Page MenuHomePhabricator

MattDevereau (Matt Devereau)
User

Projects

User does not belong to any projects.

User Details

User Since
Aug 6 2021, 8:13 AM (60 w, 5 d)

Recent Activity

Today

MattDevereau added a comment to D133484: [AArch64][SVE] Fix AArch64_SVE_VectorCall calling convention.

@paulwalker-arm I'm referring to this comment, particularly the sentence "I think we should hoist the necessary logic to construct RVLocs into LowerCall and pass it into LowerCallResult instead of Ins" which I assumed was referring to this whole block at the start of LowerCallResult here

Wed, Oct 5, 10:58 AM · Restricted Project, Restricted Project
MattDevereau updated the diff for D133484: [AArch64][SVE] Fix AArch64_SVE_VectorCall calling convention.

@paulwalker-arm In the interest of moving this ticket along I've implemented most of your feedback with the exception of hoisting the work done inside LowerFormalArguments into LowerCall. This is because LowerFormalArguments expects CallConv to be changed by CalleeInSVE/CalleeOutSVE in LowerCall. Removing the work in LowerFormalArguments causes test failures.

Wed, Oct 5, 5:28 AM · Restricted Project, Restricted Project

Yesterday

MattDevereau added inline comments to D133484: [AArch64][SVE] Fix AArch64_SVE_VectorCall calling convention.
Tue, Oct 4, 9:08 AM · Restricted Project, Restricted Project

Wed, Sep 28

MattDevereau committed rG0a4771a7e845: [AArch64][SVE] Expand gather index to 32 bits instead of 64 bits (authored by MattDevereau).
[AArch64][SVE] Expand gather index to 32 bits instead of 64 bits
Wed, Sep 28, 7:46 AM · Restricted Project, Restricted Project
MattDevereau closed D130692: [AArch64][SVE] Expand gather index to 32 bits instead of 64 bits.
Wed, Sep 28, 7:45 AM · Restricted Project, Restricted Project
MattDevereau requested review of D133116: [AArch64][SVE] Optimise repeated floating-point complex patterns to splat.
Wed, Sep 28, 6:51 AM · Restricted Project, Restricted Project

Mon, Sep 26

MattDevereau planned changes to D133116: [AArch64][SVE] Optimise repeated floating-point complex patterns to splat.

@paulwalker-arm I've moved the new function to DAG combine, and have somewhat side-graded the current complex pattern matching logic to work with the nodes present after DAG combine, which are different from the nodes previously in ISel lowering. I'll focus on implementing your other suggestion of enabling scalable vectors for AArch64ISD::DUPLANE## nodes, feel free to ignore this review for the time being

Mon, Sep 26, 10:13 AM · Restricted Project, Restricted Project
MattDevereau updated the diff for D133116: [AArch64][SVE] Optimise repeated floating-point complex patterns to splat.
Mon, Sep 26, 10:05 AM · Restricted Project, Restricted Project
MattDevereau updated the diff for D130692: [AArch64][SVE] Expand gather index to 32 bits instead of 64 bits.
Mon, Sep 26, 4:37 AM · Restricted Project, Restricted Project
MattDevereau added inline comments to D130692: [AArch64][SVE] Expand gather index to 32 bits instead of 64 bits.
Mon, Sep 26, 3:37 AM · Restricted Project, Restricted Project

Tue, Sep 20

MattDevereau updated the diff for D133484: [AArch64][SVE] Fix AArch64_SVE_VectorCall calling convention.

I've simplified the pointless if(A && B || A) check. This was leftover from when I copied and simplified the code from AArch64TargetLowering::LowerFormalArguments which has seperate logic for predicates and scalable vectors like so:

Tue, Sep 20, 3:17 AM · Restricted Project, Restricted Project

Thu, Sep 8

MattDevereau added inline comments to D133484: [AArch64][SVE] Fix AArch64_SVE_VectorCall calling convention.
Thu, Sep 8, 5:55 AM · Restricted Project, Restricted Project
MattDevereau requested review of D133484: [AArch64][SVE] Fix AArch64_SVE_VectorCall calling convention.
Thu, Sep 8, 5:10 AM · Restricted Project, Restricted Project
MattDevereau committed rG3864643dea64: [AArch64][SVE] Add out of range SVE arg CC test (authored by MattDevereau).
[AArch64][SVE] Add out of range SVE arg CC test
Thu, Sep 8, 4:50 AM · Restricted Project, Restricted Project

