Arm64: Implement SVE APIs

[kunalspathak]

Now that all the SVE instructions encoding is completed in #94549, it is time to expose these instructions through .NET APIs. Here is the list of categorized APIs with links to the issue where they were approved.

.NET 9 Goal: We aim to complete SVE APIs in .NET 9. SVE2 APIs will be pushed out to .NET 10.

SVE APIs

High Priority SVE APIs

Sve mask (Complete)

Full list

• AbsoluteCompareGreaterThan Arm64/Sve: Implement AbsoluteCompare* and Compare* APIs #104464
• AbsoluteCompareGreaterThanOrEqual Arm64/Sve: Implement AbsoluteCompare* and Compare* APIs #104464
• AbsoluteCompareLessThan Arm64/Sve: Implement AbsoluteCompare* and Compare* APIs #104464
• AbsoluteCompareLessThanOrEqual Arm64/Sve: Implement AbsoluteCompare* and Compare* APIs #104464
• Compact JIT ARM64-SVE: Add Compact API #102992
• CompareEqual Arm64/Sve: Implement AbsoluteCompare* and Compare* APIs #104464
• CompareGreaterThan Arm64/Sve: Implement AbsoluteCompare* and Compare* APIs #104464
• CompareGreaterThanOrEqual Arm64/Sve: Implement AbsoluteCompare* and Compare* APIs #104464
• CompareLessThan Arm64/Sve: Implement AbsoluteCompare* and Compare* APIs #104464
• CompareLessThanOrEqual Arm64/Sve: Implement AbsoluteCompare* and Compare* APIs #104464
• CompareNotEqualTo Arm64/Sve: Implement AbsoluteCompare* and Compare* APIs #104464
• CompareUnordered Arm64/Sve: Implement AbsoluteCompare* and Compare* APIs #104464
• ConditionalExtractAfterLastActiveElement JIT ARM64-SVE: Add Sve.ConditionalExtract* APIs #104150
• ConditionalExtractAfterLastActiveElementAndReplicate JIT ARM64-SVE: Add Sve.ConditionalExtract* APIs #104150
• ConditionalExtractLastActiveElement JIT ARM64-SVE: Add Sve.ConditionalExtract* APIs #104150
• ConditionalExtractLastActiveElementAndReplicate JIT ARM64-SVE: Add Sve.ConditionalExtract* APIs #104150
• ConditionalSelect Arm64/Sve: Predicated Abs, Predicated/UnPredicated Add, Conditional Select #100743
• CreateBreakAfterMask JIT: Added four SVE CreateBreak* APIs #104184 (Future work) Add optimization for CndSel
• CreateBreakAfterPropagateMask JIT: Added four SVE CreateBreak* APIs #104184 (Future work) Add optimization for CndSel
• CreateBreakBeforeMask JIT: Added four SVE CreateBreak* APIs #104184 (Future work) Add optimization for CndSel
• CreateBreakBeforePropagateMask JIT: Added four SVE CreateBreak* APIs #104184 (Future work) Add optimization for CndSel
• CreateBreakPropagateMask JIT: Added Sve.CreateBreakPropagateMask #104704
• CreateFalseMaskByte JIT ARM64-SVE: Add Sve.CreateFalseMask*() #102076
• CreateFalseMaskDouble JIT ARM64-SVE: Add Sve.CreateFalseMask*() #102076
• CreateFalseMaskInt16 JIT ARM64-SVE: Add Sve.CreateFalseMask*() #102076
• CreateFalseMaskInt32 JIT ARM64-SVE: Add Sve.CreateFalseMask*() #102076
• CreateFalseMaskInt64 JIT ARM64-SVE: Add Sve.CreateFalseMask*() #102076
• CreateFalseMaskSByte JIT ARM64-SVE: Add Sve.CreateFalseMask*() #102076
• CreateFalseMaskSingle JIT ARM64-SVE: Add Sve.CreateFalseMask*() #102076
• CreateFalseMaskUInt16 JIT ARM64-SVE: Add Sve.CreateFalseMask*() #102076
• CreateFalseMaskUInt32 JIT ARM64-SVE: Add Sve.CreateFalseMask*() #102076
• CreateFalseMaskUInt64 JIT ARM64-SVE: Add Sve.CreateFalseMask*() #102076
• CreateMaskForFirstActiveElement JIT: Added SVE APIs CreateMaskForFirstActiveElement and CreateMaskForNextActiveElement #104002
• CreateMaskForNextActiveElement JIT: Added SVE APIs CreateMaskForFirstActiveElement and CreateMaskForNextActiveElement #104002
• CreateTrueMaskByte JIT ARM64-SVE: Add TrueMask and LoadVector #98218
• CreateTrueMaskDouble JIT ARM64-SVE: Add TrueMask and LoadVector #98218
• CreateTrueMaskInt16 JIT ARM64-SVE: Add TrueMask and LoadVector #98218
• CreateTrueMaskInt32 JIT ARM64-SVE: Add TrueMask and LoadVector #98218
• CreateTrueMaskInt64 JIT ARM64-SVE: Add TrueMask and LoadVector #98218
• CreateTrueMaskSByte JIT ARM64-SVE: Add TrueMask and LoadVector #98218
• CreateTrueMaskSingle JIT ARM64-SVE: Add TrueMask and LoadVector #98218
• CreateTrueMaskUInt16 JIT ARM64-SVE: Add TrueMask and LoadVector #98218
• CreateTrueMaskUInt32 JIT ARM64-SVE: Add TrueMask and LoadVector #98218
• CreateTrueMaskUInt64 JIT ARM64-SVE: Add TrueMask and LoadVector #98218
• CreateWhileLessThanMask16Bit JIT ARM64-SVE: Add CreateWhileLessThan* #100949
• CreateWhileLessThanMask32Bit JIT ARM64-SVE: Add CreateWhileLessThan* #100949
• CreateWhileLessThanMask64Bit JIT ARM64-SVE: Add CreateWhileLessThan* #100949
• CreateWhileLessThanMask8Bit JIT ARM64-SVE: Add CreateWhileLessThan* #100949
• CreateWhileLessThanOrEqualMask16Bit JIT ARM64-SVE: Add CreateWhileLessThan* #100949
• CreateWhileLessThanOrEqualMask32Bit JIT ARM64-SVE: Add CreateWhileLessThan* #100949
• CreateWhileLessThanOrEqualMask64Bit JIT ARM64-SVE: Add CreateWhileLessThan* #100949
• CreateWhileLessThanOrEqualMask8Bit JIT ARM64-SVE: Add CreateWhileLessThan* #100949
• (Future item) ExtractAfterLastScalar JIT: ARM64 - Added SVE APIs ExtractLastVector, ExtractLastScalar, ExtractAfterLastVector, ExtractAfterLastScalar #103847
• (Future item) ExtractAfterLastVector JIT: ARM64 - Added SVE APIs ExtractLastVector, ExtractLastScalar, ExtractAfterLastVector, ExtractAfterLastScalar #103847
• (Future item) ExtractLastScalar JIT: ARM64 - Added SVE APIs ExtractLastVector, ExtractLastScalar, ExtractAfterLastVector, ExtractAfterLastScalar #103847
• (Future item) ExtractLastVector JIT: ARM64 - Added SVE APIs ExtractLastVector, ExtractLastScalar, ExtractAfterLastVector, ExtractAfterLastScalar #103847
• ExtractVector JIT: Added SVE APIs - Test*, ExtractVector #103739
• TestAnyTrue JIT: Added SVE APIs - Test*, ExtractVector #103739
• TestFirstTrue JIT: Added SVE APIs - Test*, ExtractVector #103739
• TestLastTrue JIT: Added SVE APIs - Test*, ExtractVector #103739

