yoffy

# clang++-4.0 -I/home/yoffy/src/libiqo/include -I/home/yoffy/src/libiqo/src/../include -Wall -Wextra -Wconversion -Wno-sign-conversion -std=c++98 -fno-exceptions  -Wall -Wextra -Wconversion -Wno-sign-conversion  -Ofast   -march=core2 -msse4.1 -mtune=westmere -S -mllvm --x86-asm-syntax=intel /home/yoffy/src/libiqo/src/IQOLanczosResizerImpl_SSE4_1.cpp

.LBB7_11:                               # =>This Loop Header: Depth=1
                                        #     Child Loop BB7_12 Depth 2
	mov	rax, qword ptr [rsp - 16] # 8-byte Reload
	movdqu	xmm1, xmmword ptr [rax + 4*r15]
	movdqu	xmm2, xmmword ptr [rax + 4*r15 + 16]
	mov	rax, qword ptr [rsp - 8] # 8-byte Reload
	lea	rdi, [rax + 4*r12]
	xorps	xmm0, xmm0

yoffy

; clang++-4.0 -I/home/yoffy/src/libiqo/include -I/home/yoffy/src/libiqo/src/../include -Wall -Wextra -Wconversion -Wno-sign-conversion -std=c++98 -fno-exceptions  -Wall -Wextra -Wconversion -Wno-sign-conversion  -Ofast   -march=core2 -msse4.1 -mtune=westmere -S -mllvm --x86-asm-syntax=intel /home/yoffy/src/libiqo/src/IQOAreaResizerImpl_SSE4_1.
cpp

.LBB5_2:                                # =>This Loop Header: Depth=1
                                        #     Child Loop BB5_4 Depth 2
	test	r14d, r14d
	jle	.LBB5_6
# BB#3:                                 #   in Loop: Header=BB5_2 Depth=1
	movdqu	xmm5, xmmword ptr [r8 + 4*r15]
	mov	rbp, r15

yoffy

// clang++ -c -std=c++11 -Wall -Wextra -Ofast -g -march=native -D NDEBUG
#include <stdint.h>
#include <math.h>
#include <vector>
#include <immintrin.h>

struct image
{
    int width;
    int height;