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

include listing.inc

INCLUDELIB MSVCRT
INCLUDELIB OLDNAMES

_DATA	SEGMENT
COMM	pack:BYTE:038H
_DATA	ENDS
msvcjmc	SEGMENT
__0998321F_concurrencysal@h DB 01H
__E9680BEC_sal@h DB 01H
__75F3BDA1_vadefs@h DB 01H
__FF647DA5_vcruntime@h DB 01H
__0DFED3C7_stdint@h DB 01H
__018B5678_khrplatform@h DB 01H
__79FC18F0_glad@h DB 01H
__04C75F1C_corecrt@h DB 01H
__0C5B3DCC_stddef@h DB 01H
__986CAB3E_glfw3@h DB 01H
__9BEA891A_mmintrin@h DB 01H
__494656A0_corecrt_malloc@h DB 01H
__E5D9469F_malloc@h DB 01H
__7FB111F1_xmmintrin@h DB 01H
__1AD3983D_emmintrin@h DB 01H
__C572F0B4_pmmintrin@h DB 01H
__75AB8336_tmmintrin@h DB 01H
__5C9096B5_smmintrin@h DB 01H
__39F21F79_nmmintrin@h DB 01H
__EC49E537_wmmintrin@h DB 01H
__27DDA830_zmmintrin@h DB 01H
__10C90AFA_immintrin@h DB 01H
__C508448F_StgSharpGraphic@h DB 01H
__C44F8F6B_corecrt_stdio_config@h DB 01H
__A7F89B2B_corecrt_wstdio@h DB 01H
__B5C48800_stdio@h DB 01H
__6DC84844_mat4@c DB 01H
msvcjmc	ENDS
PUBLIC	add_mat4
PUBLIC	sub_mat4
PUBLIC	mul_const
PUBLIC	mul_4_2
PUBLIC	mul_4_4
PUBLIC	transpose4to2
PUBLIC	transpose4to4
PUBLIC	det_mat4
PUBLIC	deinit_mat4
PUBLIC	transpose4to3
PUBLIC	__JustMyCode_Default
PUBLIC	__xmm@80000000800000008000000080000000
EXTRN	__imp__aligned_free:PROC
EXTRN	__imp__aligned_malloc:PROC
EXTRN	mulps_sum_internal:PROC
EXTRN	det_mat3_internal:PROC
EXTRN	__CheckForDebuggerJustMyCode:PROC
EXTRN	_fltused:DWORD
;	COMDAT pdata
pdata	SEGMENT
$pdata$add_mat4 DD imagerel $LN7
	DD	imagerel $LN7+103
	DD	imagerel $unwind$add_mat4
pdata	ENDS
;	COMDAT pdata
pdata	SEGMENT
$pdata$sub_mat4 DD imagerel $LN7
	DD	imagerel $LN7+103
	DD	imagerel $unwind$sub_mat4
pdata	ENDS
;	COMDAT pdata
pdata	SEGMENT
$pdata$mul_const DD imagerel $LN15
	DD	imagerel $LN15+110
	DD	imagerel $unwind$mul_const
pdata	ENDS
;	COMDAT pdata
pdata	SEGMENT
$pdata$mul_4_2 DD imagerel $LN6
	DD	imagerel $LN6+87
	DD	imagerel $unwind$mul_4_2
pdata	ENDS
;	COMDAT pdata
pdata	SEGMENT
$pdata$2$mul_4_2 DD imagerel $LN6+87
	DD	imagerel $LN6+374
	DD	imagerel $chain$2$mul_4_2
pdata	ENDS
;	COMDAT pdata
pdata	SEGMENT
$pdata$3$mul_4_2 DD imagerel $LN6+374
	DD	imagerel $LN6+399
	DD	imagerel $chain$3$mul_4_2
pdata	ENDS
;	COMDAT pdata
pdata	SEGMENT
$pdata$mul_4_4 DD imagerel $LN7
	DD	imagerel $LN7+87
	DD	imagerel $unwind$mul_4_4
pdata	ENDS
;	COMDAT pdata
pdata	SEGMENT
$pdata$2$mul_4_4 DD imagerel $LN7+87
	DD	imagerel $LN7+631
	DD	imagerel $chain$2$mul_4_4
pdata	ENDS
;	COMDAT pdata
pdata	SEGMENT
$pdata$3$mul_4_4 DD imagerel $LN7+631
	DD	imagerel $LN7+656
	DD	imagerel $chain$3$mul_4_4
pdata	ENDS
;	COMDAT pdata
pdata	SEGMENT
$pdata$transpose4to2 DD imagerel $LN4
	DD	imagerel $LN4+80
	DD	imagerel $unwind$transpose4to2
pdata	ENDS
;	COMDAT pdata
pdata	SEGMENT
$pdata$transpose4to4 DD imagerel $LN4
	DD	imagerel $LN4+113
	DD	imagerel $unwind$transpose4to4
pdata	ENDS
;	COMDAT pdata
pdata	SEGMENT
$pdata$det_mat4 DD imagerel $LN4
	DD	imagerel $LN4+278
	DD	imagerel $unwind$det_mat4
pdata	ENDS
;	COMDAT pdata
pdata	SEGMENT
$pdata$deinit_mat4 DD imagerel $LN4
	DD	imagerel $LN4+36
	DD	imagerel $unwind$deinit_mat4
pdata	ENDS
;	COMDAT pdata
pdata	SEGMENT
$pdata$transpose4to3 DD imagerel $LN4
	DD	imagerel $LN4+112
	DD	imagerel $unwind$transpose4to3
pdata	ENDS
;	COMDAT __xmm@80000000800000008000000080000000
CONST	SEGMENT
__xmm@80000000800000008000000080000000 DB 00H, 00H, 00H, 080H, 00H, 00H, 00H
	DB	080H, 00H, 00H, 00H, 080H, 00H, 00H, 00H, 080H
CONST	ENDS
;	COMDAT xdata
xdata	SEGMENT
$unwind$transpose4to3 DD 061201H
	DD	026812H
	DD	08340aH
	DD	07006520aH
xdata	ENDS
;	COMDAT xdata
xdata	SEGMENT
$unwind$deinit_mat4 DD 020601H
	DD	030023206H
xdata	ENDS
;	COMDAT xdata
xdata	SEGMENT
$unwind$det_mat4 DD 0d2e01H
	DD	0e882eH
	DD	0f7822H
	DD	010681bH
	DD	0257417H
	DD	0243417H
	DD	0220117H
	DD	0500cH
xdata	ENDS
;	COMDAT xdata
xdata	SEGMENT
$unwind$transpose4to4 DD 040a01H
	DD	06340aH
	DD	07006320aH
xdata	ENDS
;	COMDAT xdata
xdata	SEGMENT
$unwind$transpose4to2 DD 040a01H
	DD	06340aH
	DD	07006320aH
xdata	ENDS
;	COMDAT xdata
xdata	SEGMENT
$chain$3$mul_4_4 DD 021H
	DD	imagerel $LN7
	DD	imagerel $LN7+87
	DD	imagerel $unwind$mul_4_4
xdata	ENDS
;	COMDAT xdata
xdata	SEGMENT
$chain$2$mul_4_4 DD 064021H
	DD	0a8840H
	DD	0b7833H
	DD	0c6808H
	DD	imagerel $LN7
	DD	imagerel $LN7+87
	DD	imagerel $unwind$mul_4_4
xdata	ENDS
;	COMDAT xdata
xdata	SEGMENT
$unwind$mul_4_4 DD 091c01H
	DD	01e741cH
	DD	01d641cH
	DD	01c341cH
	DD	01a011cH
	DD	05010H
xdata	ENDS
;	COMDAT xdata
xdata	SEGMENT
$chain$3$mul_4_2 DD 021H
	DD	imagerel $LN6
	DD	imagerel $LN6+87
	DD	imagerel $unwind$mul_4_2
xdata	ENDS
;	COMDAT xdata
xdata	SEGMENT
$chain$2$mul_4_2 DD 064021H
	DD	0a8840H
	DD	0b7833H
	DD	0c6808H
	DD	imagerel $LN6
	DD	imagerel $LN6+87
	DD	imagerel $unwind$mul_4_2
xdata	ENDS
;	COMDAT xdata
xdata	SEGMENT
$unwind$mul_4_2 DD 091c01H
	DD	01e741cH
	DD	01d641cH
	DD	01c341cH
	DD	01a011cH
	DD	05010H
xdata	ENDS
;	COMDAT xdata
xdata	SEGMENT
$unwind$mul_const DD 040b01H
	DD	03680bH
	DD	030027206H
xdata	ENDS
;	COMDAT xdata
xdata	SEGMENT
$unwind$sub_mat4 DD 040a01H
	DD	06340aH
	DD	07006320aH
xdata	ENDS
;	COMDAT xdata
xdata	SEGMENT
$unwind$add_mat4 DD 040a01H
	DD	06340aH
	DD	07006320aH
xdata	ENDS
; Function compile flags: /Odt
;	COMDAT __JustMyCode_Default
_TEXT	SEGMENT
__JustMyCode_Default PROC				; COMDAT
  00000	c2 00 00	 ret	 0
__JustMyCode_Default ENDP
_TEXT	ENDS
; Function compile flags: /Ogtpy
; File D:\NitloadIndustry\研究项目\1-Flagship\TH2020\ProjectFile\源代码\StgShqrpGraphic\mat4.c
;	COMDAT transpose4to3
_TEXT	SEGMENT
source$ = 64
target$ = 72
transpose4to3 PROC					; COMDAT

