; Listing generated by Microsoft (R) Optimizing Compiler Version 19.41.34120.0 include listing.inc INCLUDELIB MSVCRTD INCLUDELIB OLDNAMES _DATA SEGMENT COMM infolog:BYTE:0200H _DATA ENDS msvcjmc SEGMENT __7583A0D2_mmintrin@h DB 01H __DDA0A690_concurrencysal@h DB 01H __9ECC08BE_sal@h DB 01H __E05D733A_vadefs@h DB 01H __6A355E0E_vcruntime@h DB 01H __1B0272D9_corecrt@h DB 01H __45DED006_corecrt_malloc@h DB 01H __FA77ED4C_malloc@h DB 01H __EAE0325A_xmmintrin@h DB 01H __0ED14FEE_winpackagefamily@h DB 01H __F92EF742_winapifamily@h DB 01H __22E515EB_sdkddkver@h DB 01H __A09A3A7D_excpt@h DB 01H __AC8FA393_stdarg@h DB 01H __29F49F40_specstrings_undef@h DB 01H __D0F42932_specstrings_strict@h DB 01H __F00405FD_sdv_driverspecs@h DB 01H __173E09CA_driverspecs@h DB 01H __9A452361_specstrings@h DB 01H __74484FB3_corecrt_wctype@h DB 01H __1EC467ED_ctype@h DB 01H __98517906_kernelspecs@h DB 01H __D3497022_basetsd@h DB 01H __61CC25A1_errno@h DB 01H __890838BD_vcruntime_string@h DB 01H __E4C945B4_corecrt_memcpy_s@h DB 01H __8EAFF484_corecrt_memory@h DB 01H __6490AEC5_corecrt_wstring@h DB 01H __E8295E1E_string@h DB 01H __7FCB5136_guiddef@h DB 01H __FF8A9E11_pshpack4@h DB 01H __D5438902_poppack@h DB 01H __FB07E2A3_pshpack2@h DB 01H __F6906775_pshpack8@h DB 01H __F9415CFA_pshpack1@h DB 01H __E58C6F1C_apiset@h DB 01H __A5C52262_ktmtypes@h DB 01H __FBBA8F9D_winnt@h DB 01H __A32D3D2C_minwindef@h DB 01H __7D798299_windef@h DB 01H __9AE108E9_apisetcconv@h DB 01H __9CE53D2C_minwinbase@h DB 01H __5D0AA210_apiquery2@h DB 01H __4DD4E726_processenv@h DB 01H __3575CC96_fileapi@h DB 01H __8EA220E6_fileapifromapp@h DB 01H __BF9B31FE_debugapi@h DB 01H __C3AFE134_utilapiset@h DB 01H __76F69E51_handleapi@h DB 01H __7E63D784_errhandlingapi@h DB 01H __FFA7003C_fibersapi@h DB 01H __8971CECF_namedpipeapi@h DB 01H __46C9D8A6_profileapi@h DB 01H __98D4F0A3_heapapi@h DB 01H __50EF2A88_ioapiset@h DB 01H __92EA1464_synchapi@h DB 01H __A53D8AED_interlockedapi@h DB 01H __B506CAAF_processthreadsapi@h DB 01H __FF735694_sysinfoapi@h DB 01H __29589789_memoryapi@h DB 01H __E9C7A663_enclaveapi@h DB 01H __D035F9F7_threadpoollegacyapiset@h DB 01H __C899130C_threadpoolapiset@h DB 01H __E0441EE7_jobapi@h DB 01H __CEF86838_jobapi2@h DB 01H __35AC6B9A_wow64apiset@h DB 01H __C8AE41A5_libloaderapi@h DB 01H __CC9E232D_securitybaseapi@h DB 01H __C9D0C9B8_namespaceapi@h DB 01H __30FF9CAD_systemtopologyapi@h DB 01H __4D358795_processtopologyapi@h DB 01H __40446D10_securityappcontainer@h DB 01H __3A952EDF_realtimeapiset@h DB 01H __F4865F4B_winerror@h DB 01H __53C1BD93_timezoneapi@h DB 01H __1FFBEDBF_winbase@h DB 01H __43D3FA34_wingdi@h DB 01H __D24A7391_tvout@h DB 01H __7713A6C8_winuser@h DB 01H __0B345F71_datetimeapi@h DB 01H __9AC6960C_winnls@h DB 01H __973A40A8_stringapiset@h DB 01H __CC46FEE2_wincontypes@h DB 01H __97D70BE1_consoleapi@h DB 01H __27EC5E18_consoleapi2@h DB 01H __262E342F_consoleapi3@h DB 01H __641DCD70_wincon@h DB 01H __5A96C7A7_verrsrc@h DB 01H __B69C6FF2_winver@h DB 01H __7AEB8C37_reason@h DB 01H __59F1A8A9_winreg@h DB 01H __EE0E2B7F_wnnc@h DB 01H __DCDB7054_winnetwk@h DB 01H __81DDEDE3_stralign@h DB 01H __2134D1B4_winsvc@h DB 01H __11C07376_mcx@h DB 01H __577CE3E7_ime_cmodes@h DB 01H __1E72C31E_imm@h DB 01H __E15BF856_windows@h DB 01H __8FC206A7_ssc_internal@h DB 01H __44420885_corecrt_stdio_config@h DB 01H __AB601D8D_corecrt_wstdio@h DB 01H __C1EC35D3_stdio@h DB 01H __13F5961F_stddef@h DB 01H __FD6DBD68_corecrt_search@h DB 01H __E2E33A61_corecrt_wstdlib@h DB 01H __26263363_limits@h DB 01H __6E5ACABA_stdlib@h DB 01H __9049550C_stb_image@h DB 01H __98501D5C_stdint@h DB 01H __264E89B8_khrplatform@h DB 01H __799FCA13_gl@h DB 01H __A57296D0_wgl@h DB 01H __417F438F_glfw3@h DB 01H __8F82BB96_emmintrin@h DB 01H __5023D31F_pmmintrin@h DB 01H __E0FAA09D_tmmintrin@h DB 01H __C9C1B51E_smmintrin@h DB 01H __ACA33CD2_nmmintrin@h DB 01H __7918C69C_wmmintrin@h DB 01H __B28C8B9B_zmmintrin@h DB 01H __85982951_immintrin@h DB 01H __19139D6C_assert@h DB 01H __0C16F932_StgSharpC@h DB 01H __B2F9F159_intrin0@inl@h DB 01H __0833F55F_setjmp@h DB 01H __3F5BC814_ammintrin@h DB 01H __2E054928_intrin@h DB 01H __5A8332CE_isa_availability@h DB 01H __EB6C2FE1_ssc_intrinsic@h DB 01H __58B0E32D_mat3@c DB 01H msvcjmc ENDS PUBLIC addmatrix3_sse PUBLIC addmatrix3_avx PUBLIC addmatrix3_512 PUBLIC submatrix3_sse PUBLIC submatrix3_avx PUBLIC submatrix3_512 PUBLIC transpose32 PUBLIC transpose33 PUBLIC transpose34 PUBLIC det_mat3 PUBLIC det_mat3_internal PUBLIC __JustMyCode_Default EXTRN _RTC_CheckStackVars:PROC EXTRN _RTC_InitBase:PROC EXTRN _RTC_Shutdown:PROC EXTRN __CheckForDebuggerJustMyCode:PROC EXTRN _fltused:DWORD ; COMDAT pdata pdata SEGMENT $pdata$addmatrix3_sse DD imagerel $LN3 DD imagerel $LN3+355 DD imagerel $unwind$addmatrix3_sse pdata ENDS ; COMDAT pdata pdata SEGMENT $pdata$addmatrix3_avx DD imagerel $LN3 DD imagerel $LN3+240 DD imagerel $unwind$addmatrix3_avx pdata ENDS ; COMDAT pdata pdata SEGMENT $pdata$addmatrix3_512 DD imagerel $LN3 DD imagerel $LN3+133 DD imagerel $unwind$addmatrix3_512 pdata ENDS ; COMDAT pdata pdata SEGMENT $pdata$submatrix3_sse DD imagerel $LN3 DD imagerel $LN3+355 DD imagerel $unwind$submatrix3_sse pdata ENDS ; COMDAT pdata pdata SEGMENT $pdata$submatrix3_avx DD imagerel $LN3 DD imagerel $LN3+240 DD imagerel $unwind$submatrix3_avx pdata ENDS ; COMDAT pdata pdata SEGMENT $pdata$submatrix3_512 DD imagerel $LN3 DD imagerel $LN3+133 DD imagerel $unwind$submatrix3_512 pdata ENDS ; COMDAT pdata pdata SEGMENT $pdata$transpose32 DD imagerel $LN3 DD imagerel $LN3+205 DD imagerel $unwind$transpose32 pdata ENDS ; COMDAT pdata pdata SEGMENT $pdata$transpose33 DD imagerel $LN3 DD imagerel $LN3+340 DD imagerel $unwind$transpose33 pdata ENDS ; COMDAT pdata pdata SEGMENT $pdata$transpose34 DD imagerel $LN3 DD imagerel $LN3+372 DD imagerel $unwind$transpose34 pdata ENDS ; COMDAT pdata pdata SEGMENT $pdata$det_mat3 DD imagerel $LN3 DD imagerel $LN3+154 DD imagerel $unwind$det_mat3 pdata ENDS ; COMDAT pdata pdata SEGMENT $pdata$det_mat3_internal DD imagerel $LN3 DD imagerel $LN3+371 DD imagerel $unwind$det_mat3_internal pdata ENDS ; COMDAT rtc$TMZ rtc$TMZ SEGMENT _RTC_Shutdown.rtc$TMZ DQ FLAT:_RTC_Shutdown rtc$TMZ ENDS ; COMDAT rtc$IMZ rtc$IMZ SEGMENT _RTC_InitBase.rtc$IMZ DQ FLAT:_RTC_InitBase rtc$IMZ ENDS ; COMDAT xdata xdata SEGMENT $unwind$det_mat3_internal DD 035053601H DD 0118331dH DD 070110049H DD 05010H xdata ENDS ; COMDAT CONST CONST SEGMENT det_mat3_internal$rtcName$0 DB 072H DB 065H DB 074H DB 00H ORG $+12 det_mat3_internal$rtcVarDesc DD 0160H DD 010H DQ FLAT:det_mat3_internal$rtcName$0 ORG $+48 det_mat3_internal$rtcFrameData DD 01H DD 00H DQ FLAT:det_mat3_internal$rtcVarDesc CONST ENDS ; COMDAT xdata xdata SEGMENT $unwind$det_mat3 DD 035051801H DD 01133318H DD 0700c0031H DD 0500bH xdata ENDS ; COMDAT xdata xdata SEGMENT $unwind$transpose34 DD 025051801H DD 01132318H DD 0700c0035H DD 0500bH xdata ENDS ; COMDAT xdata xdata SEGMENT $unwind$transpose33 DD 025051801H DD 01132318H DD 0700c0035H DD 0500bH xdata ENDS ; COMDAT xdata xdata SEGMENT $unwind$transpose32 DD 025051801H DD 01132318H DD 0700c0029H DD 0500bH xdata ENDS ; COMDAT xdata xdata SEGMENT $unwind$submatrix3_512 DD 02d062801H DD 011a231fH DD 070130036H DD 0d0115012H xdata ENDS ; COMDAT xdata xdata SEGMENT $unwind$submatrix3_avx DD 02d062801H DD 011a231fH DD 070130030H DD 0d0115012H xdata ENDS ; COMDAT xdata xdata SEGMENT $unwind$submatrix3_sse DD 025051d01H DD 0118231dH DD 07011002fH DD 05010H xdata ENDS ; COMDAT xdata xdata SEGMENT $unwind$addmatrix3_512 DD 02d062801H DD 011a231fH DD 070130036H DD 0d0115012H xdata ENDS ; COMDAT xdata xdata SEGMENT $unwind$addmatrix3_avx DD 02d062801H DD 011a231fH DD 070130030H DD 0d0115012H xdata ENDS ; COMDAT xdata xdata SEGMENT $unwind$addmatrix3_sse DD 025051d01H DD 0118231dH DD 07011002fH DD 05010H 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: /Odtp /RTCsu /ZI ; File D:\NitloadIndustry\研究项目\1-Flagship\TH2020\ProjectFile\内核源代码\StgSharp.C\mat3.c ; COMDAT det_mat3_internal _TEXT SEGMENT addc1$ = 16 addc2$ = 64 subc1$ = 112 subc2$ = 160 cache$ = 208 sub$ = 256 ret$ = 304 c0$ = 560 c1$ = 568 c2$ = 576 det_mat3_internal PROC ; COMDAT ; 45 : { $LN3: 00000 4c 89 44 24 18 mov QWORD PTR [rsp+24], r8 00005 48 89 54 24 10 mov QWORD PTR [rsp+16], rdx 0000a 48 89 4c 24 08 mov QWORD PTR [rsp+8], rcx 0000f 55 push rbp 00010 57 push rdi 00011 48 81 ec 48 02 00 00 sub rsp, 584 ; 00000248H 00018 48 8d 6c 24 30 lea rbp, QWORD PTR [rsp+48] 0001d 48 8d 7c 24 30 lea rdi, QWORD PTR [rsp+48] 00022 b9 56 00 00 00 mov ecx, 86 ; 00000056H 00027 b8 cc cc cc cc mov eax, -858993460 ; ccccccccH 0002c f3 ab rep stosd 0002e 48 8b 8c 24 68 02 00 00 mov rcx, QWORD PTR [rsp+616] 00036 48 8d 0d 00 00 00 00 lea rcx, OFFSET FLAT:__58B0E32D_mat3@c 0003d e8 00 00 00 00 call __CheckForDebuggerJustMyCode 00042 90 npad 1 ; 46 : //let adding row aligned ; 47 : __m128 addc1 = _mm_shuffle_ps(c1, c1, _MM_SHUFFLE(3, 0, 2, 1)); 00043 48 8b 85 38 02 00 00 mov rax, QWORD PTR c1$[rbp] 0004a 48 8b 8d 38 02 00 00 mov rcx, QWORD PTR c1$[rbp] 00051 0f 10 00 movups xmm0, XMMWORD PTR [rax] 00054 0f c6 01 c9 shufps xmm0, XMMWORD PTR [rcx], 201 ; 000000c9H 00058 0f 29 45 10 movaps XMMWORD PTR addc1$[rbp], xmm0 ; 48 : __m128 addc2 = _mm_shuffle_ps(c2, c2, _MM_SHUFFLE(3, 1, 0, 2)); 0005c 48 8b 85 40 02 00 00 mov rax, QWORD PTR c2$[rbp] 00063 48 8b 8d 40 02 00 00 mov rcx, QWORD PTR c2$[rbp] 0006a 0f 10 00 movups xmm0, XMMWORD PTR [rax] 0006d 0f c6 01 d2 shufps xmm0, XMMWORD PTR [rcx], 210 ; 000000d2H 00071 0f 29 45 40 movaps XMMWORD PTR addc2$[rbp], xmm0 ; 49 : ; 50 : //let sub row aligned ; 51 : __m128 subc1 = _mm_shuffle_ps(c1, c1, _MM_SHUFFLE(3, 1, 0, 2)); 00075 48 8b 85 38 02 00 00 mov rax, QWORD PTR c1$[rbp] 0007c 48 8b 8d 38 02 00 00 mov rcx, QWORD PTR c1$[rbp] 00083 0f 10 00 movups xmm0, XMMWORD PTR [rax] 00086 0f c6 01 d2 shufps xmm0, XMMWORD PTR [rcx], 210 ; 000000d2H 0008a 0f 29 45 70 movaps XMMWORD PTR subc1$[rbp], xmm0 ; 52 : __m128 subc2 = _mm_shuffle_ps(c2, c2, _MM_SHUFFLE(3, 0, 2, 1)); 0008e 48 8b 85 40 02 00 00 mov rax, QWORD PTR c2$[rbp] 00095 48 8b 8d 40 02 00 00 mov rcx, QWORD PTR c2$[rbp] 0009c 0f 10 00 movups xmm0, XMMWORD PTR [rax] 0009f 0f c6 01 c9 shufps xmm0, XMMWORD PTR [rcx], 201 ; 000000c9H 000a3 0f 29 85 a0 00 00 00 movaps XMMWORD PTR subc2$[rbp], xmm0 ; 53 : ; 54 : //multple all add row ; 55 : __m128 cache = _mm_mul_ps(c0, addc1); 000aa 48 8b 85 30 02 00 00 mov rax, QWORD PTR c0$[rbp] 000b1 0f 10 00 movups xmm0, XMMWORD PTR [rax] 000b4 0f 59 45 10 mulps xmm0, XMMWORD PTR addc1$[rbp] 000b8 0f 29 85 d0 00 00 00 movaps XMMWORD PTR cache$[rbp], xmm0 ; 56 : cache = _mm_mul_ps(cache, addc2); 000bf 0f 28 85 d0 00 00 00 movaps xmm0, XMMWORD PTR cache$[rbp] 000c6 0f 59 45 40 mulps xmm0, XMMWORD PTR addc2$[rbp] 000ca 0f 29 85 d0 00 00 00 movaps XMMWORD PTR cache$[rbp], xmm0 ; 57 : ; 58 : //multiple all sub row ; 59 : __m128 sub = _mm_mul_ps(c0, subc1); 000d1 48 8b 85 30 02 00 00 mov rax, QWORD PTR c0$[rbp] 000d8 