Add ASM optimizations (#208)

* Add ASM optimizations

- Add ASM optimization for CN-FAST on INTEL
- Add ASM optimization for CNV2 on AMD Bulldozer
- Alloy is now announced as XAO

* Upgraded default configs

src/crypto/asm/win/cn_fast_mainloop_sandybridge.inc

@@ -0,0 +1,70 @@
+	mov	QWORD PTR [rsp+8], rbx
+	mov	QWORD PTR [rsp+16], rbp
+	mov	QWORD PTR [rsp+24], rsi
+	mov	QWORD PTR [rsp+32], rdi
+	push	r14
+	push	r15
+	mov	rax, QWORD PTR [rcx+48]
+	mov	ebp, 262144
+	xor	rax, QWORD PTR [rcx+16]
+	mov	rdx, QWORD PTR [rcx+56]
+	xor	rdx, QWORD PTR [rcx+24]
+	mov	r8, QWORD PTR [rcx+32]
+	xor	r8, QWORD PTR [rcx]
+	movq	xmm3, rax
+	mov	rax, QWORD PTR [rcx+256]
+	mov	rdi, QWORD PTR [rcx+40]
+	movq	xmm0, rdx
+	xor	rdi, QWORD PTR [rcx+8]
+	mov	rdx, r8
+	mov	r15, QWORD PTR [rcx+264]
+	and	edx, 2097136
+	mov	r14, QWORD PTR [rax+35]
+	xor	r14, QWORD PTR [rcx+192]
+	mov	rsi, QWORD PTR [rcx+224]
+	punpcklqdq xmm3, xmm0
+	movdqu	xmm2, XMMWORD PTR [rdx+rsi]
+
+	ALIGN 64
+cn_fast_mainloop_sandybridge:
+	movq	xmm0, rdi
+	movq	xmm1, r8
+	punpcklqdq xmm1, xmm0
+	aesenc	xmm2, xmm1
+	movq r10, xmm2
+	mov r9d, r10d
+	and r9d, 2097136
+	add r9, rsi
+	movdqa	xmm0, xmm2
+	pxor	xmm0, xmm3
+	movdqa	xmm3, xmm2
+	movdqu	XMMWORD PTR [rdx+rsi], xmm0
+	psrldq	xmm0, 11
+	movq	rax, xmm0
+	movzx	eax, al
+	movzx	eax, BYTE PTR [rax+r15]
+	mov	BYTE PTR [rsi+rdx+11], al
+	mov	rbx, QWORD PTR [r9]
+	mov	r11, QWORD PTR [r9+8]
+	mov	rax, rbx
+	mul	r10
+	add	r8, rdx
+	mov	QWORD PTR [r9], r8
+	add	rdi, rax
+	mov	rax, r14
+	xor	rax, rdi
+	mov	QWORD PTR [r9+8], rax
+	xor	r8, rbx
+	mov	rdx, r8
+	and	edx, 2097136
+	movdqu	xmm2, XMMWORD PTR [rdx+rsi]
+	xor	rdi, r11
+	dec	ebp
+	jne	cnv1_mainloop_sandybridge
+
+	mov	rbx, QWORD PTR [rsp+24]
+	mov	rbp, QWORD PTR [rsp+32]
+	mov	rsi, QWORD PTR [rsp+40]
+	mov	rdi, QWORD PTR [rsp+48]
+	pop	r15
+	pop	r14