; 134  : {

$LN4:
  00000	48 89 5c 24 08	 mov	 QWORD PTR [rsp+8], rbx
  00005	57		 push	 rdi
  00006	48 83 ec 30	 sub	 rsp, 48			; 00000030H
  0000a	48 8b d9	 mov	 rbx, rcx
  0000d	0f 29 74 24 20	 movaps	 XMMWORD PTR [rsp+32], xmm6
  00012	48 8d 0d 00 00
	00 00		 lea	 rcx, OFFSET FLAT:__6DC84844_mat4@c
  00019	48 8b fa	 mov	 rdi, rdx
  0001c	e8 00 00 00 00	 call	 __CheckForDebuggerJustMyCode
  00021	0f 10 33	 movups	 xmm6, XMMWORD PTR [rbx]
  00024	0f 10 63 10	 movups	 xmm4, XMMWORD PTR [rbx+16]
  00028	0f 10 6b 20	 movups	 xmm5, XMMWORD PTR [rbx+32]
  0002c	0f 10 5b 30	 movups	 xmm3, XMMWORD PTR [rbx+48]
  00030	48 8b 5c 24 40	 mov	 rbx, QWORD PTR [rsp+64]
  00035	0f 28 d6	 movaps	 xmm2, xmm6
  00038	0f 28 cd	 movaps	 xmm1, xmm5
  0003b	0f c6 d4 44	 shufps	 xmm2, xmm4, 68		; 00000044H
  0003f	0f c6 f4 ee	 shufps	 xmm6, xmm4, 238		; 000000eeH
  00043	0f 28 c2	 movaps	 xmm0, xmm2
  00046	0f c6 cb 44	 shufps	 xmm1, xmm3, 68		; 00000044H
  0004a	0f c6 eb ee	 shufps	 xmm5, xmm3, 238		; 000000eeH
  0004e	0f c6 f5 88	 shufps	 xmm6, xmm5, 136		; 00000088H
  00052	0f c6 c1 88	 shufps	 xmm0, xmm1, 136		; 00000088H
  00056	0f c6 d1 dd	 shufps	 xmm2, xmm1, 221		; 000000ddH
  0005a	0f 11 77 20	 movups	 XMMWORD PTR [rdi+32], xmm6
  0005e	0f 28 74 24 20	 movaps	 xmm6, XMMWORD PTR [rsp+32]
  00063	0f 11 07	 movups	 XMMWORD PTR [rdi], xmm0
  00066	0f 11 57 10	 movups	 XMMWORD PTR [rdi+16], xmm2

; 135  : 	__m128 t0 = _mm_shuffle_ps(ALIGN(source->colum[0]), ALIGN(source->colum[1]), _MM_SHUFFLE(1, 0, 1, 0));
; 136  : 	__m128 t1 = _mm_shuffle_ps(ALIGN(source->colum[0]), ALIGN(source->colum[1]), _MM_SHUFFLE(3, 2, 3, 2));
; 137  : 	__m128 t2 = _mm_shuffle_ps(ALIGN(source->colum[2]), ALIGN(source->colum[3]), _MM_SHUFFLE(1, 0, 1, 0));
; 138  : 	__m128 t3 = _mm_shuffle_ps(ALIGN(source->colum[2]), ALIGN(source->colum[3]), _MM_SHUFFLE(3, 2, 3, 2));
; 139  : 
; 140  : 	target->colum[0] = _mm_shuffle_ps(t0, t2, _MM_SHUFFLE(2, 0, 2, 0));
; 141  : 	target->colum[1] = _mm_shuffle_ps(t0, t2, _MM_SHUFFLE(3, 1, 3, 1));
; 142  : 	target->colum[2] = _mm_shuffle_ps(t1, t3, _MM_SHUFFLE(2, 0, 2, 0));
; 143  : 
; 144  : }

  0006a	48 83 c4 30	 add	 rsp, 48			; 00000030H
  0006e	5f		 pop	 rdi
  0006f	c3		 ret	 0
transpose4to3 ENDP
_TEXT	ENDS
; Function compile flags: /Ogtpy
; File D:\NitloadIndustry\研究项目\1-Flagship\TH2020\ProjectFile\源代码\StgShqrpGraphic\mat4.c
;	COMDAT deinit_mat4
_TEXT	SEGMENT
matPtr$ = 48
deinit_mat4 PROC					; COMDAT

; 169  : {

$LN4:
  00000	40 53		 push	 rbx
  00002	48 83 ec 20	 sub	 rsp, 32			; 00000020H
  00006	48 8b d9	 mov	 rbx, rcx
  00009	48 8d 0d 00 00
	00 00		 lea	 rcx, OFFSET FLAT:__6DC84844_mat4@c
  00010	e8 00 00 00 00	 call	 __CheckForDebuggerJustMyCode
  00015	48 8b cb	 mov	 rcx, rbx

; 170  : 	_aligned_free(matPtr);
; 171  : }

  00018	48 83 c4 20	 add	 rsp, 32			; 00000020H
  0001c	5b		 pop	 rbx
  0001d	48 ff 25 00 00
	00 00		 rex_jmp QWORD PTR __imp__aligned_free
deinit_mat4 ENDP
_TEXT	ENDS
; Function compile flags: /Ogtpy
; File D:\NitloadIndustry\研究项目\1-Flagship\TH2020\ProjectFile\源代码\StgShqrpGraphic\mat4.c
;	COMDAT det_mat4
_TEXT	SEGMENT
$T1 = 32
$T2 = 48
$T3 = 64
$T4 = 80
$T5 = 96
$T6 = 112
$T7 = 128
$T8 = 144
$T9 = 160
$T10 = 176
$T11 = 192
$T12 = 208
matPtr$ = 288
transpose$ = 296
det_mat4 PROC						; COMDAT

