1871 lines
56 KiB
Plaintext
1871 lines
56 KiB
Plaintext
//
|
|
// Generated by NVIDIA NVVM Compiler
|
|
//
|
|
// Compiler Build ID: CL-23083092
|
|
// Cuda compilation tools, release 9.1, V9.1.85
|
|
// Based on LLVM 3.4svn
|
|
//
|
|
|
|
.version 6.1
|
|
.target sm_30
|
|
.address_size 64
|
|
|
|
// .globl _Z6oxMainv
|
|
.global .align 8 .b8 pixelID[8];
|
|
.global .align 8 .b8 resolution[8];
|
|
.global .align 4 .b8 normal[12];
|
|
.global .align 4 .b8 camPos[12];
|
|
.global .align 4 .b8 root[4];
|
|
.global .align 4 .u32 imageEnabled;
|
|
.global .texref lightmap;
|
|
.global .align 16 .b8 tileInfo[16];
|
|
.global .align 4 .u32 additive;
|
|
.global .align 1 .b8 image[1];
|
|
.global .align 1 .b8 image_HDR[1];
|
|
.global .align 1 .b8 image_HDR2[1];
|
|
.global .align 1 .b8 image_Mask[1];
|
|
.global .align 1 .b8 image_Dir[1];
|
|
.global .align 1 .b8 uvpos[1];
|
|
.global .align 1 .b8 uvnormal[1];
|
|
.global .align 4 .u32 ignoreNormal;
|
|
.global .align 1 .b8 localLights[1];
|
|
.global .align 4 .b8 _ZN21rti_internal_typeinfo7pixelIDE[8] = {82, 97, 121, 0, 8, 0, 0, 0};
|
|
.global .align 4 .b8 _ZN21rti_internal_typeinfo10resolutionE[8] = {82, 97, 121, 0, 8, 0, 0, 0};
|
|
.global .align 4 .b8 _ZN21rti_internal_typeinfo6normalE[8] = {82, 97, 121, 0, 12, 0, 0, 0};
|
|
.global .align 4 .b8 _ZN21rti_internal_typeinfo6camPosE[8] = {82, 97, 121, 0, 12, 0, 0, 0};
|
|
.global .align 4 .b8 _ZN21rti_internal_typeinfo4rootE[8] = {82, 97, 121, 0, 4, 0, 0, 0};
|
|
.global .align 4 .b8 _ZN21rti_internal_typeinfo12imageEnabledE[8] = {82, 97, 121, 0, 4, 0, 0, 0};
|
|
.global .align 4 .b8 _ZN21rti_internal_typeinfo8tileInfoE[8] = {82, 97, 121, 0, 16, 0, 0, 0};
|
|
.global .align 4 .b8 _ZN21rti_internal_typeinfo8additiveE[8] = {82, 97, 121, 0, 4, 0, 0, 0};
|
|
.global .align 4 .b8 _ZN21rti_internal_typeinfo12ignoreNormalE[8] = {82, 97, 121, 0, 4, 0, 0, 0};
|
|
.global .align 8 .u64 _ZN21rti_internal_register20reg_bitness_detectorE;
|
|
.global .align 8 .u64 _ZN21rti_internal_register24reg_exception_64_detail0E;
|
|
.global .align 8 .u64 _ZN21rti_internal_register24reg_exception_64_detail1E;
|
|
.global .align 8 .u64 _ZN21rti_internal_register24reg_exception_64_detail2E;
|
|
.global .align 8 .u64 _ZN21rti_internal_register24reg_exception_64_detail3E;
|
|
.global .align 8 .u64 _ZN21rti_internal_register24reg_exception_64_detail4E;
|
|
.global .align 8 .u64 _ZN21rti_internal_register24reg_exception_64_detail5E;
|
|
.global .align 8 .u64 _ZN21rti_internal_register24reg_exception_64_detail6E;
|
|
.global .align 8 .u64 _ZN21rti_internal_register24reg_exception_64_detail7E;
|
|
.global .align 8 .u64 _ZN21rti_internal_register24reg_exception_64_detail8E;
|
|
.global .align 8 .u64 _ZN21rti_internal_register24reg_exception_64_detail9E;
|
|
.global .align 4 .u32 _ZN21rti_internal_register21reg_exception_detail0E;
|
|
.global .align 4 .u32 _ZN21rti_internal_register21reg_exception_detail1E;
|
|
.global .align 4 .u32 _ZN21rti_internal_register21reg_exception_detail2E;
|
|
.global .align 4 .u32 _ZN21rti_internal_register21reg_exception_detail3E;
|
|
.global .align 4 .u32 _ZN21rti_internal_register21reg_exception_detail4E;
|
|
.global .align 4 .u32 _ZN21rti_internal_register21reg_exception_detail5E;
|
|
.global .align 4 .u32 _ZN21rti_internal_register21reg_exception_detail6E;
|
|
.global .align 4 .u32 _ZN21rti_internal_register21reg_exception_detail7E;
|
|
.global .align 4 .u32 _ZN21rti_internal_register21reg_exception_detail8E;
|
|
.global .align 4 .u32 _ZN21rti_internal_register21reg_exception_detail9E;
|
|
.global .align 4 .u32 _ZN21rti_internal_register14reg_rayIndex_xE;
|
|
.global .align 4 .u32 _ZN21rti_internal_register14reg_rayIndex_yE;
|
|
.global .align 4 .u32 _ZN21rti_internal_register14reg_rayIndex_zE;
|
|
.global .align 8 .b8 _ZN21rti_internal_typename7pixelIDE[6] = {117, 105, 110, 116, 50, 0};
|
|
.global .align 8 .b8 _ZN21rti_internal_typename10resolutionE[6] = {117, 105, 110, 116, 50, 0};
|
|
.global .align 8 .b8 _ZN21rti_internal_typename6normalE[7] = {102, 108, 111, 97, 116, 51, 0};
|
|
.global .align 8 .b8 _ZN21rti_internal_typename6camPosE[7] = {102, 108, 111, 97, 116, 51, 0};
|
|
.global .align 16 .b8 _ZN21rti_internal_typename4rootE[9] = {114, 116, 79, 98, 106, 101, 99, 116, 0};
|
|
.global .align 4 .b8 _ZN21rti_internal_typename12imageEnabledE[4] = {105, 110, 116, 0};
|
|
.global .align 8 .b8 _ZN21rti_internal_typename8tileInfoE[6] = {117, 105, 110, 116, 52, 0};
|
|
.global .align 4 .b8 _ZN21rti_internal_typename8additiveE[4] = {105, 110, 116, 0};
|
|
.global .align 4 .b8 _ZN21rti_internal_typename12ignoreNormalE[4] = {105, 110, 116, 0};
|
|
.global .align 4 .u32 _ZN21rti_internal_typeenum7pixelIDE = 4919;
|
|
.global .align 4 .u32 _ZN21rti_internal_typeenum10resolutionE = 4919;
|
|
.global .align 4 .u32 _ZN21rti_internal_typeenum6normalE = 4919;
|
|
.global .align 4 .u32 _ZN21rti_internal_typeenum6camPosE = 4919;
|
|
.global .align 4 .u32 _ZN21rti_internal_typeenum4rootE = 4919;
|
|
.global .align 4 .u32 _ZN21rti_internal_typeenum12imageEnabledE = 4919;
|
|
.global .align 4 .u32 _ZN21rti_internal_typeenum8tileInfoE = 4919;
|
|
.global .align 4 .u32 _ZN21rti_internal_typeenum8additiveE = 4919;
|
|
.global .align 4 .u32 _ZN21rti_internal_typeenum12ignoreNormalE = 4919;
|
|
.global .align 16 .b8 _ZN21rti_internal_semantic7pixelIDE[14] = {114, 116, 76, 97, 117, 110, 99, 104, 73, 110, 100, 101, 120, 0};
|
|
.global .align 16 .b8 _ZN21rti_internal_semantic10resolutionE[12] = {114, 116, 76, 97, 117, 110, 99, 104, 68, 105, 109, 0};
|
|
.global .align 16 .b8 _ZN21rti_internal_semantic6normalE[17] = {97, 116, 116, 114, 105, 98, 117, 116, 101, 32, 110, 111, 114, 109, 97, 108, 0};
|
|
.global .align 1 .b8 _ZN21rti_internal_semantic6camPosE[1];
|
|
.global .align 1 .b8 _ZN21rti_internal_semantic4rootE[1];
|
|
.global .align 1 .b8 _ZN21rti_internal_semantic12imageEnabledE[1];
|
|
.global .align 1 .b8 _ZN21rti_internal_semantic8tileInfoE[1];
|
|
.global .align 1 .b8 _ZN21rti_internal_semantic8additiveE[1];
|
|
.global .align 1 .b8 _ZN21rti_internal_semantic12ignoreNormalE[1];
|
|
.global .align 1 .b8 _ZN23rti_internal_annotation7pixelIDE[1];
|
|
.global .align 1 .b8 _ZN23rti_internal_annotation10resolutionE[1];
|
|
.global .align 1 .b8 _ZN23rti_internal_annotation6normalE[1];
|
|
.global .align 1 .b8 _ZN23rti_internal_annotation6camPosE[1];
|
|
.global .align 1 .b8 _ZN23rti_internal_annotation4rootE[1];
|
|
.global .align 1 .b8 _ZN23rti_internal_annotation12imageEnabledE[1];
|
|
.global .align 1 .b8 _ZN23rti_internal_annotation8tileInfoE[1];
|
|
.global .align 1 .b8 _ZN23rti_internal_annotation8additiveE[1];
|
|
.global .align 1 .b8 _ZN23rti_internal_annotation12ignoreNormalE[1];
|
|
|
|
.visible .entry _Z6oxMainv(
|
|
|
|
)
|
|
{
|
|
.local .align 4 .b8 __local_depot0[4];
|
|
.reg .b64 %SP;
|
|
.reg .b64 %SPL;
|
|
.reg .pred %p<133>;
|
|
.reg .b16 %rs<63>;
|
|
.reg .f32 %f<1214>;
|
|
.reg .b32 %r<201>;
|
|
.reg .b64 %rd<126>;
|
|
|
|
|
|
mov.u64 %rd125, __local_depot0;
|
|
cvta.local.u64 %SP, %rd125;
|
|
ld.global.v2.u32 {%r30, %r31}, [pixelID];
|
|
cvt.u64.u32 %rd10, %r30;
|
|
cvt.u64.u32 %rd11, %r31;
|
|
mov.u64 %rd14, uvnormal;
|
|
