feat(arm64): encode pairs, atomics, crypto, system and NEON slices

Assisted-by: GLM 5.3 Flash

testdata/verify/atomics_arm64.s

@@ -0,0 +1,72 @@
+// Copyright (c) 2026 Petr Balvín <opensource@petrbalvin.org> (https://petrbalvin.org)
+// SPDX-License-Identifier: BSD-3-Clause
+
+// Differential kernel for the arm64 synchronisation instructions: the
+// acquire/release loads and stores, the exclusive family and the LSE
+// atomics with acquire and release semantics, plus the register-pair
+// loads and stores.  Every function is byte-compared against go tool asm.
+
+#include "textflag.h"
+
+// func acquireRelease()
+TEXT ·acquireRelease(SB), NOSPLIT, $0-0
+	LDAR  (R1), R2
+	LDARB (R3), R4
+	LDARH (R5), R6
+	LDARW (R7), R8
+	STLR  R2, (R1)
+	STLRB R4, (R3)
+	STLRH R6, (R5)
+	STLRW R8, (R7)
+	RET
+
+// func exclusive()
+TEXT ·exclusive(SB), NOSPLIT, $0-0
+	LDAXR  (R1), R2
+	LDAXRB (R3), R4
+	LDAXRW (R5), R6
+	STLXR  R2, (R1), R8
+	STLXRB R4, (R3), R8
+	STLXRW R6, (R5), R8
+	RET
+
+// func lseAcquireRelease()
+TEXT ·lseAcquireRelease(SB), NOSPLIT, $0-0
+	CASALD   R1, (R3), R2
+	CASALW   R4, (R6), R5
+	LDADDALD R1, (R3), R2
+	LDADDALW R4, (R6), R5
+	LDCLRALB R1, (R3), R2
+	LDCLRALW R4, (R6), R5
+	LDCLRALD R1, (R3), R2
+	LDORALB  R1, (R3), R2
+	LDORALW  R4, (R6), R5
+	LDORALD  R1, (R3), R2
+	SWPALB   R1, (R3), R2
+	SWPALW   R4, (R6), R5
+	SWPALD   R1, (R3), R2
+	RET
+
+// func lseBase()
+TEXT ·lseBase(SB), NOSPLIT, $0-0
+	LDADDD R1, (R3), R2
+	LDADDW R4, (R6), R5
+	CASD   R1, (R3), R2
+	CASW   R4, (R6), R5
+	SWPD   R1, (R3), R2
+	SWPW   R4, (R6), R5
+	RET
+
+// func pairs()
+TEXT ·pairs(SB), NOSPLIT, $0-0
+	LDP   (R1), (R2, R3)
+	LDP   8(R4), (R5, R6)
+	LDP   -16(R1), (R2, R3)
+	LDPW  4(R4), (R5, R6)
+	STP   (R2, R3), 24(R7)
+	STP   (R2, R3),-8(R7)
+	STPW  (R1, R2), 4(R0)
+	FLDPD (R8), (F1, F2)
+	FLDPD 8(R8), (F3, F4)
+	FSTPD (F3, F4),-8(R9)
+	RET

testdata/verify/crypto_arm64.s

@@ -0,0 +1,42 @@
+// Copyright (c) 2026 Petr Balvín <opensource@petrbalvin.org> (https://petrbalvin.org)
+// SPDX-License-Identifier: BSD-3-Clause
+
+// Differential kernel for the arm64 cryptographic extension: the AES round
+// instructions and the SHA1, SHA256 and SHA512 families.  Every function is
+// byte-compared against go tool asm.
+
+#include "textflag.h"
+
+// func aesRound()
+TEXT ·aesRound(SB), NOSPLIT, $0-0
+	AESE   V31.B16, V29.B16
+	AESD   V22.B16, V19.B16
+	AESMC  V14.B16, V28.B16
+	AESIMC V12.B16, V27.B16
+	RET
+
+// func sha1Round()
+TEXT ·sha1Round(SB), NOSPLIT, $0-0
+	SHA1C   V8.S4, V8, V2
+	SHA1P   V3.S4, V20, V27
+	SHA1M   V0.S4, V27, V27
+	SHA1H   V17, V25
+	SHA1SU0 V17.S4, V13.S4, V16.S4
+	SHA1SU1 V24.S4, V23.S4
+	RET
+
+// func sha256Round()
+TEXT ·sha256Round(SB), NOSPLIT, $0-0
+	SHA256H   V4.S4, V2, V11
+	SHA256H2  V6.S4, V16, V11
+	SHA256SU0 V0.S4, V16.S4
+	SHA256SU1 V31.S4, V3.S4, V15.S4
+	RET
+
+// func sha512Round()
+TEXT ·sha512Round(SB), NOSPLIT, $0-0
+	SHA512H   V2.D2, V1, V0
+	SHA512H2  V4.D2, V3, V2
+	SHA512SU0 V9.D2, V8.D2
+	SHA512SU1 V7.D2, V6.D2, V5.D2
+	RET