0f 10 00 movups xmm0, XMMWORD PTR [rax] 000db 0f 59 45 70 mulps xmm0, XMMWORD PTR subc1$[rbp] 000df 0f 29 85 00 01 00 00 movaps XMMWORD PTR sub$[rbp], xmm0 ; 60 : sub = _mm_mul_ps(sub, subc2); 000e6 0f 28 85 00 01 00 00 movaps xmm0, XMMWORD PTR sub$[rbp] 000ed 0f 59 85 a0 00 00 00 mulps xmm0, XMMWORD PTR subc2$[rbp] 000f4 0f 29 85 00 01 00 00 movaps XMMWORD PTR sub$[rbp], xmm0 ; 61 : ; 62 : //main-corner sub sub-corner ; 63 : cache = _mm_sub_ps(cache, sub); 000fb 0f 28 85 d0 00 00 00 movaps xmm0, XMMWORD PTR cache$[rbp] 00102 0f 5c 85 00 01 00 00 subps xmm0, XMMWORD PTR sub$[rbp] 00109 0f 29 85 d0 00 00 00 movaps XMMWORD PTR cache$[rbp], xmm0 ; 64 : ; 65 : __m128 ret = _mm_hadd_ps(cache, cache); //element 1 add element 2 00110 0f 28 85 d0 00 00 00 movaps xmm0, XMMWORD PTR cache$[rbp] 00117 f2 0f 7c 85 d0 00 00 00 haddps xmm0, XMMWORD PTR cache$[rbp] 0011f 0f 29 85 30 01 00 00 movaps XMMWORD PTR ret$[rbp], xmm0 ; 66 : ret = _mm_add_ps(ret, cache); //(e1 add e2) add element 3 00126 0f 28 85 30 01 00 00 movaps xmm0, XMMWORD PTR ret$[rbp] 0012d 0f 58 85 d0 00 00 00 addps xmm0, XMMWORD PTR cache$[rbp] 00134 0f 29 85 30 01 00 00 movaps XMMWORD PTR ret$[rbp], xmm0 ; 67 : ; 68 : return ret.m128_f32[2]; 0013b b8 04 00 00 00 mov eax, 4 00140 48 6b c0 02 imul rax, rax, 2 00144 f3 0f 10 84 05 30 01 00 00 movss xmm0, DWORD PTR ret$[rbp+rax] ; 69 : } 0014d f3 0f 7f 44 24 20 movdqu XMMWORD PTR [rsp+32], xmm0 00153 48 8d 4d d0 lea rcx, QWORD PTR [rbp-48] 00157 48 8d 15 00 00 00 00 lea rdx, OFFSET FLAT:det_mat3_internal$rtcFrameData 0015e e8 00 00 00 00 call _RTC_CheckStackVars 00163 f3 0f 6f 44 24 20 movdqu xmm0, XMMWORD PTR [rsp+32] 00169 48 8d a5 18 02 00 00 lea rsp, QWORD PTR [rbp+536] 00170 5f pop rdi 00171 5d pop rbp 00172 c3 ret 0 det_mat3_internal ENDP _TEXT ENDS ; Function compile flags: /Odtp /RTCsu /ZI ; File D:\NitloadIndustry\研究项目\1-Flagship\TH2020\ProjectFile\内核源代码\StgSharp.C\mat3.c ; COMDAT det_mat3 _TEXT SEGMENT $T1 = 208 $T2 = 256 $T3 = 304 source$ = 368 transpose$ = 376 det_mat3 PROC ; COMDAT ; 72 : { $LN3: 00000 48 89 54 24 10 mov QWORD PTR [rsp+16], rdx 00005 48 89 4c 24 08 mov QWORD PTR [rsp+8], rcx 0000a 55 push rbp 0000b 57 push rdi 0000c 48 81 ec 88 01 00 00 sub rsp, 392 ; 00000188H 00013 48 8d 6c 24 30 lea rbp, QWORD PTR [rsp+48] 00018 48 8d 0d 00 00 00 00 lea rcx, OFFSET FLAT:__58B0E32D_mat3@c 0001f e8 00 00 00 00 call __CheckForDebuggerJustMyCode 00024 90 npad 1 ; 73 : return det_mat3_internal(source->column[0], source->column[1], source->column[2]); 00025 b8 10 00 00 00 mov eax, 16 0002a 48 6b c0 02 imul rax, rax, 2 0002e 48 8b 8d 70 01 00 00 mov rcx, QWORD PTR source$[rbp] 00035 0f 10 04 01 movups xmm0, XMMWORD PTR [rcx+rax] 00039 0f 11 85 30 01 00 00 movups XMMWORD PTR $T3[rbp], xmm0 00040 b8 10 00 00 00 mov eax, 16 00045 48 6b c0 01 imul rax, rax, 1 00049 48 8b 8d 70 01 00 00 mov rcx, QWORD PTR source$[rbp] 00050 0f 10 04 01 movups xmm0, XMMWORD PTR [rcx+rax] 00054 0f 11 85 00 01 00 00 movups XMMWORD PTR $T2[rbp], xmm0 0005b b8 10 00 00 00 mov eax, 16 00060 48 6b c0 00 imul rax, rax, 0 00064 48 8b 8d 70 01 00 00 mov rcx, QWORD PTR source$[rbp] 0006b 0f 10 04 01 movups xmm0, XMMWORD PTR [rcx+rax] 0006f 0f 11 85 d0 00 00 00 movups XMMWORD PTR $T1[rbp], xmm0 00076 4c 8d 85 30 01 00 00 lea r8, QWORD PTR $T3[rbp] 0007d 48 8d 95 00 01 00 00 lea rdx, QWORD PTR $T2[rbp] 00084 48 8d 8d d0 00 00 00 lea rcx, QWORD PTR $T1[rbp] 0008b e8 00 00 00 00 call det_mat3_internal ; 74 : } 00090 48 8d a5 58 01 00 00 lea rsp, QWORD PTR [rbp+344] 00097 5f pop rdi 00098 5d pop rbp 00099 c3 ret 0 det_mat3 ENDP _TEXT ENDS ; Function compile flags: /Odtp /RTCsu /ZI ; File D:\NitloadIndustry\研究项目\1-Flagship\TH2020\ProjectFile\内核源代码\StgSharp.C\mat3.c ; COMDAT transpose34 _TEXT SEGMENT t0$ = 16 t1$ = 64 t2$ = 112 t3$ = 160 source$ = 416 target$ = 424 transpose34 PROC ; COMDAT ; 30 : { $LN3: 00000 48 89 54 24 10 mov QWORD PTR [rsp+16], rdx 00005 48 89 4c 24 08 mov QWORD PTR [rsp+8], rcx 0000a 55 push rbp 0000b 57 push rdi 0000c 48 81 ec a8 01 00 00 sub rsp, 424 ; 000001a8H 00013 48 8d 6c 24 20 lea rbp, QWORD PTR [rsp+32] 00018 48 8d 0d 00 00 00 00 lea rcx, OFFSET FLAT:__58B0E32D_mat3@c 0001f e8 00 00 00 00 call __CheckForDebuggerJustMyCode 00024 90 npad 1 ; 31 : __m128 t0 = _mm_shuffle_ps(ALIGN(source->column[0]), ALIGN(source->column[1]), 00025 b8 10 00 00 00 mov eax, 16 0002a 48 6b c0 01 imul rax, rax, 1 0002e 48 8b 8d a0 01 00 00 mov rcx, QWORD PTR source$[rbp] 00035 48 03 c8 add rcx, rax 00038 48 8b c1 mov rax, rcx 0003b 0f 10 00 movups xmm0, XMMWORD PTR [rax] 0003e b8 10 00 00 00 mov eax, 16 00043 48 6b c0 00 imul rax, rax, 0 00047 48 8b 8d a0 01 00 00 mov rcx, QWORD PTR source$[rbp] 0004e 48 03 c8 add rcx, rax 00051 48 8b c1 mov rax, rcx 00054 0f 10 08 movups xmm1, XMMWORD PTR [rax] 00057 0f c6 c8 44 shufps xmm1, xmm0, 68 ; 00000044H 0005b 0f 28 c1 movaps xmm0, xmm1 0005e 0f 29 45 10 movaps XMMWORD PTR t0$[rbp], xmm0 ; 32 : _MM_SHUFFLE(1, 0, 1, 0)); ; 33 : __m128 t1 = _mm_shuffle_ps(ALIGN(source->column[0]), ALIGN(source->column[1]), 00062 b8 10 00 00 00 mov eax, 16 00067 48 6b c0 01 imul rax, rax, 1 0006b 48 8b 8d a0 01 00 00 mov rcx, QWORD PTR source$[rbp] 00072 48 03 c8 add rcx, rax 00075 48 8b c1 mov rax, rcx 00078 0f 10 00 movups xmm0, XMMWORD PTR [rax] 0007b b8 10 00 00 00 mov eax, 16 00080 48 6b c0 00 imul rax, rax, 0 00084 48 8b 8d a0 01 00 00 mov rcx, QWORD PTR source$[rbp] 0008b 48 03 c8 add rcx, rax 0008e 48 8b c1 mov rax, rcx 00091 0f 10 08 movups xmm1, XMMWORD PTR [rax] 00094 0f c6 c8 ee shufps xmm1, xmm0, 238 ; 000000eeH 00098 0f 28 c1 movaps xmm0, xmm1 0009b 0f 29 45 40 movaps XMMWORD PTR t1$[rbp], xmm0 ; 34 : _MM_SHUFFLE(3, 2, 3, 2)); ; 35 : __m128 t2 = _mm_shuffle_ps(ALIGN(source->column[2]), zero_vec, _MM_SHUFFLE(1, 0, 1, 0)); 0009f 0f 57 c0 xorps xmm0, xmm0 000a2 b8 10 00 00 00 mov eax, 16 000a7 48 6b c0 02 imul rax, rax, 2 000ab 48 8b 8d a0 01 00 00 mov rcx, QWORD PTR source$[rbp] 000b2 48 03 c8 add rcx, rax 000b5 48 8b c1 mov rax, rcx 000b8 0f 10 08 movups xmm1, XMMWORD PTR [rax] 000bb 0f c6 c8 44 shufps xmm1, xmm0, 68 ; 00000044H 000bf 0f 28 c1 movaps xmm0, xmm1 000c2 0f 29 45 70 movaps XMMWORD PTR t2$[rbp], xmm0 ; 36 : __m128 t3 = _mm_shuffle_ps(ALIGN(source->column[2]), zero_vec, _MM_SHUFFLE(3, 2, 3, 2)); 000c6 0f 57 c0 xorps xmm0, xmm0 000c9 b8 10 00 00 00 mov eax, 16 000ce 48 6b c0 02 imul rax, rax, 2 000d2 48 8b 8d a0 01 00 00 mov rcx, QWORD PTR source$[rbp] 000d9 48 03 c8 add rcx, rax 000dc 48 8b c1 mov rax, rcx 000df 0f 10 08 movups xmm1, XMMWORD PTR [rax] 000e2 0f c6 c8 ee shufps xmm1, xmm0, 238 ; 000000eeH 000e6 0f 28 c1 movaps xmm0, xmm1 000e9 0f 29 85 a0 00 00 00 movaps XMMWORD PTR t3$[rbp], xmm0 ; 37 : ; 38 : target->column[0] = _mm_shuffle_ps(t0, t2, _MM_SHUFFLE(2, 0, 2, 0)); 000f0 0f 28 45 10 movaps xmm0, XMMWORD PTR t0$[rbp] 000f4 0f c6 45 70 88 shufps xmm0, XMMWORD PTR t2$[rbp], 136 ; 00000088H 000f9 b8 10 00 00 00 mov eax, 16 000fe 48 6b c0 00 imul rax, rax, 0 00102 48 8b 8d a8 01 00 00 mov rcx, QWORD PTR target$[rbp] 00109 0f 11 04 01 movups XMMWORD PTR [rcx+rax], xmm0 ; 39 : target->column[1] = _mm_shuffle_ps(t0, t2, _MM_SHUFFLE(3, 1, 3, 1)); 0010d 0f 28 45 10 movaps xmm0, XMMWORD PTR t0$[rbp] 00111 0f c6 45 70 dd shufps xmm0, XMMWORD PTR t2$[rbp], 221 ; 000000ddH 00116 b8 10 00 00 00 mov eax, 16 0011b 48 6b c0 01 imul rax, rax, 1 0011f 48 8b 8d a8 01 00 00 mov rcx, QWORD PTR target$[rbp] 00126 0f 11 04 01 movups XMMWORD PTR [rcx+rax], xmm0 ; 40 : target->column[2] = _mm_shuffle_ps(t1, t3, _MM_SHUFFLE(2, 0, 2, 0)); 0012a 0f 28 45 40 movaps xmm0, XMMWORD PTR t1$[rbp] 0012e 0f c6 85 a0 00 00 00 88 shufps xmm0, XMMWORD PTR t3$[rbp], 136 ; 00000088H 00136 b8 10 00 00 00 mov eax, 16 0013b 48 6b c0 02 imul rax, rax, 2 0013f 48 8b 8d a8 01 00 00 mov rcx, QWORD PTR target$[rbp] 00146 0f 11 04 01 movups XMMWORD PTR [rcx+rax], xmm0 ; 41 : target->column[3] = _mm_shuffle_ps(t1, t3, _MM_SHUFFLE(3, 1, 3, 1)); 0014a 0f 28 45 40 movaps xmm0, XMMWORD PTR t1$[rbp] 0014e 0f c6 85 a0 00 00 00 dd shufps xmm0, XMMWORD PTR t3$[rbp], 221 ; 000000ddH 00156 b8 10 00 00 00 mov eax, 16 0015b 48 6b c0 03 imul rax, rax, 3 0015f 48 8b 8d a8 01 00 00 mov rcx, QWORD PTR target$[rbp] 00166 0f 11 04 01 movups XMMWORD PTR [rcx+rax], xmm0 ; 42 : } 0016a 48 8d a5 88 01 00 00 lea rsp, QWORD PTR [rbp+392] 00171 5f pop rdi 00172 5d pop rbp 00173 c3 ret 0 transpose34 ENDP _TEXT ENDS ; Function compile flags: /Odtp /RTCsu /ZI ; File D:\NitloadIndustry\研究项目\1-Flagship\TH2020\ProjectFile\内核源代码\StgSharp.C\mat3.c ; COMDAT transpose33 _TEXT SEGMENT t0$ = 16 t1$ = 64 t2$ = 112 t3$ = 160 source$ = 416 target$ = 424 transpose33 PROC ; COMDAT ; 16 : { $LN3: 00000 48 89 54 24 10 mov QWORD PTR [rsp+16], rdx 00005 48 89 4c 24 08 mov QWORD PTR [rsp+8], rcx 0000a 55 push rbp 0000b 57 push rdi 0000c 48 81 ec a8 01 00 00 sub rsp, 424 ; 000001a8H 00013 48 8d 6c 24 20 lea rbp, QWORD PTR [rsp+32] 00018 48 8d 0d 00 00 00 00 lea rcx, OFFSET FLAT:__58B0E32D_mat3@c 0001f e8 00 00 00 00 call __CheckForDebuggerJustMyCode 00024 90 npad 1 ; 17 : __m128 t0 = _mm_shuffle_ps(ALIGN(source->column[0]), ALIGN(source->column[1]), 00025 b8 10 00 00 00 mov eax, 16 0002a 48 6b c0 01 imul rax, rax, 1 0002e 48 8b 8d a0 01 00 00 mov rcx, QWORD PTR source$[rbp] 00035 48 03 c8 add rcx, rax 00038 48 8b c1 mov rax, rcx 0003b 0f 10 00 movups xmm0, XMMWORD PTR [rax] 0003e b8 10 00 00 00 mov eax, 16 00043 48 6b c0 00 imul rax, rax, 0 00047 48 8b 8d a0 01 00 00 mov rcx, QWORD PTR source$[rbp] 0004e 48 03 c8 add rcx, rax 00051 48 8b c1 mov rax, rcx 00054 0f 10 08 movups xmm1, XMMWORD PTR [rax] 00057 0f c6 c8 44 shufps xmm1, xmm0, 68 ; 00000044H 0005b 0f 28 c1 movaps xmm0, xmm1 0005e 0f 29 45 10 movaps XMMWORD PTR t0$[rbp], xmm0 ; 18 : _MM_SHUFFLE(1, 0, 1, 0)); ; 19 : __m128 t1 = _mm_shuffle_ps(ALIGN(source->column[0]), ALIGN(source->column[1]), 00062 b8 10 00 00 00 mov eax, 16 00067 48 6b c0 01 imul rax, rax, 1 0006b 48 8b 8d a0 01 00 00 mov rcx, QWORD PTR source$[rbp] 00072 48 03 c8 add rcx, rax 00075 48 8b c1 mov rax, rcx 00078 0f 10 00 movups xmm0, XMMWORD PTR [rax] 0007b b8 10 00 00 00 mov eax, 16 00080 48 6b c0 00 imul rax, rax, 0 00084 48 8b 8d a0 01 00 00 mov rcx, QWORD PTR source$[rbp] 0008b 48 03 c8 add rcx, rax 0008e 48 8b c1 mov rax, rcx 00091 0f 10 08 movups xmm1, XMMWORD PTR [rax] 00094 0f c6 c8 ee shufps xmm1, xmm0, 238 ; 000000eeH 00098 0f 28 c1 movaps xmm0, xmm1 0009b 0f 29 45 40 movaps XMMWORD PTR t1$[rbp], xmm0 ; 20 : _MM_SHUFFLE(3, 2, 3, 2)); ; 21 : __m128 t2 = _mm_shuffle_ps(ALIGN(source->column[2]), zero_vec, _MM_SHUFFLE(1, 0, 1, 0)); 0009f 0f 57 c0 xorps xmm0, xmm0 000a2 b8 10 00 00 00 mov eax, 16 000a7 48 6b c0 02 imul rax, rax, 2 000ab 48 8b 8d a0 01 00 00 mov rcx, QWORD PTR source$[rbp] 000b2 48 03 c8 add rcx, rax 000b5 48 8b c1 mov rax, rcx 000b8 0f 10 08 movups xmm1, XMMWORD PTR [rax] 000bb 0f c6 c8 44 shufps xmm1, xmm0, 68 ; 00000044H 000bf 0f 28 c1 movaps xmm0, xmm1 000c2 0f 29 45 70 movaps XMMWORD PTR t2$[rbp], xmm0 ; 22 : __m128 t3 = _mm_shuffle_ps(ALIGN(source->column[2]), zero_vec, _MM_SHUFFLE(3, 2, 3, 2)); 000c6 0f 57 c0 xorps xmm0, xmm0 000c9 b8 10 00 00 00 mov eax, 16 000ce 48 6b c0 02 imul rax, rax, 2 000d2 48 8b 8d a0 01 00 00 mov rcx, QWORD PTR source$[rbp] 000d9 48 03 c8 add rcx, rax 000dc 48 8b c1 mov rax, rcx 000df 0f 10 08 movups xmm1, XMMWORD PTR [rax] 000e2 0f c6 c8 ee shufps xmm1, xmm0, 238 ; 000000eeH 000e6 0f 28 c1 movaps xmm0, xmm1 000e9 0f 29 85 a0 00 00 00 movaps XMMWORD PTR t3$[rbp], xmm0 ; 23 : ; 24 : target->column[0] = _mm_shuffle_ps(t0, t2, _MM_SHUFFLE(2, 0, 2, 0)); 000f0 0f 28 45 10 movaps xmm0, XMMWORD PTR t0$[rbp] 000f4 0f c6 45 70 88 shufps xmm0, XMMWORD PTR t2$[rbp], 136 ; 00000088H 000f9 b8 10 00 00 00 mov eax, 16 000fe 48 6b c0 00 imul rax, rax, 0 00102 48 8b 8d a8 01 00 00 mov rcx, QWORD PTR target$[rbp] 00109 0f 11 04 01 movups XMMWORD PTR [rcx+rax], xmm0 ; 25 : target->column[1] = _mm_shuffle_ps(t0, t2, _MM_SHUFFLE(3, 1, 3, 1)); 0010d 0f 28 45 10 movaps xmm0, XMMWORD PTR t0$[rbp] 00111 0f c6 45 70 dd shufps xmm0, XMMWORD PTR t2$[rbp], 221 ; 000000ddH 00116 b8 10 00 00 00 mov eax, 16 0011b 48 6b c0 01 imul rax, rax, 1 0011f 48 8b 8d a8 01 00 00 mov rcx, QWORD PTR target$[rbp] 00126 0f 11 04 01 movups XMMWORD PTR [rcx+rax], xmm0 ; 26 : target->column[2] = _mm_shuffle_ps(t1, t3, _MM_SHUFFLE(2, 0, 2, 0)); 0012a 0f 28 45 40 movaps xmm0, XMMWORD PTR t1$[rbp] 0012e 0f c6 85 a0 00 00 00 88 shufps xmm0, XMMWORD PTR t3$[rbp], 136 ; 00000088H 00136 b8 10 00 00 00 mov eax, 16 0013b 48 6b c0 02 imul rax, rax, 2 0013f 48 8b 8d a8 01 00 00 mov rcx, QWORD PTR target$[rbp] 00146 0f 11 04 01 movups XMMWORD PTR [rcx+rax], xmm0 ; 27 : } 0014a 48 8d a5 88 01 00 00 lea rsp, QWORD PTR [rbp+392] 00151 5f pop rdi 00152 5d pop rbp 00153 c3 ret 0 transpose33 ENDP _TEXT ENDS ; Function compile flags: /Odtp /RTCsu /ZI ; File D:\NitloadIndustry\研究项目\1-Flagship\TH2020\ProjectFile\内核源代码\StgSharp.C\mat3.c ; COMDAT transpose32 _TEXT SEGMENT t0$ = 16 t2$ = 64 source$ = 320 target$ = 328 transpose32 PROC ; COMDAT ; 6 : { $LN3: 00000 48 89 54 24 10 mov QWORD PTR [rsp+16], rdx 00005 48 89 4c 24 08 mov QWORD PTR [rsp+8], rcx 0000a 55 push rbp 0000b 57 push rdi 0000c 48 81 ec 48 01 00 00 sub rsp, 328 ; 00000148H 00013 48 8d 6c 24 20 lea rbp, QWORD PTR [rsp+32] 00018 48 8d 0d 00 00 00 00 lea rcx, OFFSET FLAT:__58B0E32D_mat3@c 0001f e8 00 00 00 00 call __CheckForDebuggerJustMyCode 00024 90 npad 1 ; 7 : __m128 t0 = _mm_shuffle_ps(ALIGN(source->column[0]), ALIGN(source->column[1]), 00025 b8 10 00 00 00 mov eax, 16 0002a 48 6b c0 01 imul rax, rax, 1 0002e 48 8b 8d 40 01 00 00 mov rcx, QWORD PTR source$[rbp] 00035 48 03 c8 add rcx, rax 00038 48 8b c1 mov rax, rcx 0003b 0f 10 00 movups xmm0, XMMWORD PTR [rax] 0003e b8 10 00 00 00 mov eax, 16 00043 48 6b c0 00 imul rax, rax, 0 00047 48 8b 8d 40 01 00 00 mov rcx, QWORD PTR source$[rbp] 0004e 48 03 c8 add rcx, rax 00051 48 8b c1 mov rax, rcx 00054 0f 10 08 movups xmm1, XMMWORD PTR [rax] 00057 0f c6 c8 44 shufps xmm1, xmm0, 68 ; 00000044H 0005b 0f 28 c1 movaps xmm0, xmm1 0005e 0f 29 45 10 movaps XMMWORD PTR t0$[rbp], xmm0 ; 8 : _MM_SHUFFLE(1, 0, 1, 0)); ; 9 : __m128 t2 = _mm_shuffle_ps(ALIGN(source->column[2]), zero_vec, _MM_SHUFFLE(1, 0, 1, 0)); 00062 0f 57 c0 xorps xmm0, xmm0 00065 b8 10 00 00 00 mov eax, 16 0006a 48 6b c0 02 imul rax, rax, 2 0006e 48 8b 8d 40 01 00 00 mov rcx, QWORD PTR source$[rbp] 00075 48 03 c8 add rcx, rax 00078 48 8b c1 mov rax, rcx 0007b 0f 10 08 movups xmm1, XMMWORD PTR [rax] 0007e 0f c6 c8 44 shufps xmm1, xmm0, 68 ; 00000044H 00082 0f 28 c1 movaps xmm0, xmm1 00085 0f 29 45 40 movaps XMMWORD PTR t2$[rbp], xmm0 ; 10 : ; 11 : target->column[0] = _mm_shuffle_ps(t0, t2, _MM_SHUFFLE(2, 0, 2, 0)); 00089 0f 28 45 10 movaps xmm0, XMMWORD PTR t0$[rbp] 0008d 0f c6 45 40 88 shufps xmm0, XMMWORD PTR t2$[rbp], 136 ; 00000088H 00092 b8 10 00 00 00 mov eax, 16 00097 48 6b c0 00 imul rax, rax, 0 0009b 48 8b 8d 48 01 00 00 mov rcx, QWORD PTR target$[rbp] 000a2 0f 11 04 01 movups XMMWORD PTR [rcx+rax], xmm0 ; 12 : target->column[1] = _mm_shuffle_ps(t0, t2, _MM_SHUFFLE(3, 1, 3, 1)); 000a6 0f 28 45 10 movaps xmm0, XMMWORD PTR t0$[rbp] 000aa 0f c6 45 40 dd shufps xmm0, XMMWORD PTR t2$[rbp], 221 ; 000000ddH 000af b8 10 00 00 00 mov eax, 16 000b4 48 6b c0 01 imul rax, rax, 1 000b8 48 8b 8d 48 01 00 00 mov rcx, QWORD PTR target$[rbp] 000bf 0f 11 04 01 movups XMMWORD PTR [rcx+rax], xmm0 ; 13 : } 000c3 48 8d a5 28 01 00 00 lea rsp, QWORD PTR [rbp+296] 000ca 5f pop rdi 000cb 5d pop rbp 000cc c3 ret 0 transpose32 ENDP _TEXT ENDS ; Function compile flags: /Odtp /RTCsu /ZI ; File D:\NitloadIndustry\研究项目\1-Flagship\TH2020\ProjectFile\内核源代码\StgSharp.C\mat3.c ; COMDAT submatrix3_512 _TEXT SEGMENT temp$ = 64 left$ = 432 right$ = 440 ans$ = 448 submatrix3_512 PROC ; COMDAT ; 125 : { $LN3: 00000 4c 89 44 24 18 mov QWORD PTR [rsp+24], r8 00005 48 89 54 24 10 mov QWORD PTR [rsp+16], rdx 0000a 48 89 4c 24 08 mov QWORD PTR [rsp+8], rcx 0000f 41 55 push r13 00011 55 push rbp 00012 57 push rdi 00013 48 81 ec b0 01 00 00 sub rsp, 432 ; 000001b0H 0001a 4c 8d 6c 24 20 lea r13, QWORD PTR [rsp+32] 0001f 48 8d 6c 24 60 lea rbp, QWORD PTR [rsp+96] 00024 48 83 e5 c0 and rbp, -64 ; ffffffffffffffc0H 00028 48 8d 0d 00 00 00 00 lea rcx, OFFSET FLAT:__58B0E32D_mat3@c 0002f e8 00 00 00 00 call __CheckForDebuggerJustMyCode 00034 90 npad 1 ; 126 : __m512 temp = _mm512_sub_ps(_mm512_loadu_ps(left), _mm512_loadu_ps(right)); 00035 49 8b 85 b8 01 00 00 mov rax, QWORD PTR right$[r13] 0003c 62 f1 7c 48 10 00 