Sep 2 2022

MattDevereau updated the diff for D130692: [AArch64][SVE] Expand gather index to 32 bits instead of 64 bits.
Sep 2 2022, 7:09 AM · Restricted Project, Restricted Project

Sep 1 2022

MattDevereau requested review of D133116: [AArch64][SVE] Optimise repeated floating-point complex patterns to splat.
Sep 1 2022, 8:21 AM · Restricted Project, Restricted Project
MattDevereau committed rGb9062ceffc4d: [AArch64][SVE] Add floating-point repeated complex pattern llc tests (authored by MattDevereau).
[AArch64][SVE] Add floating-point repeated complex pattern llc tests
Sep 1 2022, 8:05 AM · Restricted Project, Restricted Project

Aug 25 2022

MattDevereau committed rG30b045aba603: [AArch64][SVE] Extend LD1RQ ISel patterns to cover missing addressing modes (authored by MattDevereau).
[AArch64][SVE] Extend LD1RQ ISel patterns to cover missing addressing modes
Aug 25 2022, 6:08 AM · Restricted Project, Restricted Project
MattDevereau closed D130993: [AArch64][SVE] Extend LD1RQ ISel patterns to cover missing addressing modes.
Aug 25 2022, 6:07 AM · Restricted Project, Restricted Project

Aug 22 2022

MattDevereau updated the diff for D130692: [AArch64][SVE] Expand gather index to 32 bits instead of 64 bits.

These two tests currently have regressions:
b/llvm/test/CodeGen/AArch64/sve-fixed-length-masked-gather.ll:@masked_gather_32b_scaled_sext_f64
b/llvm/test/CodeGen/AArch64/sve-fixed-length-masked-scatter.ll:@masked_scatter_32b_scaled_sext_f64

Aug 22 2022, 6:36 AM · Restricted Project, Restricted Project
MattDevereau updated the diff for D130993: [AArch64][SVE] Extend LD1RQ ISel patterns to cover missing addressing modes.

Multiclassed more LD1RQ patterns into ld1rq_pat
Added AddedComplexity to immediate patterns to prevent scalar + immediate cases regressing to scalar + scalar(mov)

Aug 22 2022, 5:16 AM · Restricted Project, Restricted Project
MattDevereau added a comment to D130692: [AArch64][SVE] Expand gather index to 32 bits instead of 64 bits.

@paulwalker-arm I've extended isVectorShrinkable to shrink sign extended and zero extended gathers/scatters, however i'm seeing the following change to a pair of gather/scatter tests in sve-fixed-length-masked-gather.ll:

Aug 22 2022, 3:45 AM · Restricted Project, Restricted Project

Aug 18 2022

MattDevereau updated the diff for D130993: [AArch64][SVE] Extend LD1RQ ISel patterns to cover missing addressing modes.

Added class LD1RQPat to match the other set of scalar variant definitions

Aug 18 2022, 7:40 AM · Restricted Project, Restricted Project

Aug 11 2022

MattDevereau updated the diff for D130993: [AArch64][SVE] Extend LD1RQ ISel patterns to cover missing addressing modes.
Aug 11 2022, 2:54 AM · Restricted Project, Restricted Project

Aug 8 2022

MattDevereau updated the diff for D130993: [AArch64][SVE] Extend LD1RQ ISel patterns to cover missing addressing modes.

Accepting changes to N2-sve-instructions.s as valid

Aug 8 2022, 9:30 AM · Restricted Project, Restricted Project

Aug 5 2022

MattDevereau added inline comments to D130993: [AArch64][SVE] Extend LD1RQ ISel patterns to cover missing addressing modes.
Aug 5 2022, 4:37 AM · Restricted Project, Restricted Project

Aug 2 2022

MattDevereau requested review of D130993: [AArch64][SVE] Extend LD1RQ ISel patterns to cover missing addressing modes.
Aug 2 2022, 9:19 AM · Restricted Project, Restricted Project
MattDevereau updated the diff for D130692: [AArch64][SVE] Expand gather index to 32 bits instead of 64 bits.