cvta.global.u64 %rd9, %rd14;
|
|
mov.u32 %r28, 2;
|
|
mov.u32 %r29, 4;
|
|
mov.u64 %rd13, 0;
|
|
// inline asm
|
|
call (%rd8), _rt_buffer_get_64, (%rd9, %r28, %r29, %rd10, %rd11, %rd13, %rd13);
|
|
// inline asm
|
|
ld.u32 %r1, [%rd8];
|
|
shr.u32 %r34, %r1, 16;
|
|
cvt.u16.u32 %rs1, %r34;
|
|
and.b16 %rs5, %rs1, 255;
|
|
cvt.u16.u32 %rs6, %r1;
|
|
or.b16 %rs7, %rs6, %rs5;
|
|
setp.eq.s16 %p8, %rs7, 0;
|
|
mov.f32 %f1155, 0f00000000;
|
|
mov.f32 %f1156, %f1155;
|
|
mov.f32 %f1157, %f1155;
|
|
@%p8 bra BB0_2;
|
|
|
|
ld.u8 %rs8, [%rd8+1];
|
|
and.b16 %rs10, %rs6, 255;
|
|
cvt.rn.f32.u16 %f205, %rs10;
|
|
div.rn.f32 %f206, %f205, 0f437F0000;
|
|
fma.rn.f32 %f207, %f206, 0f40000000, 0fBF800000;
|
|
cvt.rn.f32.u16 %f208, %rs8;
|
|
div.rn.f32 %f209, %f208, 0f437F0000;
|
|
fma.rn.f32 %f210, %f209, 0f40000000, 0fBF800000;
|
|
cvt.rn.f32.u16 %f211, %rs5;
|
|
div.rn.f32 %f212, %f211, 0f437F0000;
|
|
fma.rn.f32 %f213, %f212, 0f40000000, 0fBF800000;
|
|
mul.f32 %f214, %f210, %f210;
|
|
fma.rn.f32 %f215, %f207, %f207, %f214;
|
|
fma.rn.f32 %f216, %f213, %f213, %f215;
|
|
sqrt.rn.f32 %f217, %f216;
|
|
rcp.rn.f32 %f218, %f217;
|
|
mul.f32 %f1155, %f207, %f218;
|
|
mul.f32 %f1156, %f210, %f218;
|
|
mul.f32 %f1157, %f213, %f218;
|
|
|
|
BB0_2:
|
|
ld.global.v2.u32 {%r35, %r36}, [pixelID];
|
|
ld.global.v2.u32 {%r38, %r39}, [tileInfo];
|
|
add.s32 %r2, %r35, %r38;
|
|
add.s32 %r3, %r36, %r39;
|
|
setp.eq.f32 %p9, %f1156, 0f00000000;
|
|
setp.eq.f32 %p10, %f1155, 0f00000000;
|
|
and.pred %p11, %p10, %p9;
|
|
setp.eq.f32 %p12, %f1157, 0f00000000;
|
|
and.pred %p13, %p11, %p12;
|
|
@%p13 bra BB0_100;
|
|
bra.uni BB0_3;
|
|
|
|
BB0_100:
|
|
ld.global.u32 %r200, [imageEnabled];
|
|
and.b32 %r175, %r200, 1;
|
|
setp.eq.b32 %p127, %r175, 1;
|
|
@!%p127 bra BB0_102;
|
|
bra.uni BB0_101;
|
|
|
|
BB0_101:
|
|
cvt.u64.u32 %rd86, %r2;
|
|
cvt.u64.u32 %rd87, %r3;
|
|
mov.u64 %rd90, image;
|
|
cvta.global.u64 %rd85, %rd90;
|
|
// inline asm
|
|
call (%rd84), _rt_buffer_get_64, (%rd85, %r28, %r29, %rd86, %rd87, %rd13, %rd13);
|
|
// inline asm
|
|
mov.u16 %rs43, 0;
|
|
st.v4.u8 [%rd84], {%rs43, %rs43, %rs43, %rs43};
|
|
ld.global.u32 %r200, [imageEnabled];
|
|
|
|
BB0_102:
|
|
and.b32 %r178, %r200, 8;
|
|
setp.eq.s32 %p128, %r178, 0;
|
|
@%p128 bra BB0_104;
|
|
|
|
cvt.u64.u32 %rd93, %r2;
|
|
cvt.u64.u32 %rd94, %r3;
|
|
mov.u64 %rd97, image_Mask;
|
|
cvta.global.u64 %rd92, %rd97;
|
|
// inline asm
|
|
call (%rd91), _rt_buffer_get_64, (%rd92, %r28, %r28, %rd93, %rd94, %rd13, %rd13);
|
|
// inline asm
|
|
mov.f32 %f1147, 0f00000000;
|
|
cvt.rzi.u32.f32 %r181, %f1147;
|
|
cvt.u16.u32 %rs44, %r181;
|
|
mov.u16 %rs45, 0;
|
|
st.v2.u8 [%rd91], {%rs44, %rs45};
|
|
ld.global.u32 %r200, [imageEnabled];
|
|
|
|
BB0_104:
|
|
and.b32 %r182, %r200, 4;
|
|
setp.eq.s32 %p129, %r182, 0;
|
|
@%p129 bra BB0_108;
|
|
|
|
ld.global.u32 %r183, [additive];
|
|
setp.eq.s32 %p130, %r183, 0;
|
|
cvt.u64.u32 %rd6, %r2;
|
|
cvt.u64.u32 %rd7, %r3;
|
|
@%p130 bra BB0_107;
|
|
|
|
mov.u64 %rd110, image_HDR;
|
|
cvta.global.u64 %rd99, %rd110;
|
|
mov.u32 %r187, 8;
|
|
// inline asm
|
|
call (%rd98), _rt_buffer_get_64, (%rd99, %r28, %r187, %rd6, %rd7, %rd13, %rd13);
|
|
// inline asm
|
|
ld.v4.u16 {%rs52, %rs53, %rs54, %rs55}, [%rd98];
|
|
// inline asm
|
|
{ cvt.f32.f16 %f1148, %rs52;}
|
|
|
|
// inline asm
|
|
// inline asm
|
|
{ cvt.f32.f16 %f1149, %rs53;}
|
|
|
|
// inline asm
|
|
// inline asm
|
|
{ cvt.f32.f16 %f1150, %rs54;}
|
|
|
|
// inline asm
|
|
// inline asm
|
|
call (%rd104), _rt_buffer_get_64, (%rd99, %r28, %r187, %rd6, %rd7, %rd13, %rd13);
|
|
// inline asm
|
|
add.f32 %f1151, %f1148, 0f00000000;
|
|
add.f32 %f1152, %f1149, 0f00000000;
|
|
add.f32 %f1153, %f1150, 0f00000000;
|
|
// inline asm
|
|
{ cvt.rn.f16.f32 %rs51, %f1153;}
|
|
|
|
// inline asm
|
|
// inline asm
|
|
{ cvt.rn.f16.f32 %rs50, %f1152;}
|
|
|
|
// inline asm
|
|
// inline asm
|
|
{ cvt.rn.f16.f32 %rs49, %f1151;}
|
|
|
|
// inline asm
|
|
mov.u16 %rs56, 0;
|
|
st.v4.u16 [%rd104], {%rs49, %rs50, %rs51, %rs56};
|
|
bra.uni BB0_108;
|
|
|
|
BB0_3:
|
|
ld.global.v2.u32 {%r47, %r48}, [pixelID];
|
|
cvt.u64.u32 %rd17, %r47;
|
|
cvt.u64.u32 %rd18, %r48;
|
|
mov.u64 %rd26, uvpos;
|
|
cvta.global.u64 %rd16, %rd26;
|
|
mov.u32 %r44, 12;
|
|
// inline asm
|
|
call (%rd15), _rt_buffer_get_64, (%rd16, %r28, %r44, %rd17, %rd18, %rd13, %rd13);
|
|
// inline asm
|
|
ld.f32 %f9, [%rd15+8];
|
|
ld.f32 %f8, [%rd15+4];
|
|
ld.f32 %f7, [%rd15];
|
|
mul.f32 %f226, %f7, 0f3456BF95;
|
|
mul.f32 %f227, %f8, 0f3456BF95;
|
|
mul.f32 %f228, %f9, 0f3456BF95;
|
|
abs.f32 %f229, %f1155;
|
|
div.rn.f32 %f230, %f226, %f229;
|
|
abs.f32 %f231, %f1156;
|
|
div.rn.f32 %f232, %f227, %f231;
|
|
abs.f32 %f233, %f1157;
|
|
div.rn.f32 %f234, %f228, %f233;
|
|
abs.f32 %f235, %f230;
|
|
abs.f32 %f236, %f232;
|
|
abs.f32 %f237, %f234;
|
|
mov.f32 %f238, 0f38D1B717;
|
|
max.f32 %f239, %f235, %f238;
|
|
max.f32 %f240, %f236, %f238;
|
|
max.f32 %f241, %f237, %f238;
|
|
fma.rn.f32 %f10, %f1155, %f239, %f7;
|
|
fma.rn.f32 %f11, %f1156, %f240, %f8;
|
|
fma.rn.f32 %f12, %f1157, %f241, %f9;
|
|
mov.u64 %rd27, localLights;
|
|
cvta.global.u64 %rd25, %rd27;
|
|
mov.u32 %r45, 1;
|
|
mov.u32 %r46, 96;
|
|
// inline asm
|
|
call (%rd21, %rd22, %rd23, %rd24), _rt_buffer_get_size_64, (%rd25, %r45, %r46);
|
|
// inline asm
|
|
cvt.u32.u64 %r4, %rd21;
|
|
setp.eq.s32 %p14, %r4, 0;
|
|
mov.f32 %f1158, 0f00000000;
|
|
mov.f32 %f18, %f1158;
|
|
mov.f32 %f19, %f1158;
|
|
mov.f32 %f20, %f1158;
|
|
mov.f32 %f1162, %f1158;
|
|
mov.f32 %f1163, %f1158;
|
|
mov.f32 %f1164, %f1158;
|
|
@%p14 bra BB0_46;
|
|
|
|
mov.f32 %f249, 0f40000000;
|
|
cvt.rzi.f32.f32 %f250, %f249;
|
|
add.f32 %f251, %f250, %f250;
|
|
mov.f32 %f252, 0f40800000;
|
|
sub.f32 %f253, %f252, %f251;
|
|
abs.f32 %f13, %f253;
|
|
mul.f32 %f14, %f10, 0f3456BF95;
|
|
mul.f32 %f15, %f11, 0f3456BF95;
|
|
mul.f32 %f16, %f12, 0f3456BF95;
|
|
mov.f32 %f248, 0f00000000;
|
|
mov.u32 %r192, 0;
|
|
abs.f32 %f432, %f14;
|
|
abs.f32 %f433, %f15;
|
|
max.f32 %f434, %f432, %f433;
|
|
abs.f32 %f435, %f16;
|
|
max.f32 %f436, %f434, %f435;
|
|
mov.f32 %f1158, %f248;
|
|
mov.f32 %f18, %f248;
|
|
mov.f32 %f19, %f248;
|
|
mov.f32 %f20, %f248;
|
|
mov.f32 %f1162, %f248;
|
|
mov.f32 %f1163, %f248;
|
|
mov.f32 %f1164, %f248;
|
|
|
|
BB0_5:
|
|
cvt.u64.u32 %rd30, %r192;
|
|
// inline asm
|
|
call (%rd28), _rt_buffer_get_64, (%rd25, %r45, %r46, %rd30, %rd13, %rd13, %rd13);
|
|
// inline asm
|
|
ld.v4.f32 {%f256, %f257, %f258, %f259}, [%rd28+80];
|
|
ld.v4.f32 {%f260, %f261, %f262, %f263}, [%rd28+64];
|
|
ld.v4.f32 {%f264, %f265, %f266, %f267}, [%rd28+48];
|
|
ld.v4.f32 {%f268, %f1169, %f1170, %f271}, [%rd28+32];
|
|
ld.v4.f32 {%f272, %f273, %f274, %f275}, [%rd28+16];
|
|
ld.v4.f32 {%f276, %f277, %f278, %f279}, [%rd28];
|
|
mov.b32 %r6, %f259;
|
|
sub.f32 %f281, %f277, %f7;
|
|
sub.f32 %f282, %f278, %f8;
|
|
sub.f32 %f283, %f279, %f9;
|
|
mul.f32 %f284, %f282, %f282;
|
|
fma.rn.f32 %f285, %f281, %f281, %f284;
|
|
fma.rn.f32 %f286, %f283, %f283, %f285;
|
|
sqrt.rn.f32 %f50, %f286;
|
|
rcp.rn.f32 %f287, %f50;
|
|
mul.f32 %f51, %f281, %f287;
|
|
mul.f32 %f52, %f282, %f287;
|
|
mul.f32 %f53, %f283, %f287;
|
|
mul.f32 %f54, %f50, %f275;
|
|
abs.f32 %f55, %f54;
