PINSRD	$1, (AX), X0
	PINSRD	$2, foo+4(FP), X0

// Was bug: LOOP is a branch instruction.
	JCS	2(PC)
loop:
	LOOP	loop // LOOP

// Tests for TLS reference.
	MOVL    (TLS), AX
	MOVL    8(TLS), DX

// LTYPE0 nonnon	{ outcode(int($1), &$2); }
	RET

	IEEE = 0xedb88320

	// Castagnoli's polynomial, used in iSCSI.
	// Has better error detection characteristics than IEEE.
	// https://dx.doi.org/10.1109/26.231911
	Castagnoli = 0x82f63b78

	// Koopman's polynomial.
	// Also has better error detection characteristics than IEEE.
	// https://dx.doi.org/10.1109/DSN.2002.1028931
	Koopman = 0xeb31d82e
)

// Table is a 256-word table representing the polynomial for efficient processing.

		CStride:        p.CStride,
		Rect:           r,
	}
}

func (p *YCbCr) Opaque() bool {
	return true
}

func yCbCrSize(r Rectangle, subsampleRatio YCbCrSubsampleRatio) (w, h, cw, ch int) {
	w, h = r.Dx(), r.Dy()
	switch subsampleRatio {
	case YCbCrSubsampleRatio422:
		cw = (r.Max.X+1)/2 - r.Min.X/2
		ch = h
	case YCbCrSubsampleRatio420:
		cw = (r.Max.X+1)/2 - r.Min.X/2
		ch = (r.Max.Y+1)/2 - r.Min.Y/2

// (DRAFT), Algorithm 14.
func parseDK(dx *decryptionKey, dkPKE []byte) error {
	if len(dkPKE) != decryptionKeySize {
		return errors.New("mlkem768: invalid decryption key length")
	}

	for i := range dx.s {
		f, err := polyByteDecode[nttElement](dkPKE[:encodingSize12])
		if err != nil {
			return err
		}
		dx.s[i] = f
		dkPKE = dkPKE[encodingSize12:]
	}

	return nil
}

		}
		return m
	}

	// Common individual register masks
	var (
		ax         = buildReg("AX")
		cx         = buildReg("CX")
		dx         = buildReg("DX")
		bx         = buildReg("BX")
		gp         = buildReg("AX CX DX BX BP SI DI R8 R9 R10 R11 R12 R13 R15")
		g          = buildReg("g")
		fp         = buildReg("X0 X1 X2 X3 X4 X5 X6 X7 X8 X9 X10 X11 X12 X13 X14")
		x15        = buildReg("X15")

	b0, b1 := m0.Bounds(), m1.Bounds()
	if !b0.Size().Eq(b1.Size()) {
		return fmt.Errorf("dimensions differ: %v vs %v", b0, b1)
	}
	dx := b1.Min.X - b0.Min.X
	dy := b1.Min.Y - b0.Min.Y
	for y := b0.Min.Y; y < b0.Max.Y; y++ {
		for x := b0.Min.X; x < b0.Max.X; x++ {
			c0 := m0.At(x, y)
			c1 := m1.At(x+dx, y+dy)
			r0, g0, b0, a0 := c0.RGBA()
			r1, g1, b1, a1 := c1.RGBA()
			if r0 != r1 || g0 != g1 || b0 != b1 || a0 != a1 {

	"AL", // [D_AL]
	"CL",
	"DL",
	"BL",
	"SPB",
	"BPB",
	"SIB",
	"DIB",
	"R8B",
	"R9B",
	"R10B",
	"R11B",
	"R12B",
	"R13B",
	"R14B",
	"R15B",
	"AX", // [D_AX]
	"CX",
	"DX",
	"BX",
	"SP",
	"BP",
	"SI",
	"DI",
	"R8",
	"R9",
	"R10",
	"R11",
	"R12",
	"R13",
	"R14",
	"R15",
	"AH",
	"CH",
	"DH",
	"BH",
	"F0", // [D_F0]
	"F1",
	"F2",

// i.e., d(y_1 + y_2 + ...)/dx_1, d(y_1 + y_2 + ...)/dx_2...
//
// `dx` are used as initial gradients (which represent the symbolic partial
// derivatives of some loss function `L` w.r.t. `y`).
// `dx` must be nullptr or have size `ny`.
// If `dx` is nullptr, the implementation will use dx of `OnesLike` for all
// shapes in `y`.
// The partial derivatives are returned in `dy`. `dy` should be allocated to

		Delay:     make([]int, len(frames)),
		LoopCount: 5,
	}
	for i, f := range frames {
		g, err := readGIF(f)
		if err != nil {
			t.Fatal(f, err)
		}
		m := g.Image[0]
		if m.Bounds().Dx() != width || m.Bounds().Dy() != height {
			t.Fatalf("frame %d had unexpected bounds: got %v, want width/height = %d/%d",
				i, m.Bounds(), width, height)
		}
		g0.Image[i] = m
	}

GLOBL andMask<>(SB), (NOPTR+RODATA), $240

// func gcmAesFinish(productTable *[256]byte, tagMask, T *[16]byte, pLen, dLen uint64)
TEXT ·gcmAesFinish(SB),NOSPLIT,$0
#define pTbl DI
#define tMsk SI
#define tPtr DX
#define plen AX
#define dlen CX

	MOVQ productTable+0(FP), pTbl
	MOVQ tagMask+8(FP), tMsk
	MOVQ T+16(FP), tPtr
	MOVQ pLen+24(FP), plen
	MOVQ dLen+32(FP), dlen

	MOVOU (tPtr), ACC0
	MOVOU (tMsk), T2