Update commit message
Added unsigned index check
Inlined logic instead of using a function

Aug 2 2022, 4:07 AM · Restricted Project, Restricted Project

Jul 29 2022

MattDevereau committed rGa8b726ac658a: [AArch64][SVE] Change DupLane128Combine Index comparison to 0 (authored by MattDevereau).
[AArch64][SVE] Change DupLane128Combine Index comparison to 0
Jul 29 2022, 7:31 AM · Restricted Project, Restricted Project

Jul 28 2022

MattDevereau requested review of D130692: [AArch64][SVE] Expand gather index to 32 bits instead of 64 bits.
Jul 28 2022, 2:28 AM · Restricted Project, Restricted Project

Jul 27 2022

MattDevereau committed rG35e781fb05eb: [AArch64][SVE] Add Gather Index narrowing tests (authored by MattDevereau).
[AArch64][SVE] Add Gather Index narrowing tests
Jul 27 2022, 8:33 AM · Restricted Project, Restricted Project

Jul 21 2022

MattDevereau committed rGcd3d7bf15d3e: [AArch64][SVE] Add DAG-Combine to push bitcasts from floating point loads after… (authored by MattDevereau).
[AArch64][SVE] Add DAG-Combine to push bitcasts from floating point loads after…
Jul 21 2022, 4:01 AM · Restricted Project, Restricted Project
MattDevereau closed D130013: [AArch64][SVE] Add DAG-Combine to push bitcasts from floating point loads after DUPLANE128.
Jul 21 2022, 4:00 AM · Restricted Project, Restricted Project
MattDevereau committed rGe0fbd990c9cb: [AArch64][SVE] Add ISel pattern to lower DUPLANE128 to LD1RQD (authored by MattDevereau).
[AArch64][SVE] Add ISel pattern to lower DUPLANE128 to LD1RQD
Jul 21 2022, 3:59 AM · Restricted Project, Restricted Project
MattDevereau closed D130010: [AArch64][SVE] Add ISel pattern to lower DUPLANE128 to LD1RQD.
Jul 21 2022, 3:58 AM · Restricted Project, Restricted Project

Jul 19 2022

MattDevereau updated the diff for D130013: [AArch64][SVE] Add DAG-Combine to push bitcasts from floating point loads after DUPLANE128.
Jul 19 2022, 9:18 AM · Restricted Project, Restricted Project
MattDevereau added inline comments to D130013: [AArch64][SVE] Add DAG-Combine to push bitcasts from floating point loads after DUPLANE128.
Jul 19 2022, 8:35 AM · Restricted Project, Restricted Project
MattDevereau added inline comments to D130013: [AArch64][SVE] Add DAG-Combine to push bitcasts from floating point loads after DUPLANE128.
Jul 19 2022, 8:32 AM · Restricted Project, Restricted Project

Jul 18 2022

MattDevereau updated the diff for D130010: [AArch64][SVE] Add ISel pattern to lower DUPLANE128 to LD1RQD.

Dropped _ldr from test names and moved Pats into class

Jul 18 2022, 9:56 AM · Restricted Project, Restricted Project
MattDevereau added inline comments to D130010: [AArch64][SVE] Add ISel pattern to lower DUPLANE128 to LD1RQD.
Jul 18 2022, 9:26 AM · Restricted Project, Restricted Project
MattDevereau requested review of D130013: [AArch64][SVE] Add DAG-Combine to push bitcasts from floating point loads after DUPLANE128.
Jul 18 2022, 7:52 AM · Restricted Project, Restricted Project
MattDevereau abandoned D129758: [AArch64][SVE] Lower DUPLANE128 to LD1RQD.

This is being split into two patches, the first of which being https://reviews.llvm.org/D130010

Jul 18 2022, 7:30 AM · Restricted Project, Restricted Project
MattDevereau added a comment to D130010: [AArch64][SVE] Add ISel pattern to lower DUPLANE128 to LD1RQD.

This patch has been created as a result of (https://reviews.llvm.org/D129758#inline-1248669)

Jul 18 2022, 7:29 AM · Restricted Project, Restricted Project
MattDevereau requested review of D130010: [AArch64][SVE] Add ISel pattern to lower DUPLANE128 to LD1RQD.
Jul 18 2022, 7:27 AM · Restricted Project, Restricted Project

Jul 15 2022

MattDevereau updated the diff for D129758: [AArch64][SVE] Lower DUPLANE128 to LD1RQD.
Jul 15 2022, 5:43 AM · Restricted Project, Restricted Project

Jul 14 2022

MattDevereau updated the diff for D129758: [AArch64][SVE] Lower DUPLANE128 to LD1RQD.

