComplexArithmeticGraph is used to encapsulate all the data the TTI might need in order to correctly generate the right intrinsic. It could be replaced by something a bit lighter (and that doesn't expose the implementation detail of the node list), but something will be needed to provide this info.

Feb 8 2022, 2:23 AM · Restricted Project, Restricted Project

Feb 7 2022

NickGuy updated the diff for D114174: [ARM][CodeGen] Add support for complex deinterleaving.

Applied feedback received offline, redesigned the interface/implementation, and fixed up a number of fundamental issues in the previous iteration.

Feb 7 2022, 5:33 AM · Restricted Project, Restricted Project

Jan 5 2022

NickGuy committed rG13992498cd96: [AArch64][CodeGen] Emit alignment "Max Skip" operand for AArch64 loops (authored by NickGuy).
[AArch64][CodeGen] Emit alignment "Max Skip" operand for AArch64 loops
Jan 5 2022, 4:54 AM
NickGuy committed rG73d92faa2fc0: [CodeGen] Emit alignment "Max Skip" operand (authored by NickGuy).
[CodeGen] Emit alignment "Max Skip" operand
Jan 5 2022, 4:54 AM
NickGuy closed D114879: [AArch64][CodeGen] Emit alignment "Max Skip" operand for AArch64 loops.
Jan 5 2022, 4:54 AM · Restricted Project
NickGuy closed D114590: [CodeGen] Emit alignment "Max Skip" operand for align directives.
Jan 5 2022, 4:54 AM · Restricted Project

Dec 15 2021

NickGuy updated the diff for D114879: [AArch64][CodeGen] Emit alignment "Max Skip" operand for AArch64 loops.
Dec 15 2021, 3:37 AM · Restricted Project
NickGuy updated the diff for D114590: [CodeGen] Emit alignment "Max Skip" operand for align directives.
Dec 15 2021, 3:36 AM · Restricted Project

Dec 13 2021

NickGuy updated the diff for D114879: [AArch64][CodeGen] Emit alignment "Max Skip" operand for AArch64 loops.
Dec 13 2021, 3:57 AM · Restricted Project
NickGuy updated the diff for D114590: [CodeGen] Emit alignment "Max Skip" operand for align directives.

Fixes the test to pass with this patch in isolation (i.e. without the child revision on top)

Dec 13 2021, 3:53 AM · Restricted Project

Dec 9 2021

NickGuy updated the diff for D114590: [CodeGen] Emit alignment "Max Skip" operand for align directives.
Dec 9 2021, 6:37 AM · Restricted Project

Dec 7 2021

NickGuy updated the diff for D114879: [AArch64][CodeGen] Emit alignment "Max Skip" operand for AArch64 loops.
Dec 7 2021, 2:34 AM · Restricted Project

Dec 3 2021

NickGuy added inline comments to D114590: [CodeGen] Emit alignment "Max Skip" operand for align directives.
Dec 3 2021, 6:37 AM · Restricted Project
NickGuy updated the diff for D114590: [CodeGen] Emit alignment "Max Skip" operand for align directives.

It may be better to fold this into D114879 so that there is a single patch that can be tested properly.

Dec 3 2021, 6:36 AM · Restricted Project

Dec 1 2021

NickGuy added a comment to D114590: [CodeGen] Emit alignment "Max Skip" operand for align directives.

Okay, that's fine. Perhaps upload your WIP patches too then, stack them, so that we can actually see the (full) approach?

Dec 1 2021, 8:09 AM · Restricted Project
NickGuy requested review of D114879: [AArch64][CodeGen] Emit alignment "Max Skip" operand for AArch64 loops.
Dec 1 2021, 7:51 AM · Restricted Project
NickGuy updated the diff for D114590: [CodeGen] Emit alignment "Max Skip" operand for align directives.
Dec 1 2021, 7:48 AM · Restricted Project
NickGuy added a comment to D114590: [CodeGen] Emit alignment "Max Skip" operand for align directives.

I've got a follow-up patch nearly ready with tests, yep. I want to settle on an approach here before implementing the other side of it.

Dec 1 2021, 3:07 AM · Restricted Project
NickGuy updated the diff for D114590: [CodeGen] Emit alignment "Max Skip" operand for align directives.
Dec 1 2021, 2:58 AM · Restricted Project

Nov 25 2021

NickGuy added a comment to D114590: [CodeGen] Emit alignment "Max Skip" operand for align directives.

Do we really want to add this to the base Align class? Or should it just be part of whatever controls the code alignment?

Nov 25 2021, 6:57 AM · Restricted Project
NickGuy retitled D114590: [CodeGen] Emit alignment "Max Skip" operand for align directives from [CodeGen] Emit alignment "Max Skip" operand to [CodeGen] Emit alignment "Max Skip" operand for align directives.
Nov 25 2021, 6:39 AM · Restricted Project
NickGuy requested review of D114590: [CodeGen] Emit alignment "Max Skip" operand for align directives.
Nov 25 2021, 6:39 AM · Restricted Project

Nov 19 2021

NickGuy updated the diff for D114174: [ARM][CodeGen] Add support for complex deinterleaving.

Nice one Nick.
Can you first run clang-format on this patch? It is pretty much unreadable with all these lint messages.

Nov 19 2021, 2:29 AM · Restricted Project, Restricted Project

Nov 18 2021

NickGuy requested review of D114174: [ARM][CodeGen] Add support for complex deinterleaving.
Nov 18 2021, 10:29 AM · Restricted Project, Restricted Project

Sep 28 2021

NickGuy accepted D108766: [AArch64] Model Cortex-A55 Q register NEON instructions.

LGTM

Sep 28 2021, 2:23 AM · Restricted Project

Sep 21 2021

NickGuy committed rG9e4d72675f47: [AArch64] Improve schedule modelling on the Cortex-A55 (authored by NickGuy).
[AArch64] Improve schedule modelling on the Cortex-A55
Sep 21 2021, 5:04 AM
NickGuy closed D109323: [AArch64] Improve adrp schedule modelling on the Cortex-A55.
Sep 21 2021, 5:04 AM · Restricted Project

Sep 10 2021

NickGuy added inline comments to D109323: [AArch64] Improve adrp schedule modelling on the Cortex-A55.
Sep 10 2021, 1:36 AM · Restricted Project
NickGuy updated the diff for D109323: [AArch64] Improve adrp schedule modelling on the Cortex-A55.

Updated test

Sep 10 2021, 1:36 AM · Restricted Project

Sep 8 2021

NickGuy added a comment to D109323: [AArch64] Improve adrp schedule modelling on the Cortex-A55.

OK. Can you add a test? Something that would schedule instructions apart before and keep them together now.

Sep 8 2021, 8:24 AM · Restricted Project
NickGuy updated the diff for D109323: [AArch64] Improve adrp schedule modelling on the Cortex-A55.
Sep 8 2021, 8:24 AM · Restricted Project