; 149  : {

$LN4:
  00000	48 8b c4	 mov	 rax, rsp
  00003	48 89 58 08	 mov	 QWORD PTR [rax+8], rbx
  00007	48 89 78 10	 mov	 QWORD PTR [rax+16], rdi
  0000b	55		 push	 rbp
  0000c	48 8d 68 e8	 lea	 rbp, QWORD PTR [rax-24]
  00010	48 81 ec 10 01
	00 00		 sub	 rsp, 272		; 00000110H
  00017	0f 29 70 e8	 movaps	 XMMWORD PTR [rax-24], xmm6
  0001b	48 8b d9	 mov	 rbx, rcx
  0001e	0f 29 78 d8	 movaps	 XMMWORD PTR [rax-40], xmm7
  00022	48 8d 0d 00 00
	00 00		 lea	 rcx, OFFSET FLAT:__6DC84844_mat4@c
  00029	44 0f 29 40 c8	 movaps	 XMMWORD PTR [rax-56], xmm8
  0002e	48 8b fa	 mov	 rdi, rdx
  00031	e8 00 00 00 00	 call	 __CheckForDebuggerJustMyCode
  00036	0f 10 1b	 movups	 xmm3, XMMWORD PTR [rbx]
  00039	4c 8d 44 24 20	 lea	 r8, QWORD PTR $T1[rsp]
  0003e	0f 10 53 10	 movups	 xmm2, XMMWORD PTR [rbx+16]
  00042	48 8d 54 24 30	 lea	 rdx, QWORD PTR $T2[rsp]
  00047	0f 10 4b 20	 movups	 xmm1, XMMWORD PTR [rbx+32]
  0004b	48 8d 4c 24 40	 lea	 rcx, QWORD PTR $T3[rsp]
  00050	0f 10 43 30	 movups	 xmm0, XMMWORD PTR [rbx+48]
  00054	0f 29 4d c0	 movaps	 XMMWORD PTR $T11[rbp-256], xmm1
  00058	0f 29 45 b0	 movaps	 XMMWORD PTR $T10[rbp-256], xmm0
  0005c	0f 29 55 d0	 movaps	 XMMWORD PTR $T12[rbp-256], xmm2
  00060	0f 29 45 80	 movaps	 XMMWORD PTR $T7[rbp-256], xmm0
  00064	0f 29 4d 90	 movaps	 XMMWORD PTR $T8[rbp-256], xmm1
  00068	0f 29 5d a0	 movaps	 XMMWORD PTR $T9[rbp-256], xmm3
  0006c	0f 29 44 24 50	 movaps	 XMMWORD PTR $T4[rsp], xmm0
  00071	0f 29 54 24 60	 movaps	 XMMWORD PTR $T5[rsp], xmm2
  00076	0f 29 5c 24 70	 movaps	 XMMWORD PTR $T6[rsp], xmm3
  0007b	0f 29 4c 24 20	 movaps	 XMMWORD PTR $T1[rsp], xmm1
  00080	0f 29 54 24 30	 movaps	 XMMWORD PTR $T2[rsp], xmm2
  00085	0f 29 5c 24 40	 movaps	 XMMWORD PTR $T3[rsp], xmm3
  0008a	e8 00 00 00 00	 call	 det_mat3_internal
  0008f	4c 8d 44 24 50	 lea	 r8, QWORD PTR $T4[rsp]
  00094	44 0f 28 c0	 movaps	 xmm8, xmm0
  00098	48 8d 54 24 60	 lea	 rdx, QWORD PTR $T5[rsp]
  0009d	48 8d 4c 24 70	 lea	 rcx, QWORD PTR $T6[rsp]
  000a2	e8 00 00 00 00	 call	 det_mat3_internal
  000a7	4c 8d 45 80	 lea	 r8, QWORD PTR $T7[rbp-256]
  000ab	0f 28 f8	 movaps	 xmm7, xmm0
  000ae	48 8d 55 90	 lea	 rdx, QWORD PTR $T8[rbp-256]
  000b2	48 8d 4d a0	 lea	 rcx, QWORD PTR $T9[rbp-256]
  000b6	e8 00 00 00 00	 call	 det_mat3_internal
  000bb	4c 8d 45 b0	 lea	 r8, QWORD PTR $T10[rbp-256]
  000bf	0f 28 f0	 movaps	 xmm6, xmm0
  000c2	48 8d 55 c0	 lea	 rdx, QWORD PTR $T11[rbp-256]
  000c6	48 8d 4d d0	 lea	 rcx, QWORD PTR $T12[rbp-256]
  000ca	e8 00 00 00 00	 call	 det_mat3_internal
  000cf	0f 10 4f 30	 movups	 xmm1, XMMWORD PTR [rdi+48]
  000d3	4c 8d 9c 24 10
	01 00 00	 lea	 r11, QWORD PTR [rsp+272]
  000db	0f 14 c6	 unpcklps xmm0, xmm6
  000de	49 8b 5b 10	 mov	 rbx, QWORD PTR [r11+16]
  000e2	49 8b 7b 18	 mov	 rdi, QWORD PTR [r11+24]
  000e6	41 0f 28 73 f0	 movaps	 xmm6, XMMWORD PTR [r11-16]
  000eb	41 0f 14 f8	 unpcklps xmm7, xmm8
  000ef	45 0f 28 43 d0	 movaps	 xmm8, XMMWORD PTR [r11-48]
  000f4	0f 16 c7	 movlhps xmm0, xmm7
  000f7	41 0f 28 7b e0	 movaps	 xmm7, XMMWORD PTR [r11-32]
  000fc	0f 59 c8	 mulps	 xmm1, xmm0
  000ff	f2 0f 7d c9	 hsubps	 xmm1, xmm1
  00103	f2 0f 7c c9	 haddps	 xmm1, xmm1
  00107	0f 57 0d 00 00
	00 00		 xorps	 xmm1, DWORD PTR __xmm@80000000800000008000000080000000
  0010e	0f 28 c1	 movaps	 xmm0, xmm1

; 150  : 	__m128 mc0 = ALIGN(matPtr->colum[0]);
; 151  : 	__m128 mc1 = ALIGN(matPtr->colum[1]);
; 152  : 	__m128 mc2 = ALIGN(matPtr->colum[2]);
; 153  : 	__m128 mc3 = ALIGN(matPtr->colum[3]);
; 154  : 
; 155  : 	__m128 cogeneration = _mm_set_ps(
; 156  : 		det_mat3_internal(mc0, mc1, mc2),
; 157  : 		det_mat3_internal(mc0, mc1, mc3),
; 158  : 		det_mat3_internal(mc0, mc2, mc3),
; 159  : 		det_mat3_internal(mc1, mc2, mc3)
; 160  : 		);
; 161  : 	__m128 retvec = _mm_mul_ps(ALIGN(transpose->colum[3]),cogeneration);
; 162  : 	retvec = _mm_hsub_ps(retvec,retvec);
; 163  : 	retvec = _mm_hadd_ps(retvec,retvec);
; 164  : 	return -retvec.m128_f32[0];
; 165  : 
; 166  : }

  00111	49 8b e3	 mov	 rsp, r11
  00114	5d		 pop	 rbp
  00115	c3		 ret	 0
det_mat4 ENDP
_TEXT	ENDS
; Function compile flags: /Ogtpy
; File D:\NitloadIndustry\研究项目\1-Flagship\TH2020\ProjectFile\源代码\StgShqrpGraphic\mat4.c
;	COMDAT transpose4to4
_TEXT	SEGMENT
source$ = 48
target$ = 56
transpose4to4 PROC					; COMDAT

; 120  : {

$LN4:
  00000	48 89 5c 24 08	 mov	 QWORD PTR [rsp+8], rbx
  00005	57		 push	 rdi
  00006	48 83 ec 20	 sub	 rsp, 32			; 00000020H
  0000a	48 8b d9	 mov	 rbx, rcx
  0000d	48 8b fa	 mov	 rdi, rdx
  00010	48 8d 0d 00 00
	00 00		 lea	 rcx, OFFSET FLAT:__6DC84844_mat4@c
  00017	e8 00 00 00 00	 call	 __CheckForDebuggerJustMyCode
  0001c	0f 10 43 10	 movups	 xmm0, XMMWORD PTR [rbx+16]
  00020	0f 10 23	 movups	 xmm4, XMMWORD PTR [rbx]
  00023	0f 10 53 20	 movups	 xmm2, XMMWORD PTR [rbx+32]
  00027	0f 28 dc	 movaps	 xmm3, xmm4
  0002a	0f c6 e0 ee	 shufps	 xmm4, xmm0, 238		; 000000eeH
  0002e	0f c6 d8 44	 shufps	 xmm3, xmm0, 68		; 00000044H
  00032	0f 28 ca	 movaps	 xmm1, xmm2
  00035	0f 10 43 30	 movups	 xmm0, XMMWORD PTR [rbx+48]
  00039	48 8b 5c 24 30	 mov	 rbx, QWORD PTR [rsp+48]
  0003e	0f c6 c8 44	 shufps	 xmm1, xmm0, 68		; 00000044H
  00042	0f c6 d0 ee	 shufps	 xmm2, xmm0, 238		; 000000eeH
  00046	0f 28 c3	 movaps	 xmm0, xmm3
  00049	0f c6 c1 88	 shufps	 xmm0, xmm1, 136		; 00000088H
  0004d	0f 11 07	 movups	 XMMWORD PTR [rdi], xmm0
  00050	0f 28 c4	 movaps	 xmm0, xmm4
  00053	0f c6 c2 88	 shufps	 xmm0, xmm2, 136		; 00000088H
  00057	0f c6 d9 dd	 shufps	 xmm3, xmm1, 221		; 000000ddH
  0005b	0f c6 e2 dd	 shufps	 xmm4, xmm2, 221		; 000000ddH
  0005f	0f 11 47 20	 movups	 XMMWORD PTR [rdi+32], xmm0
  00063	0f 11 5f 10	 movups	 XMMWORD PTR [rdi+16], xmm3
  00067	0f 11 67 30	 movups	 XMMWORD PTR [rdi+48], xmm4

; 121  : 	__m128 t0 = _mm_shuffle_ps(ALIGN(source->colum[0]), ALIGN(source->colum[1]), _MM_SHUFFLE(1, 0, 1, 0));
; 122  : 	__m128 t1 = _mm_shuffle_ps(ALIGN(source->colum[0]), ALIGN(source->colum[1]), _MM_SHUFFLE(3, 2, 3, 2));
; 123  : 	__m128 t2 = _mm_shuffle_ps(ALIGN(source->colum[2]), ALIGN(source->colum[3]), _MM_SHUFFLE(1, 0, 1, 0));
; 124  : 	__m128 t3 = _mm_shuffle_ps(ALIGN(source->colum[2]), ALIGN(source->colum[3]), _MM_SHUFFLE(3, 2, 3, 2));
; 125  : 
; 126  : 	target->colum[0] = _mm_shuffle_ps(t0, t2, _MM_SHUFFLE(2, 0, 2, 0));
; 127  : 	target->colum[1] = _mm_shuffle_ps(t0, t2, _MM_SHUFFLE(3, 1, 3, 1));
; 128  : 	target->colum[2] = _mm_shuffle_ps(t1, t3, _MM_SHUFFLE(2, 0, 2, 0));
; 129  : 	target->colum[3] = _mm_shuffle_ps(t1, t3, _MM_SHUFFLE(3, 1, 3, 1));
; 130  : 
; 131  : }

