MOVL 16(SI), DX MOVL 20(SI), R9 MOVL 24(SI), R10 MOVL 28(SI), R11 avx2_loop0: // at each iteration works with one block (512 bit) VMOVDQU (DI), Y0 VMOVDQU 32(DI), Y1 VMOVDQU 64(DI), Y2 VMOVDQU 96(DI), Y3 VMOVDQU flip_mask<>+0(SB), Y13 // Apply Byte Flip Mask: LE -> BE VPSHUFB Y13, Y0, Y0 VPSHUFB Y13, Y1, Y1 VPSHUFB Y13, Y2, Y2 VPSHUFB Y13, Y3, Y3 // Transpose data into high/low parts VPERM2I128 $0x20, Y2, Y0, Y4 VPERM2I128 $0x31, Y2, Y0, Y5 VPERM2I128 $0x20, Y3, Y1, Y6 VPERM2I128 $0x31, Y3, Y1, Y7...