; Listing generated by Microsoft (R) Optimizing Compiler Version 19.36.32537.0 

include listing.inc

INCLUDELIB OLDNAMES

PUBLIC	det_mat3
PUBLIC	det_mat3_internal
PUBLIC	transpose3to4
PUBLIC	transpose3to3
PUBLIC	transpose3to2
;	COMDAT pdata
pdata	SEGMENT
$pdata$transpose3to3 DD imagerel $LN4@transpose3
	DD	imagerel $LN4@transpose3+86
	DD	imagerel $unwind$transpose3to3
;	COMDAT xdata
xdata	SEGMENT
$unwind$transpose3to3 DQ 00000681700031701r	; 5.65448e-310
	DD	02204H
; Function compile flags: /Ogtpy
; File D:\NitloadIndustry\研究项目\1-Flagship\TH2020\ProjectFile\源代码\StgShqrpGraphic\mat3.c
;	COMDAT det_mat3
_TEXT	SEGMENT
mat$ = 8
det_mat3 PROC						; COMDAT

; 70   :     return det_mat3_internal(

  00000	0f 10 59 10	 movups	 xmm3, XMMWORD PTR [rcx+16]
  00004	0f 10 51 20	 movups	 xmm2, XMMWORD PTR [rcx+32]

; 43   :     __m128 addc1 = _mm_shuffle_ps(c1, c1, _MM_SHUFFLE(3, 0, 2, 1));

  00008	0f 28 e3	 movaps	 xmm4, xmm3
  0000b	0f c6 e3 c9	 shufps	 xmm4, xmm3, 201		; 000000c9H

; 44   :     __m128 addc2 = _mm_shuffle_ps(c2, c2, _MM_SHUFFLE(3, 1, 0, 2));

  0000f	0f 28 c2	 movaps	 xmm0, xmm2

; 45   : 
; 46   :     //let sub row aligned
; 47   :     __m128 subc1 = _mm_shuffle_ps(c1, c1, _MM_SHUFFLE(3, 1, 0, 2));
; 48   :     __m128 subc2 = _mm_shuffle_ps(c2, c2, _MM_SHUFFLE(3, 0, 2, 1));
; 49   : 
; 50   :     //multple all add row
; 51   :     __m128 cache = _mm_mul_ps(c0,addc1);

  00012	0f 59 21	 mulps	 xmm4, XMMWORD PTR [rcx]
  00015	0f c6 c2 d2	 shufps	 xmm0, xmm2, 210		; 000000d2H
  00019	0f c6 db d2	 shufps	 xmm3, xmm3, 210		; 000000d2H

; 52   :     cache = _mm_mul_ps(cache,addc2);
; 53   : 
; 54   :     //multiple all sub row
; 55   :     __m128 sub = _mm_mul_ps(c0, subc1);

  0001d	0f 59 19	 mulps	 xmm3, XMMWORD PTR [rcx]
  00020	0f 59 e0	 mulps	 xmm4, xmm0
  00023	0f c6 d2 c9	 shufps	 xmm2, xmm2, 201		; 000000c9H

; 56   :     sub = _mm_mul_ps(sub, subc2);

  00027	0f 59 da	 mulps	 xmm3, xmm2

; 57   : 
; 58   :     //main-corner sub sub-corner
; 59   :     cache = _mm_sub_ps(cache,sub);

  0002a	0f 5c e3	 subps	 xmm4, xmm3

; 60   : 
; 61   :     __m128 ret = _mm_hadd_ps(cache,cache);    //element 1 add element 2

  0002d	0f 28 c4	 movaps	 xmm0, xmm4
  00030	f2 0f 7c c4	 haddps	 xmm0, xmm4

; 62   :     ret = _mm_add_ps(ret, cache);    //(e1 add e2) add element 3

  00034	0f 58 c4	 addps	 xmm0, xmm4

; 70   :     return det_mat3_internal(

  00037	0f c6 c0 aa	 shufps	 xmm0, xmm0, 170		; 000000aaH

; 71   :         mat->colum[0],
; 72   :         mat->colum[1],
; 73   :         mat->colum[2]
; 74   :     );
; 75   : }

  0003b	c3		 ret	 0
det_mat3 ENDP
_TEXT	ENDS
END