  0006b	48 83 c4 20	 add	 rsp, 32			; 00000020H
  0006f	5f		 pop	 rdi
  00070	c3		 ret	 0
transpose4to4 ENDP
_TEXT	ENDS
; Function compile flags: /Ogtpy
; File D:\NitloadIndustry\研究项目\1-Flagship\TH2020\ProjectFile\源代码\StgShqrpGraphic\mat4.c
;	COMDAT transpose4to2
_TEXT	SEGMENT
source$ = 48
target$ = 56
transpose4to2 PROC					; COMDAT

; 111  : {

$LN4:
  00000	48 89 5c 24 08	 mov	 QWORD PTR [rsp+8], rbx
  00005	57		 push	 rdi
  00006	48 83 ec 20	 sub	 rsp, 32			; 00000020H
  0000a	48 8b d9	 mov	 rbx, rcx
  0000d	48 8b fa	 mov	 rdi, rdx
  00010	48 8d 0d 00 00
	00 00		 lea	 rcx, OFFSET FLAT:__6DC84844_mat4@c
  00017	e8 00 00 00 00	 call	 __CheckForDebuggerJustMyCode
  0001c	0f 10 43 10	 movups	 xmm0, XMMWORD PTR [rbx+16]
  00020	0f 10 13	 movups	 xmm2, XMMWORD PTR [rbx]
  00023	0f 10 4b 20	 movups	 xmm1, XMMWORD PTR [rbx+32]
  00027	0f c6 d0 44	 shufps	 xmm2, xmm0, 68		; 00000044H
  0002b	0f 10 43 30	 movups	 xmm0, XMMWORD PTR [rbx+48]
  0002f	48 8b 5c 24 30	 mov	 rbx, QWORD PTR [rsp+48]
  00034	0f c6 c8 44	 shufps	 xmm1, xmm0, 68		; 00000044H
  00038	0f 28 c2	 movaps	 xmm0, xmm2
  0003b	0f c6 c1 88	 shufps	 xmm0, xmm1, 136		; 00000088H
  0003f	0f c6 d1 dd	 shufps	 xmm2, xmm1, 221		; 000000ddH
  00043	0f 11 07	 movups	 XMMWORD PTR [rdi], xmm0
  00046	0f 11 57 10	 movups	 XMMWORD PTR [rdi+16], xmm2

; 112  : 	__m128 t0 = _mm_shuffle_ps(ALIGN(source->colum[0]), ALIGN(source->colum[1]), _MM_SHUFFLE(1, 0, 1, 0));
; 113  : 	__m128 t2 = _mm_shuffle_ps(ALIGN(source->colum[2]), ALIGN(source->colum[3]), _MM_SHUFFLE(1, 0, 1, 0));
; 114  : 
; 115  : 	target->colum[0] = _mm_shuffle_ps(t0, t2, _MM_SHUFFLE(2, 0, 2, 0));
; 116  : 	target->colum[1] = _mm_shuffle_ps(t0, t2, _MM_SHUFFLE(3, 1, 3, 1));
; 117  : }

  0004a	48 83 c4 20	 add	 rsp, 32			; 00000020H
  0004e	5f		 pop	 rdi
  0004f	c3		 ret	 0
transpose4to2 ENDP
_TEXT	ENDS
; Function compile flags: /Ogtpy
; File D:\NitloadIndustry\研究项目\1-Flagship\TH2020\ProjectFile\源代码\StgShqrpGraphic\mat4.c
;	COMDAT mul_4_4
_TEXT	SEGMENT
$T1 = 32
$T2 = 32
$T3 = 32
$T4 = 32
$T5 = 48
$T6 = 48
$T7 = 48
$T8 = 48
$T9 = 64
$T10 = 64
$T11 = 64
$T12 = 64
$T13 = 80
$T14 = 80
$T15 = 80
$T16 = 80
$T17 = 96
$T18 = 96
$T19 = 96
$T20 = 96
$T21 = 112
$T22 = 112
$T23 = 112
$T24 = 112
$T25 = 128
$T26 = 128
$T27 = 128
$T28 = 128
$T29 = 144
$T30 = 144
$T31 = 144
$T32 = 144
left$ = 224
right$ = 232
mul_4_4	PROC						; COMDAT

; 78   : {

$LN7:
  00000	48 89 5c 24 08	 mov	 QWORD PTR [rsp+8], rbx
  00005	48 89 74 24 10	 mov	 QWORD PTR [rsp+16], rsi
  0000a	48 89 7c 24 18	 mov	 QWORD PTR [rsp+24], rdi
  0000f	55		 push	 rbp
  00010	48 8d 6c 24 a9	 lea	 rbp, QWORD PTR [rsp-87]
  00015	48 81 ec d0 00
	00 00		 sub	 rsp, 208		; 000000d0H
  0001c	48 8b f9	 mov	 rdi, rcx
  0001f	48 8b f2	 mov	 rsi, rdx
  00022	48 8d 0d 00 00
	00 00		 lea	 rcx, OFFSET FLAT:__6DC84844_mat4@c
  00029	e8 00 00 00 00	 call	 __CheckForDebuggerJustMyCode
  0002e	ba 10 00 00 00	 mov	 edx, 16
  00033	8d 4a 30	 lea	 ecx, QWORD PTR [rdx+48]
  00036	ff 15 00 00 00
	00		 call	 QWORD PTR __imp__aligned_malloc
  0003c	48 8b d8	 mov	 rbx, rax
  0003f	48 85 c0	 test	 rax, rax
  00042	0f 84 2f 02 00
	00		 je	 $LN2@mul_4_4

; 79   : 	matrix4map* retPtr = _aligned_malloc(sizeof(matrix4map), 16);
; 80   : 	if (NULL != retPtr)
; 81   : 	{
; 82   : 		retPtr->colum[0] = _mm_set_ps(

  00048	0f 10 0e	 movups	 xmm1, XMMWORD PTR [rsi]
  0004b	48 8d 55 a7	 lea	 rdx, QWORD PTR $T4[rbp-121]
  0004f	0f 10 47 30	 movups	 xmm0, XMMWORD PTR [rdi+48]
  00053	48 8d 4d b7	 lea	 rcx, QWORD PTR $T8[rbp-121]
  00057	0f 29 b4 24 c0
	00 00 00	 movaps	 XMMWORD PTR [rsp+192], xmm6
  0005f	0f 11 45 17	 movups	 XMMWORD PTR $T32[rbp-121], xmm0
  00063	0f 10 47 20	 movups	 xmm0, XMMWORD PTR [rdi+32]
  00067	0f 29 4d 07	 movaps	 XMMWORD PTR $T28[rbp-121], xmm1
  0006b	0f 11 45 f7	 movups	 XMMWORD PTR $T24[rbp-121], xmm0
  0006f	0f 10 47 10	 movups	 xmm0, XMMWORD PTR [rdi+16]
  00073	0f 29 4d e7	 movaps	 XMMWORD PTR $T20[rbp-121], xmm1
  00077	0f 29 4d c7	 movaps	 XMMWORD PTR $T12[rbp-121], xmm1
  0007b	0f 29 4d a7	 movaps	 XMMWORD PTR $T4[rbp-121], xmm1
  0007f	0f 10 0f	 movups	 xmm1, XMMWORD PTR [rdi]
  00082	0f 29 bc 24 b0
	00 00 00	 movaps	 XMMWORD PTR [rsp+176], xmm7
  0008a	0f 11 45 d7	 movups	 XMMWORD PTR $T16[rbp-121], xmm0
  0008e	44 0f 29 84 24
	a0 00 00 00	 movaps	 XMMWORD PTR [rsp+160], xmm8
  00097	0f 11 4d b7	 movups	 XMMWORD PTR $T8[rbp-121], xmm1
  0009b	e8 00 00 00 00	 call	 mulps_sum_internal
  000a0	48 8d 55 c7	 lea	 rdx, QWORD PTR $T12[rbp-121]
  000a4	44 0f 28 c0	 movaps	 xmm8, xmm0
  000a8	48 8d 4d d7	 lea	 rcx, QWORD PTR $T16[rbp-121]
  000ac	e8 00 00 00 00	 call	 mulps_sum_internal
  000b1	48 8d 55 e7	 lea	 rdx, QWORD PTR $T20[rbp-121]
  000b5	0f 28 f8	 movaps	 xmm7, xmm0
  000b8	48 8d 4d f7	 lea	 rcx, QWORD PTR $T24[rbp-121]
  000bc	e8 00 00 00 00	 call	 mulps_sum_internal
  000c1	48 8d 55 07	 lea	 rdx, QWORD PTR $T28[rbp-121]
  000c5	0f 28 f0	 movaps	 xmm6, xmm0
  000c8	48 8d 4d 17	 lea	 rcx, QWORD PTR $T32[rbp-121]
  000cc	e8 00 00 00 00	 call	 mulps_sum_internal
  000d1	0f 14 c6	 unpcklps xmm0, xmm6

