Page MenuHomePhabricator

kmclaughlin (Kerry McLaughlin)
User

Projects

User does not belong to any projects.

User Details

User Since
Jul 10 2019, 8:51 AM (63 w, 2 d)

Recent Activity

Today

kmclaughlin requested review of D88321: [SVE][CodeGen] Lower scalable fp_extend & fp_round operations.
Fri, Sep 25, 10:06 AM · Restricted Project
kmclaughlin updated the diff for D88033: [SVE][CodeGen] Legalisation of integer -> floating point conversions.
  • Reverted previous change to restrict the concat_vectors marked as custom. The extra check added to LowerCONCAT_VECTORS (isTypeLegal(Op.getOperand(0)...) will cover cases where the result is a two element vector.
Fri, Sep 25, 5:31 AM · Restricted Project
kmclaughlin updated the diff for D88033: [SVE][CodeGen] Legalisation of integer -> floating point conversions.
  • Restricted the concat_vectors marked as 'custom' to those with result types of 4+ elements only
  • Removed unused patterns for reinterpret_cast
  • Moved additional isTypeLegal check to the if statement in LowerCONCAT_VECTORS
Fri, Sep 25, 4:13 AM · Restricted Project

Yesterday

kmclaughlin updated the summary of D88033: [SVE][CodeGen] Legalisation of integer -> floating point conversions.
Thu, Sep 24, 10:51 AM · Restricted Project
kmclaughlin updated the diff for D88033: [SVE][CodeGen] Legalisation of integer -> floating point conversions.
  • Simplified the LowerCONCAT_VECTORS function so that it returns Op if the number of operands is 2.
  • Added ISel patterns for lowering floating-point concat_vectors, making this consistent with how we lower concats of predicate types.
Thu, Sep 24, 10:44 AM · Restricted Project

Wed, Sep 23

kmclaughlin committed rGd0149ba9b46d: [SVE][CodeGen] Lower legal integer -> floating point conversions (authored by kmclaughlin).
[SVE][CodeGen] Lower legal integer -> floating point conversions
Wed, Sep 23, 4:04 AM
kmclaughlin closed D87913: [SVE][CodeGen] Lower legal integer -> floating point conversions.
Wed, Sep 23, 4:04 AM · Restricted Project

Tue, Sep 22

kmclaughlin added inline comments to D88033: [SVE][CodeGen] Legalisation of integer -> floating point conversions.
Tue, Sep 22, 10:40 AM · Restricted Project
kmclaughlin updated the diff for D88033: [SVE][CodeGen] Legalisation of integer -> floating point conversions.

Changes made to the LowerCONCAT_VECTORS function:

  • Replaced OpVT.getVectorElementCount()*2 condition with Op.getNumOperands() != 2
  • Moved the isFloatingPoint() check into the assert
Tue, Sep 22, 10:40 AM · Restricted Project

Mon, Sep 21

kmclaughlin requested review of D88033: [SVE][CodeGen] Legalisation of integer -> floating point conversions.
Mon, Sep 21, 9:52 AM · Restricted Project

Fri, Sep 18

kmclaughlin requested review of D87913: [SVE][CodeGen] Lower legal integer -> floating point conversions.
Fri, Sep 18, 9:10 AM · Restricted Project

Thu, Sep 17

kmclaughlin added inline comments to D87232: [SVE][CodeGen] Lower floating point -> integer conversions.
Thu, Sep 17, 6:06 AM · Restricted Project
kmclaughlin committed rGf7185b271f5b: [SVE][CodeGen] Lower floating point -> integer conversions (authored by kmclaughlin).
[SVE][CodeGen] Lower floating point -> integer conversions
Thu, Sep 17, 6:06 AM
kmclaughlin closed D87232: [SVE][CodeGen] Lower floating point -> integer conversions.
Thu, Sep 17, 6:05 AM · Restricted Project

Wed, Sep 16

kmclaughlin added inline comments to D87232: [SVE][CodeGen] Lower floating point -> integer conversions.
Wed, Sep 16, 5:48 AM · Restricted Project
kmclaughlin updated the diff for D87232: [SVE][CodeGen] Lower floating point -> integer conversions.
  • Removed isScalableVector() check from PromoteIntRes_FP_TO_XINT
  • Updated fptoui tests where the result type is promoted to check for fcvtzu
Wed, Sep 16, 5:47 AM · Restricted Project

Fri, Sep 11

kmclaughlin updated the diff for D87232: [SVE][CodeGen] Lower floating point -> integer conversions.
  • Renamed ISD nodes to FCVTZ[S|U]_MERGE_PASSTHRU
  • Renamed AArch64fcvtz[s|u]_p to AArch64fcvtz[s|u]_mt & moved their definitions to the block containing other _mt nodes in AArch64SVEInstrInfo.td
Fri, Sep 11, 9:36 AM · Restricted Project
kmclaughlin accepted D87496: [CodeGen] Fix bug in IncrementPointer.