Sve bitwise (Complete)

Full list

• And JIT ARM64-SVE: Add simple bitwise ops #101762
• AndAcross JIT ARM64-SVE: Add simple bitwise ops #101762
• (Future work) AndNot Need to fix Arm64/Sve: Mirror some of the morph optimizations from AVX512 #101933
• BitwiseClear JIT ARM64-SVE: Add BitwiseClear and BooleanNot #101853
• BooleanNot JIT ARM64-SVE: Add BitwiseClear and BooleanNot #101853
• InsertIntoShiftedVector ARM64-SVE: Add Not, InsertIntoShiftedVector #103725
• Not ARM64-SVE: Add Not, InsertIntoShiftedVector #103725
• Or JIT ARM64-SVE: Add simple bitwise ops #101762
• OrAcross JIT ARM64-SVE: Add simple bitwise ops #101762
• (Future work) OrNot Need to fix Arm64/Sve: Mirror some of the morph optimizations from AVX512 #101933
• ShiftLeftLogical ARM64-SVE: Implement ShiftLeftLogical, ShiftRightArithmetic, ShiftRightLogical #104119
• ShiftRightArithmetic ARM64-SVE: Implement ShiftLeftLogical, ShiftRightArithmetic, ShiftRightLogical #104119
• ShiftRightArithmeticForDivide ARM64-SVE: Add ShiftRightArithmeticForDivide #104279
• ShiftRightLogical ARM64-SVE: Implement ShiftLeftLogical, ShiftRightArithmetic, ShiftRightLogical #104119
• Xor JIT ARM64-SVE: Add simple bitwise ops #101762
• XorAcross JIT ARM64-SVE: Add simple bitwise ops #101762

Sve bitmanipulate (Complete)

Full list

• DuplicateSelectedScalarToVector Add support for Sve.DuplicateSelectedScalarToVector() #103228
• ReverseBits Add support for Sve.ReverseBits() #103806
• ReverseElement Add support for Sve.ReverseElementX() #102991
• ReverseElement16 Add support for Sve.ReverseElementX() #102991
• ReverseElement32 Add support for Sve.ReverseElementX() #102991
• ReverseElement8 Add support for Sve.ReverseElementX() #102991
• Splice Add support for Sve.Splice() #103567
• TransposeEven Add support for Sve.TransposeEven/Odd() #103068
• TransposeOdd Add support for Sve.TransposeEven/Odd() #103068
• UnzipEven Add support for Sve.UnzipEven/Odd & Sve.ZipHighLow #101294
• UnzipOdd Add support for Sve.UnzipEven/Odd & Sve.ZipHighLow #101294
• VectorTableLookup Add support for Sve.VectorTableLookup() #103989
• ZipHigh Add support for Sve.UnzipEven/Odd & Sve.ZipHighLow #101294
• ZipLow Add support for Sve.UnzipEven/Odd & Sve.ZipHighLow #101294

Sve loads (Complete)

