MOVUPS (CX), X0 AESENC X0, X1 AESENC X0, X2 MOVUPS 16(CX), X0 AESENC X0, X1 AESENC X0, X2 ADDQ $0x20, CX enc128: MOVUPS (CX), X0 AESENC X0, X1 AESENC X0, X2 MOVUPS 16(CX), X0 AESENC X0, X1 AESENC X0, X2 MOVUPS 32(CX), X0 AESENC X0, X1 AESENC X0, X2 MOVUPS 48(CX), X0 AESENC X0, X1 AESENC X0, X2 MOVUPS 64(CX), X0 AESENC X0, X1 AESENC X0, X2 MOVUPS 80(CX), X0 AESENC X0, X1 AESENC X0, X2 MOVUPS 96(CX), X0 AESENC X0, X1 AESENC X0, X2 MOVUPS 112(CX), X0 AESENC X0, X1 AESENC X0, X2 MOVUPS 128(CX), X0 AESENC...

	VPCOMPRESSB X13, K1, X28                           // 62127d0963ec
	VPCOMPRESSB X8, K1, X28                            // 62127d0963c4
	VPCOMPRESSB X7, K1, -7(CX)(DX*1)                   // 62f27d09637c11f9
	VPCOMPRESSB X13, K1, -7(CX)(DX*1)                  // 62727d09636c11f9
	VPCOMPRESSB X8, K1, -7(CX)(DX*1)                   // 62727d09634411f9
	VPCOMPRESSB X7, K1, -15(R14)(R15*4)                // 62927d09637cbef1

	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)"},

	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

	CMPL runtime·writeBarrier(SB), $0
	MOVQ (CX)(R15*1), AX // ERROR "when dynamic linking, R15 is clobbered by a global variable access and is used here"
	RET
TEXT ·a19(SB), 0, $0-0
	CMPL runtime·writeBarrier(SB), $0
	MOVQ AX, (R15) // ERROR "when dynamic linking, R15 is clobbered by a global variable access and is used here"
	RET
TEXT ·a20(SB), 0, $0-0
	CMPL runtime·writeBarrier(SB), $0

	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

	SHLL	$4, foo+4(SB)
	SHLL	$4, foo+4(SB):AX // SHLL $4, AX, foo+4(SB)

// LTYPEM spec6	{ outcode(int($1), &$2); }
	MOVL	AX, BX
	MOVL	$4, BX

// LTYPEI spec7	{ outcode(int($1), &$2); }
	IMULL	AX
	IMULL	$4, CX
	IMULL	AX, BX

// LTYPEXC spec9	{ outcode(int($1), &$2); }
	CMPPD	X0, X1, 4
	CMPPD	foo+4(SB), X1, 4

// LTYPEX spec10	{ outcode(int($1), &$2); }
	PINSRD	$1, (AX), X0
	PINSRD	$2, foo+4(FP), X0