|
|
setp.lt.f32 %p15, %f55, 0f00800000;
|
|
mul.f32 %f288, %f55, 0f4B800000;
|
|
selp.f32 %f289, 0fC3170000, 0fC2FE0000, %p15;
|
|
selp.f32 %f290, %f288, %f55, %p15;
|
|
mov.b32 %r54, %f290;
|
|
and.b32 %r55, %r54, 8388607;
|
|
or.b32 %r56, %r55, 1065353216;
|
|
mov.b32 %f291, %r56;
|
|
shr.u32 %r57, %r54, 23;
|
|
cvt.rn.f32.u32 %f292, %r57;
|
|
add.f32 %f293, %f289, %f292;
|
|
setp.gt.f32 %p16, %f291, 0f3FB504F3;
|
|
mul.f32 %f294, %f291, 0f3F000000;
|
|
add.f32 %f295, %f293, 0f3F800000;
|
|
selp.f32 %f296, %f294, %f291, %p16;
|
|
selp.f32 %f297, %f295, %f293, %p16;
|
|
add.f32 %f298, %f296, 0fBF800000;
|
|
add.f32 %f255, %f296, 0f3F800000;
|
|
// inline asm
|
|
rcp.approx.ftz.f32 %f254,%f255;
|
|
// inline asm
|
|
add.f32 %f299, %f298, %f298;
|
|
mul.f32 %f300, %f254, %f299;
|
|
mul.f32 %f301, %f300, %f300;
|
|
mov.f32 %f302, 0f3C4CAF63;
|
|
mov.f32 %f303, 0f3B18F0FE;
|
|
fma.rn.f32 %f304, %f303, %f301, %f302;
|
|
mov.f32 %f305, 0f3DAAAABD;
|
|
fma.rn.f32 %f306, %f304, %f301, %f305;
|
|
mul.rn.f32 %f307, %f306, %f301;
|
|
mul.rn.f32 %f308, %f307, %f300;
|
|
sub.f32 %f309, %f298, %f300;
|
|
neg.f32 %f310, %f300;
|
|
add.f32 %f311, %f309, %f309;
|
|
fma.rn.f32 %f312, %f310, %f298, %f311;
|
|
mul.rn.f32 %f313, %f254, %f312;
|
|
add.f32 %f314, %f308, %f300;
|
|
sub.f32 %f315, %f300, %f314;
|
|
add.f32 %f316, %f308, %f315;
|
|
add.f32 %f317, %f313, %f316;
|
|
add.f32 %f318, %f314, %f317;
|
|
sub.f32 %f319, %f314, %f318;
|
|
add.f32 %f320, %f317, %f319;
|
|
mov.f32 %f321, 0f3F317200;
|
|
mul.rn.f32 %f322, %f297, %f321;
|
|
mov.f32 %f323, 0f35BFBE8E;
|
|
mul.rn.f32 %f324, %f297, %f323;
|
|
add.f32 %f325, %f322, %f318;
|
|
sub.f32 %f326, %f322, %f325;
|
|
add.f32 %f327, %f318, %f326;
|
|
add.f32 %f328, %f320, %f327;
|
|
add.f32 %f329, %f324, %f328;
|
|
add.f32 %f330, %f325, %f329;
|
|
sub.f32 %f331, %f325, %f330;
|
|
add.f32 %f332, %f329, %f331;
|
|
mul.rn.f32 %f56, %f252, %f330;
|
|
neg.f32 %f334, %f56;
|
|
fma.rn.f32 %f335, %f252, %f330, %f334;
|
|
fma.rn.f32 %f336, %f252, %f332, %f335;
|
|
fma.rn.f32 %f57, %f248, %f330, %f336;
|
|
add.rn.f32 %f58, %f56, %f57;
|
|
mov.b32 %r58, %f58;
|
|
setp.eq.s32 %p1, %r58, 1118925336;
|
|
add.s32 %r59, %r58, -1;
|
|
mov.b32 %f338, %r59;
|
|
selp.f32 %f339, %f338, %f58, %p1;
|
|
mul.f32 %f340, %f339, 0f3FB8AA3B;
|
|
cvt.rzi.f32.f32 %f341, %f340;
|
|
mov.f32 %f342, 0fBF317200;
|
|
fma.rn.f32 %f343, %f341, %f342, %f339;
|
|
mov.f32 %f344, 0fB5BFBE8E;
|
|
fma.rn.f32 %f345, %f341, %f344, %f343;
|
|
mul.f32 %f346, %f345, 0f3FB8AA3B;
|
|
ex2.approx.ftz.f32 %f347, %f346;
|
|
add.f32 %f348, %f341, 0f00000000;
|
|
ex2.approx.f32 %f349, %f348;
|
|
mul.f32 %f350, %f347, %f349;
|
|
setp.lt.f32 %p17, %f339, 0fC2D20000;
|
|
selp.f32 %f351, 0f00000000, %f350, %p17;
|
|
setp.gt.f32 %p18, %f339, 0f42D20000;
|
|
selp.f32 %f1165, 0f7F800000, %f351, %p18;
|
|
setp.eq.f32 %p19, %f1165, 0f7F800000;
|
|
@%p19 bra BB0_7;
|
|
|
|
neg.f32 %f352, %f58;
|
|
add.rn.f32 %f353, %f56, %f352;
|
|
add.rn.f32 %f354, %f353, %f57;
|
|
add.f32 %f355, %f354, 0f37000000;
|
|
selp.f32 %f356, %f355, %f354, %p1;
|
|
fma.rn.f32 %f1165, %f1165, %f356, %f1165;
|
|
|
|
BB0_7:
|
|
setp.lt.f32 %p20, %f54, 0f00000000;
|
|
setp.eq.f32 %p21, %f13, 0f3F800000;
|
|
and.pred %p2, %p20, %p21;
|
|
mov.b32 %r60, %f1165;
|
|
xor.b32 %r61, %r60, -2147483648;
|
|
mov.b32 %f357, %r61;
|
|
selp.f32 %f1167, %f357, %f1165, %p2;
|
|
setp.eq.f32 %p22, %f54, 0f00000000;
|
|
@%p22 bra BB0_10;
|
|
bra.uni BB0_8;
|
|
|
|
BB0_10:
|
|
add.f32 %f360, %f54, %f54;
|
|
selp.f32 %f1167, %f360, 0f00000000, %p21;
|
|
bra.uni BB0_11;
|
|
|
|
BB0_8:
|
|
setp.geu.f32 %p23, %f54, 0f00000000;
|
|
@%p23 bra BB0_11;
|
|
|
|
cvt.rzi.f32.f32 %f359, %f252;
|
|
setp.neu.f32 %p24, %f359, 0f40800000;
|
|
selp.f32 %f1167, 0f7FFFFFFF, %f1167, %p24;
|
|
|
|
BB0_11:
|
|
add.f32 %f361, %f55, 0f40800000;
|
|
mov.b32 %r62, %f361;
|
|
setp.lt.s32 %p26, %r62, 2139095040;
|
|
@%p26 bra BB0_16;
|
|
|
|
setp.gtu.f32 %p27, %f55, 0f7F800000;
|
|
@%p27 bra BB0_15;
|
|
bra.uni BB0_13;
|
|
|
|
BB0_15:
|
|
add.f32 %f1167, %f54, 0f40800000;
|
|
bra.uni BB0_16;
|
|
|
|
BB0_13:
|
|
setp.neu.f32 %p28, %f55, 0f7F800000;
|
|
@%p28 bra BB0_16;
|
|
|
|
selp.f32 %f1167, 0fFF800000, 0f7F800000, %p2;
|
|
|
|
BB0_16:
|
|
mul.f32 %f362, %f50, %f273;
|
|
mov.f32 %f1183, 0f3F800000;
|
|
sub.f32 %f364, %f1183, %f1167;
|
|
setp.eq.f32 %p29, %f54, 0f3F800000;
|
|
selp.f32 %f365, 0f00000000, %f364, %p29;
|
|
cvt.sat.f32.f32 %f366, %f365;
|
|
fma.rn.f32 %f367, %f362, %f362, %f274;
|
|
div.rn.f32 %f84, %f366, %f367;
|
|
mul.f32 %f368, %f1156, %f52;
|
|
fma.rn.f32 %f369, %f1155, %f51, %f368;
|
|
fma.rn.f32 %f370, %f1157, %f53, %f369;
|
|
ld.global.u32 %r63, [ignoreNormal];
|
|
setp.eq.s32 %p30, %r63, 0;
|
|
selp.f32 %f371, %f370, 0f3F800000, %p30;
|
|
cvt.sat.f32.f32 %f85, %f371;
|
|
setp.eq.f32 %p31, %f276, 0f3F800000;
|
|
@%p31 bra BB0_23;
|
|
bra.uni BB0_17;
|
|
|
|
BB0_23:
|
|
setp.leu.f32 %p35, %f271, 0f00000000;
|
|
@%p35 bra BB0_19;
|
|
|
|
mul.f32 %f402, %f256, %f51;
|
|
mul.f32 %f403, %f257, %f52;
|
|
neg.f32 %f404, %f403;
|
|
sub.f32 %f405, %f404, %f402;
|
|
mul.f32 %f406, %f258, %f53;
|
|
sub.f32 %f407, %f405, %f406;
|
|
setp.gt.f32 %p36, %f407, 0f00000000;
|
|
selp.f32 %f408, 0f3F800000, 0f00000000, %p36;
|
|
mul.f32 %f409, %f265, %f52;
|
|
fma.rn.f32 %f410, %f264, %f51, %f409;
|
|
mul.f32 %f411, %f261, %f52;
|
|
fma.rn.f32 %f412, %f260, %f51, %f411;
|
|
fma.rn.f32 %f413, %f266, %f53, %f410;
|
|
fma.rn.f32 %f414, %f262, %f53, %f412;
|
|
fma.rn.f32 %f415, %f267, %f413, 0f3F000000;
|
|
mov.f32 %f416, 0f3F800000;
|
|
sub.f32 %f398, %f416, %f415;
|
|
fma.rn.f32 %f399, %f267, %f414, 0f3F000000;
|
|
cvt.rzi.s32.f32 %r67, %f271;
|
|
mov.f32 %f401, 0f00000000;
|
|
// inline asm
|
|
call (%f394, %f395, %f396, %f397), _rt_texture_get_f_id, (%r67, %r28, %f398, %f399, %f401, %f401);
|
|
// inline asm
|
|
mul.f32 %f417, %f408, %f394;
|
|
mul.f32 %f418, %f408, %f395;
|
|
mul.f32 %f419, %f408, %f396;
|
|
mul.f32 %f1168, %f268, %f417;
|
|
mul.f32 %f1169, %f1169, %f418;
|
|
mul.f32 %f1170, %f1170, %f419;
|
|
bra.uni BB0_25;
|
|
|
|
BB0_17:
|
|
setp.eq.f32 %p32, %f276, 0f40000000;
|
|
@%p32 bra BB0_21;
|
|
bra.uni BB0_18;
|
|
|
|
BB0_21:
|
|
setp.leu.f32 %p34, %f271, 0f00000000;
|
|
@%p34 bra BB0_19;
|
|
|
|
mul.f32 %f388, %f265, %f52;
|
|
fma.rn.f32 %f389, %f264, %f51, %f388;
|
|
mul.f32 %f390, %f261, %f52;
|
|
fma.rn.f32 %f391, %f260, %f51, %f390;
|
|
mul.f32 %f392, %f257, %f52;
|
|
fma.rn.f32 %f393, %f256, %f51, %f392;
|
|
fma.rn.f32 %f385, %f266, %f53, %f389;
|
|
fma.rn.f32 %f386, %f262, %f53, %f391;
|
|
fma.rn.f32 %f387, %f258, %f53, %f393;
|
|
cvt.rzi.s32.f32 %r64, %f271;
|
|
mov.u32 %r65, 6;
|
|
mov.u32 %r66, 0;
|
|
// inline asm
|
|
call (%f381, %f382, %f383, %f384), _rt_texture_get_base_id, (%r64, %r65, %f385, %f386, %f387, %r66);
|
|
// inline asm
|
|
mul.f32 %f1168, %f268, %f381;
|
|
mul.f32 %f1169, %f1169, %f382;
|
|
mul.f32 %f1170, %f1170, %f383;
|
|
bra.uni BB0_25;
|
|
|
|
BB0_18:
|
|
setp.neu.f32 %p33, %f276, 0f40800000;
|
|
@%p33 bra BB0_19;
|
|
|
|
mul.f32 %f372, %f256, %f51;
|
|
mul.f32 %f373, %f257, %f52;
|
|
neg.f32 %f374, %f373;
|
|
sub.f32 %f375, %f374, %f372;
|
|
mul.f32 %f376, %f258, %f53;
|
|
