Skip to content

Commit

Permalink
JIT ARM64-SVE: Add CreateWhileLessThan* (dotnet#100949)
Browse files Browse the repository at this point in the history 
* JIT ARM64-SVE: Add CreateWhileLessThan*

* Set simdBaseJitType to type of input args

* Hardcode opt in codegen

* Fix gtNewSimdConvertMaskToVectorNode types

* Use HW_Flag_BaseTypeFromFirstArg

* Set base type to return type and auxiliary type to input type
  • Loading branch information
@a74nh @matouskozak
a74nh authored and matouskozak committed Apr 30, 2024
1 parent 0b12848 commit 96f726b
Show file tree
Hide file tree
Showing 9 changed files with 810 additions and 2 deletions.
11 changes: 11 additions & 0 deletions src/coreclr/jit/hwintrinsic.cpp
View file
Original file line number Diff line number Diff line change
Expand Up @@ -1539,6 +1539,17 @@ GenTree* Compiler::impHWIntrinsic(NamedIntrinsic intrinsic,
}
break;

case NI_Sve_CreateWhileLessThanMask8Bit:
case NI_Sve_CreateWhileLessThanOrEqualMask8Bit:
case NI_Sve_CreateWhileLessThanMask16Bit:
case NI_Sve_CreateWhileLessThanOrEqualMask16Bit:
case NI_Sve_CreateWhileLessThanMask32Bit:
case NI_Sve_CreateWhileLessThanOrEqualMask32Bit:
case NI_Sve_CreateWhileLessThanMask64Bit:
case NI_Sve_CreateWhileLessThanOrEqualMask64Bit:
retNode->AsHWIntrinsic()->SetAuxiliaryJitType(sigReader.op1JitType);
break;

default:
break;
}
Expand Down
34 changes: 34 additions & 0 deletions src/coreclr/jit/hwintrinsiccodegenarm64.cpp
View file
Original file line number Diff line number Diff line change
Expand Up @@ -1409,6 +1409,40 @@ void CodeGen::genHWIntrinsic(GenTreeHWIntrinsic* node)
GetEmitter()->emitIns_R_PATTERN(ins, emitSize, targetReg, opt, SVE_PATTERN_ALL);
break;

case NI_Sve_CreateWhileLessThanMask8Bit:
case NI_Sve_CreateWhileLessThanMask16Bit:
case NI_Sve_CreateWhileLessThanMask32Bit:
case NI_Sve_CreateWhileLessThanMask64Bit:
{
// Emit size and instruction is based on the scalar operands.
var_types auxType = node->GetAuxiliaryType();
emitSize = emitActualTypeSize(auxType);
if (varTypeIsUnsigned(auxType))
{
ins = INS_sve_whilelo;
}

GetEmitter()->emitIns_R_R_R(ins, emitSize, targetReg, op1Reg, op2Reg, opt);
break;
}

case NI_Sve_CreateWhileLessThanOrEqualMask8Bit:
case NI_Sve_CreateWhileLessThanOrEqualMask16Bit:
case NI_Sve_CreateWhileLessThanOrEqualMask32Bit:
case NI_Sve_CreateWhileLessThanOrEqualMask64Bit:
{
// Emit size and instruction is based on the scalar operands.
var_types auxType = node->GetAuxiliaryType();
emitSize = emitActualTypeSize(auxType);
if (varTypeIsUnsigned(auxType))
{
ins = INS_sve_whilels;
}

GetEmitter()->emitIns_R_R_R(ins, emitSize, targetReg, op1Reg, op2Reg, opt);
break;
}

default:
unreached();
}
Expand Down
10 changes: 8 additions & 2 deletions src/coreclr/jit/hwintrinsiclistarm64sve.h
View file
Original file line number Diff line number Diff line change
Expand Up @@ -30,7 +30,14 @@ HARDWARE_INTRINSIC(Sve, CreateTrueMaskSingle,
HARDWARE_INTRINSIC(Sve, CreateTrueMaskUInt16, -1, 1, false, {INS_invalid, INS_invalid, INS_invalid, INS_sve_ptrue, INS_invalid, INS_invalid, INS_invalid, INS_invalid, INS_invalid, INS_invalid}, HW_Category_EnumPattern, HW_Flag_Scalable|HW_Flag_HasImmediateOperand|HW_Flag_ReturnsPerElementMask)
HARDWARE_INTRINSIC(Sve, CreateTrueMaskUInt32, -1, 1, false, {INS_invalid, INS_invalid, INS_invalid, INS_invalid, INS_invalid, INS_sve_ptrue, INS_invalid, INS_invalid, INS_invalid, INS_invalid}, HW_Category_EnumPattern, HW_Flag_Scalable|HW_Flag_HasImmediateOperand|HW_Flag_ReturnsPerElementMask)
HARDWARE_INTRINSIC(Sve, CreateTrueMaskUInt64, -1, 1, false, {INS_invalid, INS_invalid, INS_invalid, INS_invalid, INS_invalid, INS_invalid, INS_invalid, INS_sve_ptrue, INS_invalid, INS_invalid}, HW_Category_EnumPattern, HW_Flag_Scalable|HW_Flag_HasImmediateOperand|HW_Flag_ReturnsPerElementMask)

