chundoong-lab-ta/SamsungDS22/fma-example/fma.s

	.file	"fma.c"
	.text
	.globl	get_time
	.type	get_time, @function
get_time:
.LFB4038:
	.cfi_startproc
	endbr64
	pushq	%rbp
	.cfi_def_cfa_offset 16
	.cfi_offset 6, -16
	movq	%rsp, %rbp
	.cfi_def_cfa_register 6
	subq	$32, %rsp
	movq	%fs:40, %rax
	movq	%rax, -8(%rbp)
	xorl	%eax, %eax
	leaq	-32(%rbp), %rax
	movl	$0, %esi
	movq	%rax, %rdi
	call	gettimeofday@PLT
	movq	-32(%rbp), %rax
	vcvtsi2sdq	%rax, %xmm1, %xmm1
	movq	-24(%rbp), %rax
	vcvtsi2sdq	%rax, %xmm2, %xmm2
	vmovsd	.LC0(%rip), %xmm0
	vmulsd	%xmm0, %xmm2, %xmm0
	vaddsd	%xmm0, %xmm1, %xmm0
	movq	-8(%rbp), %rax
	xorq	%fs:40, %rax
	je	.L3
	call	__stack_chk_fail@PLT
.L3:
	leave
	.cfi_def_cfa 7, 8
	ret
	.cfi_endproc
.LFE4038:
	.size	get_time, .-get_time
	.section	.rodata
.LC1:
	.string	"Result : %f\n"
.LC2:
	.string	"N : %d\n"
.LC3:
	.string	"Elapsed time : %f sec\n"
.LC6:
	.string	"Throughput : %.5f GFLOPS\n\n"
	.text
	.globl	print_result
	.type	print_result, @function
print_result:
.LFB4039:
	.cfi_startproc
	endbr64
	pushq	%rbp
	.cfi_def_cfa_offset 16
	.cfi_offset 6, -16
	movq	%rsp, %rbp
	.cfi_def_cfa_register 6
	subq	$16, %rsp
	vmovss	%xmm0, -4(%rbp)
	vmovsd	%xmm1, -16(%rbp)
	vcvtss2sd	-4(%rbp), %xmm0, %xmm0
	leaq	.LC1(%rip), %rdi
	movl	$1, %eax
	call	printf@PLT
	movl	$131072, %esi
	leaq	.LC2(%rip), %rdi
	movl	$0, %eax
	call	printf@PLT
	movq	-16(%rbp), %rax
	vmovq	%rax, %xmm0
	leaq	.LC3(%rip), %rdi
	movl	$1, %eax
	call	printf@PLT
	vmovsd	.LC4(%rip), %xmm0
	vdivsd	-16(%rbp), %xmm0, %xmm0
	vmovsd	.LC5(%rip), %xmm1
	vdivsd	%xmm1, %xmm0, %xmm0
	leaq	.LC6(%rip), %rdi
	movl	$1, %eax
	call	printf@PLT
	nop
	leave
	.cfi_def_cfa 7, 8
	ret
	.cfi_endproc
.LFE4039:
	.size	print_result, .-print_result
	.globl	naive
	.type	naive, @function
naive:
.LFB4040:
	.cfi_startproc
	endbr64
	pushq	%rbp
	.cfi_def_cfa_offset 16
	.cfi_offset 6, -16
	movq	%rsp, %rbp
	.cfi_def_cfa_register 6
	subq	$48, %rsp
	movq	%rdi, -40(%rbp)
	movq	%rsi, -48(%rbp)
	vxorps	%xmm0, %xmm0, %xmm0
	vmovss	%xmm0, -24(%rbp)
	movl	$0, %eax
	call	get_time
	vmovq	%xmm0, %rax
	movq	%rax, -16(%rbp)
	movl	$0, -20(%rbp)
	jmp	.L6
.L7:
	movl	-20(%rbp), %eax
	leaq	0(,%rax,4), %rdx
	movq	-40(%rbp), %rax
	addq	%rdx, %rax
	vmovss	(%rax), %xmm1
	movl	-20(%rbp), %eax
	leaq	0(,%rax,4), %rdx
	movq	-48(%rbp), %rax
	addq	%rdx, %rax
	vmovss	(%rax), %xmm0
	vmulss	%xmm0, %xmm1, %xmm0
	vmovss	-24(%rbp), %xmm1
	vaddss	%xmm0, %xmm1, %xmm0
	vmovss	%xmm0, -24(%rbp)
	addl	$1, -20(%rbp)
.L6:
	cmpl	$131071, -20(%rbp)
	jbe	.L7
	movl	$0, %eax
	call	get_time
	vmovq	%xmm0, %rax
	movq	%rax, -8(%rbp)
	vmovsd	-8(%rbp), %xmm0
	vsubsd	-16(%rbp), %xmm0, %xmm0
	movl	-24(%rbp), %eax
	vmovapd	%xmm0, %xmm1
	vmovd	%eax, %xmm0
	call	print_result
	nop
	leave
	.cfi_def_cfa 7, 8
	ret
	.cfi_endproc
.LFE4040:
	.size	naive, .-naive
	.globl	unroll
	.type	unroll, @function
unroll:
.LFB4041:
	.cfi_startproc
	endbr64
	pushq	%rbp
	.cfi_def_cfa_offset 16
	.cfi_offset 6, -16
	movq	%rsp, %rbp
	.cfi_def_cfa_register 6
	subq	$80, %rsp
	movq	%rdi, -72(%rbp)
	movq	%rsi, -80(%rbp)
	vxorps	%xmm0, %xmm0, %xmm0
	vmovss	%xmm0, -28(%rbp)
	vmovss	-28(%rbp), %xmm0
	vmovss	%xmm0, -32(%rbp)
	vmovss	-32(%rbp), %xmm0
	vmovss	%xmm0, -36(%rbp)
	vmovss	-36(%rbp), %xmm0
	vmovss	%xmm0, -40(%rbp)
	vmovss	-40(%rbp), %xmm0
	vmovss	%xmm0, -44(%rbp)
	vmovss	-44(%rbp), %xmm0