sub.f32 %f377, %f375, %f376;
|
|
fma.rn.f32 %f378, %f271, %f377, %f267;
|
|
cvt.sat.f32.f32 %f379, %f378;
|
|
mul.f32 %f380, %f379, %f379;
|
|
mul.f32 %f1171, %f84, %f380;
|
|
mov.f32 %f1168, %f268;
|
|
bra.uni BB0_26;
|
|
|
|
BB0_19:
|
|
mov.f32 %f1168, %f268;
|
|
|
|
BB0_25:
|
|
mov.f32 %f1171, %f84;
|
|
|
|
BB0_26:
|
|
max.f32 %f426, %f1168, %f1169;
|
|
max.f32 %f427, %f426, %f1170;
|
|
mul.f32 %f97, %f85, %f1171;
|
|
mul.f32 %f428, %f97, %f427;
|
|
setp.lt.f32 %p38, %f428, 0f3727C5AC;
|
|
mov.pred %p132, -1;
|
|
mov.f32 %f104, 0f00000000;
|
|
mov.f32 %f105, %f104;
|
|
mov.f32 %f106, %f104;
|
|
mov.f32 %f107, %f104;
|
|
mov.f32 %f108, %f104;
|
|
mov.f32 %f109, %f104;
|
|
@%p38 bra BB0_28;
|
|
|
|
mul.f32 %f104, %f1168, %f97;
|
|
mul.f32 %f105, %f1169, %f97;
|
|
mul.f32 %f106, %f1170, %f97;
|
|
ld.global.u8 %rs12, [imageEnabled];
|
|
and.b16 %rs13, %rs12, 64;
|
|
setp.eq.s16 %p40, %rs13, 0;
|
|
selp.f32 %f107, 0f00000000, %f51, %p40;
|
|
selp.f32 %f108, 0f00000000, %f52, %p40;
|
|
selp.f32 %f109, 0f00000000, %f53, %p40;
|
|
mov.pred %p132, 0;
|
|
|
|
BB0_28:
|
|
@%p132 bra BB0_45;
|
|
|
|
setp.eq.s32 %p41, %r6, 0;
|
|
mov.u16 %rs62, 0;
|
|
@%p41 bra BB0_40;
|
|
|
|
abs.s32 %r8, %r6;
|
|
mov.f32 %f1182, 0f00000000;
|
|
setp.lt.s32 %p42, %r8, 1;
|
|
@%p42 bra BB0_39;
|
|
|
|
max.f32 %f111, %f436, %f238;
|
|
and.b32 %r9, %r8, 3;
|
|
setp.eq.s32 %p43, %r9, 0;
|
|
add.u64 %rd35, %SP, 0;
|
|
cvta.to.local.u64 %rd2, %rd35;
|
|
mov.f32 %f1182, 0f00000000;
|
|
mov.u32 %r196, 0;
|
|
@%p43 bra BB0_37;
|
|
|
|
setp.eq.s32 %p44, %r9, 1;
|
|
mov.f32 %f1179, 0f00000000;
|
|
mov.u32 %r194, 0;
|
|
@%p44 bra BB0_36;
|
|
|
|
setp.eq.s32 %p45, %r9, 2;
|
|
mov.f32 %f1178, 0f00000000;
|
|
mov.u32 %r193, 0;
|
|
@%p45 bra BB0_35;
|
|
|
|
sub.f32 %f448, %f277, %f272;
|
|
sub.f32 %f449, %f278, %f272;
|
|
sub.f32 %f450, %f279, %f272;
|
|
sub.f32 %f451, %f448, %f7;
|
|
sub.f32 %f452, %f449, %f8;
|
|
sub.f32 %f453, %f450, %f9;
|
|
mul.f32 %f454, %f452, %f452;
|
|
fma.rn.f32 %f455, %f451, %f451, %f454;
|
|
fma.rn.f32 %f456, %f453, %f453, %f455;
|
|
sqrt.rn.f32 %f447, %f456;
|
|
rcp.rn.f32 %f457, %f447;
|
|
mul.f32 %f443, %f457, %f451;
|
|
mul.f32 %f444, %f457, %f452;
|
|
mul.f32 %f445, %f457, %f453;
|
|
ld.global.u32 %r76, [imageEnabled];
|
|
and.b32 %r77, %r76, 32;
|
|
setp.eq.s32 %p46, %r77, 0;
|
|
selp.f32 %f458, 0f3F800000, 0f41200000, %p46;
|
|
mul.f32 %f446, %f458, %f111;
|
|
mov.u32 %r78, 1065353216;
|
|
st.local.u32 [%rd2], %r78;
|
|
ld.global.u32 %r72, [root];
|
|
// inline asm
|
|
call _rt_trace_64, (%r72, %f10, %f11, %f12, %f443, %f444, %f445, %r45, %f446, %f447, %rd35, %r29);
|
|
// inline asm
|
|
ld.local.f32 %f459, [%rd2];
|
|
add.f32 %f1178, %f459, 0f00000000;
|
|
mov.u32 %r193, %r45;
|
|
|
|
BB0_35:
|
|
cvt.rn.f32.s32 %f468, %r193;
|
|
mul.f32 %f469, %f468, 0f3DD32618;
|
|
cvt.rmi.f32.f32 %f470, %f469;
|
|
sub.f32 %f471, %f469, %f470;
|
|
mul.f32 %f472, %f468, 0f3DD2F1AA;
|
|
cvt.rmi.f32.f32 %f473, %f472;
|
|
sub.f32 %f474, %f472, %f473;
|
|
mul.f32 %f475, %f468, 0f3DC74539;
|
|
cvt.rmi.f32.f32 %f476, %f475;
|
|
sub.f32 %f477, %f475, %f476;
|
|
add.f32 %f478, %f474, 0f4199851F;
|
|
add.f32 %f479, %f477, 0f4199851F;
|
|
add.f32 %f480, %f471, 0f4199851F;
|
|
mul.f32 %f481, %f474, %f479;
|
|
fma.rn.f32 %f482, %f471, %f478, %f481;
|
|
fma.rn.f32 %f483, %f480, %f477, %f482;
|
|
add.f32 %f484, %f471, %f483;
|
|
add.f32 %f485, %f474, %f483;
|
|
add.f32 %f486, %f477, %f483;
|
|
add.f32 %f487, %f484, %f485;
|
|
mul.f32 %f488, %f486, %f487;
|
|
cvt.rmi.f32.f32 %f489, %f488;
|
|
sub.f32 %f490, %f488, %f489;
|
|
add.f32 %f491, %f484, %f486;
|
|
mul.f32 %f492, %f485, %f491;
|
|
cvt.rmi.f32.f32 %f493, %f492;
|
|
sub.f32 %f494, %f492, %f493;
|
|
add.f32 %f495, %f485, %f486;
|
|
mul.f32 %f496, %f484, %f495;
|
|
cvt.rmi.f32.f32 %f497, %f496;
|
|
sub.f32 %f498, %f496, %f497;
|
|
fma.rn.f32 %f499, %f490, 0f40000000, 0fBF800000;
|
|
fma.rn.f32 %f500, %f494, 0f40000000, 0fBF800000;
|
|
fma.rn.f32 %f501, %f498, 0f40000000, 0fBF800000;
|
|
fma.rn.f32 %f502, %f272, %f499, %f277;
|
|
fma.rn.f32 %f503, %f272, %f500, %f278;
|
|
fma.rn.f32 %f504, %f272, %f501, %f279;
|
|
sub.f32 %f505, %f502, %f7;
|
|
sub.f32 %f506, %f503, %f8;
|
|
sub.f32 %f507, %f504, %f9;
|
|
mul.f32 %f508, %f506, %f506;
|
|
fma.rn.f32 %f509, %f505, %f505, %f508;
|
|
fma.rn.f32 %f510, %f507, %f507, %f509;
|
|
sqrt.rn.f32 %f467, %f510;
|
|
rcp.rn.f32 %f511, %f467;
|
|
mul.f32 %f463, %f511, %f505;
|
|
mul.f32 %f464, %f511, %f506;
|
|
mul.f32 %f465, %f511, %f507;
|
|
ld.global.u32 %r82, [imageEnabled];
|
|
and.b32 %r83, %r82, 32;
|
|
setp.eq.s32 %p47, %r83, 0;
|
|
selp.f32 %f512, 0f3F800000, 0f41200000, %p47;
|
|
mul.f32 %f466, %f512, %f111;
|
|
mov.u32 %r84, 1065353216;
|
|
st.local.u32 [%rd2], %r84;
|
|
ld.global.u32 %r79, [root];
|
|
// inline asm
|
|
call _rt_trace_64, (%r79, %f10, %f11, %f12, %f463, %f464, %f465, %r45, %f466, %f467, %rd35, %r29);
|
|
// inline asm
|
|
ld.local.f32 %f513, [%rd2];
|
|
add.f32 %f1179, %f1178, %f513;
|
|
add.s32 %r194, %r193, 1;
|
|
|
|
BB0_36:
|
|
cvt.rn.f32.s32 %f522, %r194;
|
|
mul.f32 %f523, %f522, 0f3DD32618;
|
|
cvt.rmi.f32.f32 %f524, %f523;
|
|
sub.f32 %f525, %f523, %f524;
|
|
mul.f32 %f526, %f522, 0f3DD2F1AA;
|
|
cvt.rmi.f32.f32 %f527, %f526;
|
|
sub.f32 %f528, %f526, %f527;
|
|
mul.f32 %f529, %f522, 0f3DC74539;
|
|
cvt.rmi.f32.f32 %f530, %f529;
|
|
sub.f32 %f531, %f529, %f530;
|
|
add.f32 %f532, %f528, 0f4199851F;
|
|
add.f32 %f533, %f531, 0f4199851F;
|
|
add.f32 %f534, %f525, 0f4199851F;
|
|
mul.f32 %f535, %f528, %f533;
|
|
fma.rn.f32 %f536, %f525, %f532, %f535;
|
|
fma.rn.f32 %f537, %f534, %f531, %f536;
|
|
add.f32 %f538, %f525, %f537;
|
|
add.f32 %f539, %f528, %f537;
|
|
add.f32 %f540, %f531, %f537;
|
|
add.f32 %f541, %f538, %f539;
|
|
mul.f32 %f542, %f540, %f541;
|
|
cvt.rmi.f32.f32 %f543, %f542;
|
|
sub.f32 %f544, %f542, %f543;
|
|
add.f32 %f545, %f538, %f540;
|
|
mul.f32 %f546, %f539, %f545;
|
|
cvt.rmi.f32.f32 %f547, %f546;
|
|
sub.f32 %f548, %f546, %f547;
|
|
add.f32 %f549, %f539, %f540;
|
|
mul.f32 %f550, %f538, %f549;
|
|
cvt.rmi.f32.f32 %f551, %f550;
|
|
sub.f32 %f552, %f550, %f551;
|
|
fma.rn.f32 %f553, %f544, 0f40000000, 0fBF800000;
|
|
fma.rn.f32 %f554, %f548, 0f40000000, 0fBF800000;
|
|
fma.rn.f32 %f555, %f552, 0f40000000, 0fBF800000;
|
|
fma.rn.f32 %f556, %f272, %f553, %f277;
|
|
fma.rn.f32 %f557, %f272, %f554, %f278;
|
|
fma.rn.f32 %f558, %f272, %f555, %f279;
|
|
sub.f32 %f559, %f556, %f7;
|
|
sub.f32 %f560, %f557, %f8;
|
|
sub.f32 %f561, %f558, %f9;
|
|
mul.f32 %f562, %f560, %f560;
|
|
fma.rn.f32 %f563, %f559, %f559, %f562;
|
|
fma.rn.f32 %f564, %f561, %f561, %f563;
|
|
sqrt.rn.f32 %f521, %f564;
|
|
rcp.rn.f32 %f565, %f521;
|
|
mul.f32 %f517, %f565, %f559;
|
|
mul.f32 %f518, %f565, %f560;
|
|
mul.f32 %f519, %f565, %f561;
|
|
ld.global.u32 %r88, [imageEnabled];
|
|
and.b32 %r89, %r88, 32;
|
|
setp.eq.s32 %p48, %r89, 0;
|
|
selp.f32 %f566, 0f3F800000, 0f41200000, %p48;
|
|
mul.f32 %f520, %f566, %f111;
|
|
mov.u32 %r90, 1065353216;
|
|
st.local.u32 [%rd2], %r90;
|
|
ld.global.u32 %r85, [root];
|
|
mov.u32 %r86, 1;
|
|
// inline asm
|
|
call _rt_trace_64, (%r85, %f10, %f11, %f12, %f517, %f518, %f519, %r86, %f520, %f521, %rd35, %r29);
|
|
// inline asm
|
|
