SHA512ROUND(V1, V4, V3, V0, V2, V24, V28, V16, V17, V15, V12, V13)

	SHA512ROUND(V0, V1, V2, V3, V4, V25, V29, V17, V18, V16, V13, V14)
	SHA512ROUND(V3, V0, V4, V2, V1, V26, V30, V18, V19, V17, V14, V15)
	SHA512ROUND(V2, V3, V1, V4, V0, V27, V31, V19, V12, V18, V15, V16)
	SHA512ROUND(V4, V2, V0, V1, V3, V28, V24, V12, V13, V19, V16, V17)
	SHA512ROUND(V1, V4, V3, V0, V2, V29, V25, V13, V14, V12, V17, V18)

	VADDUWM V9, V13, V9
	VADDUWM V10, V14, V10
	VADDUWM V11, V15, V11

	VXOR V4, V8, V4
	VXOR V5, V9, V5
	VXOR V6, V10, V6
	VXOR V7, V11, V7

	VRLW V4, V28, V4
	VRLW V5, V28, V5
	VRLW V6, V28, V6
	VRLW V7, V28, V7

	VADDUWM V0, V4, V0
	VADDUWM V1, V5, V1
	VADDUWM V2, V6, V2
	VADDUWM V3, V7, V3

	VPERMXOR V12, V0, V20, V12
	VPERMXOR V13, V1, V20, V13

	VZIP2	V26.D2, V24.D2, V6.D2
	VZIP1	V27.D2, V25.D2, V10.D2
	VZIP2	V27.D2, V25.D2, V14.D2
	VLD1.P	64(R2), [V24.B16, V25.B16, V26.B16, V27.B16]
	VZIP1	V30.D2, V28.D2, V3.D2
	VZIP2	V30.D2, V28.D2, V7.D2
	VZIP1	V31.D2, V29.D2, V11.D2
	VZIP2	V31.D2, V29.D2, V15.D2
	VLD1.P	64(R2), [V28.B16, V29.B16, V30.B16, V31.B16]
	VEOR	V0.B16, V16.B16, V16.B16
	VEOR	V1.B16, V17.B16, V17.B16
	VEOR	V2.B16, V18.B16, V18.B16
	VEOR	V3.B16, V19.B16, V19.B16

int foo_gpr0() {
        asm volatile("":::"r30","r29","r28");
}
int foo_gpr1() {
        asm volatile("":::"fr31", "fr30","fr29","fr28","r30","r29","r28");
}
int foo_vr() {
        asm volatile("":::"v31","v30","v29","v28");
}
*/
import "C"

import "fmt"

func main() {
	C.foo_fpr()
	C.foo_gpr0()
	C.foo_gpr1()
	C.foo_vr()
	fmt.Println("success")

	VLD1.P	64(R2), [V16.S4, V17.S4, V18.S4, V19.S4]
	VLD1.P	64(R2), [V20.S4, V21.S4, V22.S4, V23.S4]
	VLD1.P	64(R2), [V24.S4, V25.S4, V26.S4, V27.S4]
	VLD1	(R2), [V28.S4, V29.S4, V30.S4, V31.S4]     //load 64*4bytes K constant(K0-K63)

blockloop:

	VLD1.P	16(R1), [V4.B16]                            // load 16bytes message

	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)       \
	MOVD	$(offset+16*11), rtmp \
	STVX	V31, (rtmp)(R1)

	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
	VS19

#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  \
	VAF    b1, b0, b0  \