	vmovss	%xmm0, -48(%rbp)
	vmovss	-48(%rbp), %xmm0
	vmovss	%xmm0, -52(%rbp)
	vmovss	-52(%rbp), %xmm0
	vmovss	%xmm0, -56(%rbp)
	movl	$0, %eax
	call	get_time
	vmovq	%xmm0, %rax
	movq	%rax, -16(%rbp)
	movl	$0, -24(%rbp)
	jmp	.L9
.L10:
	movl	-24(%rbp), %eax
	sall	$3, %eax
	movl	%eax, %eax
	leaq	0(,%rax,4), %rdx
	movq	-72(%rbp), %rax
	addq	%rdx, %rax
	vmovss	(%rax), %xmm1
	movl	-24(%rbp), %eax
	sall	$3, %eax
	movl	%eax, %eax
	leaq	0(,%rax,4), %rdx
	movq	-80(%rbp), %rax
	addq	%rdx, %rax
	vmovss	(%rax), %xmm0
	vmulss	%xmm0, %xmm1, %xmm0
	vmovss	-56(%rbp), %xmm1
	vaddss	%xmm0, %xmm1, %xmm0
	vmovss	%xmm0, -56(%rbp)
	movl	-24(%rbp), %eax
	sall	$3, %eax
	addl	$1, %eax
	movl	%eax, %eax
	leaq	0(,%rax,4), %rdx
	movq	-72(%rbp), %rax
	addq	%rdx, %rax
	vmovss	(%rax), %xmm1
	movl	-24(%rbp), %eax
	sall	$3, %eax
	addl	$1, %eax
	movl	%eax, %eax
	leaq	0(,%rax,4), %rdx
	movq	-80(%rbp), %rax
	addq	%rdx, %rax
	vmovss	(%rax), %xmm0
	vmulss	%xmm0, %xmm1, %xmm0
	vmovss	-52(%rbp), %xmm1
	vaddss	%xmm0, %xmm1, %xmm0
	vmovss	%xmm0, -52(%rbp)
	movl	-24(%rbp), %eax
	sall	$3, %eax
	addl	$2, %eax
	movl	%eax, %eax
	leaq	0(,%rax,4), %rdx
	movq	-72(%rbp), %rax
	addq	%rdx, %rax
	vmovss	(%rax), %xmm1
	movl	-24(%rbp), %eax
	sall	$3, %eax
	addl	$2, %eax
	movl	%eax, %eax
	leaq	0(,%rax,4), %rdx
	movq	-80(%rbp), %rax
	addq	%rdx, %rax
	vmovss	(%rax), %xmm0
	vmulss	%xmm0, %xmm1, %xmm0
	vmovss	-48(%rbp), %xmm1
	vaddss	%xmm0, %xmm1, %xmm0
	vmovss	%xmm0, -48(%rbp)
	movl	-24(%rbp), %eax
	sall	$3, %eax
	addl	$3, %eax
	movl	%eax, %eax
	leaq	0(,%rax,4), %rdx
	movq	-72(%rbp), %rax
	addq	%rdx, %rax
	vmovss	(%rax), %xmm1
	movl	-24(%rbp), %eax
	sall	$3, %eax
	addl	$3, %eax
	movl	%eax, %eax
	leaq	0(,%rax,4), %rdx
	movq	-80(%rbp), %rax
	addq	%rdx, %rax
	vmovss	(%rax), %xmm0
	vmulss	%xmm0, %xmm1, %xmm0
	vmovss	-44(%rbp), %xmm1
	vaddss	%xmm0, %xmm1, %xmm0
	vmovss	%xmm0, -44(%rbp)
	movl	-24(%rbp), %eax
	sall	$3, %eax
	addl	$4, %eax
	movl	%eax, %eax
	leaq	0(,%rax,4), %rdx
	movq	-72(%rbp), %rax
	addq	%rdx, %rax
	vmovss	(%rax), %xmm1
	movl	-24(%rbp), %eax
	sall	$3, %eax
	addl	$4, %eax
	movl	%eax, %eax
	leaq	0(,%rax,4), %rdx
	movq	-80(%rbp), %rax
	addq	%rdx, %rax
	vmovss	(%rax), %xmm0
	vmulss	%xmm0, %xmm1, %xmm0
	vmovss	-40(%rbp), %xmm1
	vaddss	%xmm0, %xmm1, %xmm0
	vmovss	%xmm0, -40(%rbp)
	movl	-24(%rbp), %eax
	sall	$3, %eax
	addl	$5, %eax
	movl	%eax, %eax
	leaq	0(,%rax,4), %rdx
	movq	-72(%rbp), %rax
	addq	%rdx, %rax
	vmovss	(%rax), %xmm1
	movl	-24(%rbp), %eax
	sall	$3, %eax
	addl	$5, %eax
	movl	%eax, %eax
	leaq	0(,%rax,4), %rdx
	movq	-80(%rbp), %rax
	addq	%rdx, %rax
	vmovss	(%rax), %xmm0
	vmulss	%xmm0, %xmm1, %xmm0
	vmovss	-36(%rbp), %xmm1
	vaddss	%xmm0, %xmm1, %xmm0
	vmovss	%xmm0, -36(%rbp)
	movl	-24(%rbp), %eax
	sall	$3, %eax
	addl	$6, %eax
	movl	%eax, %eax
	leaq	0(,%rax,4), %rdx
	movq	-72(%rbp), %rax
	addq	%rdx, %rax
	vmovss	(%rax), %xmm1
	movl	-24(%rbp), %eax
	sall	$3, %eax
	addl	$6, %eax
	movl	%eax, %eax
	leaq	0(,%rax,4), %rdx
	movq	-80(%rbp), %rax
	addq	%rdx, %rax
	vmovss	(%rax), %xmm0
	vmulss	%xmm0, %xmm1, %xmm0
	vmovss	-32(%rbp), %xmm1
	vaddss	%xmm0, %xmm1, %xmm0
	vmovss	%xmm0, -32(%rbp)
	movl	-24(%rbp), %eax
	sall	$3, %eax
	addl	$7, %eax
	movl	%eax, %eax
	leaq	0(,%rax,4), %rdx
	movq	-72(%rbp), %rax
	addq	%rdx, %rax
	vmovss	(%rax), %xmm1
	movl	-24(%rbp), %eax
	sall	$3, %eax
	addl	$7, %eax