Full list

• Compute16BitAddresses Arm64/Sve: Implement Compute*BitAddresses APIs #103040
• Compute32BitAddresses Arm64/Sve: Implement Compute*BitAddresses APIs #103040
• Compute64BitAddresses Arm64/Sve: Implement Compute*BitAddresses APIs #103040
• Compute8BitAddresses Arm64/Sve: Implement Compute*BitAddresses APIs #103040
• LoadVector JIT ARM64-SVE: Add TrueMask and LoadVector #98218
• LoadVector128AndReplicateToVector JIT: Added Sve.LoadVectorNonTemporal/NonFaulting/128AndReplicateToVector APIs #103392
• LoadVectorByteNonFaultingZeroExtendToInt16 JIT: Added SVE LoadVector*NonFaultingZeroExtendTo* APIs #102860
• LoadVectorByteNonFaultingZeroExtendToInt32 JIT: Added SVE LoadVector*NonFaultingZeroExtendTo* APIs #102860
• LoadVectorByteNonFaultingZeroExtendToInt64 JIT: Added SVE LoadVector*NonFaultingZeroExtendTo* APIs #102860
• LoadVectorByteNonFaultingZeroExtendToUInt16 JIT: Added SVE LoadVector*NonFaultingZeroExtendTo* APIs #102860
• LoadVectorByteNonFaultingZeroExtendToUInt32 JIT: Added SVE LoadVector*NonFaultingZeroExtendTo* APIs #102860
• LoadVectorByteNonFaultingZeroExtendToUInt64 JIT: Added SVE LoadVector*NonFaultingZeroExtendTo* APIs #102860
• LoadVectorByteZeroExtendToInt16 JIT ARM64-SVE: Add Sve.LoadVector*ZeroExtendTo*() #101291
• LoadVectorByteZeroExtendToInt32 JIT ARM64-SVE: Add Sve.LoadVector*ZeroExtendTo*() #101291
• LoadVectorByteZeroExtendToInt64 JIT ARM64-SVE: Add Sve.LoadVector*ZeroExtendTo*() #101291
• LoadVectorByteZeroExtendToUInt16 JIT ARM64-SVE: Add Sve.LoadVector*ZeroExtendTo*() #101291
• LoadVectorByteZeroExtendToUInt32 JIT ARM64-SVE: Add Sve.LoadVector*ZeroExtendTo*() #101291
• LoadVectorByteZeroExtendToUInt64 JIT ARM64-SVE: Add Sve.LoadVector*ZeroExtendTo*() #101291
• LoadVectorInt16NonFaultingSignExtendToInt32 Arm64/Sve: Implement LoadVector*NonFaultingSignExtendTo* APIs #102903
• LoadVectorInt16NonFaultingSignExtendToInt64 Arm64/Sve: Implement LoadVector*NonFaultingSignExtendTo* APIs #102903
• LoadVectorInt16NonFaultingSignExtendToUInt32 Arm64/Sve: Implement LoadVector*NonFaultingSignExtendTo* APIs #102903
• LoadVectorInt16NonFaultingSignExtendToUInt64 Arm64/Sve: Implement LoadVector*NonFaultingSignExtendTo* APIs #102903
• LoadVectorInt16SignExtendToInt32 JIT ARM64-SVE: Add Sve.LoadVector*ZeroExtendTo*() #101291
• LoadVectorInt16SignExtendToInt64 JIT ARM64-SVE: Add Sve.LoadVector*ZeroExtendTo*() #101291
• LoadVectorInt16SignExtendToUInt32 JIT ARM64-SVE: Add Sve.LoadVector*ZeroExtendTo*() #101291
• LoadVectorInt16SignExtendToUInt64 JIT ARM64-SVE: Add Sve.LoadVector*ZeroExtendTo*() #101291
• LoadVectorInt32NonFaultingSignExtendToInt64 Arm64/Sve: Implement LoadVector*NonFaultingSignExtendTo* APIs #102903
• LoadVectorInt32NonFaultingSignExtendToUInt64 Arm64/Sve: Implement LoadVector*NonFaultingSignExtendTo* APIs #102903
• LoadVectorInt32SignExtendToInt64 JIT ARM64-SVE: Add Sve.LoadVector*ZeroExtendTo*() #101291
• LoadVectorInt32SignExtendToUInt64 JIT ARM64-SVE: Add Sve.LoadVector*ZeroExtendTo*() #101291
• LoadVectorNonFaulting JIT: Added Sve.LoadVectorNonTemporal/NonFaulting/128AndReplicateToVector APIs #103392
• LoadVectorNonTemporal JIT: Added Sve.LoadVectorNonTemporal/NonFaulting/128AndReplicateToVector APIs #103392
• LoadVectorSByteNonFaultingSignExtendToInt16 Arm64/Sve: Implement LoadVector*NonFaultingSignExtendTo* APIs #102903
• LoadVectorSByteNonFaultingSignExtendToInt32 Arm64/Sve: Implement LoadVector*NonFaultingSignExtendTo* APIs #102903
• LoadVectorSByteNonFaultingSignExtendToInt64 Arm64/Sve: Implement LoadVector*NonFaultingSignExtendTo* APIs #102903
• LoadVectorSByteNonFaultingSignExtendToUInt16 Arm64/Sve: Implement LoadVector*NonFaultingSignExtendTo* APIs #102903
• LoadVectorSByteNonFaultingSignExtendToUInt32 Arm64/Sve: Implement LoadVector*NonFaultingSignExtendTo* APIs #102903
• LoadVectorSByteNonFaultingSignExtendToUInt64 Arm64/Sve: Implement LoadVector*NonFaultingSignExtendTo* APIs #102903
• LoadVectorSByteSignExtendToInt16 JIT ARM64-SVE: Add Sve.LoadVector*ZeroExtendTo*() #101291
• LoadVectorSByteSignExtendToInt32 JIT ARM64-SVE: Add Sve.LoadVector*ZeroExtendTo*() #101291
• LoadVectorSByteSignExtendToInt64 JIT ARM64-SVE: Add Sve.LoadVector*ZeroExtendTo*() #101291
• LoadVectorSByteSignExtendToUInt16 JIT ARM64-SVE: Add Sve.LoadVector*ZeroExtendTo*() #101291
• LoadVectorSByteSignExtendToUInt32 JIT ARM64-SVE: Add Sve.LoadVector*ZeroExtendTo*() #101291
• LoadVectorSByteSignExtendToUInt64 JIT ARM64-SVE: Add Sve.LoadVector*ZeroExtendTo*() #101291
• LoadVectorUInt16NonFaultingZeroExtendToInt32 JIT: Added SVE LoadVector*NonFaultingZeroExtendTo* APIs #102860
• LoadVectorUInt16NonFaultingZeroExtendToInt64 JIT: Added SVE LoadVector*NonFaultingZeroExtendTo* APIs #102860
• LoadVectorUInt16NonFaultingZeroExtendToUInt32 JIT: Added SVE LoadVector*NonFaultingZeroExtendTo* APIs #102860
• LoadVectorUInt16NonFaultingZeroExtendToUInt64 JIT: Added SVE LoadVector*NonFaultingZeroExtendTo* APIs #102860
• LoadVectorUInt16ZeroExtendToInt32 JIT ARM64-SVE: Add Sve.LoadVector*ZeroExtendTo*() #101291
• LoadVectorUInt16ZeroExtendToInt64 JIT ARM64-SVE: Add Sve.LoadVector*ZeroExtendTo*() #101291
• LoadVectorUInt16ZeroExtendToUInt32 JIT ARM64-SVE: Add Sve.LoadVector*ZeroExtendTo*() #101291
• LoadVectorUInt16ZeroExtendToUInt64 JIT ARM64-SVE: Add Sve.LoadVector*ZeroExtendTo*() #101291
• LoadVectorUInt32NonFaultingZeroExtendToInt64 JIT: Added SVE LoadVector*NonFaultingZeroExtendTo* APIs #102860
• LoadVectorUInt32NonFaultingZeroExtendToUInt64 JIT: Added SVE LoadVector*NonFaultingZeroExtendTo* APIs #102860
• LoadVectorUInt32ZeroExtendToInt64 JIT ARM64-SVE: Add Sve.LoadVector*ZeroExtendTo*() #101291
• LoadVectorUInt32ZeroExtendToUInt64 JIT ARM64-SVE: Add Sve.LoadVector*ZeroExtendTo*() #101291
• LoadVectorx2 SVE: Added Load2xVectorAndUnzip, Load3xVectorAndUnzip, Load4xVectorAndUnzip APIs #102180
• LoadVectorx3 SVE: Added Load2xVectorAndUnzip, Load3xVectorAndUnzip, Load4xVectorAndUnzip APIs #102180
• LoadVectorx4 SVE: Added Load2xVectorAndUnzip, Load3xVectorAndUnzip, Load4xVectorAndUnzip APIs #102180
• PrefetchBytes JIT: Added SVE Prefetch* APIs. #103094
• PrefetchInt16 JIT: Added SVE Prefetch* APIs. #103094
• PrefetchInt32 JIT: Added SVE Prefetch* APIs. #103094
• PrefetchInt64 JIT: Added SVE Prefetch* APIs. #103094

Sve stores (Complete)

Full list

• Store Add support for Sve.Store() #102262
• StoreNarrowing Add support for Sve.StoreNarrowing() #102605
• StoreNonTemporal Add support for Sve.StoreNonTemporal() #102769

Sve maths (Complete)