; 83   : 			mulps_sum_internal(ALIGN(left->colum[0]), ALIGN(right->colum[0])),
; 84   : 			mulps_sum_internal(ALIGN(left->colum[1]), ALIGN(right->colum[0])),
; 85   : 			mulps_sum_internal(ALIGN(left->colum[2]), ALIGN(right->colum[0])),
; 86   : 			mulps_sum_internal(ALIGN(left->colum[3]), ALIGN(right->colum[0]))
; 87   : 			);
; 88   : 		retPtr->colum[1] = _mm_set_ps(

  000d4	48 8d 55 17	 lea	 rdx, QWORD PTR $T31[rbp-121]
  000d8	41 0f 14 f8	 unpcklps xmm7, xmm8
  000dc	48 8d 4d 07	 lea	 rcx, QWORD PTR $T27[rbp-121]
  000e0	0f 16 c7	 movlhps xmm0, xmm7
  000e3	0f 11 03	 movups	 XMMWORD PTR [rbx], xmm0
  000e6	0f 10 56 10	 movups	 xmm2, XMMWORD PTR [rsi+16]
  000ea	0f 10 47 30	 movups	 xmm0, XMMWORD PTR [rdi+48]
  000ee	0f 10 4f 20	 movups	 xmm1, XMMWORD PTR [rdi+32]
  000f2	0f 11 45 a7	 movups	 XMMWORD PTR $T3[rbp-121], xmm0
  000f6	0f 10 47 10	 movups	 xmm0, XMMWORD PTR [rdi+16]
  000fa	0f 11 4d c7	 movups	 XMMWORD PTR $T11[rbp-121], xmm1
  000fe	0f 10 0f	 movups	 xmm1, XMMWORD PTR [rdi]
  00101	0f 11 45 e7	 movups	 XMMWORD PTR $T19[rbp-121], xmm0
  00105	0f 11 4d 07	 movups	 XMMWORD PTR $T27[rbp-121], xmm1
  00109	0f 29 55 b7	 movaps	 XMMWORD PTR $T7[rbp-121], xmm2
  0010d	0f 29 55 d7	 movaps	 XMMWORD PTR $T15[rbp-121], xmm2
  00111	0f 29 55 f7	 movaps	 XMMWORD PTR $T23[rbp-121], xmm2
  00115	0f 29 55 17	 movaps	 XMMWORD PTR $T31[rbp-121], xmm2
  00119	e8 00 00 00 00	 call	 mulps_sum_internal
  0011e	48 8d 55 f7	 lea	 rdx, QWORD PTR $T23[rbp-121]
  00122	44 0f 28 c0	 movaps	 xmm8, xmm0
  00126	48 8d 4d e7	 lea	 rcx, QWORD PTR $T19[rbp-121]
  0012a	e8 00 00 00 00	 call	 mulps_sum_internal
  0012f	48 8d 55 d7	 lea	 rdx, QWORD PTR $T15[rbp-121]
  00133	0f 28 f8	 movaps	 xmm7, xmm0
  00136	48 8d 4d c7	 lea	 rcx, QWORD PTR $T11[rbp-121]
  0013a	e8 00 00 00 00	 call	 mulps_sum_internal
  0013f	48 8d 55 b7	 lea	 rdx, QWORD PTR $T7[rbp-121]
  00143	0f 28 f0	 movaps	 xmm6, xmm0
  00146	48 8d 4d a7	 lea	 rcx, QWORD PTR $T3[rbp-121]
  0014a	e8 00 00 00 00	 call	 mulps_sum_internal
  0014f	0f 14 c6	 unpcklps xmm0, xmm6

; 89   : 			mulps_sum_internal(ALIGN(left->colum[0]), ALIGN(right->colum[1])),
; 90   : 			mulps_sum_internal(ALIGN(left->colum[1]), ALIGN(right->colum[1])),
; 91   : 			mulps_sum_internal(ALIGN(left->colum[2]), ALIGN(right->colum[1])),
; 92   : 			mulps_sum_internal(ALIGN(left->colum[3]), ALIGN(right->colum[1]))
; 93   : 		);
; 94   : 		retPtr->colum[1] = _mm_set_ps(

  00152	48 8d 55 17	 lea	 rdx, QWORD PTR $T30[rbp-121]
  00156	41 0f 14 f8	 unpcklps xmm7, xmm8
  0015a	0f 16 c7	 movlhps xmm0, xmm7
  0015d	0f 11 43 10	 movups	 XMMWORD PTR [rbx+16], xmm0
  00161	0f 10 56 20	 movups	 xmm2, XMMWORD PTR [rsi+32]
  00165	0f 10 47 30	 movups	 xmm0, XMMWORD PTR [rdi+48]
  00169	0f 10 4f 20	 movups	 xmm1, XMMWORD PTR [rdi+32]
  0016d	0f 11 45 a7	 movups	 XMMWORD PTR $T2[rbp-121], xmm0
  00171	0f 10 47 10	 movups	 xmm0, XMMWORD PTR [rdi+16]
  00175	0f 11 4d c7	 movups	 XMMWORD PTR $T10[rbp-121], xmm1
  00179	0f 10 0f	 movups	 xmm1, XMMWORD PTR [rdi]
  0017c	0f 11 45 e7	 movups	 XMMWORD PTR $T18[rbp-121], xmm0
  00180	0f 11 4d 07	 movups	 XMMWORD PTR $T26[rbp-121], xmm1
  00184	0f 29 55 b7	 movaps	 XMMWORD PTR $T6[rbp-121], xmm2
  00188	0f 29 55 d7	 movaps	 XMMWORD PTR $T14[rbp-121], xmm2
  0018c	0f 29 55 f7	 movaps	 XMMWORD PTR $T22[rbp-121], xmm2
  00190	0f 29 55 17	 movaps	 XMMWORD PTR $T30[rbp-121], xmm2
  00194	48 8d 4d 07	 lea	 rcx, QWORD PTR $T26[rbp-121]
  00198	e8 00 00 00 00	 call	 mulps_sum_internal
  0019d	48 8d 55 f7	 lea	 rdx, QWORD PTR $T22[rbp-121]
  001a1	44 0f 28 c0	 movaps	 xmm8, xmm0
  001a5	48 8d 4d e7	 lea	 rcx, QWORD PTR $T18[rbp-121]
  001a9	e8 00 00 00 00	 call	 mulps_sum_internal
  001ae	48 8d 55 d7	 lea	 rdx, QWORD PTR $T14[rbp-121]
  001b2	0f 28 f8	 movaps	 xmm7, xmm0
  001b5	48 8d 4d c7	 lea	 rcx, QWORD PTR $T10[rbp-121]
  001b9	e8 00 00 00 00	 call	 mulps_sum_internal
  001be	48 8d 55 b7	 lea	 rdx, QWORD PTR $T6[rbp-121]
  001c2	0f 28 f0	 movaps	 xmm6, xmm0
  001c5	48 8d 4d a7	 lea	 rcx, QWORD PTR $T2[rbp-121]
  001c9	e8 00 00 00 00	 call	 mulps_sum_internal
  001ce	0f 14 c6	 unpcklps xmm0, xmm6

; 95   : 			mulps_sum_internal(ALIGN(left->colum[0]), ALIGN(right->colum[2])),
; 96   : 			mulps_sum_internal(ALIGN(left->colum[1]), ALIGN(right->colum[2])),
; 97   : 			mulps_sum_internal(ALIGN(left->colum[2]), ALIGN(right->colum[2])),
; 98   : 			mulps_sum_internal(ALIGN(left->colum[3]), ALIGN(right->colum[2]))
; 99   : 		);
; 100  : 		retPtr->colum[1] = _mm_set_ps(