LGTM

Fri, Sep 11, 3:05 AM · Restricted Project

Thu, Sep 10

kmclaughlin updated the diff for D87232: [SVE][CodeGen] Lower floating point -> integer conversions.
  • Renamed ISD nodes to FP_TO_[S|U]INT_MERGE_PASSTHRU
  • Lower only the llvm.aarch64.sve.fcvtz[u|s] intrinsics to these nodes and not those with a type suffix (e.g. llvm.aarch64.sve.fcvtzs.i32f64)
  • Removed combineSVEConversionFP() and added the new nodes to the list in isMergePassthruOpcode()
Thu, Sep 10, 8:41 AM · Restricted Project
kmclaughlin added a comment to D86548: [SVE][CodeGen] Legalisation of truncate for scalable vectors.

Thank you @paulwalker-arm, @eli.friedman and @david-arm for the reviews!

Thu, Sep 10, 3:41 AM · Restricted Project
kmclaughlin committed rGcd89f5c91b4b: [SVE][CodeGen] Legalisation of truncate for scalable vectors (authored by kmclaughlin).
[SVE][CodeGen] Legalisation of truncate for scalable vectors
Thu, Sep 10, 3:39 AM
kmclaughlin closed D86548: [SVE][CodeGen] Legalisation of truncate for scalable vectors.
Thu, Sep 10, 3:38 AM · Restricted Project
kmclaughlin accepted D87139: [SVE][CodeGen] Fix InlineFunction for scalable vectors.

LGTM

Thu, Sep 10, 2:28 AM · Restricted Project

Tue, Sep 8

kmclaughlin updated the diff for D86548: [SVE][CodeGen] Legalisation of truncate for scalable vectors.
  • Removed DAGCombine for UNPKHI/LO and added a new case for UZP1, so that we can check for the more specific case of uzp1(unpklo(uzp1(x, y)), z)
  • Removed an unnecessary check that InVT is an integer in LowerINSERT_SUBVECTOR
  • Renamed Idx in PromoteIntOp_EXTRACT_SUBVECTOR to OpNumElts
Tue, Sep 8, 9:44 AM · Restricted Project

Mon, Sep 7

kmclaughlin requested review of D87232: [SVE][CodeGen] Lower floating point -> integer conversions.
Mon, Sep 7, 6:44 AM · Restricted Project

Fri, Sep 4

kmclaughlin added inline comments to D86548: [SVE][CodeGen] Legalisation of truncate for scalable vectors.
Fri, Sep 4, 9:24 AM · Restricted Project
kmclaughlin updated the diff for D86548: [SVE][CodeGen] Legalisation of truncate for scalable vectors.
  • Removed the restriction from PromoteIntOp_EXTRACT_SUBVECTOR which prevented concatenating more than 2 scalable vectors
  • Added a case to PerformDAGCombine for UNPKHI/LO which combines the following: unpk(undef) -> undef & unpk(uzp1(x)) -> x
Fri, Sep 4, 9:22 AM · Restricted Project

Wed, Sep 2

kmclaughlin accepted D86431: [SVE][CodeGen] Fix up warnings in sve-split-insert/extract tests.