Full list

• Abs Arm64/Sve: Predicated Abs, Predicated/UnPredicated Add, Conditional Select #100743
• AbsoluteDifference Arm64/Sve: Implement some more Math APIs #102170
• Add Arm64/Sve: Predicated Abs, Predicated/UnPredicated Add, Conditional Select #100743
• AddAcross JIT ARM64-SVE: Add AddAcross #101674
• AddSaturate Arm64/Sve: Implement some more Math APIs #102170
• Divide Arm64/Sve: Implement divide/multiply/subtract Math APIs #101578
• DotProduct Arm64/Sve: Implement Math's DotProduct* APIs #102218
• DotProductBySelectedScalar Arm64/Sve: Implement Math's DotProduct* APIs #102218
• FusedMultiplyAdd Arm64/Sve: Implement SVE Math *Multiply* APIs #102007
• FusedMultiplyAddBySelectedScalar Arm64/Sve: Implement SVE Math *Multiply* APIs #102007
• FusedMultiplyAddNegated Arm64/Sve: Implement SVE Math *Multiply* APIs #102007
• FusedMultiplySubtract Arm64/Sve: Implement SVE Math *Multiply* APIs #102007
• FusedMultiplySubtractBySelectedScalar Arm64/Sve: Implement SVE Math *Multiply* APIs #102007
• FusedMultiplySubtractNegated Arm64/Sve: Implement SVE Math *Multiply* APIs #102007
• Max Arm64/Sve: Implement SVE Math Min*/Max* APIs #101859
• MaxAcross Arm64/Sve: Implement SVE Math Min*/Max* APIs #101859
• MaxNumber Arm64/Sve: Implement SVE Math Min*/Max* APIs #101859
• MaxNumberAcross Arm64/Sve: Implement SVE Math Min*/Max* APIs #101859
• Min Arm64/Sve: Implement SVE Math Min*/Max* APIs #101859
• MinAcross Arm64/Sve: Implement SVE Math Min*/Max* APIs #101859
• MinNumber Arm64/Sve: Implement SVE Math Min*/Max* APIs #101859
• MinNumberAcross Arm64/Sve: Implement SVE Math Min*/Max* APIs #101859
• Multiply Arm64/Sve: Implement divide/multiply/subtract Math APIs #101578
• MultiplyAdd Arm64/Sve: Implement SVE Math *Multiply* APIs #102007
• MultiplyBySelectedScalar Arm64/Sve: Implement SVE Math *Multiply* APIs #102007
• MultiplyExtended Arm64/Sve: Implement some more Math APIs #102170
• MultiplySubtract Arm64/Sve: Implement SVE Math *Multiply* APIs #102007
• Negate Arm64/Sve: Implement some more Math APIs #102170
• SignExtend16 Arm64/Sve: Add SignExtend* and ZeroExtend* math APIs #101702
• SignExtend32 Arm64/Sve: Add SignExtend* and ZeroExtend* math APIs #101702
• SignExtend8 Arm64/Sve: Add SignExtend* and ZeroExtend* math APIs #101702
• SignExtendWideningLower Arm64/Sve: Add SignExtendWidening* and ZeroExtendWidening* math APIs #101743
• SignExtendWideningUpper Arm64/Sve: Add SignExtendWidening* and ZeroExtendWidening* math APIs #101743
• Subtract Arm64/Sve: Implement divide/multiply/subtract Math APIs #101578
• SubtractSaturate Arm64/Sve: Implement some more Math APIs #102170
• ZeroExtend16 Arm64/Sve: Add SignExtend* and ZeroExtend* math APIs #101702
• ZeroExtend32 Arm64/Sve: Add SignExtend* and ZeroExtend* math APIs #101702
• ZeroExtend8 Arm64/Sve: Add SignExtend* and ZeroExtend* math APIs #101702
• ZeroExtendWideningLower Arm64/Sve: Add SignExtendWidening* and ZeroExtendWidening* math APIs #101743
• ZeroExtendWideningUpper Arm64/Sve: Add SignExtendWidening* and ZeroExtendWidening* math APIs #101743

Sve counting (Complete)

Full list

• Count16BitElements JIT ARM64-SVE: Add Count*BitElements #101188
• Count32BitElements JIT ARM64-SVE: Add Count*BitElements #101188
• Count64BitElements JIT ARM64-SVE: Add Count*BitElements #101188
• Count8BitElements JIT ARM64-SVE: Add Count*BitElements #101188
• GetActiveElementCount ARM64-SVE: GetActiveElementCount #102813
• LeadingSignCount ARM64-SVE: LeadingSignCount, LeadingZeroCount, PopCount #102548
• LeadingZeroCount ARM64-SVE: LeadingSignCount, LeadingZeroCount, PopCount #102548
• PopCount ARM64-SVE: LeadingSignCount, LeadingZeroCount, PopCount #102548
• SaturatingDecrementBy16BitElementCount JIT ARM64-SVE: Add saturating decrement/increment by element count #102315
• SaturatingDecrementBy32BitElementCount JIT ARM64-SVE: Add saturating decrement/increment by element count #102315
• SaturatingDecrementBy64BitElementCount JIT ARM64-SVE: Add saturating decrement/increment by element count #102315
• SaturatingDecrementBy8BitElementCount JIT ARM64-SVE: Add saturating decrement/increment by element count #102315
• SaturatingDecrementByActiveElementCount ARM64-SVE: Saturating*ByActiveElementCount #102994
• SaturatingIncrementBy16BitElementCount JIT ARM64-SVE: Add saturating decrement/increment by element count #102315
• SaturatingIncrementBy32BitElementCount JIT ARM64-SVE: Add saturating decrement/increment by element count #102315
• SaturatingIncrementBy64BitElementCount JIT ARM64-SVE: Add saturating decrement/increment by element count #102315
• SaturatingIncrementBy8BitElementCount JIT ARM64-SVE: Add saturating decrement/increment by element count #102315
• SaturatingIncrementByActiveElementCount ARM64-SVE: Saturating*ByActiveElementCount #102994

Low Priority SVE APIs

Sve scatterstores (Complete)

Full list

• Scatter Add support for Sve.Scatter() #104555
• Scatter16BitNarrowing Add Sve.ScatterXBitYNarrowing() on Arm64 #104720
• Scatter16BitWithByteOffsetsNarrowing Add Sve.ScatterXBitYNarrowing() on Arm64 #104720
• Scatter32BitNarrowing Add Sve.ScatterXBitYNarrowing() on Arm64 #104720
• Scatter32BitWithByteOffsetsNarrowing Add Sve.ScatterXBitYNarrowing() on Arm64 #104720
• Scatter8BitNarrowing Add Sve.ScatterXBitYNarrowing() on Arm64 #104720
• Scatter8BitWithByteOffsetsNarrowing Add Sve.ScatterXBitYNarrowing() on Arm64 #104720

Sve gatherloads (Complete)

Full list

• GatherPrefetch16Bit ARM64-SVE: GatherPrefetch #103826
• GatherPrefetch32Bit ARM64-SVE: GatherPrefetch #103826
• GatherPrefetch64Bit ARM64-SVE: GatherPrefetch #103826
• GatherPrefetch8Bit ARM64-SVE: GatherPrefetch #103826
• GatherVector ARM64-SVE: gathervector #103159
• GatherVectorByteZeroExtend ARM64-SVE: gathervector extends #103370
• GatherVectorInt16SignExtend ARM64-SVE: gathervector extends #103370
• GatherVectorInt16WithByteOffsetsSignExtend ARM64-SVE: gathervector extends #103370
• GatherVectorInt32SignExtend ARM64-SVE: gathervector extends #103370
• GatherVectorInt32WithByteOffsetsSignExtend ARM64-SVE: gathervector extends #103370
• GatherVectorSByteSignExtend ARM64-SVE: gathervector extends #103370
• GatherVectorUInt16WithByteOffsetsZeroExtend ARM64-SVE: gathervector extends #103370
• GatherVectorUInt16ZeroExtend ARM64-SVE: gathervector extends #103370
• GatherVectorUInt32WithByteOffsetsZeroExtend ARM64-SVE: gathervector extends #103370
• GatherVectorUInt32ZeroExtend ARM64-SVE: gathervector extends #103370
• GatherVectorWithByteOffsets ARM64-SVE: GatherVectorWithByteOffsets #103564

Sve fp (Complete)