  001d1	48 8d 55 17	 lea	 rdx, QWORD PTR $T29[rbp-121]
  001d5	41 0f 14 f8	 unpcklps xmm7, xmm8
  001d9	48 8d 4d 07	 lea	 rcx, QWORD PTR $T25[rbp-121]
  001dd	0f 16 c7	 movlhps xmm0, xmm7
  001e0	0f 11 43 10	 movups	 XMMWORD PTR [rbx+16], xmm0
  001e4	0f 10 56 30	 movups	 xmm2, XMMWORD PTR [rsi+48]
  001e8	0f 10 47 30	 movups	 xmm0, XMMWORD PTR [rdi+48]
  001ec	0f 10 4f 20	 movups	 xmm1, XMMWORD PTR [rdi+32]
  001f0	0f 11 45 a7	 movups	 XMMWORD PTR $T1[rbp-121], xmm0
  001f4	0f 10 47 10	 movups	 xmm0, XMMWORD PTR [rdi+16]
  001f8	0f 11 4d c7	 movups	 XMMWORD PTR $T9[rbp-121], xmm1
  001fc	0f 10 0f	 movups	 xmm1, XMMWORD PTR [rdi]
  001ff	0f 11 45 e7	 movups	 XMMWORD PTR $T17[rbp-121], xmm0
  00203	0f 11 4d 07	 movups	 XMMWORD PTR $T25[rbp-121], xmm1
  00207	0f 29 55 b7	 movaps	 XMMWORD PTR $T5[rbp-121], xmm2
  0020b	0f 29 55 d7	 movaps	 XMMWORD PTR $T13[rbp-121], xmm2
  0020f	0f 29 55 f7	 movaps	 XMMWORD PTR $T21[rbp-121], xmm2
  00213	0f 29 55 17	 movaps	 XMMWORD PTR $T29[rbp-121], xmm2
  00217	e8 00 00 00 00	 call	 mulps_sum_internal
  0021c	48 8d 55 f7	 lea	 rdx, QWORD PTR $T21[rbp-121]
  00220	44 0f 28 c0	 movaps	 xmm8, xmm0
  00224	48 8d 4d e7	 lea	 rcx, QWORD PTR $T17[rbp-121]
  00228	e8 00 00 00 00	 call	 mulps_sum_internal
  0022d	48 8d 55 d7	 lea	 rdx, QWORD PTR $T13[rbp-121]
  00231	0f 28 f8	 movaps	 xmm7, xmm0
  00234	48 8d 4d c7	 lea	 rcx, QWORD PTR $T9[rbp-121]
  00238	e8 00 00 00 00	 call	 mulps_sum_internal
  0023d	48 8d 55 b7	 lea	 rdx, QWORD PTR $T5[rbp-121]
  00241	0f 28 f0	 movaps	 xmm6, xmm0
  00244	48 8d 4d a7	 lea	 rcx, QWORD PTR $T1[rbp-121]
  00248	e8 00 00 00 00	 call	 mulps_sum_internal
  0024d	41 0f 14 f8	 unpcklps xmm7, xmm8

; 101  : 			mulps_sum_internal(ALIGN(left->colum[0]), ALIGN(right->colum[3])),
; 102  : 			mulps_sum_internal(ALIGN(left->colum[1]), ALIGN(right->colum[3])),
; 103  : 			mulps_sum_internal(ALIGN(left->colum[2]), ALIGN(right->colum[3])),
; 104  : 			mulps_sum_internal(ALIGN(left->colum[3]), ALIGN(right->colum[3]))
; 105  : 		);
; 106  : 	}
; 107  : 	return retPtr;

  00251	48 8b c3	 mov	 rax, rbx
  00254	44 0f 28 84 24
	a0 00 00 00	 movaps	 xmm8, XMMWORD PTR [rsp+160]
  0025d	0f 14 c6	 unpcklps xmm0, xmm6
  00260	0f 28 b4 24 c0
	00 00 00	 movaps	 xmm6, XMMWORD PTR [rsp+192]
  00268	0f 16 c7	 movlhps xmm0, xmm7
  0026b	0f 28 bc 24 b0
	00 00 00	 movaps	 xmm7, XMMWORD PTR [rsp+176]
  00273	0f 11 43 10	 movups	 XMMWORD PTR [rbx+16], xmm0
$LN2@mul_4_4:

; 108  : }

  00277	4c 8d 9c 24 d0
	00 00 00	 lea	 r11, QWORD PTR [rsp+208]
  0027f	49 8b 5b 10	 mov	 rbx, QWORD PTR [r11+16]
  00283	49 8b 73 18	 mov	 rsi, QWORD PTR [r11+24]
  00287	49 8b 7b 20	 mov	 rdi, QWORD PTR [r11+32]
  0028b	49 8b e3	 mov	 rsp, r11
  0028e	5d		 pop	 rbp
  0028f	c3		 ret	 0
mul_4_4	ENDP
_TEXT	ENDS
; Function compile flags: /Ogtpy
; File D:\NitloadIndustry\研究项目\1-Flagship\TH2020\ProjectFile\源代码\StgShqrpGraphic\mat4.c
;	COMDAT mul_4_2
_TEXT	SEGMENT
$T1 = 32
$T2 = 32
$T3 = 48
$T4 = 48
$T5 = 64
$T6 = 64
$T7 = 80
$T8 = 80
$T9 = 96
$T10 = 96
$T11 = 112
$T12 = 112
$T13 = 128
$T14 = 128
$T15 = 144
$T16 = 144
left$ = 224
right$ = 232
mul_4_2	PROC						; COMDAT

; 57   : {

$LN6:
  00000	48 89 5c 24 08	 mov	 QWORD PTR [rsp+8], rbx
  00005	48 89 74 24 10	 mov	 QWORD PTR [rsp+16], rsi
  0000a	48 89 7c 24 18	 mov	 QWORD PTR [rsp+24], rdi
  0000f	55		 push	 rbp
  00010	48 8d 6c 24 a9	 lea	 rbp, QWORD PTR [rsp-87]
  00015	48 81 ec d0 00
	00 00		 sub	 rsp, 208		; 000000d0H
  0001c	48 8b f9	 mov	 rdi, rcx
  0001f	48 8b f2	 mov	 rsi, rdx
  00022	48 8d 0d 00 00
	00 00		 lea	 rcx, OFFSET FLAT:__6DC84844_mat4@c
  00029	e8 00 00 00 00	 call	 __CheckForDebuggerJustMyCode
  0002e	ba 10 00 00 00	 mov	 edx, 16
  00033	8d 4a 10	 lea	 ecx, QWORD PTR [rdx+16]
  00036	ff 15 00 00 00
	00		 call	 QWORD PTR __imp__aligned_malloc
  0003c	48 8b d8	 mov	 rbx, rax
  0003f	48 85 c0	 test	 rax, rax
  00042	0f 84 2e 01 00
	00		 je	 $LN2@mul_4_2

; 58   : 	matrix2map* retPtr = _aligned_malloc(sizeof(matrix2map), 16);
; 59   : 	if (NULL != retPtr)
; 60   : 	{
; 61   : 		retPtr->colum[0] = _mm_set_ps(

  00048	0f 10 0e	 movups	 xmm1, XMMWORD PTR [rsi]
  0004b	48 8d 55 a7	 lea	 rdx, QWORD PTR $T2[rbp-121]
  0004f	0f 10 47 30	 movups	 xmm0, XMMWORD PTR [rdi+48]
  00053	48 8d 4d b7	 lea	 rcx, QWORD PTR $T4[rbp-121]
  00057	0f 29 b4 24 c0
	00 00 00	 movaps	 XMMWORD PTR [rsp+192], xmm6
  0005f	0f 11 45 17	 movups	 XMMWORD PTR $T16[rbp-121], xmm0
  00063	0f 10 47 20	 movups	 xmm0, XMMWORD PTR [rdi+32]
  00067	0f 29 4d 07	 movaps	 XMMWORD PTR $T14[rbp-121], xmm1
  0006b	0f 11 45 f7	 movups	 XMMWORD PTR $T12[rbp-121], xmm0
  0006f	0f 10 47 10	 movups	 xmm0, XMMWORD PTR [rdi+16]
  00073	0f 29 4d e7	 movaps	 XMMWORD PTR $T10[rbp-121], xmm1
  00077	0f 29 4d c7	 movaps	 XMMWORD PTR $T6[rbp-121], xmm1
  0007b	0f 29 4d a7	 movaps	 XMMWORD PTR $T2[rbp-121], xmm1
  0007f	0f 10 0f	 movups	 xmm1, XMMWORD PTR [rdi]
  00082	0f 29 bc 24 b0
	00 00 00	 movaps	 XMMWORD PTR [rsp+176], xmm7
  0008a	0f 11 45 d7	 movups	 XMMWORD PTR $T8[rbp-121], xmm0
  0008e	44 0f 29 84 24
	a0 00 00 00	 movaps	 XMMWORD PTR [rsp+160], xmm8
  00097	0f 11 4d b7	 movups	 XMMWORD PTR $T4[rbp-121], xmm1
  0009b	e8 00 00 00 00	 call	 mulps_sum_internal
  000a0	48 8d 55 c7	 lea	 rdx, QWORD PTR $T6[rbp-121]
  000a4	44 0f 28 c0	 movaps	 xmm8, xmm0
  000a8	48 8d 4d d7	 lea	 rcx, QWORD PTR $T8[rbp-121]
  000ac	e8 00 00 00 00	 call	 mulps_sum_internal
  000b1	48 8d 55 e7	 lea	 rdx, QWORD PTR $T10[rbp-121]
  000b5	0f 28 f8	 movaps	 xmm7, xmm0
  000b8	48 8d 4d f7	 lea	 rcx, QWORD PTR $T12[rbp-121]
  000bc	e8 00 00 00 00	 call	 mulps_sum_internal
  000c1	48 8d 55 07	 lea	 rdx, QWORD PTR $T14[rbp-121]
  000c5	0f 28 f0	 movaps	 xmm6, xmm0
  000c8	48 8d 4d 17	 lea	 rcx, QWORD PTR $T16[rbp-121]
  000cc	e8 00 00 00 00	 call	 mulps_sum_internal
  000d1	0f 14 c6	 unpcklps xmm0, xmm6

