CMPBLE R3, $16, b1

	// Load the 2 remaining blocks (17-32 bytes remaining).
	MOVD $-17(R3), R0    // index of final byte to load modulo 16
	VL   (R2), T_0       // load full 16 byte block
	VLL  R0, 16(R2), T_1 // load final (possibly partial) block and pad with zeros to 16 bytes

	// The Poly1305 algorithm requires that a 1 bit be appended to
	// each message block. If the final block is less than 16 bytes

	VGEG	$1, 8(R15)(V30*1), V31  // e7fef0081c12
	VSCEG	$1, V31, 16(R15)(V30*1) // e7fef0101c1a
	VGEF	$0, 2048(R15)(V1*1), V2 // e721f8000013
	VSCEF	$0, V2, 4095(R15)(V1*1) // e721ffff001b
	VLL	R0, (R15), V1           // e710f0000037
	VSTL	R0, V16, (R15)          // e700f000083f
	VGMH	$8, $16, V12            // e7c008101046
	VLEIB	$15, $255, V0           // e70000fff040
	VLEIH	$7, $-32768, V15        // e7f080007041