ld.local.f32 %f567, [%rd2];
|
|
add.f32 %f1182, %f1179, %f567;
|
|
add.s32 %r196, %r194, 1;
|
|
|
|
BB0_37:
|
|
setp.lt.u32 %p49, %r8, 4;
|
|
@%p49 bra BB0_39;
|
|
|
|
BB0_38:
|
|
cvt.rn.f32.s32 %f600, %r196;
|
|
mul.f32 %f601, %f600, 0f3DD32618;
|
|
cvt.rmi.f32.f32 %f602, %f601;
|
|
sub.f32 %f603, %f601, %f602;
|
|
mul.f32 %f604, %f600, 0f3DD2F1AA;
|
|
cvt.rmi.f32.f32 %f605, %f604;
|
|
sub.f32 %f606, %f604, %f605;
|
|
mul.f32 %f607, %f600, 0f3DC74539;
|
|
cvt.rmi.f32.f32 %f608, %f607;
|
|
sub.f32 %f609, %f607, %f608;
|
|
add.f32 %f610, %f606, 0f4199851F;
|
|
add.f32 %f611, %f609, 0f4199851F;
|
|
add.f32 %f612, %f603, 0f4199851F;
|
|
mul.f32 %f613, %f606, %f611;
|
|
fma.rn.f32 %f614, %f603, %f610, %f613;
|
|
fma.rn.f32 %f615, %f612, %f609, %f614;
|
|
add.f32 %f616, %f603, %f615;
|
|
add.f32 %f617, %f606, %f615;
|
|
add.f32 %f618, %f609, %f615;
|
|
add.f32 %f619, %f616, %f617;
|
|
mul.f32 %f620, %f618, %f619;
|
|
cvt.rmi.f32.f32 %f621, %f620;
|
|
sub.f32 %f622, %f620, %f621;
|
|
add.f32 %f623, %f616, %f618;
|
|
mul.f32 %f624, %f617, %f623;
|
|
cvt.rmi.f32.f32 %f625, %f624;
|
|
sub.f32 %f626, %f624, %f625;
|
|
add.f32 %f627, %f617, %f618;
|
|
mul.f32 %f628, %f616, %f627;
|
|
cvt.rmi.f32.f32 %f629, %f628;
|
|
sub.f32 %f630, %f628, %f629;
|
|
fma.rn.f32 %f631, %f622, 0f40000000, 0fBF800000;
|
|
fma.rn.f32 %f632, %f626, 0f40000000, 0fBF800000;
|
|
fma.rn.f32 %f633, %f630, 0f40000000, 0fBF800000;
|
|
fma.rn.f32 %f634, %f272, %f631, %f277;
|
|
fma.rn.f32 %f635, %f272, %f632, %f278;
|
|
fma.rn.f32 %f636, %f272, %f633, %f279;
|
|
sub.f32 %f637, %f634, %f7;
|
|
sub.f32 %f638, %f635, %f8;
|
|
sub.f32 %f639, %f636, %f9;
|
|
mul.f32 %f640, %f638, %f638;
|
|
fma.rn.f32 %f641, %f637, %f637, %f640;
|
|
fma.rn.f32 %f642, %f639, %f639, %f641;
|
|
sqrt.rn.f32 %f575, %f642;
|
|
rcp.rn.f32 %f643, %f575;
|
|
mul.f32 %f571, %f643, %f637;
|
|
mul.f32 %f572, %f643, %f638;
|
|
mul.f32 %f573, %f643, %f639;
|
|
ld.global.u32 %r103, [imageEnabled];
|
|
and.b32 %r104, %r103, 32;
|
|
setp.eq.s32 %p50, %r104, 0;
|
|
selp.f32 %f644, 0f3F800000, 0f41200000, %p50;
|
|
mul.f32 %f574, %f644, %f111;
|
|
mov.u32 %r105, 1065353216;
|
|
st.local.u32 [%rd2], %r105;
|
|
ld.global.u32 %r91, [root];
|
|
mov.u32 %r101, 1;
|
|
// inline asm
|
|
call _rt_trace_64, (%r91, %f10, %f11, %f12, %f571, %f572, %f573, %r101, %f574, %f575, %rd35, %r29);
|
|
// inline asm
|
|
ld.local.f32 %f645, [%rd2];
|
|
add.f32 %f646, %f1182, %f645;
|
|
add.s32 %r106, %r196, 1;
|
|
cvt.rn.f32.s32 %f647, %r106;
|
|
mul.f32 %f648, %f647, 0f3DD32618;
|
|
cvt.rmi.f32.f32 %f649, %f648;
|
|
sub.f32 %f650, %f648, %f649;
|
|
mul.f32 %f651, %f647, 0f3DD2F1AA;
|
|
cvt.rmi.f32.f32 %f652, %f651;
|
|
sub.f32 %f653, %f651, %f652;
|
|
mul.f32 %f654, %f647, 0f3DC74539;
|
|
cvt.rmi.f32.f32 %f655, %f654;
|
|
sub.f32 %f656, %f654, %f655;
|
|
add.f32 %f657, %f653, 0f4199851F;
|
|
add.f32 %f658, %f656, 0f4199851F;
|
|
add.f32 %f659, %f650, 0f4199851F;
|
|
mul.f32 %f660, %f653, %f658;
|
|
fma.rn.f32 %f661, %f650, %f657, %f660;
|
|
fma.rn.f32 %f662, %f659, %f656, %f661;
|
|
add.f32 %f663, %f650, %f662;
|
|
add.f32 %f664, %f653, %f662;
|
|
add.f32 %f665, %f656, %f662;
|
|
add.f32 %f666, %f663, %f664;
|
|
mul.f32 %f667, %f665, %f666;
|
|
cvt.rmi.f32.f32 %f668, %f667;
|
|
sub.f32 %f669, %f667, %f668;
|
|
add.f32 %f670, %f663, %f665;
|
|
mul.f32 %f671, %f664, %f670;
|
|
cvt.rmi.f32.f32 %f672, %f671;
|
|
sub.f32 %f673, %f671, %f672;
|
|
add.f32 %f674, %f664, %f665;
|
|
mul.f32 %f675, %f663, %f674;
|
|
cvt.rmi.f32.f32 %f676, %f675;
|
|
sub.f32 %f677, %f675, %f676;
|
|
fma.rn.f32 %f678, %f669, 0f40000000, 0fBF800000;
|
|
fma.rn.f32 %f679, %f673, 0f40000000, 0fBF800000;
|
|
fma.rn.f32 %f680, %f677, 0f40000000, 0fBF800000;
|
|
fma.rn.f32 %f681, %f272, %f678, %f277;
|
|
fma.rn.f32 %f682, %f272, %f679, %f278;
|
|
fma.rn.f32 %f683, %f272, %f680, %f279;
|
|
sub.f32 %f684, %f681, %f7;
|
|
sub.f32 %f685, %f682, %f8;
|
|
sub.f32 %f686, %f683, %f9;
|
|
mul.f32 %f687, %f685, %f685;
|
|
fma.rn.f32 %f688, %f684, %f684, %f687;
|
|
fma.rn.f32 %f689, %f686, %f686, %f688;
|
|
sqrt.rn.f32 %f583, %f689;
|
|
rcp.rn.f32 %f690, %f583;
|
|
mul.f32 %f579, %f690, %f684;
|
|
mul.f32 %f580, %f690, %f685;
|
|
mul.f32 %f581, %f690, %f686;
|
|
ld.global.u32 %r107, [imageEnabled];
|
|
and.b32 %r108, %r107, 32;
|
|
setp.eq.s32 %p51, %r108, 0;
|
|
selp.f32 %f691, 0f3F800000, 0f41200000, %p51;
|
|
mul.f32 %f582, %f691, %f111;
|
|
st.local.u32 [%rd2], %r105;
|
|
ld.global.u32 %r94, [root];
|
|
// inline asm
|
|
call _rt_trace_64, (%r94, %f10, %f11, %f12, %f579, %f580, %f581, %r101, %f582, %f583, %rd35, %r29);
|
|
// inline asm
|
|
ld.local.f32 %f692, [%rd2];
|
|
add.f32 %f693, %f646, %f692;
|
|
add.s32 %r109, %r196, 2;
|
|
cvt.rn.f32.s32 %f694, %r109;
|
|
mul.f32 %f695, %f694, 0f3DD32618;
|
|
cvt.rmi.f32.f32 %f696, %f695;
|
|
sub.f32 %f697, %f695, %f696;
|
|
mul.f32 %f698, %f694, 0f3DD2F1AA;
|
|
cvt.rmi.f32.f32 %f699, %f698;
|
|
sub.f32 %f700, %f698, %f699;
|
|
mul.f32 %f701, %f694, 0f3DC74539;
|
|
cvt.rmi.f32.f32 %f702, %f701;
|
|
sub.f32 %f703, %f701, %f702;
|
|
add.f32 %f704, %f700, 0f4199851F;
|
|
add.f32 %f705, %f703, 0f4199851F;
|
|
add.f32 %f706, %f697, 0f4199851F;
|
|
mul.f32 %f707, %f700, %f705;
|
|
fma.rn.f32 %f708, %f697, %f704, %f707;
|
|
fma.rn.f32 %f709, %f706, %f703, %f708;
|
|
add.f32 %f710, %f697, %f709;
|
|
add.f32 %f711, %f700, %f709;
|
|
add.f32 %f712, %f703, %f709;
|
|
add.f32 %f713, %f710, %f711;
|
|
mul.f32 %f714, %f712, %f713;
|
|
cvt.rmi.f32.f32 %f715, %f714;
|
|
sub.f32 %f716, %f714, %f715;
|
|
add.f32 %f717, %f710, %f712;
|
|
mul.f32 %f718, %f711, %f717;
|
|
cvt.rmi.f32.f32 %f719, %f718;
|
|
sub.f32 %f720, %f718, %f719;
|
|
add.f32 %f721, %f711, %f712;
|
|
mul.f32 %f722, %f710, %f721;
|
|
cvt.rmi.f32.f32 %f723, %f722;
|
|
sub.f32 %f724, %f722, %f723;
|
|
fma.rn.f32 %f725, %f716, 0f40000000, 0fBF800000;
|
|
fma.rn.f32 %f726, %f720, 0f40000000, 0fBF800000;
|
|
fma.rn.f32 %f727, %f724, 0f40000000, 0fBF800000;
|
|
fma.rn.f32 %f728, %f272, %f725, %f277;
|
|
fma.rn.f32 %f729, %f272, %f726, %f278;
|
|
fma.rn.f32 %f730, %f272, %f727, %f279;
|
|
sub.f32 %f731, %f728, %f7;
|
|
sub.f32 %f732, %f729, %f8;
|
|
sub.f32 %f733, %f730, %f9;
|
|
mul.f32 %f734, %f732, %f732;
|
|
fma.rn.f32 %f735, %f731, %f731, %f734;
|
|
fma.rn.f32 %f736, %f733, %f733, %f735;
|
|
sqrt.rn.f32 %f591, %f736;
|
|
rcp.rn.f32 %f737, %f591;
|
|
mul.f32 %f587, %f737, %f731;
|
|
mul.f32 %f588, %f737, %f732;
|
|
mul.f32 %f589, %f737, %f733;
|
|
ld.global.u32 %r110, [imageEnabled];
|
|
and.b32 %r111, %r110, 32;
|
|
setp.eq.s32 %p52, %r111, 0;
|
|
selp.f32 %f738, 0f3F800000, 0f41200000, %p52;
|
|
mul.f32 %f590, %f738, %f111;
|
|
st.local.u32 [%rd2], %r105;
|
|
ld.global.u32 %r97, [root];
|
|
// inline asm
|
|
call _rt_trace_64, (%r97, %f10, %f11, %f12, %f587, %f588, %f589, %r101, %f590, %f591, %rd35, %r29);
|
|
// inline asm
|
|
ld.local.f32 %f739, [%rd2];
|
|
add.f32 %f740, %f693, %f739;
|
|
add.s32 %r112, %r196, 3;
|
|
cvt.rn.f32.s32 %f741, %r112;
|
|
mul.f32 %f742, %f741, 0f3DD32618;
|
|
cvt.rmi.f32.f32 %f743, %f742;
|
|
sub.f32 %f744, %f742, %f743;
|
|
mul.f32 %f745, %f741, 0f3DD2F1AA;
|
|
cvt.rmi.f32.f32 %f746, %f745;
|
|
sub.f32 %f747, %f745, %f746;
|
|
mul.f32 %f748, %f741, 0f3DC74539;