; 62   : 			mulps_sum_internal(ALIGN(left->colum[0]), ALIGN(right->colum[0])),
; 63   : 			mulps_sum_internal(ALIGN(left->colum[1]), ALIGN(right->colum[0])),
; 64   : 			mulps_sum_internal(ALIGN(left->colum[2]), ALIGN(right->colum[0])),
; 65   : 			mulps_sum_internal(ALIGN(left->colum[3]), ALIGN(right->colum[0]))
; 66   : 		);
; 67   : 		retPtr->colum[1] = _mm_set_ps(

  000d4	48 8d 55 17	 lea	 rdx, QWORD PTR $T15[rbp-121]
  000d8	41 0f 14 f8	 unpcklps xmm7, xmm8
  000dc	48 8d 4d 07	 lea	 rcx, QWORD PTR $T13[rbp-121]
  000e0	0f 16 c7	 movlhps xmm0, xmm7
  000e3	0f 11 03	 movups	 XMMWORD PTR [rbx], xmm0
  000e6	0f 10 56 10	 movups	 xmm2, XMMWORD PTR [rsi+16]
  000ea	0f 10 47 30	 movups	 xmm0, XMMWORD PTR [rdi+48]
  000ee	0f 10 4f 20	 movups	 xmm1, XMMWORD PTR [rdi+32]
  000f2	0f 11 45 a7	 movups	 XMMWORD PTR $T1[rbp-121], xmm0
  000f6	0f 10 47 10	 movups	 xmm0, XMMWORD PTR [rdi+16]
  000fa	0f 11 4d c7	 movups	 XMMWORD PTR $T5[rbp-121], xmm1
  000fe	0f 10 0f	 movups	 xmm1, XMMWORD PTR [rdi]
  00101	0f 11 45 e7	 movups	 XMMWORD PTR $T9[rbp-121], xmm0
  00105	0f 11 4d 07	 movups	 XMMWORD PTR $T13[rbp-121], xmm1
  00109	0f 29 55 b7	 movaps	 XMMWORD PTR $T3[rbp-121], xmm2
  0010d	0f 29 55 d7	 movaps	 XMMWORD PTR $T7[rbp-121], xmm2
  00111	0f 29 55 f7	 movaps	 XMMWORD PTR $T11[rbp-121], xmm2
  00115	0f 29 55 17	 movaps	 XMMWORD PTR $T15[rbp-121], xmm2
  00119	e8 00 00 00 00	 call	 mulps_sum_internal
  0011e	48 8d 55 f7	 lea	 rdx, QWORD PTR $T11[rbp-121]
  00122	44 0f 28 c0	 movaps	 xmm8, xmm0
  00126	48 8d 4d e7	 lea	 rcx, QWORD PTR $T9[rbp-121]
  0012a	e8 00 00 00 00	 call	 mulps_sum_internal
  0012f	48 8d 55 d7	 lea	 rdx, QWORD PTR $T7[rbp-121]
  00133	0f 28 f8	 movaps	 xmm7, xmm0
  00136	48 8d 4d c7	 lea	 rcx, QWORD PTR $T5[rbp-121]
  0013a	e8 00 00 00 00	 call	 mulps_sum_internal
  0013f	48 8d 55 b7	 lea	 rdx, QWORD PTR $T3[rbp-121]
  00143	0f 28 f0	 movaps	 xmm6, xmm0
  00146	48 8d 4d a7	 lea	 rcx, QWORD PTR $T1[rbp-121]
  0014a	e8 00 00 00 00	 call	 mulps_sum_internal
  0014f	41 0f 14 f8	 unpcklps xmm7, xmm8
  00153	44 0f 28 84 24
	a0 00 00 00	 movaps	 xmm8, XMMWORD PTR [rsp+160]
  0015c	0f 14 c6	 unpcklps xmm0, xmm6
  0015f	0f 28 b4 24 c0
	00 00 00	 movaps	 xmm6, XMMWORD PTR [rsp+192]
  00167	0f 16 c7	 movlhps xmm0, xmm7
  0016a	0f 28 bc 24 b0
	00 00 00	 movaps	 xmm7, XMMWORD PTR [rsp+176]
  00172	0f 11 43 10	 movups	 XMMWORD PTR [rbx+16], xmm0
$LN2@mul_4_2:

; 68   : 			mulps_sum_internal(ALIGN(left->colum[0]), ALIGN(right->colum[1])),
; 69   : 			mulps_sum_internal(ALIGN(left->colum[1]), ALIGN(right->colum[1])),
; 70   : 			mulps_sum_internal(ALIGN(left->colum[2]), ALIGN(right->colum[1])),
; 71   : 			mulps_sum_internal(ALIGN(left->colum[3]), ALIGN(right->colum[1]))
; 72   : 		);
; 73   : 	}
; 74   : }

  00176	4c 8d 9c 24 d0
	00 00 00	 lea	 r11, QWORD PTR [rsp+208]
  0017e	49 8b 5b 10	 mov	 rbx, QWORD PTR [r11+16]
  00182	49 8b 73 18	 mov	 rsi, QWORD PTR [r11+24]
  00186	49 8b 7b 20	 mov	 rdi, QWORD PTR [r11+32]
  0018a	49 8b e3	 mov	 rsp, r11
  0018d	5d		 pop	 rbp
  0018e	c3		 ret	 0
mul_4_2	ENDP
_TEXT	ENDS
; Function compile flags: /Ogtpy
; File D:\NitloadIndustry\研究项目\1-Flagship\TH2020\ProjectFile\源代码\StgShqrpGraphic\mat4.c
;	COMDAT mul_const
_TEXT	SEGMENT
cst128$1 = 32
mat$ = 80
value$ = 88
mul_const PROC						; COMDAT

; 37   : {

$LN15:
  00000	40 53		 push	 rbx
  00002	48 83 ec 40	 sub	 rsp, 64			; 00000040H
  00006	0f 29 74 24 30	 movaps	 XMMWORD PTR [rsp+48], xmm6
  0000b	48 8b d9	 mov	 rbx, rcx
  0000e	0f 28 f1	 movaps	 xmm6, xmm1
  00011	48 8d 0d 00 00
	00 00		 lea	 rcx, OFFSET FLAT:__6DC84844_mat4@c
  00018	0f c6 f6 00	 shufps	 xmm6, xmm6, 0
  0001c	e8 00 00 00 00	 call	 __CheckForDebuggerJustMyCode
  00021	ba 10 00 00 00	 mov	 edx, 16
  00026	8d 4a 70	 lea	 ecx, QWORD PTR [rdx+112]
  00029	ff 15 00 00 00
	00		 call	 QWORD PTR __imp__aligned_malloc
  0002f	48 85 c0	 test	 rax, rax
  00032	74 2f		 je	 SHORT $LN12@mul_const

; 38   : 	matrix4map* ret = _aligned_malloc(sizeof(matrix4),16);
; 39   : 
; 40   : 	if (NULL != ret)
; 41   : 	{
; 42   : 		float cstarray[4] = { value, value, value, value };
; 43   : 
; 44   : 		__m128 cst128 = _mm_loadu_ps(&cstarray);

  00034	0f 28 c6	 movaps	 xmm0, xmm6
  00037	0f 29 74 24 20	 movaps	 XMMWORD PTR cst128$1[rsp], xmm6

; 45   : 
; 46   : 		ret->colum[0] = _mm_mul_ps(mat->colum[0], cst128);