testdata/verify/integer_arm64.s

@@ -0,0 +1,66 @@
+// Copyright (c) 2026 Petr Balvín <opensource@petrbalvin.org> (https://petrbalvin.org)
+// SPDX-License-Identifier: BSD-3-Clause
+
+// Differential kernel for the arm64 integer slice: carry-setting arithmetic,
+// widening multiplies, bit manipulation, conditional compares, the compare
+// and test branches, ADR and the wide-constant moves.  Every function is
+// byte-compared against go tool asm.
+
+#include "textflag.h"
+
+// func carryArith()
+TEXT ·carryArith(SB), NOSPLIT, $0-0
+	ADC  R0, R2, R12
+	ADCS R23, R22, R22
+	ADC  $0, R1
+	SBC  R25, R10, R26
+	SBCS R5, R9, R5
+	SBCS $0, R1
+	RET
+
+// func wideningMul()
+TEXT ·wideningMul(SB), NOSPLIT, $0-0
+	MUL   R4, R3, R0
+	MSUB  R19, R16, R26, R2
+	SMULH R24, R20, R24
+	UMULH R24, R20, R24
+	RET
+
+// func bitManip()
+TEXT ·bitManip(SB), NOSPLIT, $0-0
+	RBIT  R11, R4
+	REV   R1, R2
+	CLZ   R21, R9
+	REVW  R1, R2
+	CLSW  R1, R2
+	UBFX  $33, R17, $25, R5
+	UBFXW $4, R1, $9, R2
+	RET
+
+// func condCompare()
+TEXT ·condCompare(SB), NOSPLIT, $0-0
+	CCMP  LE, R7, $19, $3
+	CCMP  LT, R30, R6, $7
+	CCMN  EQ, R1, R2, $3
+	CCMPW LE, R7, $19, $3
+	RET
+
+// func branchForms()
+TEXT ·branchForms(SB), NOSPLIT, $0-0
+	CBZ   R1, target
+	CBNZ  R7, target
+	CBNZW R2, target
+	TBZ   $4, R7, target
+	TBNZ  $33, R7, target
+	ADR   target, R10
+
+target:
+	RET
+
+// func wideMoves()
+TEXT ·wideMoves(SB), NOSPLIT, $0-0
+	MOVK  $1234, R5
+	MOVK  $305397760, R5
+	MOVKW $1234, R5
+	MOVK  $16771847290880, R21
+	RET