	movl	%eax, %eax
	leaq	0(,%rax,4), %rdx
	movq	-80(%rbp), %rax
	addq	%rdx, %rax
	vmovss	(%rax), %xmm0
	vmulss	%xmm0, %xmm1, %xmm0
	vmovss	-28(%rbp), %xmm1
	vaddss	%xmm0, %xmm1, %xmm0
	vmovss	%xmm0, -28(%rbp)
	addl	$1, -24(%rbp)
.L9:
	cmpl	$16383, -24(%rbp)
	jbe	.L10
	vmovss	-56(%rbp), %xmm0
	vaddss	-52(%rbp), %xmm0, %xmm0
	vaddss	-48(%rbp), %xmm0, %xmm0
	vaddss	-44(%rbp), %xmm0, %xmm0
	vaddss	-40(%rbp), %xmm0, %xmm0
	vaddss	-36(%rbp), %xmm0, %xmm0
	vaddss	-32(%rbp), %xmm0, %xmm0
	vmovss	-28(%rbp), %xmm1
	vaddss	%xmm0, %xmm1, %xmm0
	vmovss	%xmm0, -20(%rbp)
	movl	$0, %eax
	call	get_time
	vmovq	%xmm0, %rax
	movq	%rax, -8(%rbp)
	vmovsd	-8(%rbp), %xmm0
	vsubsd	-16(%rbp), %xmm0, %xmm0
	movl	-20(%rbp), %eax
	vmovapd	%xmm0, %xmm1
	vmovd	%eax, %xmm0
	call	print_result
	nop
	leave
	.cfi_def_cfa 7, 8
	ret
	.cfi_endproc
.LFE4041:
	.size	unroll, .-unroll
	.globl	vector
	.type	vector, @function
vector:
.LFB4042:
	.cfi_startproc
	endbr64
	leaq	8(%rsp), %r10
	.cfi_def_cfa 10, 0
	andq	$-32, %rsp
	pushq	-8(%r10)
	pushq	%rbp
	movq	%rsp, %rbp
	.cfi_escape 0x10,0x6,0x2,0x76,0
	pushq	%r10
	.cfi_escape 0xf,0x3,0x76,0x78,0x6
	subq	$328, %rsp
	movq	%rdi, -328(%rbp)
	movq	%rsi, -336(%rbp)
	movq	%fs:40, %rax
	movq	%rax, -24(%rbp)
	xorl	%eax, %eax
	vxorps	%xmm0, %xmm0, %xmm0
	vmovss	%xmm0, -304(%rbp)
	vxorps	%xmm0, %xmm0, %xmm0
	vmovss	%xmm0, -300(%rbp)
	vxorps	%xmm0, %xmm0, %xmm0
	vmovss	%xmm0, -296(%rbp)
	vxorps	%xmm0, %xmm0, %xmm0
	vmovss	%xmm0, -292(%rbp)
	vxorps	%xmm0, %xmm0, %xmm0
	vmovss	%xmm0, -288(%rbp)
	vxorps	%xmm0, %xmm0, %xmm0
	vmovss	%xmm0, -284(%rbp)
	vxorps	%xmm0, %xmm0, %xmm0
	vmovss	%xmm0, -280(%rbp)
	vxorps	%xmm0, %xmm0, %xmm0
	vmovss	%xmm0, -276(%rbp)
	vmovss	-304(%rbp), %xmm1
	vmovss	-300(%rbp), %xmm0
	vunpcklps	%xmm1, %xmm0, %xmm2
	vmovss	-296(%rbp), %xmm1
	vmovss	-292(%rbp), %xmm0
	vunpcklps	%xmm1, %xmm0, %xmm1
	vmovss	-288(%rbp), %xmm3
	vmovss	-284(%rbp), %xmm0
	vunpcklps	%xmm3, %xmm0, %xmm3
	vmovss	-280(%rbp), %xmm4
	vmovss	-276(%rbp), %xmm0
	vunpcklps	%xmm4, %xmm0, %xmm0
	vmovlhps	%xmm3, %xmm0, %xmm0
	vmovlhps	%xmm2, %xmm1, %xmm1
	vinsertf128	$0x1, %xmm1, %ymm0, %ymm0
	vmovaps	%ymm0, -240(%rbp)
	movl	$0, %eax
	call	get_time
	vmovq	%xmm0, %rax
	movq	%rax, -272(%rbp)
	movl	$0, -312(%rbp)
	jmp	.L13
.L17:
	movl	-312(%rbp), %eax
	sall	$3, %eax
	movl	%eax, %eax
	leaq	0(,%rax,4), %rdx
	movq	-328(%rbp), %rax
	addq	%rdx, %rax
	movq	%rax, -248(%rbp)
	movq	-248(%rbp), %rax
	vmovaps	(%rax), %ymm0
	vmovaps	%ymm0, -208(%rbp)
	movl	-312(%rbp), %eax
	sall	$3, %eax
	movl	%eax, %eax
	leaq	0(,%rax,4), %rdx
	movq	-336(%rbp), %rax
	addq	%rdx, %rax
	movq	%rax, -256(%rbp)
	movq	-256(%rbp), %rax
	vmovaps	(%rax), %ymm0
	vmovaps	%ymm0, -176(%rbp)
	vmovaps	-240(%rbp), %ymm0
	vmovaps	-208(%rbp), %ymm1
	vmovaps	%ymm1, -144(%rbp)
	vmovaps	-176(%rbp), %ymm1
	vmovaps	%ymm1, -112(%rbp)
	vmovaps	%ymm0, -80(%rbp)
	vmovaps	-112(%rbp), %ymm1
	vmovaps	-80(%rbp), %ymm0
	vfmadd231ps	-144(%rbp), %ymm1, %ymm0
	nop
	vmovaps	%ymm0, -240(%rbp)
	addl	$1, -312(%rbp)
.L13:
	cmpl	$16383, -312(%rbp)
	jbe	.L17
	vmovss	-240(%rbp), %xmm1
	vmovss	-236(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-232(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-228(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-224(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-220(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-216(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-212(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm0