|
|
cvt.rmi.f32.f32 %f749, %f748;
|
|
sub.f32 %f750, %f748, %f749;
|
|
add.f32 %f751, %f747, 0f4199851F;
|
|
add.f32 %f752, %f750, 0f4199851F;
|
|
add.f32 %f753, %f744, 0f4199851F;
|
|
mul.f32 %f754, %f747, %f752;
|
|
fma.rn.f32 %f755, %f744, %f751, %f754;
|
|
fma.rn.f32 %f756, %f753, %f750, %f755;
|
|
add.f32 %f757, %f744, %f756;
|
|
add.f32 %f758, %f747, %f756;
|
|
add.f32 %f759, %f750, %f756;
|
|
add.f32 %f760, %f757, %f758;
|
|
mul.f32 %f761, %f759, %f760;
|
|
cvt.rmi.f32.f32 %f762, %f761;
|
|
sub.f32 %f763, %f761, %f762;
|
|
add.f32 %f764, %f757, %f759;
|
|
mul.f32 %f765, %f758, %f764;
|
|
cvt.rmi.f32.f32 %f766, %f765;
|
|
sub.f32 %f767, %f765, %f766;
|
|
add.f32 %f768, %f758, %f759;
|
|
mul.f32 %f769, %f757, %f768;
|
|
cvt.rmi.f32.f32 %f770, %f769;
|
|
sub.f32 %f771, %f769, %f770;
|
|
fma.rn.f32 %f772, %f763, 0f40000000, 0fBF800000;
|
|
fma.rn.f32 %f773, %f767, 0f40000000, 0fBF800000;
|
|
fma.rn.f32 %f774, %f771, 0f40000000, 0fBF800000;
|
|
fma.rn.f32 %f775, %f272, %f772, %f277;
|
|
fma.rn.f32 %f776, %f272, %f773, %f278;
|
|
fma.rn.f32 %f777, %f272, %f774, %f279;
|
|
sub.f32 %f778, %f775, %f7;
|
|
sub.f32 %f779, %f776, %f8;
|
|
sub.f32 %f780, %f777, %f9;
|
|
mul.f32 %f781, %f779, %f779;
|
|
fma.rn.f32 %f782, %f778, %f778, %f781;
|
|
fma.rn.f32 %f783, %f780, %f780, %f782;
|
|
sqrt.rn.f32 %f599, %f783;
|
|
rcp.rn.f32 %f784, %f599;
|
|
mul.f32 %f595, %f784, %f778;
|
|
mul.f32 %f596, %f784, %f779;
|
|
mul.f32 %f597, %f784, %f780;
|
|
ld.global.u32 %r113, [imageEnabled];
|
|
and.b32 %r114, %r113, 32;
|
|
setp.eq.s32 %p53, %r114, 0;
|
|
selp.f32 %f785, 0f3F800000, 0f41200000, %p53;
|
|
mul.f32 %f598, %f785, %f111;
|
|
st.local.u32 [%rd2], %r105;
|
|
ld.global.u32 %r100, [root];
|
|
// inline asm
|
|
call _rt_trace_64, (%r100, %f10, %f11, %f12, %f595, %f596, %f597, %r101, %f598, %f599, %rd35, %r29);
|
|
// inline asm
|
|
ld.local.f32 %f786, [%rd2];
|
|
add.f32 %f1182, %f740, %f786;
|
|
add.s32 %r196, %r196, 4;
|
|
setp.lt.s32 %p54, %r196, %r8;
|
|
@%p54 bra BB0_38;
|
|
|
|
BB0_39:
|
|
cvt.rn.f32.s32 %f787, %r8;
|
|
div.rn.f32 %f1183, %f1182, %f787;
|
|
shr.u32 %r115, %r6, 31;
|
|
cvt.u16.u32 %rs62, %r115;
|
|
|
|
BB0_40:
|
|
fma.rn.f32 %f1164, %f104, %f1183, %f1164;
|
|
fma.rn.f32 %f1163, %f105, %f1183, %f1163;
|
|
fma.rn.f32 %f1162, %f106, %f1183, %f1162;
|
|
ld.global.u8 %rs15, [imageEnabled];
|
|
and.b16 %rs16, %rs15, 64;
|
|
setp.eq.s16 %p55, %rs16, 0;
|
|
@%p55 bra BB0_42;
|
|
|
|
mul.f32 %f788, %f105, 0f3F372474;
|
|
fma.rn.f32 %f789, %f104, 0f3E59999A, %f788;
|
|
fma.rn.f32 %f790, %f106, 0f3D93A92A, %f789;
|
|
fma.rn.f32 %f20, %f107, %f790, %f20;
|
|
fma.rn.f32 %f19, %f108, %f790, %f19;
|
|
fma.rn.f32 %f18, %f790, %f109, %f18;
|
|
|
|
BB0_42:
|
|
setp.eq.s16 %p56, %rs62, 0;
|
|
@%p56 bra BB0_44;
|
|
|
|
div.rn.f32 %f791, %f104, %f268;
|
|
div.rn.f32 %f792, %f791, %f84;
|
|
cvt.sat.f32.f32 %f793, %f792;
|
|
mul.f32 %f1183, %f1183, %f793;
|
|
|
|
BB0_44:
|
|
add.f32 %f1158, %f1158, %f1183;
|
|
|
|
BB0_45:
|
|
add.s32 %r192, %r192, 1;
|
|
setp.lt.u32 %p57, %r192, %r4;
|
|
@%p57 bra BB0_5;
|
|
|
|
BB0_46:
|
|
ld.global.u32 %r198, [imageEnabled];
|
|
and.b32 %r116, %r198, 8;
|
|
setp.eq.s32 %p58, %r116, 0;
|
|
@%p58 bra BB0_59;
|
|
|
|
cvt.sat.f32.f32 %f149, %f1158;
|
|
cvt.u64.u32 %rd46, %r3;
|
|
cvt.u64.u32 %rd45, %r2;
|
|
mov.u64 %rd49, image_Mask;
|
|
cvta.global.u64 %rd44, %rd49;
|
|
// inline asm
|
|
call (%rd43), _rt_buffer_get_64, (%rd44, %r28, %r28, %rd45, %rd46, %rd13, %rd13);
|
|
// inline asm
|
|
mov.f32 %f796, 0f3E68BA2E;
|
|
cvt.rzi.f32.f32 %f797, %f796;
|
|
fma.rn.f32 %f798, %f797, 0fC0000000, 0f3EE8BA2E;
|
|
abs.f32 %f150, %f798;
|
|
abs.f32 %f151, %f149;
|
|
setp.lt.f32 %p59, %f151, 0f00800000;
|
|
mul.f32 %f799, %f151, 0f4B800000;
|
|
selp.f32 %f800, 0fC3170000, 0fC2FE0000, %p59;
|
|
selp.f32 %f801, %f799, %f151, %p59;
|
|
mov.b32 %r119, %f801;
|
|
and.b32 %r120, %r119, 8388607;
|
|
or.b32 %r121, %r120, 1065353216;
|
|
mov.b32 %f802, %r121;
|
|
shr.u32 %r122, %r119, 23;
|
|
cvt.rn.f32.u32 %f803, %r122;
|
|
add.f32 %f804, %f800, %f803;
|
|
setp.gt.f32 %p60, %f802, 0f3FB504F3;
|
|
mul.f32 %f805, %f802, 0f3F000000;
|
|
add.f32 %f806, %f804, 0f3F800000;
|
|
selp.f32 %f807, %f805, %f802, %p60;
|
|
selp.f32 %f808, %f806, %f804, %p60;
|
|
add.f32 %f809, %f807, 0fBF800000;
|
|
add.f32 %f795, %f807, 0f3F800000;
|
|
// inline asm
|
|
rcp.approx.ftz.f32 %f794,%f795;
|
|
// inline asm
|
|
add.f32 %f810, %f809, %f809;
|
|
mul.f32 %f811, %f794, %f810;
|
|
mul.f32 %f812, %f811, %f811;
|
|
mov.f32 %f813, 0f3C4CAF63;
|
|
mov.f32 %f814, 0f3B18F0FE;
|
|
fma.rn.f32 %f815, %f814, %f812, %f813;
|
|
mov.f32 %f816, 0f3DAAAABD;
|
|
fma.rn.f32 %f817, %f815, %f812, %f816;
|
|
mul.rn.f32 %f818, %f817, %f812;
|
|
mul.rn.f32 %f819, %f818, %f811;
|
|
sub.f32 %f820, %f809, %f811;
|
|
neg.f32 %f821, %f811;
|
|
add.f32 %f822, %f820, %f820;
|
|
fma.rn.f32 %f823, %f821, %f809, %f822;
|
|
mul.rn.f32 %f824, %f794, %f823;
|
|
add.f32 %f825, %f819, %f811;
|
|
sub.f32 %f826, %f811, %f825;
|
|
add.f32 %f827, %f819, %f826;
|
|
add.f32 %f828, %f824, %f827;
|
|
add.f32 %f829, %f825, %f828;
|
|
sub.f32 %f830, %f825, %f829;
|
|
add.f32 %f831, %f828, %f830;
|
|
mov.f32 %f832, 0f3F317200;
|
|
mul.rn.f32 %f833, %f808, %f832;
|
|
mov.f32 %f834, 0f35BFBE8E;
|
|
mul.rn.f32 %f835, %f808, %f834;
|
|
add.f32 %f836, %f833, %f829;
|
|
sub.f32 %f837, %f833, %f836;
|
|
add.f32 %f838, %f829, %f837;
|
|
add.f32 %f839, %f831, %f838;
|
|
add.f32 %f840, %f835, %f839;
|
|
add.f32 %f841, %f836, %f840;
|
|
sub.f32 %f842, %f836, %f841;
|
|
add.f32 %f843, %f840, %f842;
|
|
mov.f32 %f844, 0f3EE8BA2E;
|
|
mul.rn.f32 %f845, %f844, %f841;
|
|
neg.f32 %f846, %f845;
|
|
fma.rn.f32 %f847, %f844, %f841, %f846;
|
|
fma.rn.f32 %f848, %f844, %f843, %f847;
|
|
mov.f32 %f849, 0f00000000;
|
|
fma.rn.f32 %f850, %f849, %f841, %f848;
|
|
add.rn.f32 %f851, %f845, %f850;
|
|
neg.f32 %f852, %f851;
|
|
add.rn.f32 %f853, %f845, %f852;
|
|
add.rn.f32 %f854, %f853, %f850;
|
|
mov.b32 %r123, %f851;
|
|
setp.eq.s32 %p61, %r123, 1118925336;
|
|
add.s32 %r124, %r123, -1;
|
|
mov.b32 %f855, %r124;
|
|
add.f32 %f856, %f854, 0f37000000;
|
|
selp.f32 %f857, %f855, %f851, %p61;
|
|
selp.f32 %f152, %f856, %f854, %p61;
|
|
mul.f32 %f858, %f857, 0f3FB8AA3B;
|
|
cvt.rzi.f32.f32 %f859, %f858;
|
|
mov.f32 %f860, 0fBF317200;
|
|
fma.rn.f32 %f861, %f859, %f860, %f857;
|
|
mov.f32 %f862, 0fB5BFBE8E;
|
|
fma.rn.f32 %f863, %f859, %f862, %f861;
|
|
mul.f32 %f864, %f863, 0f3FB8AA3B;
|
|
ex2.approx.ftz.f32 %f865, %f864;
|
|
add.f32 %f866, %f859, 0f00000000;
|
|
ex2.approx.f32 %f867, %f866;
|
|
mul.f32 %f868, %f865, %f867;
|
|
setp.lt.f32 %p62, %f857, 0fC2D20000;
|
|
selp.f32 %f869, 0f00000000, %f868, %p62;
|
|
setp.gt.f32 %p63, %f857, 0f42D20000;
|
|
selp.f32 %f1202, 0f7F800000, %f869, %p63;
|
|
setp.eq.f32 %p64, %f1202, 0f7F800000;
|
|
@%p64 bra BB0_49;
|
|
|
|
fma.rn.f32 %f1202, %f1202, %f152, %f1202;
|
|
|
|
BB0_49:
|
|
setp.lt.f32 %p65, %f149, 0f00000000;
|
|
setp.eq.f32 %p66, %f150, 0f3F800000;
|
|
and.pred %p4, %p65, %p66;
|
|
mov.b32 %r125, %f1202;
|
|
xor.b32 %r126, %r125, -2147483648;
|
|
mov.b32 %f870, %r126;
|
|
selp.f32 %f1204, %f870, %f1202, %p4;
|
|
setp.eq.f32 %p67, %f149, 0f00000000;
|
|
@%p67 bra BB0_52;
|