Full list

• AddRotateComplex ARM64-SVE: Add AddRotateComplex, MultiplyAddRotateComplex #104926
• AddSequentialAcross ARM64-SVE: Add AddSequentialAcross #104640
• ConvertToDouble ARM64-SVE: Add ConvertToSingle, ConvertToDouble; fix CovertTo* tests #104478
• ConvertToInt32 Arm64/SVE: Implemented ConvertToInt32 and ConvertToUInt32 for float #103098
• ConvertToInt64 Arm64/SVE: Implemented ConvertToint64 and ConvertToUInt64 #104069
• ConvertToSingle ARM64-SVE: Add ConvertToSingle, ConvertToDouble; fix CovertTo* tests #104478
• ConvertToUInt32 Arm64/SVE: Implemented ConvertToInt32 and ConvertToUInt32 for float #103098
• ConvertToUInt64 Arm64/SVE: Implemented ConvertToint64 and ConvertToUInt64 #104069
• FloatingPointExponentialAccelerator ARM64-SVE: Add FloatingPointExponentialAccelerator #104649
• MultiplyAddRotateComplex ARM64-SVE: Add AddRotateComplex, MultiplyAddRotateComplex #104926
• MultiplyAddRotateComplexBySelectedScalar ARM64-SVE: Add MultiplyAddRotateComplexBySelectedScalar #105002
• ReciprocalEstimate Arm64/SVE: Implemented ReciprocalEstimate, ReciprocalExponent, ReciprocalSqrtEstimate, ReciprocalSqrtStep, and ReciprocalStep #103673
• ReciprocalExponent Arm64/SVE: Implemented ReciprocalEstimate, ReciprocalExponent, ReciprocalSqrtEstimate, ReciprocalSqrtStep, and ReciprocalStep #103673
• ReciprocalSqrtEstimate Arm64/SVE: Implemented ReciprocalEstimate, ReciprocalExponent, ReciprocalSqrtEstimate, ReciprocalSqrtStep, and ReciprocalStep #103673
• ReciprocalSqrtStep Arm64/SVE: Implemented ReciprocalEstimate, ReciprocalExponent, ReciprocalSqrtEstimate, ReciprocalSqrtStep, and ReciprocalStep #103673
• ReciprocalStep Arm64/SVE: Implemented ReciprocalEstimate, ReciprocalExponent, ReciprocalSqrtEstimate, ReciprocalSqrtStep, and ReciprocalStep #103673
• RoundAwayFromZero Arm64/SVE: Implemented RoundAwayFromZero, RoundToNearest, RouteToNegativeInfininty, RoundToPositiveInfinity, RoundToZero  #103588
• RoundToNearest Arm64/SVE: Implemented RoundAwayFromZero, RoundToNearest, RouteToNegativeInfininty, RoundToPositiveInfinity, RoundToZero  #103588
• RoundToNegativeInfinity Arm64/SVE: Implemented RoundAwayFromZero, RoundToNearest, RouteToNegativeInfininty, RoundToPositiveInfinity, RoundToZero  #103588
• RoundToPositiveInfinity Arm64/SVE: Implemented RoundAwayFromZero, RoundToNearest, RouteToNegativeInfininty, RoundToPositiveInfinity, RoundToZero  #103588
• RoundToZero Arm64/SVE: Implemented RoundAwayFromZero, RoundToNearest, RouteToNegativeInfininty, RoundToPositiveInfinity, RoundToZero  #103588
• Scale Arm64/SVE: Implemented Scale and Sqrt #103663
• Sqrt Arm64/SVE: Implemented Scale and Sqrt #103663
• TrigonometricMultiplyAddCoefficient ARM64-SVE: Add TrigonometricMultiplyAddCoefficient #104697
• TrigonometricSelectCoefficient ARM64-SVE: Add TrigonometricSelectCoefficient, TrigonometricStartingValue #104681
• TrigonometricStartingValue ARM64-SVE: Add TrigonometricSelectCoefficient, TrigonometricStartingValue #104681

Sve firstfaulting (Complete)

Full list

• GatherVectorByteZeroExtendFirstFaulting (Swapnil) Add support for Add Sve.GatherVectorUInt*ZeroExtendFirstFaulting() #105030
• GatherVectorFirstFaulting JIT: Added SVE GetFfr, SetFfr, LoadVectorFirstFaulting, GatherVectorFirstFaulting #104502
• GatherVectorInt16SignExtendFirstFaulting (Swapnil) Add support for Add Sve.GatherVectorUInt*ZeroExtendFirstFaulting() #105030
• GatherVectorInt16WithByteOffsetsSignExtendFirstFaulting (Swapnil) Add support for Add Sve.GatherVectorUInt*ZeroExtendFirstFaulting() #105030
• GatherVectorInt32SignExtendFirstFaulting (Swapnil) Add support for Add Sve.GatherVectorUInt*ZeroExtendFirstFaulting() #105030
• GatherVectorInt32WithByteOffsetsSignExtendFirstFaulting (Swapnil) Add support for Add Sve.GatherVectorUInt*ZeroExtendFirstFaulting() #105030
• GatherVectorSByteSignExtendFirstFaulting (Swapnil) Add support for Add Sve.GatherVectorUInt*ZeroExtendFirstFaulting() #105030
• GatherVectorUInt16WithByteOffsetsZeroExtendFirstFaulting (Swapnil) Add support for Add Sve.GatherVectorUInt*ZeroExtendFirstFaulting() #105030
• GatherVectorUInt16ZeroExtendFirstFaulting (Swapnil) Add support for Add Sve.GatherVectorUInt*ZeroExtendFirstFaulting() #105030
• GatherVectorUInt32WithByteOffsetsZeroExtendFirstFaulting (Swapnil) Add support for Add Sve.GatherVectorUInt*ZeroExtendFirstFaulting() #105030
• GatherVectorUInt32ZeroExtendFirstFaulting (Swapnil) Add support for Add Sve.GatherVectorUInt*ZeroExtendFirstFaulting() #105030
• GatherVectorWithByteOffsetFirstFaulting (Aman) ARM64-SVE: Add GatherVectorWithByteOffsetFirstFaulting #106199
• GetFfr JIT: Added SVE GetFfr, SetFfr, LoadVectorFirstFaulting, GatherVectorFirstFaulting #104502
• LoadVectorByteZeroExtendFirstFaulting JIT ARM64-SVE: Add Sve.LoadVector*FirstFaulting APIs #104964
• LoadVectorFirstFaulting JIT: Added SVE GetFfr, SetFfr, LoadVectorFirstFaulting, GatherVectorFirstFaulting #104502
• LoadVectorInt16SignExtendFirstFaulting JIT ARM64-SVE: Add Sve.LoadVector*FirstFaulting APIs #104964
• LoadVectorInt32SignExtendFirstFaulting JIT ARM64-SVE: Add Sve.LoadVector*FirstFaulting APIs #104964
• LoadVectorSByteSignExtendFirstFaulting JIT ARM64-SVE: Add Sve.LoadVector*FirstFaulting APIs #104964
• LoadVectorUInt16ZeroExtendFirstFaulting JIT ARM64-SVE: Add Sve.LoadVector*FirstFaulting APIs #104964
• LoadVectorUInt32ZeroExtendFirstFaulting JIT ARM64-SVE: Add Sve.LoadVector*FirstFaulting APIs #104964
• SetFfr JIT: Added SVE GetFfr, SetFfr, LoadVectorFirstFaulting, GatherVectorFirstFaulting #104502

SVE2 APIs

Full list

Sve2 scatterstores

• Scatter16BitNarrowing
• Scatter16BitWithByteOffsetsNarrowing
• Scatter32BitNarrowing
• Scatter32BitWithByteOffsetsNarrowing
• Scatter8BitNarrowing
• Scatter8BitWithByteOffsetsNarrowing
• ScatterNonTemporal