	vmovss	%xmm0, -308(%rbp)
	movl	$0, %eax
	call	get_time
	vmovq	%xmm0, %rax
	movq	%rax, -264(%rbp)
	vmovsd	-264(%rbp), %xmm0
	vsubsd	-272(%rbp), %xmm0, %xmm0
	movl	-308(%rbp), %eax
	vmovapd	%xmm0, %xmm1
	vmovd	%eax, %xmm0
	call	print_result
	nop
	movq	-24(%rbp), %rax
	xorq	%fs:40, %rax
	je	.L18
	call	__stack_chk_fail@PLT
.L18:
	addq	$328, %rsp
	popq	%r10
	.cfi_def_cfa 10, 0
	popq	%rbp
	leaq	-8(%r10), %rsp
	.cfi_def_cfa 7, 8
	ret
	.cfi_endproc
.LFE4042:
	.size	vector, .-vector
	.globl	unroll_vector
	.type	unroll_vector, @function
unroll_vector:
.LFB4043:
	.cfi_startproc
	endbr64
	leaq	8(%rsp), %r10
	.cfi_def_cfa 10, 0
	andq	$-32, %rsp
	pushq	-8(%r10)
	pushq	%rbp
	movq	%rsp, %rbp
	.cfi_escape 0x10,0x6,0x2,0x76,0
	pushq	%r10
	.cfi_escape 0xf,0x3,0x76,0x78,0x6
	subq	$1864, %rsp
	movq	%rdi, -1848(%rbp)
	movq	%rsi, -1856(%rbp)
	movq	%fs:40, %rax
	movq	%rax, -24(%rbp)
	xorl	%eax, %eax
	vxorps	%xmm0, %xmm0, %xmm0
	vmovss	%xmm0, -1760(%rbp)
	vxorps	%xmm0, %xmm0, %xmm0
	vmovss	%xmm0, -1756(%rbp)
	vxorps	%xmm0, %xmm0, %xmm0
	vmovss	%xmm0, -1752(%rbp)
	vxorps	%xmm0, %xmm0, %xmm0
	vmovss	%xmm0, -1748(%rbp)
	vxorps	%xmm0, %xmm0, %xmm0
	vmovss	%xmm0, -1744(%rbp)
	vxorps	%xmm0, %xmm0, %xmm0
	vmovss	%xmm0, -1740(%rbp)
	vxorps	%xmm0, %xmm0, %xmm0
	vmovss	%xmm0, -1736(%rbp)
	vxorps	%xmm0, %xmm0, %xmm0
	vmovss	%xmm0, -1732(%rbp)
	vmovss	-1760(%rbp), %xmm1
	vmovss	-1756(%rbp), %xmm0
	vunpcklps	%xmm1, %xmm0, %xmm2
	vmovss	-1752(%rbp), %xmm1
	vmovss	-1748(%rbp), %xmm0
	vunpcklps	%xmm1, %xmm0, %xmm1
	vmovss	-1744(%rbp), %xmm3
	vmovss	-1740(%rbp), %xmm0
	vunpcklps	%xmm3, %xmm0, %xmm3
	vmovss	-1736(%rbp), %xmm4
	vmovss	-1732(%rbp), %xmm0
	vunpcklps	%xmm4, %xmm0, %xmm0
	vmovlhps	%xmm3, %xmm0, %xmm0
	vmovlhps	%xmm2, %xmm1, %xmm1
	vinsertf128	$0x1, %xmm1, %ymm0, %ymm0
	vmovaps	%ymm0, -1488(%rbp)
	vmovaps	-1488(%rbp), %ymm0
	vmovaps	%ymm0, -1520(%rbp)
	vmovaps	-1520(%rbp), %ymm0
	vmovaps	%ymm0, -1552(%rbp)
	vmovaps	-1552(%rbp), %ymm0
	vmovaps	%ymm0, -1584(%rbp)
	vxorps	%xmm0, %xmm0, %xmm0
	vmovss	%xmm0, -1792(%rbp)
	vxorps	%xmm0, %xmm0, %xmm0
	vmovss	%xmm0, -1788(%rbp)
	vxorps	%xmm0, %xmm0, %xmm0
	vmovss	%xmm0, -1784(%rbp)
	vxorps	%xmm0, %xmm0, %xmm0
	vmovss	%xmm0, -1780(%rbp)
	vxorps	%xmm0, %xmm0, %xmm0
	vmovss	%xmm0, -1776(%rbp)
	vxorps	%xmm0, %xmm0, %xmm0
	vmovss	%xmm0, -1772(%rbp)
	vxorps	%xmm0, %xmm0, %xmm0
	vmovss	%xmm0, -1768(%rbp)
	vxorps	%xmm0, %xmm0, %xmm0
	vmovss	%xmm0, -1764(%rbp)
	vmovss	-1792(%rbp), %xmm1
	vmovss	-1788(%rbp), %xmm0
	vunpcklps	%xmm1, %xmm0, %xmm2
	vmovss	-1784(%rbp), %xmm1
	vmovss	-1780(%rbp), %xmm0
	vunpcklps	%xmm1, %xmm0, %xmm1
	vmovss	-1776(%rbp), %xmm3
	vmovss	-1772(%rbp), %xmm0
	vunpcklps	%xmm3, %xmm0, %xmm3
	vmovss	-1768(%rbp), %xmm4
	vmovss	-1764(%rbp), %xmm0
	vunpcklps	%xmm4, %xmm0, %xmm0
	vmovlhps	%xmm3, %xmm0, %xmm0
	vmovlhps	%xmm2, %xmm1, %xmm1
	vinsertf128	$0x1, %xmm1, %ymm0, %ymm0
	vmovaps	%ymm0, -1360(%rbp)
	vmovaps	-1360(%rbp), %ymm0
	vmovaps	%ymm0, -1392(%rbp)
	vmovaps	-1392(%rbp), %ymm0
	vmovaps	%ymm0, -1424(%rbp)
	vmovaps	-1424(%rbp), %ymm0
	vmovaps	%ymm0, -1456(%rbp)
	movl	$0, %eax
	call	get_time
	vmovq	%xmm0, %rax
	movq	%rax, -1728(%rbp)
	movl	$0, -1832(%rbp)
	jmp	.L22