|
bra.uni BB0_50;
|
|
|
|
BB0_52:
|
|
add.f32 %f873, %f149, %f149;
|
|
selp.f32 %f1204, %f873, 0f00000000, %p66;
|
|
bra.uni BB0_53;
|
|
|
|
BB0_107:
|
|
mov.u64 %rd117, image_HDR;
|
|
cvta.global.u64 %rd112, %rd117;
|
|
mov.u32 %r189, 8;
|
|
// inline asm
|
|
call (%rd111), _rt_buffer_get_64, (%rd112, %r28, %r189, %rd6, %rd7, %rd13, %rd13);
|
|
// inline asm
|
|
mov.f32 %f1154, 0f00000000;
|
|
// inline asm
|
|
{ cvt.rn.f16.f32 %rs57, %f1154;}
|
|
|
|
// inline asm
|
|
mov.u16 %rs58, 0;
|
|
st.v4.u16 [%rd111], {%rs57, %rs57, %rs57, %rs58};
|
|
|
|
BB0_108:
|
|
ld.global.u8 %rs59, [imageEnabled];
|
|
and.b16 %rs60, %rs59, 64;
|
|
setp.eq.s16 %p131, %rs60, 0;
|
|
@%p131 bra BB0_110;
|
|
|
|
cvt.u64.u32 %rd120, %r2;
|
|
cvt.u64.u32 %rd121, %r3;
|
|
mov.u64 %rd124, image_Dir;
|
|
cvta.global.u64 %rd119, %rd124;
|
|
// inline asm
|
|
call (%rd118), _rt_buffer_get_64, (%rd119, %r28, %r29, %rd120, %rd121, %rd13, %rd13);
|
|
// inline asm
|
|
mov.u16 %rs61, 0;
|
|
st.v4.u8 [%rd118], {%rs61, %rs61, %rs61, %rs61};
|
|
bra.uni BB0_110;
|
|
|
|
BB0_50:
|
|
setp.geu.f32 %p68, %f149, 0f00000000;
|
|
@%p68 bra BB0_53;
|
|
|
|
cvt.rzi.f32.f32 %f872, %f844;
|
|
setp.neu.f32 %p69, %f872, 0f3EE8BA2E;
|
|
selp.f32 %f1204, 0f7FFFFFFF, %f1204, %p69;
|
|
|
|
BB0_53:
|
|
add.f32 %f874, %f151, 0f3EE8BA2E;
|
|
mov.b32 %r127, %f874;
|
|
setp.lt.s32 %p71, %r127, 2139095040;
|
|
@%p71 bra BB0_58;
|
|
|
|
setp.gtu.f32 %p72, %f151, 0f7F800000;
|
|
@%p72 bra BB0_57;
|
|
bra.uni BB0_55;
|
|
|
|
BB0_57:
|
|
add.f32 %f1204, %f149, 0f3EE8BA2E;
|
|
bra.uni BB0_58;
|
|
|
|
BB0_55:
|
|
setp.neu.f32 %p73, %f151, 0f7F800000;
|
|
@%p73 bra BB0_58;
|
|
|
|
selp.f32 %f1204, 0fFF800000, 0f7F800000, %p4;
|
|
|
|
BB0_58:
|
|
mul.f32 %f875, %f1204, 0f437F0000;
|
|
setp.eq.f32 %p74, %f149, 0f3F800000;
|
|
selp.f32 %f876, 0f437F0000, %f875, %p74;
|
|
cvt.rzi.u32.f32 %r128, %f876;
|
|
cvt.u16.u32 %rs17, %r128;
|
|
mov.u16 %rs18, 255;
|
|
st.v2.u8 [%rd43], {%rs17, %rs18};
|
|
ld.global.u32 %r198, [imageEnabled];
|
|
|
|
BB0_59:
|
|
and.b32 %r129, %r198, 1;
|
|
setp.eq.b32 %p75, %r129, 1;
|
|
@!%p75 bra BB0_94;
|
|
bra.uni BB0_60;
|
|
|
|
BB0_60:
|
|
mov.f32 %f879, 0f3E666666;
|
|
cvt.rzi.f32.f32 %f880, %f879;
|
|
fma.rn.f32 %f881, %f880, 0fC0000000, 0f3EE66666;
|
|
abs.f32 %f163, %f881;
|
|
abs.f32 %f164, %f1164;
|
|
setp.lt.f32 %p76, %f164, 0f00800000;
|
|
mul.f32 %f882, %f164, 0f4B800000;
|
|
selp.f32 %f883, 0fC3170000, 0fC2FE0000, %p76;
|
|
selp.f32 %f884, %f882, %f164, %p76;
|
|
mov.b32 %r130, %f884;
|
|
and.b32 %r131, %r130, 8388607;
|
|
or.b32 %r132, %r131, 1065353216;
|
|
mov.b32 %f885, %r132;
|
|
shr.u32 %r133, %r130, 23;
|
|
cvt.rn.f32.u32 %f886, %r133;
|
|
add.f32 %f887, %f883, %f886;
|
|
setp.gt.f32 %p77, %f885, 0f3FB504F3;
|
|
mul.f32 %f888, %f885, 0f3F000000;
|
|
add.f32 %f889, %f887, 0f3F800000;
|
|
selp.f32 %f890, %f888, %f885, %p77;
|
|
selp.f32 %f891, %f889, %f887, %p77;
|
|
add.f32 %f892, %f890, 0fBF800000;
|
|
add.f32 %f878, %f890, 0f3F800000;
|
|
// inline asm
|
|
rcp.approx.ftz.f32 %f877,%f878;
|
|
// inline asm
|
|
add.f32 %f893, %f892, %f892;
|
|
mul.f32 %f894, %f877, %f893;
|
|
mul.f32 %f895, %f894, %f894;
|
|
mov.f32 %f896, 0f3C4CAF63;
|
|
mov.f32 %f897, 0f3B18F0FE;
|
|
fma.rn.f32 %f898, %f897, %f895, %f896;
|
|
mov.f32 %f899, 0f3DAAAABD;
|
|
fma.rn.f32 %f900, %f898, %f895, %f899;
|
|
mul.rn.f32 %f901, %f900, %f895;
|
|
mul.rn.f32 %f902, %f901, %f894;
|
|
sub.f32 %f903, %f892, %f894;
|
|
neg.f32 %f904, %f894;
|
|
add.f32 %f905, %f903, %f903;
|
|
fma.rn.f32 %f906, %f904, %f892, %f905;
|
|
mul.rn.f32 %f907, %f877, %f906;
|
|
add.f32 %f908, %f902, %f894;
|
|
sub.f32 %f909, %f894, %f908;
|
|
add.f32 %f910, %f902, %f909;
|
|
add.f32 %f911, %f907, %f910;
|
|
add.f32 %f912, %f908, %f911;
|
|
sub.f32 %f913, %f908, %f912;
|
|
add.f32 %f914, %f911, %f913;
|
|
mov.f32 %f915, 0f3F317200;
|
|
mul.rn.f32 %f916, %f891, %f915;
|
|
mov.f32 %f917, 0f35BFBE8E;
|
|
mul.rn.f32 %f918, %f891, %f917;
|
|
add.f32 %f919, %f916, %f912;
|
|
sub.f32 %f920, %f916, %f919;
|
|
add.f32 %f921, %f912, %f920;
|
|
add.f32 %f922, %f914, %f921;
|
|
add.f32 %f923, %f918, %f922;
|
|
add.f32 %f924, %f919, %f923;
|
|
sub.f32 %f925, %f919, %f924;
|
|
add.f32 %f926, %f923, %f925;
|
|
mov.f32 %f927, 0f3EE66666;
|
|
mul.rn.f32 %f928, %f927, %f924;
|
|
neg.f32 %f929, %f928;
|
|
fma.rn.f32 %f930, %f927, %f924, %f929;
|
|
fma.rn.f32 %f931, %f927, %f926, %f930;
|
|
mov.f32 %f932, 0f00000000;
|
|
fma.rn.f32 %f933, %f932, %f924, %f931;
|
|
add.rn.f32 %f934, %f928, %f933;
|
|
neg.f32 %f935, %f934;
|
|
add.rn.f32 %f936, %f928, %f935;
|
|
add.rn.f32 %f937, %f936, %f933;
|
|
mov.b32 %r134, %f934;
|
|
setp.eq.s32 %p78, %r134, 1118925336;
|
|
add.s32 %r135, %r134, -1;
|
|
mov.b32 %f938, %r135;
|
|
add.f32 %f939, %f937, 0f37000000;
|
|
selp.f32 %f940, %f938, %f934, %p78;
|
|
selp.f32 %f165, %f939, %f937, %p78;
|
|
mul.f32 %f941, %f940, 0f3FB8AA3B;
|
|
cvt.rzi.f32.f32 %f942, %f941;
|
|
mov.f32 %f943, 0fBF317200;
|
|
fma.rn.f32 %f944, %f942, %f943, %f940;
|
|
mov.f32 %f945, 0fB5BFBE8E;
|
|
fma.rn.f32 %f946, %f942, %f945, %f944;
|
|
mul.f32 %f947, %f946, 0f3FB8AA3B;
|
|
ex2.approx.ftz.f32 %f948, %f947;
|
|
add.f32 %f949, %f942, 0f00000000;
|
|
ex2.approx.f32 %f950, %f949;
|
|
mul.f32 %f951, %f948, %f950;
|
|
setp.lt.f32 %p79, %f940, 0fC2D20000;
|
|
selp.f32 %f952, 0f00000000, %f951, %p79;
|
|
setp.gt.f32 %p80, %f940, 0f42D20000;
|
|
selp.f32 %f1205, 0f7F800000, %f952, %p80;
|
|
setp.eq.f32 %p81, %f1205, 0f7F800000;
|
|
@%p81 bra BB0_62;
|
|
|
|
fma.rn.f32 %f1205, %f1205, %f165, %f1205;
|
|
|
|
BB0_62:
|
|
setp.lt.f32 %p82, %f1164, 0f00000000;
|
|
setp.eq.f32 %p83, %f163, 0f3F800000;
|
|
and.pred %p5, %p82, %p83;
|
|
mov.b32 %r136, %f1205;
|
|
xor.b32 %r137, %r136, -2147483648;
|
|
mov.b32 %f953, %r137;
|
|
selp.f32 %f1207, %f953, %f1205, %p5;
|
|
setp.eq.f32 %p84, %f1164, 0f00000000;
|
|
@%p84 bra BB0_65;
|
|
bra.uni BB0_63;
|
|
|
|
BB0_65:
|
|
add.f32 %f956, %f1164, %f1164;
|
|
selp.f32 %f1207, %f956, 0f00000000, %p83;
|
|
bra.uni BB0_66;
|
|
|
|
BB0_63:
|
|
setp.geu.f32 %p85, %f1164, 0f00000000;
|
|
@%p85 bra BB0_66;
|
|
|
|
cvt.rzi.f32.f32 %f955, %f927;
|
|
setp.neu.f32 %p86, %f955, 0f3EE66666;
|
|
selp.f32 %f1207, 0f7FFFFFFF, %f1207, %p86;
|
|
|
|
BB0_66:
|
|
add.f32 %f957, %f164, 0f3EE66666;
|
|
mov.b32 %r138, %f957;
|
|
setp.lt.s32 %p88, %r138, 2139095040;
|
|
@%p88 bra BB0_71;
|
|
|
|
setp.gtu.f32 %p89, %f164, 0f7F800000;
|
|
@%p89 bra BB0_70;
|
|
bra.uni BB0_68;
|
|
|
|
BB0_70:
|
|
add.f32 %f1207, %f1164, 0f3EE66666;
|
|
bra.uni BB0_71;
|
|
|
|
BB0_68:
|
|
setp.neu.f32 %p90, %f164, 0f7F800000;
|
|
@%p90 bra BB0_71;
|
|
|
|
selp.f32 %f1207, 0fFF800000, 0f7F800000, %p5;
|
|
|
|
BB0_71:
|
|
setp.eq.f32 %p91, %f1164, 0f3F800000;
|
|
selp.f32 %f176, 0f3F800000, %f1207, %p91;
|
|
abs.f32 %f177, %f1163;
|
|
setp.lt.f32 %p92, %f177, 0f00800000;
|
|
mul.f32 %f960, %f177, 0f4B800000;
|
|
selp.f32 %f961, 0fC3170000, 0fC2FE0000, %p92;
|
|
selp.f32 %f962, %f960, %f177, %p92;
|
|
mov.b32 %r139, %f962;
|
|
and.b32 %r140, %r139, 8388607;
|
|
or.b32 %r141, %r140, 1065353216;
|
|
mov.b32 %f963, %r141;
|
|
shr.u32 %r142, %r139, 23;
|
|
cvt.rn.f32.u32 %f964, %r142;
|
|
add.f32 %f965, %f961, %f964;
|
|
setp.gt.f32 %p93, %f963, 0f3FB504F3;