HARDWARE_INTRINSIC(Sve, CreateWhileLessThanMask16Bit, -1, 2, false, {INS_invalid, INS_invalid, INS_invalid, INS_sve_whilelt, INS_invalid, INS_invalid, INS_invalid, INS_invalid, INS_invalid, INS_invalid}, HW_Category_SIMD, HW_Flag_Scalable|HW_Flag_SpecialCodeGen|HW_Flag_ReturnsPerElementMask)
HARDWARE_INTRINSIC(Sve, CreateWhileLessThanMask32Bit, -1, 2, false, {INS_invalid, INS_invalid, INS_invalid, INS_invalid, INS_invalid, INS_sve_whilelt, INS_invalid, INS_invalid, INS_invalid, INS_invalid}, HW_Category_SIMD, HW_Flag_Scalable|HW_Flag_SpecialCodeGen|HW_Flag_ReturnsPerElementMask)
HARDWARE_INTRINSIC(Sve, CreateWhileLessThanMask64Bit, -1, 2, false, {INS_invalid, INS_invalid, INS_invalid, INS_invalid, INS_invalid, INS_invalid, INS_invalid, INS_sve_whilelt, INS_invalid, INS_invalid}, HW_Category_SIMD, HW_Flag_Scalable|HW_Flag_SpecialCodeGen|HW_Flag_ReturnsPerElementMask)
HARDWARE_INTRINSIC(Sve, CreateWhileLessThanMask8Bit, -1, 2, false, {INS_invalid, INS_sve_whilelt, INS_invalid, INS_invalid, INS_invalid, INS_invalid, INS_invalid, INS_invalid, INS_invalid, INS_invalid}, HW_Category_SIMD, HW_Flag_Scalable|HW_Flag_SpecialCodeGen|HW_Flag_ReturnsPerElementMask)
HARDWARE_INTRINSIC(Sve, CreateWhileLessThanOrEqualMask16Bit, -1, 2, false, {INS_invalid, INS_invalid, INS_invalid, INS_sve_whilele, INS_invalid, INS_invalid, INS_invalid, INS_invalid, INS_invalid, INS_invalid}, HW_Category_SIMD, HW_Flag_Scalable|HW_Flag_SpecialCodeGen|HW_Flag_ReturnsPerElementMask)
HARDWARE_INTRINSIC(Sve, CreateWhileLessThanOrEqualMask32Bit, -1, 2, false, {INS_invalid, INS_invalid, INS_invalid, INS_invalid, INS_invalid, INS_sve_whilele, INS_invalid, INS_invalid, INS_invalid, INS_invalid}, HW_Category_SIMD, HW_Flag_Scalable|HW_Flag_SpecialCodeGen|HW_Flag_ReturnsPerElementMask)
HARDWARE_INTRINSIC(Sve, CreateWhileLessThanOrEqualMask64Bit, -1, 2, false, {INS_invalid, INS_invalid, INS_invalid, INS_invalid, INS_invalid, INS_invalid, INS_invalid, INS_sve_whilele, INS_invalid, INS_invalid}, HW_Category_SIMD, HW_Flag_Scalable|HW_Flag_SpecialCodeGen|HW_Flag_ReturnsPerElementMask)
HARDWARE_INTRINSIC(Sve, CreateWhileLessThanOrEqualMask8Bit, -1, 2, false, {INS_invalid, INS_sve_whilele, INS_invalid, INS_invalid, INS_invalid, INS_invalid, INS_invalid, INS_invalid, INS_invalid, INS_invalid}, HW_Category_SIMD, HW_Flag_Scalable|HW_Flag_SpecialCodeGen|HW_Flag_ReturnsPerElementMask)
HARDWARE_INTRINSIC(Sve, LoadVector, -1, 2, true, {INS_sve_ld1b, INS_sve_ld1b, INS_sve_ld1h, INS_sve_ld1h, INS_sve_ld1w, INS_sve_ld1w, INS_sve_ld1d, INS_sve_ld1d, INS_sve_ld1w, INS_sve_ld1d}, HW_Category_MemoryLoad, HW_Flag_Scalable|HW_Flag_ExplicitMaskedOperation|HW_Flag_LowMaskedOperation)
HARDWARE_INTRINSIC(Sve, LoadVectorByteZeroExtendToInt16, -1, 2, false, {INS_invalid, INS_invalid, INS_sve_ld1b, INS_invalid, INS_invalid, INS_invalid, INS_invalid, INS_invalid, INS_invalid, INS_invalid}, HW_Category_MemoryLoad, HW_Flag_Scalable|HW_Flag_ExplicitMaskedOperation|HW_Flag_LowMaskedOperation)
HARDWARE_INTRINSIC(Sve, LoadVectorByteZeroExtendToInt32, -1, 2, false, {INS_invalid, INS_invalid, INS_invalid, INS_invalid, INS_sve_ld1b, INS_invalid, INS_invalid, INS_invalid, INS_invalid, INS_invalid}, HW_Category_MemoryLoad, HW_Flag_Scalable|HW_Flag_ExplicitMaskedOperation|HW_Flag_LowMaskedOperation)
Expand Down Expand Up @@ -58,7 +65,6 @@ HARDWARE_INTRINSIC(Sve, LoadVectorUInt32ZeroExtendToInt64,
HARDWARE_INTRINSIC(Sve, LoadVectorUInt32ZeroExtendToUInt64, -1, 2, false, {INS_invalid, INS_invalid, INS_invalid, INS_invalid, INS_invalid, INS_invalid, INS_invalid, INS_sve_ld1w, INS_invalid, INS_invalid}, HW_Category_MemoryLoad, HW_Flag_Scalable|HW_Flag_ExplicitMaskedOperation|HW_Flag_LowMaskedOperation)



// ***************************************************************************************************************************************************************************************************************************************************************************************************************************************************************************************************************************************
// ISA Function name SIMD size NumArg EncodesExtraTypeArg Instructions Category Flags
// {TYP_BYTE, TYP_UBYTE, TYP_SHORT, TYP_USHORT, TYP_INT, TYP_UINT, TYP_LONG, TYP_ULONG, TYP_FLOAT, TYP_DOUBLE}
Expand Down
Loading

0 comments on commit 96f726b

Please sign in to comment.