VPDI $0x4, V11, V11, V11 // flip the doublewords to big-endian order
	VPDI $0x4, V12, V12, V12 // flip the doublewords to big-endian order

	VACCCQ V3, V11, V26, V27
	VACQ   V3, V11, V26, V19
	VACCCQ V4, V12, V27, V28
	VACQ   V4, V12, V27, V20

	VLM 0(R5), V7, V8   // 32-bytes into V1..V8
	VLM 0(R6), V15, V16 // 32-bytes into V9..V16
	ADD $32, R5
	ADD $32, R6

	STVX	V24, (rtmp)(R1)       \
	MOVD	$(offset+16*5), rtmp  \
	STVX	V25, (rtmp)(R1)       \
	MOVD	$(offset+16*6), rtmp  \
	STVX	V26, (rtmp)(R1)       \
	MOVD	$(offset+16*7), rtmp  \
	STVX	V27, (rtmp)(R1)       \
	MOVD	$(offset+16*8), rtmp  \
	STVX	V28, (rtmp)(R1)       \
	MOVD	$(offset+16*9), rtmp  \
	STVX	V29, (rtmp)(R1)       \
	MOVD	$(offset+16*10), rtmp \
	STVX	V30, (rtmp)(R1)       \

	{"V16", "V16"},
	{"V17", "V17"},
	{"V18", "V18"},
	{"V19", "V19"},
	{"V20", "V20"},
	{"V21", "V21"},
	{"V22", "V22"},
	{"V23", "V23"},
	{"V24", "V24"},
	{"V25", "V25"},
	{"V26", "V26"},
	{"V27", "V27"},
	{"V28", "V28"},
	{"V29", "V29"},
	{"V30", "V30"},
	{"V31", "V31"},
	{"F14", "F14"},
	{"F15", "F15"},
	{"F16", "F16"},
	{"F17", "F17"},
	{"F18", "F18"},
	{"F19", "F19"},

	V2
	V3
	V4
	V5
	V6
	V7
	V8
	V9
	V10
	V11
	V12
	V13
	V14
	V15
	V16
	V17
	V18
	V19
	V20
	V21
	V22
	V23
	V24
	V25
	V26
	V27
	V28
	V29
	V30
	V31
	VS0
	VS1
	VS2
	VS3
	VS4
	VS5
	VS6
	VS7
	VS8
	VS9
	VS10
	VS11
	VS12
	VS13
	VS14
	VS15
	VS16
	VS17
	VS18

	VTBL	V15.B8, [V6.B16, V7.B16, V8.B16], V2.B8                                 // c2400f0e
	VTBL	V2.B16, [V27.B16, V28.B16, V29.B16, V30.B16], V18.B16                   // 7263024e
	VTBL	V11.B16, [V13.B16], V27.B16                                             // bb010b4e
	VTBL	V3.B8, [V7.B16, V8.B16], V25.B8                                         // f920030e

#define X1    V17
#define X2    V18
#define X3    V19
#define X4    V20
#define X5    V21
#define X6    V22
#define X7    V23
#define X8    V24
#define X9    V25
#define X10   V26
#define X11   V27
#define X12   V28
#define X13   V29
#define X14   V30
#define X15   V31

#define NUM_ROUNDS 20

#define ROUND4(a0, a1, a2, a3, b0, b1, b2, b3, c0, c1, c2, c3, d0, d1, d2, d3) \
	VAF    a1, a0, a0  \

 */
/*
 * Some of the annotations below were added after we released our separate
 * com.google.guava:listenablefuture:1.0 artifact. (For more on that artifact, see
 * https://github.com/google/guava/releases/tag/v27.0) This means that the copy of ListenableFuture
 * in com.google.guava:guava differs from the "frozen" copy in the listenablefuture artifact. This

 */
/*
 * Some of the annotations below were added after we released our separate
 * com.google.guava:listenablefuture:1.0 artifact. (For more on that artifact, see
 * https://github.com/google/guava/releases/tag/v27.0) This means that the copy of ListenableFuture
 * in com.google.guava:guava differs from the "frozen" copy in the listenablefuture artifact. This

 */
/*
 * Some of the annotations below were added after we released our separate
 * com.google.guava:listenablefuture:1.0 artifact. (For more on that artifact, see
 * https://github.com/google/guava/releases/tag/v27.0) This means that the copy of ListenableFuture
 * in com.google.guava:guava differs from the "frozen" copy in the listenablefuture artifact. This

#undef SEL2
#undef CAR1
#undef CAR2
#undef RED1
#undef RED2
#undef PL
#undef PH

// ---------------------------------------
// p256MulInternal
// V0-V3 V30,V31 - Not Modified
// V4-V15 V27-V29 - Volatile

#define CPOOL   R7

// Parameters
#define X0    V0 // Not modified
#define X1    V1 // Not modified
#define Y0    V2 // Not modified
#define Y1    V3 // Not modified