vmovups zmm0, ZMMWORD PTR [rax] 00042 49 8b 85 b0 01 00 00 mov rax, QWORD PTR left$[r13] 00049 62 f1 7c 48 10 08 vmovups zmm1, ZMMWORD PTR [rax] 0004f 62 f1 74 48 5c c0 vsubps zmm0, zmm1, zmm0 00055 62 f1 7c 48 11 45 01 vmovups ZMMWORD PTR temp$[rbp], zmm0 ; 127 : _mm512_mask_store_ps(ans, 0x0fff, temp); 0005c b8 ff 0f 00 00 mov eax, 4095 ; 00000fffH 00061 c5 f8 92 c8 kmovw k1, ax 00065 49 8b 85 c0 01 00 00 mov rax, QWORD PTR ans$[r13] 0006c 62 f1 7c 48 10 45 01 vmovups zmm0, ZMMWORD PTR temp$[rbp] 00073 62 f1 7c 49 11 00 vmovups ZMMWORD PTR [rax] {k1}, zmm0 ; 128 : } 00079 49 8d a5 90 01 00 00 lea rsp, QWORD PTR [r13+400] 00080 5f pop rdi 00081 5d pop rbp 00082 41 5d pop r13 00084 c3 ret 0 submatrix3_512 ENDP _TEXT ENDS ; Function compile flags: /Odtp /RTCsu /ZI ; File D:\NitloadIndustry\研究项目\1-Flagship\TH2020\ProjectFile\内核源代码\StgSharp.C\mat3.c ; COMDAT submatrix3_avx _TEXT SEGMENT temp0$ = 32 temp1$ = 96 left$ = 384 right$ = 392 ans$ = 400 submatrix3_avx PROC ; COMDAT ; 116 : { $LN3: 00000 4c 89 44 24 18 mov QWORD PTR [rsp+24], r8 00005 48 89 54 24 10 mov QWORD PTR [rsp+16], rdx 0000a 48 89 4c 24 08 mov QWORD PTR [rsp+8], rcx 0000f 41 55 push r13 00011 55 push rbp 00012 57 push rdi 00013 48 81 ec 80 01 00 00 sub rsp, 384 ; 00000180H 0001a 4c 8d 6c 24 20 lea r13, QWORD PTR [rsp+32] 0001f 48 8d 6c 24 40 lea rbp, QWORD PTR [rsp+64] 00024 48 83 e5 e0 and rbp, -32 ; ffffffffffffffe0H 00028 48 8d 0d 00 00 00 00 lea rcx, OFFSET FLAT:__58B0E32D_mat3@c 0002f e8 00 00 00 00 call __CheckForDebuggerJustMyCode 00034 90 npad 1 ; 117 : __m256 temp0 = _mm256_sub_ps(ALIGN256(left->part), ALIGN256(right->part)); 00035 49 8b 85 88 01 00 00 mov rax, QWORD PTR right$[r13] 0003c c5 fc 10 00 vmovups ymm0, YMMWORD PTR [rax] 00040 49 8b 85 80 01 00 00 mov rax, QWORD PTR left$[r13] 00047 c5 fc 10 08 vmovups ymm1, YMMWORD PTR [rax] 0004b c5 f4 5c c0 vsubps ymm0, ymm1, ymm0 0004f c5 fc 11 45 20 vmovups YMMWORD PTR temp0$[rbp], ymm0 ; 118 : __m128 temp1 = _mm_sub_ps(ALIGN(left->column[2]), ALIGN(right->column[2])); 00054 b8 10 00 00 00 mov eax, 16 00059 48 6b c0 02 imul rax, rax, 2 0005d 49 8b 8d 88 01 00 00 mov rcx, QWORD PTR right$[r13] 00064 48 03 c8 add rcx, rax 00067 48 8b c1 mov rax, rcx 0006a 0f 10 00 movups xmm0, XMMWORD PTR [rax] 0006d b8 10 00 00 00 mov eax, 16 00072 48 6b c0 02 imul rax, rax, 2 00076 49 8b 8d 80 01 00 00 mov rcx, QWORD PTR left$[r13] 0007d 48 03 c8 add rcx, rax 00080 48 8b c1 mov rax, rcx 00083 0f 10 08 movups xmm1, XMMWORD PTR [rax] 00086 0f 5c c8 subps xmm1, xmm0 00089 0f 28 c1 movaps xmm0, xmm1 0008c 0f 29 45 60 movaps XMMWORD PTR temp1$[rbp], xmm0 ; 119 : ; 120 : _mm256_storeu_ps(&ans->m[0][0], temp0); 00090 b8 0c 00 00 00 mov eax, 12 00095 48 6b c0 00 imul rax, rax, 0 00099 49 8b 8d 90 01 00 00 mov rcx, QWORD PTR ans$[r13] 000a0 48 03 c8 add rcx, rax 000a3 48 8b c1 mov rax, rcx 000a6 b9 04 00 00 00 mov ecx, 4 000ab 48 6b c9 00 imul rcx, rcx, 0 000af 48 03 c1 add rax, rcx 000b2 c5 fc 10 45 20 vmovups ymm0, YMMWORD PTR temp0$[rbp] 000b7 c5 fc 11 00 vmovups YMMWORD PTR [rax], ymm0 ; 121 : _mm_storeu_ps(&ans->m[0][2], temp1); 000bb b8 0c 00 00 00 mov eax, 12 000c0 48 6b c0 00 imul rax, rax, 0 000c4 49 8b 8d 90 01 00 00 mov rcx, QWORD PTR ans$[r13] 000cb 48 03 c8 add rcx, rax 000ce 48 8b c1 mov rax, rcx 000d1 b9 04 00 00 00 mov ecx, 4 000d6 48 6b c9 02 imul rcx, rcx, 2 000da 48 03 c1 add rax, rcx 000dd 0f 28 45 60 movaps xmm0, XMMWORD PTR temp1$[rbp] 000e1 0f 11 00 movups XMMWORD PTR [rax], xmm0 ; 122 : } 000e4 49 8d a5 60 01 00 00 lea rsp, QWORD PTR [r13+352] 000eb 5f pop rdi 000ec 5d pop rbp 000ed 41 5d pop r13 000ef c3 ret 0 submatrix3_avx ENDP _TEXT ENDS ; Function compile flags: /Odtp /RTCsu /ZI ; File D:\NitloadIndustry\研究项目\1-Flagship\TH2020\ProjectFile\内核源代码\StgSharp.C\mat3.c ; COMDAT submatrix3_sse _TEXT SEGMENT temp0$ = 16 temp1$ = 64 temp2$ = 112 left$ = 368 right$ = 376 ans$ = 384 submatrix3_sse PROC ; COMDAT ; 105 : { $LN3: 00000 4c 89 44 24 18 mov QWORD PTR [rsp+24], r8 00005 48 89 54 24 10 mov QWORD PTR [rsp+16], rdx 0000a 48 89 4c 24 08 mov QWORD PTR [rsp+8], rcx 0000f 55 push rbp 00010 57 push rdi 00011 48 81 ec 78 01 00 00 sub rsp, 376 ; 00000178H 00018 48 8d 6c 24 20 lea rbp, QWORD PTR [rsp+32] 0001d 48 8d 0d 00 00 00 00 lea rcx, OFFSET FLAT:__58B0E32D_mat3@c 00024 e8 00 00 00 00 call __CheckForDebuggerJustMyCode 00029 90 npad 1 ; 106 : __m128 temp0 = _mm_sub_ps(ALIGN(left->column[0]), ALIGN(right->column[0])); 0002a b8 10 00 00 00 mov eax, 16 0002f 48 6b c0 00 imul rax, rax, 0 00033 48 8b 8d 78 01 00 00 mov rcx, QWORD PTR right$[rbp] 0003a 48 03 c8 add rcx, rax 0003d 48 8b c1 mov rax, rcx 00040 0f 10 00 movups xmm0, XMMWORD PTR [rax] 00043 b8 10 00 00 00 mov eax, 16 00048 48 6b c0 00 imul rax, rax, 0 0004c 48 8b 8d 70 01 00 00 mov rcx, QWORD PTR left$[rbp] 00053 48 03 c8 add rcx, rax 00056 48 8b c1 mov rax, rcx 00059 0f 10 08 movups xmm1, XMMWORD PTR [rax] 0005c 0f 5c c8 subps xmm1, xmm0 0005f 0f 28 c1 movaps xmm0, xmm1 00062 0f 29 45 10 movaps XMMWORD PTR temp0$[rbp], xmm0 ; 107 : __m128 temp1 = _mm_sub_ps(ALIGN(left->column[1]), ALIGN(right->column[1])); 00066 b8 10 00 00 00 mov eax, 16 0006b 48 6b c0 01 imul rax, rax, 1 0006f 48 8b 8d 78 01 00 00 mov rcx, QWORD PTR right$[rbp] 00076 48 03 c8 add rcx, rax 00079 48 8b c1 mov rax, rcx 0007c 0f 10 00 movups xmm0, XMMWORD PTR [rax] 0007f b8 10 00 00 00 mov eax, 16 00084 48 6b c0 01 imul rax, rax, 1 00088 48 8b 8d 70 01 00 00 mov rcx, QWORD PTR left$[rbp] 0008f 48 03 c8 add rcx, rax 00092 48 8b c1 