Following an offline talk, ld1rqd/w/h/s needs to respect the original width of the load type due to big endian targets

Jul 14 2022, 6:59 AM · Restricted Project, Restricted Project
MattDevereau requested review of D129758: [AArch64][SVE] Lower DUPLANE128 to LD1RQD.
Jul 14 2022, 4:57 AM · Restricted Project, Restricted Project

Jul 1 2022

MattDevereau committed rG5166345f5041: [SVE][AArch64] Refine hasSVEArgsOrReturn (authored by MattDevereau).
[SVE][AArch64] Refine hasSVEArgsOrReturn
Jul 1 2022, 6:26 AM · Restricted Project, Restricted Project
MattDevereau closed D127209: [SVE][AArch64] Refine hasSVEArgsOrReturn.
Jul 1 2022, 6:26 AM · Restricted Project, Restricted Project
MattDevereau committed rG018a0dd5c88b: [AArch64][SVE] Create AArch64ISD node for DUPQLANE128 (authored by MattDevereau).
[AArch64][SVE] Create AArch64ISD node for DUPQLANE128
Jul 1 2022, 4:47 AM · Restricted Project, Restricted Project
MattDevereau closed D128902: [AArch64][SVE] Create AArch64ISD node for DUPQLANE128.
Jul 1 2022, 4:47 AM · Restricted Project, Restricted Project

Jun 30 2022

MattDevereau added inline comments to D128902: [AArch64][SVE] Create AArch64ISD node for DUPQLANE128.
Jun 30 2022, 5:09 AM · Restricted Project, Restricted Project
MattDevereau retitled D128902: [AArch64][SVE] Create AArch64ISD node for DUPQLANE128 from [AArch64][SVE] Create AArch64ISD node for DUPQLANE to [AArch64][SVE] Create AArch64ISD node for DUPQLANE128.
Jun 30 2022, 5:07 AM · Restricted Project, Restricted Project
MattDevereau updated the diff for D128902: [AArch64][SVE] Create AArch64ISD node for DUPQLANE128.

removed redundant changes and made naming more consistent with previously added patterns

Jun 30 2022, 3:58 AM · Restricted Project, Restricted Project
MattDevereau abandoned D128503: [AArch64][SVE] Lower aarch64_sve_dupq_lane to ld1rq.

Abandoning in favour of https://reviews.llvm.org/D128902, which should result in a simpler combine across 2 patches

Jun 30 2022, 3:22 AM · Restricted Project, Restricted Project
MattDevereau requested review of D128902: [AArch64][SVE] Create AArch64ISD node for DUPQLANE128.
Jun 30 2022, 3:20 AM · Restricted Project, Restricted Project

Jun 29 2022

MattDevereau updated the diff for D127209: [SVE][AArch64] Refine hasSVEArgsOrReturn.

Added logic to LowerFormalArguments to check the return type for scalable vector types. This is more reliable than checking the return types in LowerReturn as LowerReturn does not always run when checking calls, i.e. in the tail call case

Jun 29 2022, 8:15 AM · Restricted Project, Restricted Project

Jun 28 2022

MattDevereau planned changes to D127209: [SVE][AArch64] Refine hasSVEArgsOrReturn.
Jun 28 2022, 3:39 AM · Restricted Project, Restricted Project

Jun 26 2022

MattDevereau updated the diff for D128503: [AArch64][SVE] Lower aarch64_sve_dupq_lane to ld1rq.

Fix broken tests

Jun 26 2022, 11:39 PM · Restricted Project, Restricted Project

Jun 24 2022

MattDevereau requested review of D128503: [AArch64][SVE] Lower aarch64_sve_dupq_lane to ld1rq.
Jun 24 2022, 1:04 AM · Restricted Project, Restricted Project
MattDevereau committed rGcc3ef26f60b1: [AArch64][SVE] Add sve.dupq.lane(insert(constant vector, 0), 0) ld1rq tests (authored by MattDevereau).
[AArch64][SVE] Add sve.dupq.lane(insert(constant vector, 0), 0) ld1rq tests
Jun 24 2022, 12:44 AM · Restricted Project, Restricted Project

Jun 22 2022

MattDevereau added a reviewer for D127209: [SVE][AArch64] Refine hasSVEArgsOrReturn: peterwaller-arm.
Jun 22 2022, 1:52 AM · Restricted Project, Restricted Project

Jun 20 2022

MattDevereau added inline comments to D127209: [SVE][AArch64] Refine hasSVEArgsOrReturn.
Jun 20 2022, 5:26 AM · Restricted Project, Restricted Project