  0003c	0f 59 03	 mulps	 xmm0, XMMWORD PTR [rbx]

; 47   : 		ret->colum[1] = _mm_mul_ps(mat->colum[1], cst128);

  0003f	0f 28 ce	 movaps	 xmm1, xmm6
  00042	0f 28 d6	 movaps	 xmm2, xmm6
  00045	0f 11 00	 movups	 XMMWORD PTR [rax], xmm0

; 48   : 		ret->colum[2] = _mm_mul_ps(mat->colum[2], cst128);

  00048	0f 28 c6	 movaps	 xmm0, xmm6
  0004b	0f 59 4b 10	 mulps	 xmm1, XMMWORD PTR [rbx+16]
  0004f	0f 11 48 10	 movups	 XMMWORD PTR [rax+16], xmm1
  00053	0f 59 43 20	 mulps	 xmm0, XMMWORD PTR [rbx+32]
  00057	0f 11 40 20	 movups	 XMMWORD PTR [rax+32], xmm0

; 49   : 		ret->colum[3] = _mm_mul_ps(mat->colum[3], cst128);

  0005b	0f 59 53 30	 mulps	 xmm2, XMMWORD PTR [rbx+48]
  0005f	0f 11 50 30	 movups	 XMMWORD PTR [rax+48], xmm2
$LN12@mul_const:

; 50   : 	}
; 51   : 
; 52   : 	return ret;
; 53   : 
; 54   : }

  00063	0f 28 74 24 30	 movaps	 xmm6, XMMWORD PTR [rsp+48]
  00068	48 83 c4 40	 add	 rsp, 64			; 00000040H
  0006c	5b		 pop	 rbx
  0006d	c3		 ret	 0
mul_const ENDP
_TEXT	ENDS
; Function compile flags: /Ogtpy
; File D:\NitloadIndustry\研究项目\1-Flagship\TH2020\ProjectFile\源代码\StgShqrpGraphic\mat4.c
;	COMDAT sub_mat4
_TEXT	SEGMENT
mat1$ = 48
mat2$ = 56
sub_mat4 PROC						; COMDAT

; 22   : {

$LN7:
  00000	48 89 5c 24 08	 mov	 QWORD PTR [rsp+8], rbx
  00005	57		 push	 rdi
  00006	48 83 ec 20	 sub	 rsp, 32			; 00000020H
  0000a	48 8b f9	 mov	 rdi, rcx
  0000d	48 8b da	 mov	 rbx, rdx
  00010	48 8d 0d 00 00
	00 00		 lea	 rcx, OFFSET FLAT:__6DC84844_mat4@c
  00017	e8 00 00 00 00	 call	 __CheckForDebuggerJustMyCode
  0001c	ba 10 00 00 00	 mov	 edx, 16
  00021	8d 4a 70	 lea	 ecx, QWORD PTR [rdx+112]
  00024	ff 15 00 00 00
	00		 call	 QWORD PTR __imp__aligned_malloc
  0002a	48 85 c0	 test	 rax, rax
  0002d	74 2d		 je	 SHORT $LN4@sub_mat4

; 23   : 	matrix4map* ret = _aligned_malloc(sizeof(matrix4), 16);
; 24   : 
; 25   : 	if (ret != 0)
; 26   : 	{
; 27   : 		ret->colum[0] = _mm_sub_ps(mat1->colum[0], mat2->colum[0]);

  0002f	0f 10 07	 movups	 xmm0, XMMWORD PTR [rdi]
  00032	0f 5c 03	 subps	 xmm0, XMMWORD PTR [rbx]
  00035	0f 11 00	 movups	 XMMWORD PTR [rax], xmm0

; 28   : 		ret->colum[1] = _mm_sub_ps(mat1->colum[1], mat2->colum[1]);

  00038	0f 10 4f 10	 movups	 xmm1, XMMWORD PTR [rdi+16]
  0003c	0f 5c 4b 10	 subps	 xmm1, XMMWORD PTR [rbx+16]
  00040	0f 11 48 10	 movups	 XMMWORD PTR [rax+16], xmm1

; 29   : 		ret->colum[2] = _mm_sub_ps(mat1->colum[2], mat2->colum[2]);

  00044	0f 10 47 20	 movups	 xmm0, XMMWORD PTR [rdi+32]
  00048	0f 5c 43 20	 subps	 xmm0, XMMWORD PTR [rbx+32]
  0004c	0f 11 40 20	 movups	 XMMWORD PTR [rax+32], xmm0

; 30   : 		ret->colum[3] = _mm_sub_ps(mat1->colum[3], mat2->colum[3]);

  00050	0f 10 4f 30	 movups	 xmm1, XMMWORD PTR [rdi+48]
  00054	0f 5c 4b 30	 subps	 xmm1, XMMWORD PTR [rbx+48]
  00058	0f 11 48 30	 movups	 XMMWORD PTR [rax+48], xmm1
$LN4@sub_mat4:

; 31   : 	}
; 32   : 
; 33   : 	return ret;
; 34   : }

  0005c	48 8b 5c 24 30	 mov	 rbx, QWORD PTR [rsp+48]
  00061	48 83 c4 20	 add	 rsp, 32			; 00000020H
  00065	5f		 pop	 rdi
  00066	c3		 ret	 0
sub_mat4 ENDP
_TEXT	ENDS
; Function compile flags: /Ogtpy
; File D:\NitloadIndustry\研究项目\1-Flagship\TH2020\ProjectFile\源代码\StgShqrpGraphic\mat4.c
;	COMDAT add_mat4
_TEXT	SEGMENT
mat1$ = 48
mat2$ = 56
add_mat4 PROC						; COMDAT

; 7    : {

$LN7:
  00000	48 89 5c 24 08	 mov	 QWORD PTR [rsp+8], rbx
  00005	57		 push	 rdi
  00006	48 83 ec 20	 sub	 rsp, 32			; 00000020H
  0000a	48 8b f9	 mov	 rdi, rcx
  0000d	48 8b da	 mov	 rbx, rdx
  00010	48 8d 0d 00 00
	00 00		 lea	 rcx, OFFSET FLAT:__6DC84844_mat4@c
  00017	e8 00 00 00 00	 call	 __CheckForDebuggerJustMyCode
  0001c	ba 10 00 00 00	 mov	 edx, 16
  00021	8d 4a 70	 lea	 ecx, QWORD PTR [rdx+112]
  00024	ff 15 00 00 00
	00		 call	 QWORD PTR __imp__aligned_malloc
  0002a	48 85 c0	 test	 rax, rax
  0002d	74 2d		 je	 SHORT $LN4@add_mat4

; 8    :     matrix4map* ret = _aligned_malloc(sizeof(matrix4), 16);
; 9    : 
; 10   : 	if (ret != 0)
; 11   : 	{
; 12   : 		ret->colum[0] = _mm_add_ps(mat1->colum[0], mat2->colum[0]);

  0002f	0f 10 07	 movups	 xmm0, XMMWORD PTR [rdi]
  00032	0f 58 03	 addps	 xmm0, XMMWORD PTR [rbx]
  00035	0f 11 00	 movups	 XMMWORD PTR [rax], xmm0

; 13   : 		ret->colum[1] = _mm_add_ps(mat1->colum[1], mat2->colum[1]);

  00038	0f 10 4f 10	 movups	 xmm1, XMMWORD PTR [rdi+16]
  0003c	0f 58 4b 10	 addps	 xmm1, XMMWORD PTR [rbx+16]
  00040	0f 11 48 10	 movups	 XMMWORD PTR [rax+16], xmm1

; 14   : 		ret->colum[2] = _mm_add_ps(mat1->colum[2], mat2->colum[2]);

  00044	0f 10 47 20	 movups	 xmm0, XMMWORD PTR [rdi+32]
  00048	0f 58 43 20	 addps	 xmm0, XMMWORD PTR [rbx+32]
  0004c	0f 11 40 20	 movups	 XMMWORD PTR [rax+32], xmm0

; 15   : 		ret->colum[3] = _mm_add_ps(mat1->colum[3], mat2->colum[3]);

  00050	0f 10 4f 30	 movups	 xmm1, XMMWORD PTR [rdi+48]
  00054	0f 58 4b 30	 addps	 xmm1, XMMWORD PTR [rbx+48]
  00058	0f 11 48 30	 movups	 XMMWORD PTR [rax+48], xmm1
$LN4@add_mat4:

; 16   : 	}
; 17   : 
; 18   : 	return ret;
; 19   : }

  0005c	48 8b 5c 24 30	 mov	 rbx, QWORD PTR [rsp+48]
  00061	48 83 c4 20	 add	 rsp, 32			; 00000020H
  00065	5f		 pop	 rdi
  00066	c3		 ret	 0
add_mat4 ENDP
_TEXT	ENDS
END