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 +1,76 @@
+// Carry arithmetic, rotates, unsigned/signed division and bit tests: the
+// scalar families GOROOT's big-number and crypto kernels use.  Every result
+// is folded back so no instruction is dead.
+
+#include "textflag.h"
+
+// func carry(a, b uint64) uint64
+TEXT ·carry(SB), NOSPLIT, $0-24
+	MOVQ a+0(FP), AX
+	MOVQ b+8(FP), BX
+	ADDQ BX, AX
+	ADCQ $0, AX
+	MOVQ BX, CX
+	SBBQ $1, CX
+	ADCL BX, AX
+	ADCB AL, BL
+	ADCW $7, CX
+	MOVQ AX, ret+16(FP)
+	RET
+
+// func borrow(a, b uint64) uint64
+TEXT ·borrow(SB), NOSPLIT, $0-24
+	MOVQ a+0(FP), AX
+	MOVQ b+8(FP), BX
+	SUBQ BX, AX
+	SBBQ $0, AX
+	SBBQ BX, CX
+	MOVQ AX, ret+16(FP)
+	RET
+
+// func rot(x uint64, n uint32) uint64
+TEXT ·rot(SB), NOSPLIT, $0-24
+	MOVQ x+0(FP), AX
+	MOVL n+8(FP), CX
+	ROLQ CL, AX
+	RORQ $7, AX
+	ROLL $1, AX
+	RORL CL, AX
+	RCLQ $1, AX
+	RCRQ CL, AX
+	ROLW $3, AX
+	SALQ $2, AX
+	SALB $1, AX
+	MOVQ AX, ret+8(FP)
+	RET
+
+// func muldiv(a, b uint64) uint64
+TEXT ·muldiv(SB), NOSPLIT, $0-24
+	MOVQ  a+0(FP), AX
+	MOVQ  b+8(FP), BX
+	MULQ  BX
+	MULQ  (BX)
+	MOVL  (BX), CX
+	MULL  CX
+	DIVQ  BX
+	IDIVQ BX
+	MOVL  a+0(FP), AX
+	DIVL  CX
+	IDIVL CX
+	MOVQ  AX, ret+16(FP)
+	RET
+
+// func bitfield(w *uint64) uint64
+TEXT ·bitfield(SB), NOSPLIT, $0-16
+	MOVQ  (DI), AX
+	MOVQ  (DI), CX
+	BTQ   AX, CX
+	BTQ   $3, (DI)
+	BTL   AX, CX
+	BTW   $1, CX
+	BTSQ  $5, AX
+	BTRQ  AX, CX
+	BTCQ  $7, (DI)
+	SETCS AL
+	MOVQ  AX, ret+8(FP)
+	RET