Jun 16 2022

MattDevereau added inline comments to D127209: [SVE][AArch64] Refine hasSVEArgsOrReturn.
Jun 16 2022, 10:36 AM · Restricted Project, Restricted Project
MattDevereau updated the diff for D127209: [SVE][AArch64] Refine hasSVEArgsOrReturn.
Jun 16 2022, 6:28 AM · Restricted Project, Restricted Project

Jun 15 2022

MattDevereau added inline comments to D127209: [SVE][AArch64] Refine hasSVEArgsOrReturn.
Jun 15 2022, 5:51 AM · Restricted Project, Restricted Project

Jun 10 2022

MattDevereau updated the summary of D127209: [SVE][AArch64] Refine hasSVEArgsOrReturn.
Jun 10 2022, 6:06 AM · Restricted Project, Restricted Project
MattDevereau updated the diff for D127209: [SVE][AArch64] Refine hasSVEArgsOrReturn.

Removed hasSVEArgsOrReturn

Jun 10 2022, 5:29 AM · Restricted Project, Restricted Project
MattDevereau added inline comments to D127209: [SVE][AArch64] Refine hasSVEArgsOrReturn.
Jun 10 2022, 4:25 AM · Restricted Project, Restricted Project
MattDevereau updated the diff for D127209: [SVE][AArch64] Refine hasSVEArgsOrReturn.

Moved SVE function deduction from AArch64RegisterInfo::hasSVEArgsOrReturn to AArch64TargetLowering::LowerFormalArguments
Added IsSVE bool to AArch64FunctionInfo which describes if an AArch64Function has SVE args or return type in physical registers

Jun 10 2022, 3:47 AM · Restricted Project, Restricted Project

Jun 7 2022

MattDevereau requested review of D127209: [SVE][AArch64] Refine hasSVEArgsOrReturn.
Jun 7 2022, 5:28 AM · Restricted Project, Restricted Project

May 11 2022

MattDevereau committed rG75bb815231f6: [AArch64][SVE] Add aarch64_sve_pcs attribute to Clang (authored by MattDevereau).
[AArch64][SVE] Add aarch64_sve_pcs attribute to Clang
May 11 2022, 6:37 AM · Restricted Project, Restricted Project
MattDevereau closed D124998: [AArch64][SVE] Add aarch64_sve_pcs attribute to Clang.
May 11 2022, 6:36 AM · Restricted Project, Restricted Project

May 5 2022

MattDevereau updated the diff for D124998: [AArch64][SVE] Add aarch64_sve_pcs attribute to Clang.

set CXCallingConv_AArch64SVEPcs= 17 to 18 to resolve ABI break
renamed CC_AArch64SVEPcs to CC_AArch64SVEPCS

May 5 2022, 8:35 AM · Restricted Project, Restricted Project
MattDevereau requested review of D124998: [AArch64][SVE] Add aarch64_sve_pcs attribute to Clang.
May 5 2022, 3:35 AM · Restricted Project, Restricted Project

Apr 5 2022

MattDevereau committed rG2c3f66519c5e: [SVE] Extend support for folding select + masked gathers (authored by MattDevereau).
[SVE] Extend support for folding select + masked gathers
Apr 5 2022, 9:28 AM · Restricted Project, Restricted Project
MattDevereau closed D122896: [InstCombine] Extend support for folding select + masked gathers.
Apr 5 2022, 9:28 AM · Restricted Project, Restricted Project

Apr 4 2022

MattDevereau retitled D122896: [InstCombine] Extend support for folding select + masked gathers from [SVE] Extend support for folding select + masked gathers to [InstCombine] Extend support for folding select + masked gathers.
Apr 4 2022, 3:34 AM · Restricted Project, Restricted Project

Apr 1 2022

MattDevereau requested review of D122896: [InstCombine] Extend support for folding select + masked gathers.
Apr 1 2022, 5:41 AM · Restricted Project, Restricted Project

Mar 17 2022

MattDevereau committed rGa9e08bc7c1e5: [AArch64][SVE] InstCombine llvm.aarch64.sve.sel to select (authored by MattDevereau).
[AArch64][SVE] InstCombine llvm.aarch64.sve.sel to select
Mar 17 2022, 9:21 AM · Restricted Project
MattDevereau closed D121792: [AArch64][SVE] InstCombine llvm.aarch64.sve.sel to select.
Mar 17 2022, 9:21 AM · Restricted Project, Restricted Project, Restricted Project