LGTM

Wed, Sep 2, 3:49 AM · Restricted Project

Tue, Sep 1

kmclaughlin added inline comments to D86548: [SVE][CodeGen] Legalisation of truncate for scalable vectors.
Tue, Sep 1, 10:50 AM · Restricted Project
kmclaughlin updated the diff for D86548: [SVE][CodeGen] Legalisation of truncate for scalable vectors.
  • Set EXTRACT_SUBVECTOR to Custom for the illegal types nxv8i8, nxv4i16 & nxv2i32 only.
  • Changed LowerINSERT_SUBVECTOR to apply the same checks for both the low & high cases.
Tue, Sep 1, 10:49 AM · Restricted Project

Aug 25 2020

kmclaughlin requested review of D86548: [SVE][CodeGen] Legalisation of truncate for scalable vectors.
Aug 25 2020, 9:47 AM · Restricted Project

Aug 13 2020

kmclaughlin committed rG30af595f05b5: [SVE][CodeGen] Legalisation of EXTRACT_VECTOR_ELT for scalable vectors (authored by kmclaughlin).
[SVE][CodeGen] Legalisation of EXTRACT_VECTOR_ELT for scalable vectors
Aug 13 2020, 4:34 AM
kmclaughlin closed D85754: [SVE][CodeGen] Legalisation of EXTRACT_VECTOR_ELT for scalable vectors.
Aug 13 2020, 4:33 AM · Restricted Project

Aug 12 2020

kmclaughlin added a comment to D85220: [CodeGen] Refactor getMemBasePlusOffset & getObjectPtrOffset to accept a TypeSize.

This will cause compilation failures in our downstream fork. Is there any reason for replacing the integer overload instead of adding a TypeSize overload?
I think adding TypeSize::Fixed( to all call sites is not ideal since it's overly verbose and also confusing since it's an offset and not a type size.
It would have also been nice to add a motivation for the change in the commit message rather than just explaining what's changing.

Aug 12 2020, 6:41 AM · Restricted Project

Aug 11 2020

kmclaughlin requested review of D85754: [SVE][CodeGen] Legalisation of EXTRACT_VECTOR_ELT for scalable vectors.
Aug 11 2020, 9:59 AM · Restricted Project
kmclaughlin added a comment to D84874: [SVE][CodeGen] Legalisation of INSERT_VECTOR_ELT for scalable vectors.

Thanks for reviewing this patch, @efriedma & @david-arm!

Aug 11 2020, 4:59 AM · Restricted Project
kmclaughlin committed rG455ed56d48e3: [SVE][CodeGen] Legalisation of INSERT_VECTOR_ELT for scalable vectors (authored by kmclaughlin).
[SVE][CodeGen] Legalisation of INSERT_VECTOR_ELT for scalable vectors
Aug 11 2020, 4:58 AM
kmclaughlin closed D84874: [SVE][CodeGen] Legalisation of INSERT_VECTOR_ELT for scalable vectors.
Aug 11 2020, 4:58 AM · Restricted Project
kmclaughlin committed rG85c7e89f3b33: [CodeGen] Refactor getMemBasePlusOffset & getObjectPtrOffset to accept a… (authored by kmclaughlin).
[CodeGen] Refactor getMemBasePlusOffset & getObjectPtrOffset to accept a…
Aug 11 2020, 4:18 AM
kmclaughlin closed D85220: [CodeGen] Refactor getMemBasePlusOffset & getObjectPtrOffset to accept a TypeSize.
Aug 11 2020, 4:18 AM · Restricted Project

Aug 6 2020

kmclaughlin added inline comments to D84874: [SVE][CodeGen] Legalisation of INSERT_VECTOR_ELT for scalable vectors.
Aug 6 2020, 9:11 AM · Restricted Project
kmclaughlin updated the diff for D84874: [SVE][CodeGen] Legalisation of INSERT_VECTOR_ELT for scalable vectors.
  • Replaced call to getMemBasePlusOffset in LegalizeVectorTypes.cpp with IncrementPointer
Aug 6 2020, 9:04 AM · Restricted Project

Aug 5 2020

kmclaughlin updated the diff for D85220: [CodeGen] Refactor getMemBasePlusOffset & getObjectPtrOffset to accept a TypeSize.
  • Additionally refactored getObjectPtrOffset to accept a TypeSize as the Offset argument
Aug 5 2020, 8:50 AM · Restricted Project

Aug 4 2020

kmclaughlin added inline comments to D84874: [SVE][CodeGen] Legalisation of INSERT_VECTOR_ELT for scalable vectors.
Aug 4 2020, 10:14 AM · Restricted Project
kmclaughlin updated the diff for D84874: [SVE][CodeGen] Legalisation of INSERT_VECTOR_ELT for scalable vectors.
  • Rebased and made this patch dependent on D85220, which changes the type of the Offset argument passed to getMemBasePlusOffset() to TypeSize
Aug 4 2020, 9:50 AM · Restricted Project
kmclaughlin requested review of D85220: [CodeGen] Refactor getMemBasePlusOffset & getObjectPtrOffset to accept a TypeSize.
Aug 4 2020, 9:43 AM · Restricted Project