Sve2 maths

• AbsoluteDifferenceAdd
• AbsoluteDifferenceAddWideningLower
• AbsoluteDifferenceAddWideningUpper
• AbsoluteDifferenceWideningLower
• AbsoluteDifferenceWideningUpper
• AddCarryWideningLower
• AddCarryWideningUpper
• AddHighNarowingLower
• AddHighNarowingUpper
• AddPairwise
• AddPairwiseWidening
• AddSaturate
• AddSaturateWithSignedAddend
• AddSaturateWithUnsignedAddend
• AddWideLower
• AddWideUpper
• AddWideningLower
• AddWideningLowerUpper
• AddWideningUpper
• DotProductComplex
• HalvingAdd
• HalvingSubtract
• HalvingSubtractReversed
• MaxNumberPairwise
• MaxPairwise
• MinNumberPairwise
• MinPairwise
• MultiplyAddBySelectedScalar
• MultiplyAddWideningLower
• MultiplyAddWideningUpper
• MultiplyBySelectedScalar
• MultiplySubtractBySelectedScalar
• MultiplySubtractWideningLower
• MultiplySubtractWideningUpper
• MultiplyWideningLower
• MultiplyWideningUpper
• PolynomialMultiply
• PolynomialMultiplyWideningLower
• PolynomialMultiplyWideningUpper
• RoundingAddHighNarowingLower
• RoundingAddHighNarowingUpper
• RoundingHalvingAdd
• RoundingSubtractHighNarowingLower
• RoundingSubtractHighNarowingUpper
• SaturatingAbs
• SaturatingDoublingMultiplyAddWideningLower
• SaturatingDoublingMultiplyAddWideningLowerUpper
• SaturatingDoublingMultiplyAddWideningUpper
• SaturatingDoublingMultiplyHigh
• SaturatingDoublingMultiplySubtractWideningLower
• SaturatingDoublingMultiplySubtractWideningLowerUpper
• SaturatingDoublingMultiplySubtractWideningUpper
• SaturatingDoublingMultiplyWideningLower
• SaturatingDoublingMultiplyWideningUpper
• SaturatingNegate
• SaturatingRoundingDoublingMultiplyAddHigh
• SaturatingRoundingDoublingMultiplyHigh
• SaturatingRoundingDoublingMultiplySubtractHigh
• SubtractHighNarowingLower
• SubtractHighNarowingUpper
• SubtractSaturate
• SubtractSaturateReversed
• SubtractWideLower
• SubtractWideUpper
• SubtractWideningLower
• SubtractWideningLowerUpper
• SubtractWideningUpper
• SubtractWideningUpperLower
• SubtractWithBorrowWideningLower
• SubtractWithBorrowWideningUpper

Sve2 mask

• CreateWhileGreaterThanMask
• CreateWhileGreaterThanOrEqualMask
• CreateWhileReadAfterWriteMask
• CreateWhileWriteAfterReadMask
• Match
• NoMatch
• SaturatingExtractNarrowingLower
• SaturatingExtractNarrowingUpper
• SaturatingExtractUnsignedNarrowingLower
• SaturatingExtractUnsignedNarrowingUpper

Sve2 gatherloads

• GatherVectorByteZeroExtendNonTemporal
• GatherVectorInt16SignExtendNonTemporal
• GatherVectorInt16WithByteOffsetsSignExtendNonTemporal
• GatherVectorInt32SignExtendNonTemporal
• GatherVectorInt32WithByteOffsetsSignExtendNonTemporal
• GatherVectorNonTemporal
• GatherVectorSByteSignExtendNonTemporal
• GatherVectorUInt16WithByteOffsetsZeroExtendNonTemporal
• GatherVectorUInt16ZeroExtendNonTemporal
• GatherVectorUInt32WithByteOffsetsZeroExtendNonTemporal
• GatherVectorUInt32ZeroExtendNonTemporal

Sve2 fp

• AddRotateComplex
• DownConvertNarrowingUpper
• DownConvertRoundingOdd
• DownConvertRoundingOddUpper
• Log2
• MultiplyAddRotateComplex
• MultiplyAddRotateComplexBySelectedScalar
• ReciprocalEstimate
• ReciprocalSqrtEstimate
• SaturatingComplexAddRotate
• SaturatingRoundingDoublingComplexMultiplyAddHighRotate
• UpConvertWideningUpper

Sve2 counting

• CountMatchingElements
• CountMatchingElementsIn128BitSegments

Sve2 bitwise

• BitwiseClearXor
• BitwiseSelect
• BitwiseSelectLeftInverted
• BitwiseSelectRightInverted
• ShiftArithmeticRounded
• ShiftArithmeticRoundedSaturate
• ShiftArithmeticSaturate
• ShiftLeftAndInsert
• ShiftLeftLogicalSaturate
• ShiftLeftLogicalSaturateUnsigned
• ShiftLeftLogicalWideningEven
• ShiftLeftLogicalWideningOdd
• ShiftLogicalRounded
• ShiftLogicalRoundedSaturate
• ShiftRightAndInsert
• ShiftRightArithmeticAdd
• ShiftRightArithmeticNarrowingSaturateEven
• ShiftRightArithmeticNarrowingSaturateOdd
• ShiftRightArithmeticNarrowingSaturateUnsignedEven
• ShiftRightArithmeticNarrowingSaturateUnsignedOdd
• ShiftRightArithmeticRounded
• ShiftRightArithmeticRoundedAdd
• ShiftRightArithmeticRoundedNarrowingSaturateEven
• ShiftRightArithmeticRoundedNarrowingSaturateOdd
• ShiftRightArithmeticRoundedNarrowingSaturateUnsignedEven
• ShiftRightArithmeticRoundedNarrowingSaturateUnsignedOdd
• ShiftRightLogicalAdd
• ShiftRightLogicalNarrowingEven
• ShiftRightLogicalNarrowingOdd
• ShiftRightLogicalRounded
• ShiftRightLogicalRoundedAdd
• ShiftRightLogicalRoundedNarrowingEven
• ShiftRightLogicalRoundedNarrowingOdd
• ShiftRightLogicalRoundedNarrowingSaturateEven
• ShiftRightLogicalRoundedNarrowingSaturateOdd
• Xor
• XorRotateRight

Sve2 bitmanipulate

• InterleavingXorLowerUpper
• InterleavingXorUpperLower
• MoveWideningLower
• MoveWideningUpper
• VectorTableLookup
• VectorTableLookupExtension

SveBf16

• Bfloat16DotProduct
• Bfloat16MatrixMultiplyAccumulate
• Bfloat16MultiplyAddWideningToSinglePrecisionLower
• Bfloat16MultiplyAddWideningToSinglePrecisionUpper
• ConcatenateEvenInt128FromTwoInputs
• ConcatenateOddInt128FromTwoInputs
• ConditionalExtractAfterLastActiveElement
• ConditionalExtractAfterLastActiveElementAndReplicate
• ConditionalExtractLastActiveElement
• ConditionalExtractLastActiveElementAndReplicate
• ConditionalSelect
• ConvertToBFloat16
• CreateFalseMaskBFloat16
• CreateTrueMaskBFloat16
• CreateWhileReadAfterWriteMask
• CreateWhileWriteAfterReadMask
• DotProductBySelectedScalar
• DownConvertNarrowingUpper
• DuplicateSelectedScalarToVector
• ExtractAfterLastScalar
• ExtractAfterLastVector
• ExtractLastScalar
• ExtractLastVector
• ExtractVector
• GetActiveElementCount
• InsertIntoShiftedVector
• InterleaveEvenInt128FromTwoInputs
• InterleaveInt128FromHighHalvesOfTwoInputs
• InterleaveInt128FromLowHalvesOfTwoInputs
• InterleaveOddInt128FromTwoInputs
• LoadVector
• LoadVector128AndReplicateToVector
• LoadVector256AndReplicateToVector
• LoadVectorFirstFaulting
• LoadVectorNonFaulting
• LoadVectorNonTemporal
• Load2xVector
• Load3xVector
• Load4xVector
• PopCount
• ReverseElement
• Splice
• Store
• StoreNonTemporal
• TransposeEven
• TransposeOdd
• UnzipEven
• UnzipOdd
• VectorTableLookup
• VectorTableLookupExtension
• ZipHigh
• ZipLow