Mar 16 2022

MattDevereau requested review of D121792: [AArch64][SVE] InstCombine llvm.aarch64.sve.sel to select.
Mar 16 2022, 5:01 AM · Restricted Project, Restricted Project, Restricted Project

Mar 11 2022

MattDevereau committed rG6c5da880e03c: [AArch64][SVE][Clang] Fix crash for incorrect svptrue and svcnt parameters (authored by MattDevereau).
[AArch64][SVE][Clang] Fix crash for incorrect svptrue and svcnt parameters
Mar 11 2022, 3:22 AM · Restricted Project
MattDevereau closed D121294: [AArch64][SVE][Clang] Fix crash for incorrect svptrue and svcnt parameters.
Mar 11 2022, 3:21 AM · Restricted Project, Restricted Project

Mar 9 2022

MattDevereau added a comment to D121294: [AArch64][SVE][Clang] Fix crash for incorrect svptrue and svcnt parameters.

This is missing tests for svundef, svrdffr, svsetffr and svpfalse?

Mar 9 2022, 8:22 AM · Restricted Project, Restricted Project
MattDevereau requested review of D121294: [AArch64][SVE][Clang] Fix crash for incorrect svptrue and svcnt parameters.
Mar 9 2022, 7:53 AM · Restricted Project, Restricted Project

Mar 1 2022

MattDevereau abandoned D120715: [AArch64][SVE] Optimize mov and sel away for masked loads in sel.
Mar 1 2022, 9:31 AM · Restricted Project
MattDevereau planned changes to D120715: [AArch64][SVE] Optimize mov and sel away for masked loads in sel.
Mar 1 2022, 6:14 AM · Restricted Project
MattDevereau requested review of D120715: [AArch64][SVE] Optimize mov and sel away for masked loads in sel.
Mar 1 2022, 4:42 AM · Restricted Project

Feb 28 2022

MattDevereau abandoned D119926: [Clang][AArch64] Enable _Float16 _Complex type.

Abandoning this patch as it is redundant due to changes in D105331. This patch also drew attention to unused code that has since been removed in 841355c1e4e35fc02b5b171419979f5f9af0ebc8. Many thanks to @aaron.ballman

Feb 28 2022, 5:34 AM · Restricted Project

Feb 17 2022

MattDevereau committed rG2f2dcb4fb134: [AArch64][SVE] Invert VSelect operand order and condition for predicated… (authored by MattDevereau).
[AArch64][SVE] Invert VSelect operand order and condition for predicated…
Feb 17 2022, 8:02 AM
MattDevereau closed D119424: [AArch64][SVE] Invert VSelect operand order and condition for predicated arithmetic operations.
Feb 17 2022, 8:01 AM · Restricted Project

Feb 16 2022

MattDevereau updated the diff for D119926: [Clang][AArch64] Enable _Float16 _Complex type.

Removed -O1 and -ffast-math flags

Feb 16 2022, 6:52 AM · Restricted Project
MattDevereau requested review of D119926: [Clang][AArch64] Enable _Float16 _Complex type.
Feb 16 2022, 2:45 AM · Restricted Project
MattDevereau updated the summary of D119424: [AArch64][SVE] Invert VSelect operand order and condition for predicated arithmetic operations.
Feb 16 2022, 2:33 AM · Restricted Project
MattDevereau updated the summary of D119424: [AArch64][SVE] Invert VSelect operand order and condition for predicated arithmetic operations.
Feb 16 2022, 2:33 AM · Restricted Project
MattDevereau updated the diff for D119424: [AArch64][SVE] Invert VSelect operand order and condition for predicated arithmetic operations.
Feb 16 2022, 2:32 AM · Restricted Project

Feb 15 2022

MattDevereau updated the diff for D119424: [AArch64][SVE] Invert VSelect operand order and condition for predicated arithmetic operations.

Removed SetCCOp0 == NOp2 and SetCCOp0 != NOp1 exit conditions
Added SelectA != SelectB.getOperand(0) exit condition

Feb 15 2022, 7:35 AM · Restricted Project
MattDevereau committed rG7dce12de6888: [AArch64] Suggest b.nfrst if the user tries b.nfirst. (authored by MattDevereau).
[AArch64] Suggest b.nfrst if the user tries b.nfirst.
Feb 15 2022, 7:06 AM
MattDevereau closed D119453: [AArch64] Suggest b.nfrst if the user tries b.nfirst..
Feb 15 2022, 7:06 AM · Restricted Project