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

Assisted-by: DeepSeek V4.1 Flash
2026-09-20 06:44:51 +02:00
parent 70eb8fb8bd
commit 56376a0e59
9 changed files with 2377 additions and 30 deletions
@@ -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