.L47:
	movl	-1832(%rbp), %eax
	sall	$6, %eax
	movl	%eax, %eax
	leaq	0(,%rax,4), %rdx
	movq	-1848(%rbp), %rax
	addq	%rdx, %rax
	movq	%rax, -1592(%rbp)
	movq	-1592(%rbp), %rax
	vmovaps	(%rax), %ymm0
	vmovaps	%ymm0, -1328(%rbp)
	movl	-1832(%rbp), %eax
	sall	$6, %eax
	movl	%eax, %eax
	leaq	0(,%rax,4), %rdx
	movq	-1856(%rbp), %rax
	addq	%rdx, %rax
	movq	%rax, -1600(%rbp)
	movq	-1600(%rbp), %rax
	vmovaps	(%rax), %ymm0
	vmovaps	%ymm0, -1296(%rbp)
	movl	-1832(%rbp), %eax
	sall	$6, %eax
	movl	%eax, %eax
	addq	$8, %rax
	leaq	0(,%rax,4), %rdx
	movq	-1848(%rbp), %rax
	addq	%rdx, %rax
	movq	%rax, -1608(%rbp)
	movq	-1608(%rbp), %rax
	vmovaps	(%rax), %ymm0
	vmovaps	%ymm0, -1264(%rbp)
	movl	-1832(%rbp), %eax
	sall	$6, %eax
	movl	%eax, %eax
	addq	$8, %rax
	leaq	0(,%rax,4), %rdx
	movq	-1856(%rbp), %rax
	addq	%rdx, %rax
	movq	%rax, -1616(%rbp)
	movq	-1616(%rbp), %rax
	vmovaps	(%rax), %ymm0
	vmovaps	%ymm0, -1232(%rbp)
	movl	-1832(%rbp), %eax
	sall	$6, %eax
	movl	%eax, %eax
	addq	$16, %rax
	leaq	0(,%rax,4), %rdx
	movq	-1848(%rbp), %rax
	addq	%rdx, %rax
	movq	%rax, -1624(%rbp)
	movq	-1624(%rbp), %rax
	vmovaps	(%rax), %ymm0
	vmovaps	%ymm0, -1200(%rbp)
	movl	-1832(%rbp), %eax
	sall	$6, %eax
	movl	%eax, %eax
	addq	$16, %rax
	leaq	0(,%rax,4), %rdx
	movq	-1856(%rbp), %rax
	addq	%rdx, %rax
	movq	%rax, -1632(%rbp)
	movq	-1632(%rbp), %rax
	vmovaps	(%rax), %ymm0
	vmovaps	%ymm0, -1168(%rbp)
	movl	-1832(%rbp), %eax
	sall	$6, %eax
	movl	%eax, %eax
	addq	$24, %rax
	leaq	0(,%rax,4), %rdx
	movq	-1848(%rbp), %rax
	addq	%rdx, %rax
	movq	%rax, -1640(%rbp)
	movq	-1640(%rbp), %rax
	vmovaps	(%rax), %ymm0
	vmovaps	%ymm0, -1136(%rbp)
	movl	-1832(%rbp), %eax
	sall	$6, %eax
	movl	%eax, %eax
	addq	$24, %rax
	leaq	0(,%rax,4), %rdx
	movq	-1856(%rbp), %rax
	addq	%rdx, %rax
	movq	%rax, -1648(%rbp)
	movq	-1648(%rbp), %rax
	vmovaps	(%rax), %ymm0
	vmovaps	%ymm0, -1104(%rbp)
	movl	-1832(%rbp), %eax
	sall	$6, %eax
	movl	%eax, %eax
	addq	$32, %rax
	leaq	0(,%rax,4), %rdx
	movq	-1848(%rbp), %rax
	addq	%rdx, %rax
	movq	%rax, -1656(%rbp)
	movq	-1656(%rbp), %rax
	vmovaps	(%rax), %ymm0
	vmovaps	%ymm0, -1072(%rbp)
	movl	-1832(%rbp), %eax
	sall	$6, %eax
	movl	%eax, %eax
	addq	$32, %rax
	leaq	0(,%rax,4), %rdx
	movq	-1856(%rbp), %rax
	addq	%rdx, %rax
	movq	%rax, -1664(%rbp)
	movq	-1664(%rbp), %rax
	vmovaps	(%rax), %ymm0
	vmovaps	%ymm0, -1040(%rbp)
	movl	-1832(%rbp), %eax
	sall	$6, %eax
	movl	%eax, %eax
	addq	$40, %rax
	leaq	0(,%rax,4), %rdx
	movq	-1848(%rbp), %rax
	addq	%rdx, %rax
	movq	%rax, -1672(%rbp)
	movq	-1672(%rbp), %rax
	vmovaps	(%rax), %ymm0
	vmovaps	%ymm0, -1008(%rbp)
	movl	-1832(%rbp), %eax
	sall	$6, %eax
	movl	%eax, %eax
	addq	$40, %rax
	leaq	0(,%rax,4), %rdx
	movq	-1856(%rbp), %rax
	addq	%rdx, %rax
	movq	%rax, -1680(%rbp)
	movq	-1680(%rbp), %rax
	vmovaps	(%rax), %ymm0
	vmovaps	%ymm0, -976(%rbp)
	movl	-1832(%rbp), %eax
	sall	$6, %eax
	movl	%eax, %eax
	addq	$48, %rax
	leaq	0(,%rax,4), %rdx
	movq	-1848(%rbp), %rax
	addq	%rdx, %rax
	movq	%rax, -1688(%rbp)
	movq	-1688(%rbp), %rax
	vmovaps	(%rax), %ymm0
	vmovaps	%ymm0, -944(%rbp)
	movl	-1832(%rbp), %eax
	sall	$6, %eax
	movl	%eax, %eax
	addq	$48, %rax
	leaq	0(,%rax,4), %rdx
	movq	-1856(%rbp), %rax
	addq	%rdx, %rax
	movq	%rax, -1696(%rbp)
	movq	-1696(%rbp), %rax
	vmovaps	(%rax), %ymm0
	vmovaps	%ymm0, -912(%rbp)
	movl	-1832(%rbp), %eax
	sall	$6, %eax
