feat(amd64): assemble the double-shift and static-SB operand shapes

Assisted-by: GLM 5.3 Flash

testdata/verify/doubleshift_amd64.s

@@ -0,0 +1,33 @@
+// The three-operand SHL/SHR forms, which go tool asm encodes as SHLD/SHRD:
+// immediate and CL (or its CX spelling) counts at the Q and W widths, next
+// to the two-operand CX-count spelling GOROOT's bignum kernels use.  Every
+// result is folded back so no instruction is dead.
+
+#include "textflag.h"
+
+// func dblshift(x, y uint64) uint64
+TEXT ·dblshift(SB), NOSPLIT, $0-24
+	MOVQ x+0(FP), SI
+	MOVQ y+8(FP), DI
+	MOVQ $12, CX
+	SHLQ $13, SI, DI
+	SHRQ $7, DI, SI
+	SHLQ CX, SI, DI
+	SHRQ CX, DI, SI
+	SHLQ CX, SI
+	SHLQ $9, DI
+	SHLW $1, SI, DI
+	SHRW $3, DI, SI
+	XORQ DI, SI
+	MOVQ SI, ret+16(FP)
+	RET
+
+// func dblshift32(a, b uint32) uint32
+TEXT ·dblshift32(SB), NOSPLIT, $0-12
+	MOVL a+0(FP), SI
+	MOVL b+4(FP), DI
+	SHLL $5, SI, DI
+	SHRL $2, DI, SI
+	XORL SI, DI
+	MOVL DI, ret+8(FP)
+	RET

testdata/verify/ssestatic_amd64.s

@@ -0,0 +1,27 @@
+// Legacy SSE octa moves against static (SB) symbols: the load and store
+// shapes GOROOT's AES-CTR, AES-GCM and P-256 kernels spell (MOVOU
+// bswapMask<>+0(SB), X0 and the reverse), including offsets into the symbol
+// and the aligned MOVO pair.  Every result is folded back so no instruction
+// is dead.
+
+#include "textflag.h"
+
+// func ssestatic() uint64
+TEXT ·ssestatic(SB), NOSPLIT, $0-8
+	MOVOU bswapMask<>+0(SB), X0
+	MOVOU bswapMask<>+8(SB), X1
+	MOVO  rodataMask<>+0(SB), X2
+	PXOR  X1, X0
+	PXOR  X2, X0
+	MOVOU X0, sink<>+0(SB)
+	MOVOU sink<>+0(SB), X3
+	PXOR  X3, X0
+	MOVQ  X0, AX
+	MOVQ  AX, ret+0(FP)
+	RET
+
+GLOBL bswapMask<>(SB), RODATA|NOPTR, $16
+
+GLOBL rodataMask<>(SB), RODATA|NOPTR, $16
+
+GLOBL sink<>(SB), NOPTR, $16