Jul 30 2020

kmclaughlin added inline comments to D84874: [SVE][CodeGen] Legalisation of INSERT_VECTOR_ELT for scalable vectors.
Jul 30 2020, 10:00 AM · Restricted Project
kmclaughlin added inline comments to D84874: [SVE][CodeGen] Legalisation of INSERT_VECTOR_ELT for scalable vectors.
Jul 30 2020, 9:53 AM · Restricted Project
kmclaughlin updated the diff for D84874: [SVE][CodeGen] Legalisation of INSERT_VECTOR_ELT for scalable vectors.
  • Replaced uses of getKnownMinSize() with getFixedSize() where appropriate
Jul 30 2020, 9:50 AM · Restricted Project

Jul 29 2020

kmclaughlin requested review of D84874: [SVE][CodeGen] Legalisation of INSERT_VECTOR_ELT for scalable vectors.
Jul 29 2020, 10:34 AM · Restricted Project

Jul 16 2020

kmclaughlin committed rG2762da0a16a7: [SVE][CodeGen] Legalisation of masked loads and stores (authored by kmclaughlin).
[SVE][CodeGen] Legalisation of masked loads and stores
Jul 16 2020, 2:58 AM
kmclaughlin closed D83137: [SVE][CodeGen] Legalisation of masked loads and stores.
Jul 16 2020, 2:57 AM · Restricted Project

Jul 15 2020

kmclaughlin added a comment to D83137: [SVE][CodeGen] Legalisation of masked loads and stores.

Thanks for reviewing this patch, @efriedma & @david-arm

Jul 15 2020, 10:55 AM · Restricted Project

Jul 13 2020

kmclaughlin committed rGafcc9a81d2dc: [SVE][Codegen] Add a helper function for pointer increment logic (authored by kmclaughlin).
[SVE][Codegen] Add a helper function for pointer increment logic
Jul 13 2020, 3:04 AM
kmclaughlin closed D83577: [SVE][Codegen] Add a helper function for pointer increment logic.
Jul 13 2020, 3:04 AM · Restricted Project

Jul 10 2020

Herald added a project to D83577: [SVE][Codegen] Add a helper function for pointer increment logic: Restricted Project.
Jul 10 2020, 10:54 AM · Restricted Project
kmclaughlin added inline comments to D83137: [SVE][CodeGen] Legalisation of masked loads and stores.
Jul 10 2020, 9:42 AM · Restricted Project

Jul 9 2020

kmclaughlin accepted D83203: [CodeGen] Fix warnings in SelectionDAG::SplitVector.

LGTM

Jul 9 2020, 5:47 AM · Restricted Project

Jul 7 2020

kmclaughlin added inline comments to D83137: [SVE][CodeGen] Legalisation of masked loads and stores.
Jul 7 2020, 11:10 AM · Restricted Project
kmclaughlin updated the diff for D83137: [SVE][CodeGen] Legalisation of masked loads and stores.

Changes to IncrementMemoryAddress:

  • Changed the assert added for scalable vectors to a report_fatal_error
  • Replaced Addr.getValueSizeInBits().getFixedSize() with AddrVT.getSizeInBits().getFixedSize()
  • Use DataVT.getStoreSize() instead of DataVT.getSizeInBits()
Jul 7 2020, 11:08 AM · Restricted Project
kmclaughlin committed rGcdf2eef613f7: [SVE][CodeGen] Legalisation of unpredicated store instructions (authored by kmclaughlin).
[SVE][CodeGen] Legalisation of unpredicated store instructions
Jul 7 2020, 4:01 AM
kmclaughlin closed D83041: [SVE][CodeGen] Legalisation of unpredicated store instructions.
Jul 7 2020, 4:01 AM · Restricted Project
kmclaughlin added a comment to D82792: [SVE][CodeGen] Legalisation of unpredicated load instructions.

Thanks for reviewing this change, @efriedma & @david-arm!

