ivlo+32(FP), SI MOVQ ivhi+40(FP), DI MOVOU bswapMask<>+0(SB), X0 MOVQ SI, X1 PINSRQ $0x01, DI, X1 MOVAPS X1, X8 PSHUFB X0, X1 MOVQ SI, R8 ADDQ $0x07, R8 JC ctr8_slow XORQ R8, R8 INCQ R8 PXOR X9, X9 PINSRQ $0x00, R8, X9 PADDQ X9, X8 MOVAPS X8, X2 PADDQ X9, X8 MOVAPS X8, X3 PADDQ X9, X8 MOVAPS X8, X4 PADDQ X9, X8 MOVAPS X8, X5 PADDQ X9, X8 MOVAPS X8, X6 PADDQ X9, X8 MOVAPS X8, X7 PADDQ X9, X8 MOVAPS X8, X8 JMP ctr8_done ctr8_slow: ADDQ $0x01, SI ADCQ $0x00, DI MOVQ SI, X2 PINSRQ $0x01, DI, X2 ADDQ $0x01, SI...

	VMOVQ		V10.HU[2], R6   // 46c9f372
	VMOVQ		V11.WU[2], R7   // 67e9f372
	VMOVQ		V31.VU[1], R8   // e8f7f372
	XVMOVQ		X1.W[2], R7     // 27c8ef76
	XVMOVQ		X6.V[2], R8     // c8e8ef76
	XVMOVQ		X8.WU[2], R7    // 07c9f376
	XVMOVQ		X31.VU[2], R8   // e8ebf376

	// Move general-purpose register to a vector element: VMOVQ  Rn, <Vd>.<T>[index]
	VMOVQ		R4, V2.B[0]     // 8280eb72
	VMOVQ		R4, V3.B[1]     // 8384eb72