	movl	%eax, %eax
	addq	$56, %rax
	leaq	0(,%rax,4), %rdx
	movq	-1848(%rbp), %rax
	addq	%rdx, %rax
	movq	%rax, -1704(%rbp)
	movq	-1704(%rbp), %rax
	vmovaps	(%rax), %ymm0
	vmovaps	%ymm0, -880(%rbp)
	movl	-1832(%rbp), %eax
	sall	$6, %eax
	movl	%eax, %eax
	addq	$56, %rax
	leaq	0(,%rax,4), %rdx
	movq	-1856(%rbp), %rax
	addq	%rdx, %rax
	movq	%rax, -1712(%rbp)
	movq	-1712(%rbp), %rax
	vmovaps	(%rax), %ymm0
	vmovaps	%ymm0, -848(%rbp)
	vmovaps	-1584(%rbp), %ymm0
	vmovaps	-1328(%rbp), %ymm1
	vmovaps	%ymm1, -144(%rbp)
	vmovaps	-1296(%rbp), %ymm1
	vmovaps	%ymm1, -112(%rbp)
	vmovaps	%ymm0, -80(%rbp)
	vmovaps	-112(%rbp), %ymm1
	vmovaps	-80(%rbp), %ymm0
	vfmadd231ps	-144(%rbp), %ymm1, %ymm0
	nop
	vmovaps	%ymm0, -1584(%rbp)
	vmovaps	-1552(%rbp), %ymm0
	vmovaps	-1264(%rbp), %ymm1
	vmovaps	%ymm1, -240(%rbp)
	vmovaps	-1232(%rbp), %ymm1
	vmovaps	%ymm1, -208(%rbp)
	vmovaps	%ymm0, -176(%rbp)
	vmovaps	-208(%rbp), %ymm1
	vmovaps	-176(%rbp), %ymm0
	vfmadd231ps	-240(%rbp), %ymm1, %ymm0
	nop
	vmovaps	%ymm0, -1552(%rbp)
	vmovaps	-1520(%rbp), %ymm0
	vmovaps	-1200(%rbp), %ymm1
	vmovaps	%ymm1, -336(%rbp)
	vmovaps	-1168(%rbp), %ymm1
	vmovaps	%ymm1, -304(%rbp)
	vmovaps	%ymm0, -272(%rbp)
	vmovaps	-304(%rbp), %ymm1
	vmovaps	-272(%rbp), %ymm0
	vfmadd231ps	-336(%rbp), %ymm1, %ymm0
	nop
	vmovaps	%ymm0, -1520(%rbp)
	vmovaps	-1488(%rbp), %ymm0
	vmovaps	-1136(%rbp), %ymm1
	vmovaps	%ymm1, -432(%rbp)
	vmovaps	-1104(%rbp), %ymm1
	vmovaps	%ymm1, -400(%rbp)
	vmovaps	%ymm0, -368(%rbp)
	vmovaps	-400(%rbp), %ymm1
	vmovaps	-368(%rbp), %ymm0
	vfmadd231ps	-432(%rbp), %ymm1, %ymm0
	nop
	vmovaps	%ymm0, -1488(%rbp)
	vmovaps	-1456(%rbp), %ymm0
	vmovaps	-1072(%rbp), %ymm1
	vmovaps	%ymm1, -528(%rbp)
	vmovaps	-1040(%rbp), %ymm1
	vmovaps	%ymm1, -496(%rbp)
	vmovaps	%ymm0, -464(%rbp)
	vmovaps	-496(%rbp), %ymm1
	vmovaps	-464(%rbp), %ymm0
	vfmadd231ps	-528(%rbp), %ymm1, %ymm0
	nop
	vmovaps	%ymm0, -1456(%rbp)
	vmovaps	-1424(%rbp), %ymm0
	vmovaps	-1008(%rbp), %ymm1
	vmovaps	%ymm1, -624(%rbp)
	vmovaps	-976(%rbp), %ymm1
	vmovaps	%ymm1, -592(%rbp)
	vmovaps	%ymm0, -560(%rbp)
	vmovaps	-592(%rbp), %ymm1
	vmovaps	-560(%rbp), %ymm0
	vfmadd231ps	-624(%rbp), %ymm1, %ymm0
	nop
	vmovaps	%ymm0, -1424(%rbp)
	vmovaps	-1392(%rbp), %ymm0
	vmovaps	-944(%rbp), %ymm1
	vmovaps	%ymm1, -720(%rbp)
	vmovaps	-912(%rbp), %ymm1
	vmovaps	%ymm1, -688(%rbp)
	vmovaps	%ymm0, -656(%rbp)
	vmovaps	-688(%rbp), %ymm1
	vmovaps	-656(%rbp), %ymm0
	vfmadd231ps	-720(%rbp), %ymm1, %ymm0
	nop
	vmovaps	%ymm0, -1392(%rbp)
	vmovaps	-1360(%rbp), %ymm0
	vmovaps	-880(%rbp), %ymm1
	vmovaps	%ymm1, -816(%rbp)
	vmovaps	-848(%rbp), %ymm1
	vmovaps	%ymm1, -784(%rbp)
	vmovaps	%ymm0, -752(%rbp)
	vmovaps	-784(%rbp), %ymm1
	vmovaps	-752(%rbp), %ymm0
	vfmadd231ps	-816(%rbp), %ymm1, %ymm0
	nop
	vmovaps	%ymm0, -1360(%rbp)
	addl	$1, -1832(%rbp)
.L22:
	cmpl	$2047, -1832(%rbp)
	jbe	.L47
	vmovss	-1584(%rbp), %xmm1
	vmovss	-1580(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-1576(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-1572(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-1568(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-1564(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-1560(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-1556(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm0
	vmovss	%xmm0, -1828(%rbp)
	vmovss	-1552(%rbp), %xmm1