Jul 7 2020, 3:26 AM · Restricted Project
kmclaughlin committed rG5e8084beba20: [SVE][CodeGen] Legalisation of unpredicated load instructions (authored by kmclaughlin).
[SVE][CodeGen] Legalisation of unpredicated load instructions
Jul 7 2020, 3:24 AM
kmclaughlin closed D82792: [SVE][CodeGen] Legalisation of unpredicated load instructions.
Jul 7 2020, 3:24 AM · Restricted Project

Jul 6 2020

kmclaughlin accepted D82943: [SVE] Add more warnings checks to clang and LLVM SVE tests.

LGTM

Jul 6 2020, 3:44 AM · Restricted Project, Restricted Project

Jul 3 2020

kmclaughlin created D83137: [SVE][CodeGen] Legalisation of masked loads and stores.
Jul 3 2020, 10:12 AM · Restricted Project

Jul 2 2020

kmclaughlin created D83041: [SVE][CodeGen] Legalisation of unpredicated store instructions.
Jul 2 2020, 6:25 AM · Restricted Project
kmclaughlin committed rGfd6193d5ea4e: [AArch64][SVE] Add reg+imm addressing mode for unpredicated stores (authored by kmclaughlin).
[AArch64][SVE] Add reg+imm addressing mode for unpredicated stores
Jul 2 2020, 4:16 AM
kmclaughlin closed D82985: [AArch64][SVE] Add reg+imm addressing mode for unpredicated stores.
Jul 2 2020, 4:16 AM · Restricted Project

Jul 1 2020

kmclaughlin created D82985: [AArch64][SVE] Add reg+imm addressing mode for unpredicated stores.
Jul 1 2020, 11:20 AM · Restricted Project
kmclaughlin updated the diff for D82792: [SVE][CodeGen] Legalisation of unpredicated load instructions.
  • Use sextOrTrunc in getVScale() to ensure that MulImm matches the return type of the vscale
  • Add an assertion to getNode() which checks that the operand and return types of vscale match
Jul 1 2020, 10:48 AM · Restricted Project
kmclaughlin accepted D82655: [CodeGen] Fix up warnings in visitEXTRACT_SUBVECTOR.

LGTM!

Jul 1 2020, 4:17 AM · Restricted Project
kmclaughlin committed rG4c6683eafc17: [AArch64][SVE] Add reg+imm addressing mode for unpredicated loads (authored by kmclaughlin).
[AArch64][SVE] Add reg+imm addressing mode for unpredicated loads
Jul 1 2020, 3:12 AM
kmclaughlin closed D82893: [AArch64][SVE] Add reg+imm addressing mode for unpredicated loads.
Jul 1 2020, 3:12 AM · Restricted Project

Jun 30 2020

kmclaughlin added inline comments to D82792: [SVE][CodeGen] Legalisation of unpredicated load instructions.
Jun 30 2020, 11:24 AM · Restricted Project
kmclaughlin updated the diff for D82792: [SVE][CodeGen] Legalisation of unpredicated load instructions.
  • Split the addressing mode changes into a separate patch (D82893)
  • Changed MPI to MachinePointerInfo(LD->getPointerInfo()->getAddrSpace()) in SplitVecRes_LOAD
  • Use getFixedSize when creating the APInt in SplitVecRes_LOAD
Jun 30 2020, 10:50 AM · Restricted Project
kmclaughlin added reviewers for D82893: [AArch64][SVE] Add reg+imm addressing mode for unpredicated loads: sdesmalen, david-arm.
Jun 30 2020, 10:50 AM · Restricted Project
kmclaughlin created D82893: [AArch64][SVE] Add reg+imm addressing mode for unpredicated loads.
Jun 30 2020, 10:50 AM · Restricted Project

Jun 29 2020

kmclaughlin added inline comments to D82792: [SVE][CodeGen] Legalisation of unpredicated load instructions.
Jun 29 2020, 11:21 AM · Restricted Project
kmclaughlin created D82792: [SVE][CodeGen] Legalisation of unpredicated load instructions.
Jun 29 2020, 10:48 AM · Restricted Project
kmclaughlin committed rGbb6603f0132b: [AArch64][SVE] Bail out of performPostLD1Combine for scalable types (authored by kmclaughlin).
[AArch64][SVE] Bail out of performPostLD1Combine for scalable types
Jun 29 2020, 4:17 AM
kmclaughlin closed D82670: [AArch64][SVE] Bail out of performPostLD1Combine for scalable types.
Jun 29 2020, 4:17 AM · Restricted Project