testdata/verify/simd_arm64.s

@@ -0,0 +1,98 @@
+// Copyright (c) 2026 Petr Balvín <opensource@petrbalvin.org> (https://petrbalvin.org)
+// SPDX-License-Identifier: BSD-3-Clause
+
+// Differential kernel for the arm64 NEON slice: the logical and arithmetic
+// three-register operations, permutations, comparisons, shifts, the crypto
+// four-register group, element moves, table lookups and the structure
+// loads and stores.  Every function is byte-compared against go tool asm.
+
+#include "textflag.h"
+
+// func simdLogic()
+TEXT ·simdLogic(SB), NOSPLIT, $0-0
+	VADD  V1.B16, V2.B16, V3.B16
+	VADD  V1.B8, V2.B8, V3.B8
+	VSUB  V1.S4, V2.S4, V3.S4
+	VMUL  V1.H8, V2.H8, V3.H8
+	VAND  V4.B16, V4.B16, V9.B16
+	VORR  V5.B16, V4.B16, V3.B16
+	VEOR  V0.B16, V1.B16, V0.B16
+	VADDP V1.H8, V2.H8, V3.H8
+	VCMEQ V24.S4, V13.S4, V12.S4
+	VCMEQ $0, V2.H4, V3.H4
+	RET
+
+// func simdPerm()
+TEXT ·simdPerm(SB), NOSPLIT, $0-0
+	VZIP1   V16.H8, V3.H8, V19.H8
+	VZIP1   V6.D2, V9.D2, V11.D2
+	VZIP2   V22.D2, V25.D2, V21.D2
+	VREV32  V2.H8, V1.H8
+	VREV64  V2.S4, V3.S4
+	VUADDLV V31.S4, V11
+	VEXT    $4, V2.B8, V1.B8, V3.B8
+	VEXT    $8, V2.B16, V1.B16, V3.B16
+	RET
+
+// func simdShift()
+TEXT ·simdShift(SB), NOSPLIT, $0-0
+	VSHL  $7, V22.D2, V25.D2
+	VSHL  $24, V1.S4, V2.S4
+	VUSHR $6, V22.H8, V23.H8
+	VUSHR $56, V1.D2, V2.D2
+	VSRI  $24, V1.S4, V2.S4
+	VSRI  $56, V1.D2, V2.D2
+	RET
+
+// func simdCrypto4()
+TEXT ·simdCrypto4(SB), NOSPLIT, $0-0
+	VEOR3   V2.B16, V7.B16, V12.B16, V25.B16
+	VBCAX   V1.B16, V2.B16, V26.B16, V31.B16
+	VXAR    $63, V27.D2, V21.D2, V26.D2
+	VRAX1   V26.D2, V29.D2, V30.D2
+	VPMULL  V2.D1, V1.D1, V3.Q1
+	VPMULL  V2.B8, V1.B8, V3.H8
+	VPMULL2 V2.D2, V1.D2, V4.Q1
+	VPMULL2 V2.B16, V1.B16, V4.H8
+	RET
+
+// func simdElement()
+TEXT ·simdElement(SB), NOSPLIT, $0-0
+	VDUP V31.B[15], V18
+	VDUP V19.S[3], V18.S4
+	VDUP V1.D[1], V2.D2
+	VMOV V13.S[0], R20
+	VMOV V11.B[11], V16.B[12]
+	VMOV R20, V21.B[2]
+	VMOV V2.B16, V4.B16
+	RET
+
+// func simdTable()
+TEXT ·simdTable(SB), NOSPLIT, $0-0
+	VTBL V22.B16, [V28.B16], V11.B16
+	VTBL V18.B8, [V17.B16, V18.B16], V22.B8
+	VTBL V31.B8, [V14.B16, V15.B16, V16.B16, V17.B16], V15.B8
+	RET
+
+// func simdLoadStore()
+TEXT ·simdLoadStore(SB), NOSPLIT, $0-0
+	VLD1 (R2), [V21.B16]
+	VLD1 (R24), [V18.D1, V19.D1, V20.D1]
+	VLD1 (R29), [V14.D1, V15.D1, V16.D1, V17.D1]
+	VLD1.P 32(R1), [V2.B16, V3.B16]
+	VLD1.P 64(R4), [V5.B16, V6.B16, V7.B16, V8.B16]
+	VLD1R (R1), [V9.B8]
+	VLD1R (R0), [V0.B16]
+	VLD4R (R0), [V0.B8, V1.B8, V2.B8, V3.B8]
+	VST1 [V2.S4, V3.S4, V4.S4, V5.S4], (R14)
+	VST1 [V14.H4, V15.H4, V16.H4], (R27)
+	VST1.P [V2.B16], (R1)
+	VST1.P [V2.B16, V3.B16], 32(R1)
+	RET
+
+// func simdLiteral()
+TEXT ·simdLiteral(SB), NOSPLIT, $0-0
+	VMOVS $0x80402010, V11
+	VMOVD $0x8040201008040201, V20
+	VMOVQ $0x7040201008040201, $0x8040201008040201, V10
+	RET

testdata/verify/system_arm64.s

@@ -0,0 +1,61 @@
+// Copyright (c) 2026 Petr Balvín <opensource@petrbalvin.org> (https://petrbalvin.org)
+// SPDX-License-Identifier: BSD-3-Clause
+
+// Differential kernel for the arm64 system instructions: barriers,
+// cache maintenance, the system register accesses, supervisor calls,
+// breakpoints and prefetches.  Every function is byte-compared against
+// go tool asm.
+
+#include "textflag.h"
+
+// func barriers()
+TEXT ·barriers(SB), NOSPLIT, $0-0
+	DMB $15
+	DMB $1
+	DSB $15
+	DSB $4
+	ISB $15
+	ISB $1
+	RET
+
+// func cacheOps()
+TEXT ·cacheOps(SB), NOSPLIT, $0-0
+	DC  ZVA, R4
+	DC  IVAC, R1
+	DC  CVAC, R2
+	DC  CVAU, R3
+	DC  CIVAC, R7
+	RET
+
+// func sysRegs()
+TEXT ·sysRegs(SB), NOSPLIT, $0-0
+	MRS DCZID_EL0, R3
+	MRS CNTVCT_EL0, R0
+	MRS CNTPCT_EL0, R1
+	MRS CNTFRQ_EL0, R2
+	MRS MIDR_EL1, R0
+	MRS ID_AA64PFR0_EL1, R0
+	MRS ID_AA64ISAR0_EL1, R0
+	MRS ID_AA64ISAR1_EL1, R0
+	MRS DIT, R0
+	MSR $3, SPSel
+	MSR $9, DAIFSet
+	MSR $6, DAIFClr
+	MSR $1, DIT
+	RET
+
+// func exceptions()
+TEXT ·exceptions(SB), NOSPLIT, $0-0
+	SVC $0
+	SVC $7165
+	BRK
+	BRK $35943
+	RET
+
+// func prefetch()
+TEXT ·prefetch(SB), NOSPLIT, $0-0
+	PRFM (R0), PLDL1KEEP
+	PRFM (R3), PLDL3KEEP
+	PRFM (R4), PSTL1KEEP
+	PRFM (R2), $25
+	RET