SveF32mm

• MatrixMultiplyAccumulate

SveF64mm

• ConcatenateEvenInt128FromTwoInputs
• ConcatenateOddInt128FromTwoInputs
• InterleaveEvenInt128FromTwoInputs
• InterleaveInt128FromHighHalvesOfTwoInputs
• InterleaveInt128FromLowHalvesOfTwoInputs
• InterleaveOddInt128FromTwoInputs
• LoadVector256AndReplicateToVector
• MatrixMultiplyAccumulate

SveFp16

• Abs
• AbsoluteCompareGreaterThan
• AbsoluteCompareGreaterThanOrEqual
• AbsoluteCompareLessThan
• AbsoluteCompareLessThanOrEqual
• AbsoluteDifference
• Add
• AddAcross
• AddPairwise
• AddRotateComplex
• AddSequentialAcross
• CompareEqual
• CompareGreaterThan
• CompareGreaterThanOrEqual
• CompareLessThan
• CompareLessThanOrEqual
• CompareNotEqualTo
• CompareUnordered
• ConcatenateEvenInt128FromTwoInputs
• ConcatenateOddInt128FromTwoInputs
• ConditionalExtractAfterLastActiveElement
• ConditionalExtractAfterLastActiveElementAndReplicate
• ConditionalExtractLastActiveElement
• ConditionalExtractLastActiveElementAndReplicate
• ConditionalSelect
• ConvertToDouble
• ConvertToHalf
• ConvertToInt16
• ConvertToInt32
• ConvertToInt64
• ConvertToSingle
• ConvertToUInt16
• ConvertToUInt32
• ConvertToUInt64
• CreateFalseMaskHalf
• CreateTrueMaskHalf
• CreateWhileReadAfterWriteMask
• CreateWhileWriteAfterReadMask
• Divide
• DownConvertNarrowingUpper
• DuplicateSelectedScalarToVector
• ExtractAfterLastScalar
• ExtractAfterLastVector
• ExtractLastScalar
• ExtractLastVector
• ExtractVector
• FloatingPointExponentialAccelerator
• FusedMultiplyAdd
• FusedMultiplyAddBySelectedScalar
• FusedMultiplyAddNegated
• FusedMultiplySubtract
• FusedMultiplySubtractBySelectedScalar
• FusedMultiplySubtractNegated
• GetActiveElementCount
• InsertIntoShiftedVector
• InterleaveEvenInt128FromTwoInputs
• InterleaveInt128FromHighHalvesOfTwoInputs
• InterleaveInt128FromLowHalvesOfTwoInputs
• InterleaveOddInt128FromTwoInputs
• LoadVector
• LoadVector128AndReplicateToVector
• LoadVector256AndReplicateToVector
• LoadVectorFirstFaulting
• LoadVectorNonFaulting
• LoadVectorNonTemporal
• LoadVectorx2
• LoadVectorx3
• LoadVectorx4
• Log2
• Max
• MaxAcross
• MaxNumber
• MaxNumberAcross
• MaxNumberPairwise
• MaxPairwise
• Min
• MinAcross
• MinNumber
• MinNumberAcross
• MinNumberPairwise
• MinPairwise
• Multiply
• MultiplyAddRotateComplex
• MultiplyAddRotateComplexBySelectedScalar
• MultiplyAddWideningLower
• MultiplyAddWideningUpper
• MultiplyBySelectedScalar
• MultiplyExtended
• MultiplySubtractWideningLower
• MultiplySubtractWideningUpper
• Negate
• PopCount
• ReciprocalEstimate
• ReciprocalExponent
• ReciprocalSqrtEstimate
• ReciprocalSqrtStep
• ReciprocalStep
• ReverseElement
• RoundAwayFromZero
• RoundToNearest
• RoundToNegativeInfinity
• RoundToPositiveInfinity
• RoundToZero
• Scale
• Splice
• Sqrt
• Store
• StoreNonTemporal
• Subtract
• TransposeEven
• TransposeOdd
• TrigonometricMultiplyAddCoefficient
• TrigonometricSelectCoefficient
• TrigonometricStartingValue
• UnzipEven
• UnzipOdd
• UpConvertWideningUpper
• VectorTableLookup
• VectorTableLookupExtension
• ZipHigh
• ZipLow

SveI8mm

• DotProductSignedUnsigned
• DotProductUnsignedSigned
• MatrixMultiplyAccumulate
• MatrixMultiplyAccumulateUnsignedSigned

Sha3

• BitwiseClearXor
• BitwiseRotateLeftBy1AndXor
• Xor
• XorRotateRight

Sm4

• Sm4EncryptionAndDecryption
• Sm4KeyUpdates

SveAes

• AesInverseMixColumns
• AesMixColumns
• AesSingleRoundDecryption
• AesSingleRoundEncryption
• PolynomialMultiplyWideningLower
• PolynomialMultiplyWideningUpper

SveBitperm

• GatherLowerBitsFromPositionsSelectedByBitmask
• GroupBitsToRightOrLeftAsSelectedByBitmask
• ScatterLowerBitsIntoPositionsSelectedByBitmask

SveSha3

• BitwiseRotateLeftBy1AndXor

SveSm4

• Sm4EncryptionAndDecryption
• Sm4KeyUpdates

Credits to @a74nh for populating the list and also some files in https://github.com/a74nh/runtime/tree/api_github/sve_api that will help to implement them.

Contributes to #93095

[a74nh]

Recommendation for how to implement.
Examples of this can be found in 100134

API

• src/libraries/System.Private.CoreLib/src/System/Runtime/Intrinsics/Arm/Sve.PlatformNotSupported.cs
• src/libraries/System.Private.CoreLib/src/System/Runtime/Intrinsics/Arm/Sve.cs
• src/libraries/System.Runtime.Intrinsics/ref/System.Runtime.Intrinsics.cs

Copy/paste contents from files in https://github.com/a74nh/runtime/tree/api_github/sve_api/out_cs_api/ . There should be no need to edit these changes. Keep alphabetical ordering.

The same files have been given additional annotation and can be found in https://github.com/a74nh/runtime/tree/api_github/sve_api/out_helper_api . These are for development use only and are not for commiting.