	vmovss	-1548(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-1544(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-1540(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-1536(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-1532(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-1528(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-1524(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm0
	vmovss	%xmm0, -1824(%rbp)
	vmovss	-1520(%rbp), %xmm1
	vmovss	-1516(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-1512(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-1508(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-1504(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-1500(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-1496(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-1492(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm0
	vmovss	%xmm0, -1820(%rbp)
	vmovss	-1488(%rbp), %xmm1
	vmovss	-1484(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-1480(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-1476(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-1472(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-1468(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-1464(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-1460(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm0
	vmovss	%xmm0, -1816(%rbp)
	vmovss	-1456(%rbp), %xmm1
	vmovss	-1452(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-1448(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-1444(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-1440(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-1436(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-1432(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-1428(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm0
	vmovss	%xmm0, -1812(%rbp)
	vmovss	-1424(%rbp), %xmm1
	vmovss	-1420(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-1416(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-1412(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-1408(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-1404(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-1400(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-1396(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm0
	vmovss	%xmm0, -1808(%rbp)
	vmovss	-1392(%rbp), %xmm1
	vmovss	-1388(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-1384(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-1380(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-1376(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-1372(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-1368(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-1364(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm0
	vmovss	%xmm0, -1804(%rbp)
	vmovss	-1360(%rbp), %xmm1
	vmovss	-1356(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-1352(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-1348(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-1344(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-1340(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-1336(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm1
	vmovss	-1332(%rbp), %xmm0
	vaddss	%xmm0, %xmm1, %xmm0