Jun 26 2020

kmclaughlin created D82670: [AArch64][SVE] Bail out of performPostLD1Combine for scalable types.
Jun 26 2020, 11:29 AM · Restricted Project
kmclaughlin added inline comments to D82464: [AArch64][SVE] Predicate bfloat16 load patterns with HasBF16.
Jun 26 2020, 11:29 AM · Restricted Project
kmclaughlin committed rG6b313f198c95: [AArch64][SVE] Remove asserts from AArch64ISelLowering for bfloat16 types (authored by kmclaughlin).
[AArch64][SVE] Remove asserts from AArch64ISelLowering for bfloat16 types
Jun 26 2020, 7:04 AM
kmclaughlin committed rGedcfef8fee13: [AArch64][SVE] Add bfloat16 support to store intrinsics (authored by kmclaughlin).
[AArch64][SVE] Add bfloat16 support to store intrinsics
Jun 26 2020, 3:14 AM
kmclaughlin committed rG0ccfe1b267af: [AArch64][SVE] Predicate bfloat16 load patterns with HasBF16 (authored by kmclaughlin).
[AArch64][SVE] Predicate bfloat16 load patterns with HasBF16
Jun 26 2020, 3:14 AM
kmclaughlin closed D82448: [AArch64][SVE] Add bfloat16 support to store intrinsics.
Jun 26 2020, 3:14 AM · Restricted Project, Restricted Project
kmclaughlin closed D82464: [AArch64][SVE] Predicate bfloat16 load patterns with HasBF16.
Jun 26 2020, 3:13 AM · Restricted Project

Jun 25 2020

kmclaughlin added a comment to D82448: [AArch64][SVE] Add bfloat16 support to store intrinsics.

Thanks for reviewing this again, @fpetrogalli!

Jun 25 2020, 6:53 AM · Restricted Project, Restricted Project
kmclaughlin updated the diff for D82448: [AArch64][SVE] Add bfloat16 support to store intrinsics.
  • Added HasSVE to Predicates in AArch64SVEInstrInfo.td
  • Removed unnecessary indentation changes in AArch64SVEInstrInfo.td
  • Removed hasBF16 variable from performST1Combine/performSTNT1Combine
Jun 25 2020, 6:53 AM · Restricted Project, Restricted Project
kmclaughlin added inline comments to D82464: [AArch64][SVE] Predicate bfloat16 load patterns with HasBF16.
Jun 25 2020, 4:17 AM · Restricted Project
kmclaughlin updated the diff for D82464: [AArch64][SVE] Predicate bfloat16 load patterns with HasBF16.
  • Moved hasBF16() check into the assert in performLDNT1Combine
  • Added HasSVE to the Predicates
  • Added a function attribute for the bfloat tests
Jun 25 2020, 4:17 AM · Restricted Project

Jun 24 2020

kmclaughlin updated the diff for D82448: [AArch64][SVE] Add bfloat16 support to store intrinsics.
  • Added [HasBF16] predicate to new store pattern in AArch64SVEInstrInfo.td
  • Check hasBF16() is true for bfloat16 types in performST1Combine/performSTNT1Combine
  • Added bfloat16 test to sve-pred-contiguous-ldst-addressing-mode-reg-reg.ll
Jun 24 2020, 10:47 AM · Restricted Project, Restricted Project
kmclaughlin updated the diff for D82464: [AArch64][SVE] Predicate bfloat16 load patterns with HasBF16.
  • Added an assert in performLDNT1Combine to check hasBF16() is true where the type is a bfloat16
Jun 24 2020, 9:42 AM · Restricted Project
kmclaughlin created D82464: [AArch64][SVE] Predicate bfloat16 load patterns with HasBF16.
Jun 24 2020, 7:31 AM · Restricted Project
kmclaughlin created D82448: [AArch64][SVE] Add bfloat16 support to store intrinsics.
Jun 24 2020, 3:44 AM · Restricted Project, Restricted Project
kmclaughlin committed rG3d6cab271c7c: [AArch64][SVE] Add bfloat16 support to load intrinsics (authored by kmclaughlin).
[AArch64][SVE] Add bfloat16 support to load intrinsics
Jun 24 2020, 2:40 AM
kmclaughlin closed D82298: [AArch64][SVE] Add bfloat16 support to load intrinsics.
Jun 24 2020, 2:40 AM · Restricted Project, Restricted Project