VPDPBUSDS 7(AX)(CX*4), X14, K4, X19                // 62e20d0c519c8807000000
	VPDPBUSDS 7(AX)(CX*1), X14, K4, X19                // 62e20d0c519c0807000000
	VPDPBUSDS X25, X0, K4, X19                         // 62827d0c51d9
	VPDPBUSDS X11, X0, K4, X19                         // 62c27d0c51db
	VPDPBUSDS X17, X0, K4, X19                         // 62a27d0c51d9

	VPMULTISHIFTQB 7(AX)(CX*4), Z2, K7, Z18            // 62e2ed4f83948807000000
	VPMULTISHIFTQB 7(AX)(CX*1), Z2, K7, Z18            // 62e2ed4f83940807000000
	VPMULTISHIFTQB Z7, Z21, K7, Z18                    // 62e2d54783d7
	VPMULTISHIFTQB Z13, Z21, K7, Z18                   // 62c2d54783d5
	VPMULTISHIFTQB 7(AX)(CX*4), Z21, K7, Z18           // 62e2d54783948807000000

	VAESDECLAST X1, X31, X9                            // 62720500dfc9 or 62728500dfc9
	VAESDECLAST X11, X31, X9                           // 62520500dfcb or 62528500dfcb
	VAESDECLAST -7(CX), X31, X9                        // 62720500df89f9ffffff or 62728500df89f9ffffff
	VAESDECLAST 15(DX)(BX*4), X31, X9                  // 62720500df8c9a0f000000 or 62728500df8c9a0f000000

	VPCONFLICTQ 7(AX)(CX*8), K4, Y1                    // 62f2fd2cc48cc807000000
	VPCONFLICTQ Z27, K7, Z3                            // 6292fd4fc4db
	VPCONFLICTQ Z15, K7, Z3                            // 62d2fd4fc4df
	VPCONFLICTQ 7(AX)(CX*4), K7, Z3                    // 62f2fd4fc49c8807000000
	VPCONFLICTQ 7(AX)(CX*1), K7, Z3                    // 62f2fd4fc49c0807000000

	VRCP28PD Z2, K2, Z5                                // 62f2fd4acaea
	VRCP28PD -7(CX)(DX*1), K2, Z5                      // 62f2fd4acaac11f9ffffff
	VRCP28PD -15(R14)(R15*4), K2, Z5                   // 6292fd4acaacbef1ffffff
	VRCP28PD Z2, K2, Z23                               // 62e2fd4acafa
	VRCP28PD -7(CX)(DX*1), K2, Z23                     // 62e2fd4acabc11f9ffffff

	{"$~15", "$-16"},
	{"(((8)&0xf)*4)(SP)", "32(SP)"},
	{"(((8-14)&0xf)*4)(SP)", "40(SP)"},
	{"(6+8)(AX)", "14(AX)"},
	{"(8*4)(BP)", "32(BP)"},
	{"(AX)", "(AX)"},
	{"(AX)(CX*8)", "(AX)(CX*8)"},
	{"(BP)(CX*4)", "(BP)(CX*4)"},
	{"(BP)(DX*4)", "(BP)(DX*4)"},
	{"(BP)(R8*4)", "(BP)(R8*4)"},
	{"(BX)", "(BX)"},
	{"(DI)", "(DI)"},
	{"(DI)(BX*1)", "(DI)(BX*1)"},
	{"(DX)", "(DX)"},
	{"(R9)", "(R9)"},

	VPMADD52LUQ -7(CX)(DX*8), Y9, K1, Y2               // 62f2b529b494d1f9ffffff
	VPMADD52LUQ Y3, Y1, K1, Y2                         // 62f2f529b4d3
	VPMADD52LUQ Y2, Y1, K1, Y2                         // 62f2f529b4d2
	VPMADD52LUQ Y9, Y1, K1, Y2                         // 62d2f529b4d1
	VPMADD52LUQ 17(SP)(BP*1), Y1, K1, Y2               // 62f2f529b4942c11000000

	VGF2P8AFFINEQB $126, -7(CX)(DX*4), Y12, K2, Y0     // 62f39d2ace8491f9ffffff7e
	VGF2P8AFFINEQB $126, Y17, Y1, K2, Y0               // 62b3f52acec17e
	VGF2P8AFFINEQB $126, Y7, Y1, K2, Y0                // 62f3f52acec77e
	VGF2P8AFFINEQB $126, Y9, Y1, K2, Y0                // 62d3f52acec17e
	VGF2P8AFFINEQB $126, 15(R8)(R14*4), Y1, K2, Y0     // 6293f52ace84b00f0000007e

<code>g</code> pointer into.
</p>

<p>
For example, the sequence to load <code>g</code> and <code>m</code>
using <code>CX</code> looks like this:
</p>

<pre>
#include "go_tls.h"
#include "go_asm.h"
...
get_tls(CX)
MOVL	g(CX), AX     // Move g into AX.
MOVL	g_m(AX), BX   // Move g.m into BX.
</pre>

<p>

	VPOPCNTW (CX), K3, X11                             // 6272fd0b5419
	VPOPCNTW 99(R15), K3, X11                          // 6252fd0b549f63000000
	VPOPCNTW X20, K3, X23                              // 62a2fd0b54fc
	VPOPCNTW X5, K3, X23                               // 62e2fd0b54fd
	VPOPCNTW X25, K3, X23                              // 6282fd0b54f9
	VPOPCNTW (CX), K3, X23                             // 62e2fd0b5439