HW Intrinsics

• src/coreclr/jit/hwintrinsiclistarm64sve.h

Copy/paste from https://github.com/a74nh/runtime/blob/api_github/sve_api/out_hwintrinsiclistarm64sve.h
For entries with multiple instructions for a single type, this will need fixing via a special code path.
The flags and category columns will probably need manually fixing.
Flags that are not automatically detected:

• HW_Flag_LowMaskedOperation : The predicate in arg1 is 0-7
• HW_Flag_HasRMWSemantics : src1 and dest use the same register.
• HW_Flag_EmbeddedMaskedOperation : APIs that have just have "predicated" version. These APIs are converted into ConditionalSelect(AllTrue, CALL_API(operands...), Zero) to get the effect of "predicate" registers. E.g. Abs, Divide.
• HW_Flag_OptionalEmbeddedMaskedOperation : APIs that have both "predicated" and "unpredicated" version. These APIs can be used stand alone, for which "unpredicated" version of the instruction will be generated. They can also be wrapped in ConditionalSelect in a user code and in which case, "predicated" version of the instruction will be emitted. E.g. Add, Multiply, etc.
• HW_Flag_ExplicitMaskedOperation : These APIs take "mask" explicitly as the first argument. E.g. ConditionalSelect
• HW_Flag_Scalable : All APIs have this flag to identify that they operate on scalable vector length.
• Any other restrictions on the register number.

For any special case where there is no flag, you have options:

1. Add a new flag. Add code in hwintrinsics to use the flag. There is limited space for new flags, so only do this where there are many instructions that would require it.
2. If changes need making in codegen, then mark as HW_Flag_SpecialCodeGen and add a new case to CodeGen::genHWIntrinsic().
3. If changes need making at the import stage then mark as HW_Category_Special and add a new case to Compiler::impSpecialIntrinsic()
4. Mark as both HW_Flag_SpecialCodeGen and HW_Category_Special

Testing

• src/tests/Common/GenerateHWIntrinsicTests/GenerateHWIntrinsicTests_Arm.cs

Copy/paste from https://raw.githubusercontent.com/a74nh/runtime/api_github/sve_api/out_GenerateHWIntrinsicTests_Arm.cs
Rename the template (first column) to a more generic template. We want as few new templates as possible. Existing AdvSimd templates can be copied and then edited to include extra Sve parts.
The ValidateIterResult and NextValueOpN entires will need editing to fit the template.
Use existing entires as a guide.

Linux

Tests can be build using:

rm -fr ./artifacts/tests/coreclr/obj/linux.arm64.Checked/Managed/JIT/HardwareIntrinsics/Arm/Sve/
./src/tests/build.sh checked -test:JIT/HardwareIntrinsics/HardwareIntrinsics_Arm_ro.csproj

Tests can then be run:

./artifacts/tests/coreclr/linux.arm64.Checked/JIT/HardwareIntrinsics/HardwareIntrinsics_Arm_ro/HardwareIntrinsics_Arm_ro.sh

Generated C# files are in artifacts/tests/coreclr/obj/linux.arm64.Checked/Managed/JIT/HardwareIntrinsics/Arm/Sve/Sve_ro/Sve_ro/gen/

There are a lot of tests that will be run. To make life easier run the .dll directly and pass it the name of the test (a substring will do). Eg:

$CORE_ROOT/corerun ./artifacts/tests/coreclr/linux.arm64.Checked/JIT/HardwareIntrinsics/HardwareIntrinsics_Arm_ro/HardwareIntrinsics_Arm_ro.dll Sve_Add_uint
$CORE_ROOT/corerun ./artifacts/tests/coreclr/linux.arm64.Checked/JIT/HardwareIntrinsics/HardwareIntrinsics_Arm_ro/HardwareIntrinsics_Arm_ro.dll Sve

Windows

Tests can be build using:

del /F /S /Q repo\artifacts\tests\coreclr\obj\windows.arm64.Release\Managed\JIT\HardwareIntrinsics\Arm\Sve\
pushd repo\src\tests\
build.cmd Release -test JIT\HardwareIntrinsics\HardwareIntrinsics_Arm_r.csproj /p:TargetArchitecture=arm64
build.cmd Release -test JIT\HardwareIntrinsics\HardwareIntrinsics_Arm_ro.csproj /p:TargetArchitecture=arm64

Tests can then be run:

pushd repo\artifacts\tests\coreclr\windows.arm64.Release\JIT\HardwareIntrinsics\HardwareIntrinsics_Arm_r
HardwareIntrinsics_Arm_r.cmd

Generated C# files are in artifacts\tests\coreclr\obj\windows.arm64.Release\Managed\JIT\HardwareIntrinsics\Arm\Sve\Sve_ro\Sve_ro\gen\

There are a lot of tests that will be run. To make life easier run the .dll directly and pass it the name of the test (a substring will do). Eg:

$CORE_ROOT\corerun .\artifacts\tests\coreclr\windows.arm64.Release\JIT\HardwareIntrinsics\HardwareIntrinsics_Arm_ro\HardwareIntrinsics_Arm_ro.dll Sve_Add_uint
$CORE_ROOT\corerun .\artifacts\tests\coreclr\windows.arm64.Release\JIT\HardwareIntrinsics\HardwareIntrinsics_Arm_ro\HardwareIntrinsics_Arm_ro.dll Sve

Altjit

All the testing works as usual using AltJit* environment variables. Only thing to remember is to set additional environment variable DOTNET_MaxVectorTBitWidth=128 to avoid getting asserts assert(size == info.compCompHnd->getClassSize(typeHnd));

Stress testing

All the tests should be run using all the various stress modes.
https://github.com/a74nh/runtime/blob/api_github/sve_api/stress_tester.py is used to run your test in the various modes. Pass it the full command line for running your test. Eg:

stress_tester.py $CORE_ROOT/corerun ./artifacts/tests/coreclr/linux.arm64.Checked/JIT/HardwareIntrinsics/HardwareIntrinsics_Arm_ro/HardwareIntrinsics_Arm_ro.dll Sve_Add_uint

Writing Tests

• Once the .cs files have been created, you can edit then manually and rebuild. Copy the changes back to the template once the test works. This can save time fiddling with template params.
• Where possible, we want to avoid calling other API calls within a test. This stops dependencies building up in the tests. For bonus points, write your test functions once without additional API calls and once with.
• When an API call uses a mask (either input or return) the type of that mask is a vector<T>, this means you can treat it like a normal vector and itterate through it, set values etc. A mask should only contain the values 0 or 1. Within the jit it will be converted to/from a vector of boolean value so that they can be placed in the SVE predicate registers (p0 to p15).

[a74nh]

For choosing APIs.

• For now, only pick APIs that do not have an embedded mask (ie: Those where the Arm instruction takes in a Predicate register as arg2, but does not expose the mask at the API level. For example most of the Sve Maths methods).
  • Support for embedded masks is ongoing.
  • the helper API files indicate which methods have embedded masks with the label "Embedded arg1 mask predicate". Alternatively, see the flag HW_Flag_EmbeddedMaskedOperation in out_hwintrinsiclistarm64sve.h
• Sve is highest priority, then Sve2, then all of the smaller extensions.
  • I recommend starting with the loads and stores

[a74nh]

As the testing grows it will increasingly become difficult to test just a single API. this is ok during CI, but painful during development and bug fixing.

I recommend someone writes a patch so that a testname can be passed in as an argument so that only that test will run. Eg:
HardwareIntrinsics_Arm_ro.sh Sve.Add.uint

[kunalspathak]

I recommend someone writes a patch so that a testname can be passed in as an argument so that only that test will run. Eg: HardwareIntrinsics_Arm_ro.sh Sve.Add.uint

I agree. I have asked @TIHan to come up with a design for this. @TIHan - any update on this?

[TIHan]

I have not looked at this yet, but can this week.