feat/refactor(rlp): improve implementations

a.asm

@@ -0,0 +1,218 @@
+.section .text.alloy_rlp::header::Header::decode_bytes,"ax",@progbits
+	.globl	alloy_rlp::header::Header::decode_bytes
+	.p2align	4, 0x90
+	.type	alloy_rlp::header::Header::decode_bytes,@function
+alloy_rlp::header::Header::decode_bytes:
+
+	.cfi_startproc
+	push rbp
+	.cfi_def_cfa_offset 16
+	push r15
+	.cfi_def_cfa_offset 24
+	push r14
+	.cfi_def_cfa_offset 32
+	push r13
+	.cfi_def_cfa_offset 40
+	push r12
+	.cfi_def_cfa_offset 48
+	push rbx
+	.cfi_def_cfa_offset 56
+	push rax
+	.cfi_def_cfa_offset 64
+	.cfi_offset rbx, -56
+	.cfi_offset r12, -48
+	.cfi_offset r13, -40
+	.cfi_offset r14, -32
+	.cfi_offset r15, -24
+	.cfi_offset rbp, -16
+
+	mov r14, qword ptr [rsi + 8]
+
+	mov eax, 2
+
+	mov rbx, rdi
+
+	test r14, r14
+	je .LBB12_20
+
+	mov r15, rsi
+	mov rsi, qword ptr [rsi]
+
+	mov ebp, edx
+
+	movzx r12d, byte ptr [rsi]
+
+	test r12b, r12b
+	js .LBB12_2
+
+.LBB12_17:
+	mov edi, 1
+
+	test bpl, bpl
+	je .LBB12_8
+
+.LBB12_18:
+	movzx eax, bpl
+	xor rax, 7
+	mov qword ptr [rbx], rax
+	jmp .LBB12_21
+
+.LBB12_2:
+	cmp r12b, -72
+	jae .LBB12_3
+
+	inc rsi
+
+	dec r14
+
+	xor r12, 128
+
+	mov qword ptr [r15], rsi
+	mov qword ptr [r15 + 8], r14
+
+	cmp r12b, 1
+	jne .LBB12_14
+
+	test r14, r14
+	je .LBB12_20
+
+	cmp byte ptr [rsi], 0
+	mov eax, 3
+	jns .LBB12_20
+	jmp .LBB12_17
+
+.LBB12_3:
+	inc rsi
+	lea ecx, [r12 + 8]
+	dec r14
+	mov qword ptr [r15], rsi
+	mov qword ptr [r15 + 8], r14
+	cmp cl, -56
+	jae .LBB12_4
+
+	cmp r12b, -8
+
+	mov edx, r12d
+	setae cl
+
+	shl cl, 6
+
+	sub dl, cl
+	add dl, 73
+
+	movzx edx, dl
+
+	sub r14, rdx
+
+	jb .LBB12_20
+
+	lea r13, [rsi + rdx]
+
+	mov qword ptr [rsp], 0
+
+	mov qword ptr [r15], r13
+	mov qword ptr [r15 + 8], r14
+
+	cmp byte ptr [rsi], 0
+	je .LBB12_19
+
+	mov rdi, rsp
+
+	sub rdi, rdx
+	add rdi, 8
+
+	call qword ptr [rip + memcpy@GOTPCREL]
+
+	movbe rdi, qword ptr [rsp]
+
+	mov eax, 4
+
+	cmp rdi, 56
+	jb .LBB12_20
+
+	cmp r12b, -8
+	mov rsi, r13
+	setae cl
+
+	mov eax, 2
+	cmp r14, rdi
+	jae .LBB12_6
+	jmp .LBB12_20
+
+.LBB12_14:
+	xor ecx, ecx
+	mov rdi, r12
+
+	mov eax, 2
+	cmp r14, rdi
+	jae .LBB12_6
+	jmp .LBB12_20
+
+.LBB12_4:
+	add r12b, 64
+
+	mov cl, 1
+	movzx edi, r12b
+
+	mov eax, 2
+
+	cmp r14, rdi
+	jb .LBB12_20
+
+.LBB12_6:
+	test cl, cl
+	setne al
+
+	xor al, bpl
+
+	jne .LBB12_18
+
+	cmp r14, rdi
+	jb .LBB12_22
+
+.LBB12_8:
+	lea rax, [rsi + rdi]
+
+	sub r14, rdi
+
+	mov qword ptr [rbx + 8], rsi
+	mov qword ptr [rbx + 16], rdi
+	mov qword ptr [rbx], 10
+
+	mov qword ptr [r15], rax
+	mov qword ptr [r15 + 8], r14
+	jmp .LBB12_21
+
+.LBB12_19:
+	mov eax, 1
+
+.LBB12_20:
+	mov qword ptr [rbx], rax
+	mov qword ptr [rbx + 8], 0
+
+.LBB12_21:
+	mov rax, rbx
+	add rsp, 8
+	.cfi_def_cfa_offset 56
+	pop rbx
+	.cfi_def_cfa_offset 48
+	pop r12
+	.cfi_def_cfa_offset 40
+	pop r13
+	.cfi_def_cfa_offset 32
+	pop r14
+	.cfi_def_cfa_offset 24
+	pop r15
+	.cfi_def_cfa_offset 16
+	pop rbp
+	.cfi_def_cfa_offset 8
+	ret
+
+.LBB12_22:
+	.cfi_def_cfa_offset 64
+	lea rdx, [rip + .Lanon.46cbeb1407b6e7c335190fff0c774a14.13]
+	mov rsi, r14
+	call qword ptr [rip + core::slice::index::slice_start_index_len_fail@GOTPCREL]
+
+	ud2
+