	vmovss	%xmm0, -1800(%rbp)
	vmovss	-1828(%rbp), %xmm0
	vaddss	-1824(%rbp), %xmm0, %xmm0
	vaddss	-1820(%rbp), %xmm0, %xmm0
	vaddss	-1816(%rbp), %xmm0, %xmm0
	vaddss	-1812(%rbp), %xmm0, %xmm0
	vaddss	-1808(%rbp), %xmm0, %xmm0
	vaddss	-1804(%rbp), %xmm0, %xmm0
	vmovss	-1800(%rbp), %xmm1
	vaddss	%xmm0, %xmm1, %xmm0
	vmovss	%xmm0, -1796(%rbp)
	movl	$0, %eax
	call	get_time
	vmovq	%xmm0, %rax
	movq	%rax, -1720(%rbp)
	vmovsd	-1720(%rbp), %xmm0
	vsubsd	-1728(%rbp), %xmm0, %xmm0
	movl	-1796(%rbp), %eax
	vmovapd	%xmm0, %xmm1
	vmovd	%eax, %xmm0
	call	print_result
	nop
	movq	-24(%rbp), %rax
	xorq	%fs:40, %rax
	je	.L48
	call	__stack_chk_fail@PLT
.L48:
	addq	$1864, %rsp
	popq	%r10
	.cfi_def_cfa 10, 0
	popq	%rbp
	leaq	-8(%r10), %rsp
	.cfi_def_cfa 7, 8
	ret
	.cfi_endproc
.LFE4043:
	.size	unroll_vector, .-unroll_vector
	.section	.rodata
.LC9:
	.string	"========= Naive ========="
.LC10:
	.string	"========= Unroll ========="
	.align 8
.LC11:
	.string	"========= Vector Instruction(FMA) ========="
	.align 8
.LC12:
	.string	"========= Unroll + Vector Instruction(FMA) ========="
	.text
	.globl	main
	.type	main, @function
main:
.LFB4044:
	.cfi_startproc
	endbr64
	pushq	%rbp
	.cfi_def_cfa_offset 16
	.cfi_offset 6, -16
	movq	%rsp, %rbp
	.cfi_def_cfa_register 6
	subq	$64, %rsp
	movq	%fs:40, %rax
	movq	%rax, -8(%rbp)
	xorl	%eax, %eax
	leaq	-32(%rbp), %rax
	movl	$0, %esi
	movq	%rax, %rdi
	call	gettimeofday@PLT
	movq	-32(%rbp), %rax
	movl	%eax, %edi
	call	srand@PLT
	movl	$524288, %esi
	movl	$32, %edi
	call	aligned_alloc@PLT
	movq	%rax, -48(%rbp)
	movl	$524288, %esi
	movl	$32, %edi
	call	aligned_alloc@PLT
	movq	%rax, -40(%rbp)
	movl	$0, -52(%rbp)
	jmp	.L50
.L51:
	call	rand@PLT
	vcvtsi2ssl	%eax, %xmm0, %xmm0
	movl	-52(%rbp), %eax
	leaq	0(,%rax,4), %rdx
	movq	-48(%rbp), %rax
	addq	%rdx, %rax
	vmovss	.LC8(%rip), %xmm1
	vdivss	%xmm1, %xmm0, %xmm0
	vmovss	%xmm0, (%rax)
	call	rand@PLT
	vcvtsi2ssl	%eax, %xmm0, %xmm0
	movl	-52(%rbp), %eax
	leaq	0(,%rax,4), %rdx
	movq	-40(%rbp), %rax
	addq	%rdx, %rax
	vmovss	.LC8(%rip), %xmm1
	vdivss	%xmm1, %xmm0, %xmm0
	vmovss	%xmm0, (%rax)
	addl	$1, -52(%rbp)
.L50:
	cmpl	$131071, -52(%rbp)
	jbe	.L51
	leaq	.LC9(%rip), %rdi
	call	puts@PLT
	movq	-40(%rbp), %rdx
	movq	-48(%rbp), %rax
	movq	%rdx, %rsi
	movq	%rax, %rdi
	call	naive
	leaq	.LC10(%rip), %rdi
	call	puts@PLT
	movq	-40(%rbp), %rdx
	movq	-48(%rbp), %rax
	movq	%rdx, %rsi
	movq	%rax, %rdi
	call	unroll
	leaq	.LC11(%rip), %rdi
	call	puts@PLT
	movq	-40(%rbp), %rdx
	movq	-48(%rbp), %rax
	movq	%rdx, %rsi
	movq	%rax, %rdi
	call	vector
	leaq	.LC12(%rip), %rdi
	call	puts@PLT
	movq	-40(%rbp), %rdx
	movq	-48(%rbp), %rax
	movq	%rdx, %rsi
	movq	%rax, %rdi
	call	unroll_vector
	movl	$0, %eax
	movq	-8(%rbp), %rcx
	xorq	%fs:40, %rcx
	je	.L53
	call	__stack_chk_fail@PLT
.L53:
	leave
	.cfi_def_cfa 7, 8
	ret
	.cfi_endproc
.LFE4044:
	.size	main, .-main
	.section	.rodata
	.align 8
.LC0:
	.long	2696277389
	.long	1051772663
	.align 8
.LC4:
	.long	0
	.long	1091567616
	.align 8
.LC5:
	.long	0
	.long	1104006501
	.align 4
.LC8:
	.long	1325400064
	.ident	"GCC: (Ubuntu 9.4.0-1ubuntu1~20.04.1) 9.4.0"
	.section	.note.GNU-stack,"",@progbits
	.section	.note.gnu.property,"a"
	.align 8
	.long	 1f - 0f
	.long	 4f - 1f
	.long	 5
0:
	.string	 "GNU"
1:
	.align 8
	.long	 0xc0000002
	.long	 3f - 2f
2:
	.long	 0x3
3:
	.align 8
4: