feat(amd64): encode the GOROOT instruction families

Assisted-by: GLM 5.3 Flash
2026-09-20 06:44:51 +02:00
parent 39d2e80145
commit fc2d92eabd
16 changed files with 1709 additions and 43 deletions
@@ -0,0 +1,57 @@
+// The AES-NI, SHA and carry-less multiply round instructions as GOROOT's
+// crypto kernels spell them.  Every result is folded back so no instruction
+// is dead.
+
+#include "textflag.h"
+
+// func aesround(blk, rk *byte)
+TEXT ·aesround(SB), NOSPLIT, $0-16
+	MOVQ            blk+0(FP), SI
+	MOVQ            rk+8(FP), DI
+	MOVOU           (SI), X0
+	MOVOU           (DI), X1
+	AESENC          X1, X0
+	AESENCLAST      X1, X0
+	AESDEC          X1, X0
+	AESDECLAST      X1, X0
+	AESIMC          X1, X2
+	AESKEYGENASSIST $1, X1, X3
+	MOVOU           X0, (SI)
+	MOVOU           X2, (DI)
+	RET
+
+// func sha1block(p *byte, n int, h *[5]uint32)
+TEXT ·sha1block(SB), NOSPLIT, $0-24
+	MOVQ      p+0(FP), SI
+	MOVQ      h+16(FP), DI
+	MOVOU     (SI), X0
+	MOVOU     16(SI), X1
+	SHA1RNDS4 $0, X1, X0
+	SHA1NEXTE X1, X0
+	SHA1MSG1  X1, X2
+	SHA1MSG2  X1, X2
+	MOVOU     X0, (DI)
+	RET
+
+// func sha256block(p *byte, n int, h *[8]uint32)
+TEXT ·sha256block(SB), NOSPLIT, $0-24
+	MOVQ        p+0(FP), SI
+	MOVQ        h+16(FP), DI
+	MOVOU       (SI), X0
+	MOVOU       16(SI), X1
+	SHA256RNDS2 X0, X1, X0
+	SHA256MSG1  X1, X2
+	SHA256MSG2  X1, X2
+	MOVOU       X0, (DI)
+	RET
+
+// func pclmul(a, b *byte)
+TEXT ·pclmul(SB), NOSPLIT, $0-16
+	MOVQ      a+0(FP), SI
+	MOVQ      b+8(FP), DI
+	MOVOU     (SI), X0
+	MOVOU     (DI), X1
+	PCLMULQDQ $0, X1, X0
+	PCLMULQDQ $17, (DI), X0
+	MOVOU     X0, (SI)
+	RET