Accelerate Vector128<long>::op_Multiply on x64 (#103555)

Co-authored-by: Tanner Gooding <tagoo@outlook.com>

Author: EgorBo

src/coreclr/jit/gentree.cpp

@@ -21492,19 +21492,63 @@ GenTree* Compiler::gtNewSimdBinOpNode(
                 {
                     assert((simdSize == 16) || (simdSize == 32) || (simdSize == 64));
 
-                    if (simdSize == 64)
+                    bool isV512Supported = false;
+                    if (compIsEvexOpportunisticallySupported(isV512Supported, InstructionSet_AVX512DQ_VL))
                     {
-                        assert(compIsaSupportedDebugOnly(InstructionSet_AVX512DQ));
-                        intrinsic = NI_AVX512DQ_MultiplyLow;
-                    }
-                    else if (compOpportunisticallyDependsOn(InstructionSet_AVX10v1))
-                    {
-                        intrinsic = NI_AVX10v1_MultiplyLow;
+                        if (simdSize == 64)
+                        {
+                            assert(isV512Supported);
+                            intrinsic = NI_AVX512DQ_MultiplyLow;
+                        }
+                        else
+                        {
+                            intrinsic = !isV512Supported ? NI_AVX10v1_MultiplyLow : NI_AVX512DQ_VL_MultiplyLow;
+                        }
                     }
                     else
                     {
-                        assert(compIsaSupportedDebugOnly(InstructionSet_AVX512DQ_VL));
-                        intrinsic = NI_AVX512DQ_VL_MultiplyLow;
+                        assert(((simdSize == 16) && compOpportunisticallyDependsOn(InstructionSet_SSE41)) ||
+                               ((simdSize == 32) && compOpportunisticallyDependsOn(InstructionSet_AVX2)));
+
+                        // Make op1 and op2 multi-use:
+                        GenTree* op1Dup = fgMakeMultiUse(&op1);
+                        GenTree* op2Dup = fgMakeMultiUse(&op2);
+
+                        const bool is256 = simdSize == 32;
+
+                        // Vector256<ulong> tmp0 = Avx2.Multiply(left, right);
+                        GenTreeHWIntrinsic* tmp0 =
+                            gtNewSimdHWIntrinsicNode(type, op1, op2, is256 ? NI_AVX2_Multiply : NI_SSE2_Multiply,
+                                                     CORINFO_TYPE_ULONG, simdSize);
+
+                        // Vector256<uint> tmp1 = Avx2.Shuffle(right.AsUInt32(), ZWXY);
+                        GenTree*            shuffleMask = gtNewIconNode(SHUFFLE_ZWXY, TYP_INT);
+                        GenTreeHWIntrinsic* tmp1        = gtNewSimdHWIntrinsicNode(type, op2Dup, shuffleMask,
+                                                                            is256 ? NI_AVX2_Shuffle : NI_SSE2_Shuffle,
+                                                                                   CORINFO_TYPE_UINT, simdSize);
+
+                        // Vector256<uint> tmp2 = Avx2.MultiplyLow(left.AsUInt32(), tmp1);
+                        GenTreeHWIntrinsic* tmp2 =
+                            gtNewSimdHWIntrinsicNode(type, op1Dup, tmp1,
+                                                     is256 ? NI_AVX2_MultiplyLow : NI_SSE41_MultiplyLow,
+                                                     CORINFO_TYPE_UINT, simdSize);
+
+                        // Vector256<int> tmp3 = Avx2.HorizontalAdd(tmp2.AsInt32(), Vector256<int>.Zero);
+                        GenTreeHWIntrinsic* tmp3 =
+                            gtNewSimdHWIntrinsicNode(type, tmp2, gtNewZeroConNode(type),
+                                                     is256 ? NI_AVX2_HorizontalAdd : NI_SSSE3_HorizontalAdd,
+                                                     CORINFO_TYPE_UINT, simdSize);
+
+                        // Vector256<int> tmp4 = Avx2.Shuffle(tmp3, YWXW);
+                        shuffleMask = gtNewIconNode(SHUFFLE_YWXW, TYP_INT);
+                        GenTreeHWIntrinsic* tmp4 =
+                            gtNewSimdHWIntrinsicNode(type, tmp3, shuffleMask, is256 ? NI_AVX2_Shuffle : NI_SSE2_Shuffle,
+                                                     CORINFO_TYPE_UINT, simdSize);
+
+                        // result = tmp0 + tmp4;
+                        op1       = tmp0;
+                        op2       = tmp4;
+                        intrinsic = simdSize == 32 ? NI_AVX2_Add : NI_SSE2_Add;
                     }
 
                     break;

src/coreclr/jit/hwintrinsicxarch.cpp

@@ -2750,17 +2750,25 @@ GenTree* Compiler::impSpecialIntrinsic(NamedIntrinsic        intrinsic,
 
             if (varTypeIsLong(simdBaseType))
             {
-                if (simdSize != 64 && !canUseEvexEncoding())
+                if (TARGET_POINTER_SIZE == 4)
                 {
-                    // TODO-XARCH-CQ: We should support long/ulong multiplication
+                    // TODO-XARCH-CQ: 32bit support
                     break;
                 }
-                // else if simdSize == 64 then above assert would check if baseline isa supported
 
-#if defined(TARGET_X86)
-                // TODO-XARCH-CQ: We need to support 64-bit CreateBroadcast
-                break;
-#endif // TARGET_X86
+                if ((simdSize == 32) && compOpportunisticallyDependsOn(InstructionSet_AVX2))
+                {
+                    // Emulate NI_AVX512DQ_VL_MultiplyLow with AVX2 for SIMD32
+                }
+                else if ((simdSize == 16) && compOpportunisticallyDependsOn(InstructionSet_SSE41))
+                {
+                    // Emulate NI_AVX512DQ_VL_MultiplyLow with SSE41 for SIMD16
+                }
+                else
+                {
+                    // Software fallback
+                    break;
+                }
             }
 
             CORINFO_ARG_LIST_HANDLE arg1     = sig->args;

src/coreclr/jit/simd.h

@@ -1019,6 +1019,7 @@ void BroadcastConstantToSimd(TSimd* result, TBase arg0)
 #define SHUFFLE_XYZW 0x1B // 00 01 10 11
 #define SHUFFLE_YXYX 0x44 // 01 00 01 00
 #define SHUFFLE_YWXZ 0x72 // 01 11 00 10
+#define SHUFFLE_YWXW 0x73 // 01 11 00 11
 #define SHUFFLE_YYZZ 0x5A // 01 01 10 10
 #define SHUFFLE_ZXXX 0x80 // 10 00 00 00
 #define SHUFFLE_ZXXY 0x81 // 10 00 00 01

src/libraries/System.Private.CoreLib/src/System/Runtime/Intrinsics/Vector128_1.cs

@@ -1,4 +1,4 @@
-// Licensed to the .NET Foundation under one or more agreements.
+// Licensed to the .NET Foundation under one or more agreements.
 // The .NET Foundation licenses this file to you under the MIT license.
 
 using System.Diagnostics;