VREPF $3, H_3, R_3 // [r₂₆[3], r₂₆[3], r₂₆[3], r₂₆[3]]
	VREPF $3, H_4, R_4 // [r₂₆[4], r₂₆[4], r₂₆[4], r₂₆[4]]

	// zero out lane 1 of h
	VLEIG $1, $0, H_0 // [h₂₆[0], 0]
	VLEIG $1, $0, H_1 // [h₂₆[1], 0]
	VLEIG $1, $0, H_2 // [h₂₆[2], 0]
	VLEIG $1, $0, H_3 // [h₂₆[3], 0]
	VLEIG $1, $0, H_4 // [h₂₆[4], 0]

	// calculate 5r (ignore least significant limb)
	VREPIF $5, T_0

	"VLREP",
	"VLREPB",
	"VLREPH",
	"VLREPF",
	"VLREPG",
	"VLC",
	"VLCB",
	"VLCH",
	"VLCF",
	"VLCG",
	"VLEH",
	"VLEF",
	"VLEG",
	"VLEB",
	"VLEIH",
	"VLEIF",
	"VLEIG",
	"VLEIB",
	"VFI",
	"VFIDB",
	"WFIDB",
	"VLGV",
	"VLGVB",
	"VLGVH",
	"VLGVF",
	"VLGVG",
	"VLLEZ",
	"VLLEZB",
	"VLLEZH",
	"VLLEZF",
	"VLLEZG",
	"VLM",
	"VLP",

	ADD     $16, R3
	ADD     $-16, R4

	// Process remaining data chunks
	CMP     R4 ,$16
	BGE     fold_16bytes_loop

final_fold:
	VLEIB   $7, $0x40, V9
	VSRLB   V9, CONST_R4R3, V0
	VLEIG   $0, $1, V0

	VGFMG   V0, V1, V1

	VLEIB   $7, $0x20, V9         // Shift by words
	VSRLB   V9, V1, V2            // Store remaining bits in V2
	VUPLLF  V1, V1                // Split rightmost doubleword

	VGMH	$8, $16, V12            // e7c008101046
	VLEIB	$15, $255, V0           // e70000fff040
	VLEIH	$7, $-32768, V15        // e7f080007041
	VLEIF	$2, $-43, V16           // e700ffd52843
	VLEIG	$1, $32767, V31         // e7f07fff1842
	VSLDB	$3, V1, V16, V18        // e72100030a77
	VERIMB	$2, V31, V1, V2         // e72f10020472
	VSEL	V1, V2, V3, V4          // e7412000308d