mov rax, rcx 00095 0f 10 08 movups xmm1, XMMWORD PTR [rax] 00098 0f 5c c8 subps xmm1, xmm0 0009b 0f 28 c1 movaps xmm0, xmm1 0009e 0f 29 45 40 movaps XMMWORD PTR temp1$[rbp], xmm0 ; 108 : __m128 temp2 = _mm_sub_ps(ALIGN(left->column[2]), ALIGN(right->column[2])); 000a2 b8 10 00 00 00 mov eax, 16 000a7 48 6b c0 02 imul rax, rax, 2 000ab 48 8b 8d 78 01 00 00 mov rcx, QWORD PTR right$[rbp] 000b2 48 03 c8 add rcx, rax 000b5 48 8b c1 mov rax, rcx 000b8 0f 10 00 movups xmm0, XMMWORD PTR [rax] 000bb b8 10 00 00 00 mov eax, 16 000c0 48 6b c0 02 imul rax, rax, 2 000c4 48 8b 8d 70 01 00 00 mov rcx, QWORD PTR left$[rbp] 000cb 48 03 c8 add rcx, rax 000ce 48 8b c1 mov rax, rcx 000d1 0f 10 08 movups xmm1, XMMWORD PTR [rax] 000d4 0f 5c c8 subps xmm1, xmm0 000d7 0f 28 c1 movaps xmm0, xmm1 000da 0f 29 45 70 movaps XMMWORD PTR temp2$[rbp], xmm0 ; 109 : ; 110 : _mm_storeu_ps(&ans->m[0][0], temp0); 000de b8 0c 00 00 00 mov eax, 12 000e3 48 6b c0 00 imul rax, rax, 0 000e7 48 8b 8d 80 01 00 00 mov rcx, QWORD PTR ans$[rbp] 000ee 48 03 c8 add rcx, rax 000f1 48 8b c1 mov rax, rcx 000f4 b9 04 00 00 00 mov ecx, 4 000f9 48 6b c9 00 imul rcx, rcx, 0 000fd 48 03 c1 add rax, rcx 00100 0f 28 45 10 movaps xmm0, XMMWORD PTR temp0$[rbp] 00104 0f 11 00 movups XMMWORD PTR [rax], xmm0 ; 111 : _mm_storeu_ps(&ans->m[0][1], temp1); 00107 b8 0c 00 00 00 mov eax, 12 0010c 48 6b c0 00 imul rax, rax, 0 00110 48 8b 8d 80 01 00 00 mov rcx, QWORD PTR ans$[rbp] 00117 48 03 c8 add rcx, rax 0011a 48 8b c1 mov rax, rcx 0011d b9 04 00 00 00 mov ecx, 4 00122 48 6b c9 01 imul rcx, rcx, 1 00126 48 03 c1 add rax, rcx 00129 0f 28 45 40 movaps xmm0, XMMWORD PTR temp1$[rbp] 0012d 0f 11 00 movups XMMWORD PTR [rax], xmm0 ; 112 : _mm_storeu_ps(&ans->m[0][2], temp2); 00130 b8 0c 00 00 00 mov eax, 12 00135 48 6b c0 00 imul rax, rax, 0 00139 48 8b 8d 80 01 00 00 mov rcx, QWORD PTR ans$[rbp] 00140 48 03 c8 add rcx, rax 00143 48 8b c1 mov rax, rcx 00146 b9 04 00 00 00 mov ecx, 4 0014b 48 6b c9 02 imul rcx, rcx, 2 0014f 48 03 c1 add rax, rcx 00152 0f 28 45 70 movaps xmm0, XMMWORD PTR temp2$[rbp] 00156 0f 11 00 movups XMMWORD PTR [rax], xmm0 ; 113 : } 00159 48 8d a5 58 01 00 00 lea rsp, QWORD PTR [rbp+344] 00160 5f pop rdi 00161 5d pop rbp 00162 c3 ret 0 submatrix3_sse ENDP _TEXT ENDS ; Function compile flags: /Odtp /RTCsu /ZI ; File D:\NitloadIndustry\研究项目\1-Flagship\TH2020\ProjectFile\内核源代码\StgSharp.C\mat3.c ; COMDAT addmatrix3_512 _TEXT SEGMENT temp$ = 64 left$ = 432 right$ = 440 ans$ = 448 addmatrix3_512 PROC ; COMDAT ; 99 : { $LN3: 00000 4c 89 44 24 18 mov QWORD PTR [rsp+24], r8 00005 48 89 54 24 10 mov QWORD PTR [rsp+16], rdx 0000a 48 89 4c 24 08 mov QWORD PTR [rsp+8], rcx 0000f 41 55 push r13 00011 55 push rbp 00012 57 push rdi 00013 48 81 ec b0 01 00 00 sub rsp, 432 ; 000001b0H 0001a 4c 8d 6c 24 20 lea r13, QWORD PTR [rsp+32] 0001f 48 8d 6c 24 60 lea rbp, QWORD PTR [rsp+96] 00024 48 83 e5 c0 and rbp, -64 ; ffffffffffffffc0H 00028 48 8d 0d 00 00 00 00 lea rcx, OFFSET FLAT:__58B0E32D_mat3@c 0002f e8 00 00 00 00 call __CheckForDebuggerJustMyCode 00034 90 npad 1 ; 100 : __m512 temp = _mm512_add_ps(_mm512_loadu_ps(left), _mm512_loadu_ps(right)); 00035 49 8b 85 b8 01 00 00 mov rax, QWORD PTR right$[r13] 0003c 62 f1 7c 48 10 00 vmovups zmm0, ZMMWORD PTR [rax] 00042 49 8b 85 b0 01 00 00 mov rax, QWORD PTR left$[r13] 00049 62 f1 7c 48 10 08 vmovups zmm1, ZMMWORD PTR [rax] 0004f 62 f1 74 48 58 c0 vaddps zmm0, zmm1, zmm0 00055 62 f1 7c 48 11 45 01 vmovups ZMMWORD PTR temp$[rbp], zmm0 ; 101 : _mm512_mask_store_ps(ans, 0x0fff, temp); 0005c b8 ff 0f 00 00 mov eax, 4095 ; 00000fffH 00061 c5 f8 92 c8 kmovw k1, ax 00065 49 8b 85 c0 01 00 00 mov rax, QWORD PTR ans$[r13] 0006c 62 f1 7c 48 10 45 01 vmovups zmm0, ZMMWORD PTR temp$[rbp] 00073 62 f1 7c 49 11 00 vmovups ZMMWORD PTR [rax] {k1}, zmm0 ; 102 : } 00079 49 8d a5 90 01 00 00 lea rsp, QWORD PTR [r13+400] 00080 5f pop rdi 00081 5d pop rbp 00082 41 5d pop r13 00084 c3 ret 0 addmatrix3_512 ENDP _TEXT ENDS ; Function compile flags: /Odtp /RTCsu /ZI ; File D:\NitloadIndustry\研究项目\1-Flagship\TH2020\ProjectFile\内核源代码\StgSharp.C\mat3.c ; COMDAT addmatrix3_avx _TEXT SEGMENT temp0$ = 32 temp1$ = 96 left$ = 384 right$ = 392 ans$ = 400 addmatrix3_avx PROC ; COMDAT ; 90 : { $LN3: 00000 4c 89 44 24 18 mov QWORD PTR [rsp+24], r8 00005 48 89 54 24 10 mov QWORD PTR [rsp+16], rdx 0000a 48 89 4c 24 08 mov QWORD PTR [rsp+8], rcx 0000f 41 55 push r13 00011 55 push rbp 00012 57 push rdi 00013 48 81 ec 80 01 00 00 sub rsp, 384 ; 00000180H 0001a 4c 8d 6c 24 20 lea r13, QWORD PTR [rsp+32] 0001f 48 8d 6c 24 40 lea rbp, QWORD PTR [rsp+64] 00024 48 83 e5 e0 and rbp, -32 ; ffffffffffffffe0H 00028 48 8d 0d 00 00 00 00 lea rcx, OFFSET FLAT:__58B0E32D_mat3@c 0002f e8 00 00 00 00 call __CheckForDebuggerJustMyCode 00034 90 npad 1 ; 91 : __m256 temp0 = _mm256_add_ps(ALIGN256(left->part), ALIGN256(right->part)); 00035 49 8b 85 88 01 00 00 mov rax, QWORD PTR right$[r13] 0003c c5 fc 10 00 vmovups ymm0, YMMWORD PTR [rax] 00040 49 8b 85 80 01 00 00 mov rax, QWORD PTR left$[r13] 00047 c5 fc 10 08 vmovups ymm1, YMMWORD PTR [rax] 0004b c5 f4 58 c0 vaddps ymm0, ymm1, ymm0 0004f c5 fc 11 45 20 vmovups YMMWORD PTR temp0$[rbp], ymm0 ; 92 : __m128 temp1 = _mm_add_ps(ALIGN(left->column[2]), ALIGN(right->column[2])); 00054 b8 10 00 00 00 mov eax, 16 00059 48 6b c0 02 imul rax, rax, 2 0005d 49 8b 8d 88 01 00 00 mov rcx, QWORD PTR right$[r13] 00064 48 03 c8 add rcx, rax 00067 48 8b c1 mov rax, rcx 0006a 0f 10 00 movups xmm0, XMMWORD PTR [rax] 0006d b8 10 00 00 00 mov eax, 16 00072 48 6b c0 02 imul rax, rax, 2 00076 49 8b 8d 80 01 00 00 mov rcx, QWORD PTR left$[r13] 0007d 48 03 c8 add rcx, rax 00080 48 8b c1 mov rax, rcx 00083 0f 10 08 movups xmm1, XMMWORD PTR [rax] 00086 0f 58 c8 addps xmm1, xmm0 00089 0f 28 c1 movaps xmm0, xmm1 0008c 0f 29 45 60 movaps XMMWORD PTR temp1$[rbp], xmm0 ; 93 : ; 94 : _mm256_storeu_ps(&ans->m[0][0], temp0); 00090 b8 0c 00 00 00 mov eax, 12 00095 48 6b c0 00 imul rax, rax, 0 00099 49 8b 8d 90 01 00 00 mov rcx, QWORD PTR ans$[r13] 000a0 48 03 c8 add rcx, rax 000a3 48 8b c1 mov rax, rcx 000a6 b9 04 00 00 00 mov ecx, 4 000ab 48 6b c9 00 imul rcx, rcx, 0 000af 48 03 c1 add rax, rcx 000b2 c5 fc 10 45 20 vmovups ymm0, YMMWORD PTR temp0$[rbp] 000b7 c5 fc 11 00 vmovups YMMWORD PTR [rax], ymm0 ; 95 : _mm_storeu_ps(&ans->m[0][2], temp1); 000bb b8 0c 00 00 00 mov eax, 12 000c0 48 6b c0 00 imul rax, rax, 0 000c4 49 8b 8d 90 01 00 00 mov rcx, QWORD PTR ans$[r13] 000cb 48 03 c8 add rcx, rax 000ce 48 8b c1 mov rax, rcx 000d1 b9 04 00 00 00 mov ecx, 4 000d6 48 6b c9 02 imul rcx, rcx, 2 000da 48 03 c1 add rax, rcx 000dd 0f 28 45 60 movaps xmm0, XMMWORD PTR temp1$[rbp] 000e1 0f 11 00 movups XMMWORD PTR [rax], xmm0 ; 96 : } 000e4 49 8d a5 60 01 00 00 lea rsp, QWORD PTR [r13+352] 000eb 5f pop rdi 000ec 5d pop rbp 000ed 41 5d pop r13 000ef c3 ret 0 addmatrix3_avx ENDP _TEXT ENDS ; Function compile flags: /Odtp /RTCsu /ZI ; File D:\NitloadIndustry\研究项目\1-Flagship\TH2020\ProjectFile\内核源代码\StgSharp.C\mat3.c ; COMDAT addmatrix3_sse _TEXT SEGMENT temp0$ = 16 temp1$ = 64 temp2$ = 112 left$ = 368 right$ = 376 ans$ = 384 addmatrix3_sse PROC ; COMDAT ; 79 : { $LN3: 00000 4c 89 44 24 18 mov QWORD PTR [rsp+24], r8 00005 48 89 54 24 10 mov QWORD PTR [rsp+16], rdx 0000a 48 89 4c 24 08 mov QWORD PTR [rsp+8], rcx 0000f 55 push rbp 00010 57 push rdi 00011 48 81 ec 78 01 00 00 sub rsp, 376 ; 00000178H 00018 48 8d 6c 24 20 lea rbp, QWORD PTR [rsp+32] 0001d 48 8d 0d 00 00 00 00 lea rcx, OFFSET FLAT:__58B0E32D_mat3@c 00024 e8 00 00 00 00 call __CheckForDebuggerJustMyCode 00029 90 npad 1 ; 80 : __m128 temp0 = _mm_add_ps(ALIGN(left->column[0]), ALIGN(right->column[0])); 0002a b8 10 00 00 00 mov eax, 16 0002f 48 6b c0 00 imul rax, rax, 0 00033 48 8b 8d 78 01 00 00 mov rcx, QWORD PTR right$[rbp] 0003a 48 03 c8 add rcx, rax 0003d 48 8b c1 mov rax, rcx 00040 0f 10 00 movups xmm0, XMMWORD PTR [rax] 00043 b8 10 00 00 00 mov eax, 16 00048 48 6b c0 00 imul rax, rax, 0 0004c 48 8b 8d 70 01 00 00 mov rcx, QWORD PTR left$[rbp] 00053 48 03 c8 add rcx, rax 00056 48 8b c1 mov rax, rcx 00059 0f 10 08 movups xmm1, XMMWORD PTR [rax] 0005c 0f 58 c8 addps xmm1, xmm0 0005f 0f 28 c1 movaps xmm0, xmm1 00062 0f 29 45 10 movaps XMMWORD PTR temp0$[rbp], xmm0 ; 81 : __m128 temp1 = _mm_add_ps(ALIGN(left->column[1]), ALIGN(right->column[1])); 00066 b8 10 00 00 00 mov eax, 16 0006b 48 6b c0 01 imul rax, rax, 1 0006f 48 8b 8d 78 01 00 00 mov rcx, QWORD PTR right$[rbp] 00076 48 03 c8 add rcx, rax 00079 48 8b c1 mov rax, rcx 0007c 0f 10 00 movups xmm0, XMMWORD PTR [rax] 0007f b8 10 00 00 00 mov eax, 16 00084 48 6b c0 01 imul rax, rax, 1 00088 48 8b 8d 70 01 00 00 mov rcx, QWORD PTR left$[rbp] 0008f 48 03 c8 add rcx, rax 00092 48 8b c1 mov rax, rcx 00095 0f 10 08 movups xmm1, XMMWORD PTR [rax] 00098 0f 58 c8 addps xmm1, xmm0 0009b 0f 28 c1 movaps xmm0, xmm1 0009e 0f 29 45 40 movaps XMMWORD PTR temp1$[rbp], xmm0 ; 82 : __m128 temp2 = _mm_add_ps(ALIGN(left->column[2]), ALIGN(right->column[2])); 000a2 b8 10 00 00 00 mov eax, 16 000a7 48 6b c0 02 imul rax, rax, 2 000ab 48 8b 8d 78 01 00 00 mov rcx, QWORD PTR right$[rbp] 000b2 48 03 c8 add rcx, rax 000b5 48 8b c1 mov rax, rcx 000b8 0f 10 00 movups xmm0, XMMWORD PTR [rax] 000bb b8 10 00 00 00 mov eax, 16 000c0 48 6b c0 02 imul rax, rax, 2 000c4 48 8b 8d 70 01 00 00 mov rcx, QWORD PTR left$[rbp] 000cb 48 03 c8 add rcx, rax 000ce 48 8b c1 mov rax, rcx 000d1 0f 10 08 movups xmm1, XMMWORD PTR [rax] 000d4 0f 58 c8 addps xmm1, xmm0 000d7 0f 28 c1 movaps xmm0, xmm1 000da 0f 29 45 70 movaps XMMWORD PTR temp2$[rbp], xmm0 ; 83 : ; 84 : _mm_storeu_ps(&ans->m[0][0], temp0); 000de b8 0c 00 00 00 mov eax, 12 000e3 48 6b c0 00 imul rax, rax, 0 000e7 48 8b 8d 80 01 00 00 mov rcx, QWORD PTR ans$[rbp] 000ee 48 03 c8 add rcx, rax 000f1 48 8b c1 mov rax, rcx 000f4 b9 04 00 00 00 mov ecx, 4 000f9 48 6b c9 00 imul rcx, rcx, 0 000fd 48 03 c1 add rax, rcx 00100 0f 28 45 10 movaps xmm0, XMMWORD PTR temp0$[rbp] 00104 0f 11 00 movups XMMWORD PTR [rax], xmm0 ; 85 : _mm_storeu_ps(&ans->m[0][1], temp1); 00107 b8 0c 00 00 00 mov eax, 12 0010c 48 6b c0 00 imul rax, rax, 0 00110 48 8b 8d 80 01 00 00 mov rcx, QWORD PTR ans$[rbp] 00117 48 03 c8 add rcx, rax 0011a 48 8b c1 mov rax, rcx 0011d b9 04 00 00 00 mov ecx, 4 00122 48 6b c9 01 imul rcx, rcx, 1 00126 48 03 c1 add rax, rcx 00129 0f 28 45 40 movaps xmm0, XMMWORD PTR temp1$[rbp] 0012d 0f 11 00 movups XMMWORD PTR [rax], xmm0 ; 86 : _mm_storeu_ps(&ans->m[0][2], temp2); 00130 b8 0c 00 00 00 mov eax, 12 00135 48 6b c0 00 imul rax, rax, 0 00139 48 8b 8d 80 01 00 00 mov rcx, QWORD PTR ans$[rbp] 00140 48 03 c8 add rcx, rax 00143 48 8b c1 mov rax, rcx 00146 b9 04 00 00 00 mov ecx, 4 0014b 48 6b c9 02 imul rcx, rcx, 2 0014f 48 03 c1 add rax, rcx 00152 0f 28 45 70 movaps xmm0, XMMWORD PTR temp2$[rbp] 00156 0f 11 00 movups XMMWORD PTR [rax], xmm0 ; 87 : } 00159 48 8d a5 58 01 00 00 lea rsp, QWORD PTR [rbp+344] 00160 5f pop rdi 00161 5d pop rbp 00162 c3 ret 0 addmatrix3_sse ENDP _TEXT ENDS END