|
|
mul.f32 %f966, %f963, 0f3F000000;
|
|
add.f32 %f967, %f965, 0f3F800000;
|
|
selp.f32 %f968, %f966, %f963, %p93;
|
|
selp.f32 %f969, %f967, %f965, %p93;
|
|
add.f32 %f970, %f968, 0fBF800000;
|
|
add.f32 %f959, %f968, 0f3F800000;
|
|
// inline asm
|
|
rcp.approx.ftz.f32 %f958,%f959;
|
|
// inline asm
|
|
add.f32 %f971, %f970, %f970;
|
|
mul.f32 %f972, %f958, %f971;
|
|
mul.f32 %f973, %f972, %f972;
|
|
fma.rn.f32 %f976, %f897, %f973, %f896;
|
|
fma.rn.f32 %f978, %f976, %f973, %f899;
|
|
mul.rn.f32 %f979, %f978, %f973;
|
|
mul.rn.f32 %f980, %f979, %f972;
|
|
sub.f32 %f981, %f970, %f972;
|
|
neg.f32 %f982, %f972;
|
|
add.f32 %f983, %f981, %f981;
|
|
fma.rn.f32 %f984, %f982, %f970, %f983;
|
|
mul.rn.f32 %f985, %f958, %f984;
|
|
add.f32 %f986, %f980, %f972;
|
|
sub.f32 %f987, %f972, %f986;
|
|
add.f32 %f988, %f980, %f987;
|
|
add.f32 %f989, %f985, %f988;
|
|
add.f32 %f990, %f986, %f989;
|
|
sub.f32 %f991, %f986, %f990;
|
|
add.f32 %f992, %f989, %f991;
|
|
mul.rn.f32 %f994, %f969, %f915;
|
|
mul.rn.f32 %f996, %f969, %f917;
|
|
add.f32 %f997, %f994, %f990;
|
|
sub.f32 %f998, %f994, %f997;
|
|
add.f32 %f999, %f990, %f998;
|
|
add.f32 %f1000, %f992, %f999;
|
|
add.f32 %f1001, %f996, %f1000;
|
|
add.f32 %f1002, %f997, %f1001;
|
|
sub.f32 %f1003, %f997, %f1002;
|
|
add.f32 %f1004, %f1001, %f1003;
|
|
mul.rn.f32 %f1006, %f927, %f1002;
|
|
neg.f32 %f1007, %f1006;
|
|
fma.rn.f32 %f1008, %f927, %f1002, %f1007;
|
|
fma.rn.f32 %f1009, %f927, %f1004, %f1008;
|
|
fma.rn.f32 %f1011, %f932, %f1002, %f1009;
|
|
add.rn.f32 %f1012, %f1006, %f1011;
|
|
neg.f32 %f1013, %f1012;
|
|
add.rn.f32 %f1014, %f1006, %f1013;
|
|
add.rn.f32 %f1015, %f1014, %f1011;
|
|
mov.b32 %r143, %f1012;
|
|
setp.eq.s32 %p94, %r143, 1118925336;
|
|
add.s32 %r144, %r143, -1;
|
|
mov.b32 %f1016, %r144;
|
|
add.f32 %f1017, %f1015, 0f37000000;
|
|
selp.f32 %f1018, %f1016, %f1012, %p94;
|
|
selp.f32 %f178, %f1017, %f1015, %p94;
|
|
mul.f32 %f1019, %f1018, 0f3FB8AA3B;
|
|
cvt.rzi.f32.f32 %f1020, %f1019;
|
|
fma.rn.f32 %f1022, %f1020, %f943, %f1018;
|
|
fma.rn.f32 %f1024, %f1020, %f945, %f1022;
|
|
mul.f32 %f1025, %f1024, 0f3FB8AA3B;
|
|
ex2.approx.ftz.f32 %f1026, %f1025;
|
|
add.f32 %f1027, %f1020, 0f00000000;
|
|
ex2.approx.f32 %f1028, %f1027;
|
|
mul.f32 %f1029, %f1026, %f1028;
|
|
setp.lt.f32 %p95, %f1018, 0fC2D20000;
|
|
selp.f32 %f1030, 0f00000000, %f1029, %p95;
|
|
setp.gt.f32 %p96, %f1018, 0f42D20000;
|
|
selp.f32 %f1208, 0f7F800000, %f1030, %p96;
|
|
setp.eq.f32 %p97, %f1208, 0f7F800000;
|
|
@%p97 bra BB0_73;
|
|
|
|
fma.rn.f32 %f1208, %f1208, %f178, %f1208;
|
|
|
|
BB0_73:
|
|
setp.lt.f32 %p98, %f1163, 0f00000000;
|
|
and.pred %p6, %p98, %p83;
|
|
mov.b32 %r145, %f1208;
|
|
xor.b32 %r146, %r145, -2147483648;
|
|
mov.b32 %f1031, %r146;
|
|
selp.f32 %f1210, %f1031, %f1208, %p6;
|
|
setp.eq.f32 %p100, %f1163, 0f00000000;
|
|
@%p100 bra BB0_76;
|
|
bra.uni BB0_74;
|
|
|
|
BB0_76:
|
|
add.f32 %f1034, %f1163, %f1163;
|
|
selp.f32 %f1210, %f1034, 0f00000000, %p83;
|
|
bra.uni BB0_77;
|
|
|
|
BB0_74:
|
|
setp.geu.f32 %p101, %f1163, 0f00000000;
|
|
@%p101 bra BB0_77;
|
|
|
|
cvt.rzi.f32.f32 %f1033, %f927;
|
|
setp.neu.f32 %p102, %f1033, 0f3EE66666;
|
|
selp.f32 %f1210, 0f7FFFFFFF, %f1210, %p102;
|
|
|
|
BB0_77:
|
|
add.f32 %f1035, %f177, 0f3EE66666;
|
|
mov.b32 %r147, %f1035;
|
|
setp.lt.s32 %p104, %r147, 2139095040;
|
|
@%p104 bra BB0_82;
|
|
|
|
setp.gtu.f32 %p105, %f177, 0f7F800000;
|
|
@%p105 bra BB0_81;
|
|
bra.uni BB0_79;
|
|
|
|
BB0_81:
|
|
add.f32 %f1210, %f1163, 0f3EE66666;
|
|
bra.uni BB0_82;
|
|
|
|
BB0_79:
|
|
setp.neu.f32 %p106, %f177, 0f7F800000;
|
|
@%p106 bra BB0_82;
|
|
|
|
selp.f32 %f1210, 0fFF800000, 0f7F800000, %p6;
|
|
|
|
BB0_82:
|
|
setp.eq.f32 %p107, %f1163, 0f3F800000;
|
|
selp.f32 %f189, 0f3F800000, %f1210, %p107;
|
|
abs.f32 %f190, %f1162;
|
|
setp.lt.f32 %p108, %f190, 0f00800000;
|
|
mul.f32 %f1038, %f190, 0f4B800000;
|
|
selp.f32 %f1039, 0fC3170000, 0fC2FE0000, %p108;
|
|
selp.f32 %f1040, %f1038, %f190, %p108;
|
|
mov.b32 %r148, %f1040;
|
|
and.b32 %r149, %r148, 8388607;
|
|
or.b32 %r150, %r149, 1065353216;
|
|
mov.b32 %f1041, %r150;
|
|
shr.u32 %r151, %r148, 23;
|
|
cvt.rn.f32.u32 %f1042, %r151;
|
|
add.f32 %f1043, %f1039, %f1042;
|
|
setp.gt.f32 %p109, %f1041, 0f3FB504F3;
|
|
mul.f32 %f1044, %f1041, 0f3F000000;
|
|
add.f32 %f1045, %f1043, 0f3F800000;
|
|
selp.f32 %f1046, %f1044, %f1041, %p109;
|
|
selp.f32 %f1047, %f1045, %f1043, %p109;
|
|
add.f32 %f1048, %f1046, 0fBF800000;
|
|
add.f32 %f1037, %f1046, 0f3F800000;
|
|
// inline asm
|
|
rcp.approx.ftz.f32 %f1036,%f1037;
|
|
// inline asm
|
|
add.f32 %f1049, %f1048, %f1048;
|
|
mul.f32 %f1050, %f1036, %f1049;
|
|
mul.f32 %f1051, %f1050, %f1050;
|
|
fma.rn.f32 %f1054, %f897, %f1051, %f896;
|
|
fma.rn.f32 %f1056, %f1054, %f1051, %f899;
|
|
mul.rn.f32 %f1057, %f1056, %f1051;
|
|
mul.rn.f32 %f1058, %f1057, %f1050;
|
|
sub.f32 %f1059, %f1048, %f1050;
|
|
neg.f32 %f1060, %f1050;
|
|
add.f32 %f1061, %f1059, %f1059;
|
|
fma.rn.f32 %f1062, %f1060, %f1048, %f1061;
|
|
mul.rn.f32 %f1063, %f1036, %f1062;
|
|
add.f32 %f1064, %f1058, %f1050;
|
|
sub.f32 %f1065, %f1050, %f1064;
|
|
add.f32 %f1066, %f1058, %f1065;
|
|
add.f32 %f1067, %f1063, %f1066;
|
|
add.f32 %f1068, %f1064, %f1067;
|
|
sub.f32 %f1069, %f1064, %f1068;
|
|
add.f32 %f1070, %f1067, %f1069;
|
|
mul.rn.f32 %f1072, %f1047, %f915;
|
|
mul.rn.f32 %f1074, %f1047, %f917;
|
|
add.f32 %f1075, %f1072, %f1068;
|
|
sub.f32 %f1076, %f1072, %f1075;
|
|
add.f32 %f1077, %f1068, %f1076;
|
|
add.f32 %f1078, %f1070, %f1077;
|
|
add.f32 %f1079, %f1074, %f1078;
|
|
add.f32 %f1080, %f1075, %f1079;
|
|
sub.f32 %f1081, %f1075, %f1080;
|
|
add.f32 %f1082, %f1079, %f1081;
|
|
mul.rn.f32 %f1084, %f927, %f1080;
|
|
neg.f32 %f1085, %f1084;
|
|
fma.rn.f32 %f1086, %f927, %f1080, %f1085;
|
|
fma.rn.f32 %f1087, %f927, %f1082, %f1086;
|
|
fma.rn.f32 %f1089, %f932, %f1080, %f1087;
|
|
add.rn.f32 %f1090, %f1084, %f1089;
|
|
neg.f32 %f1091, %f1090;
|
|
add.rn.f32 %f1092, %f1084, %f1091;
|
|
add.rn.f32 %f1093, %f1092, %f1089;
|
|
mov.b32 %r152, %f1090;
|
|
setp.eq.s32 %p110, %r152, 1118925336;
|
|
add.s32 %r153, %r152, -1;
|
|
mov.b32 %f1094, %r153;
|
|
add.f32 %f1095, %f1093, 0f37000000;
|
|
selp.f32 %f1096, %f1094, %f1090, %p110;
|
|
selp.f32 %f191, %f1095, %f1093, %p110;
|
|
mul.f32 %f1097, %f1096, 0f3FB8AA3B;
|
|
cvt.rzi.f32.f32 %f1098, %f1097;
|
|
fma.rn.f32 %f1100, %f1098, %f943, %f1096;
|
|
fma.rn.f32 %f1102, %f1098, %f945, %f1100;
|
|
mul.f32 %f1103, %f1102, 0f3FB8AA3B;
|
|
ex2.approx.ftz.f32 %f1104, %f1103;
|
|
add.f32 %f1105, %f1098, 0f00000000;
|
|
ex2.approx.f32 %f1106, %f1105;
|
|
mul.f32 %f1107, %f1104, %f1106;
|
|
setp.lt.f32 %p111, %f1096, 0fC2D20000;
|
|
selp.f32 %f1108, 0f00000000, %f1107, %p111;
|
|
setp.gt.f32 %p112, %f1096, 0f42D20000;
|
|
selp.f32 %f1211, 0f7F800000, %f1108, %p112;
|
|
setp.eq.f32 %p113, %f1211, 0f7F800000;
|
|
@%p113 bra BB0_84;
|
|
|
|
fma.rn.f32 %f1211, %f1211, %f191, %f1211;
|
|
|
|
BB0_84:
|
|
setp.lt.f32 %p114, %f1162, 0f00000000;
|
|
and.pred %p7, %p114, %p83;
|
|
mov.b32 %r154, %f1211;
|
|
xor.b32 %r155, %r154, -2147483648;
|
|
mov.b32 %f1109, %r155;
|
|
selp.f32 %f1213, %f1109, %f1211, %p7;
|
|
setp.eq.f32 %p116, %f1162, 0f00000000;
|
|
@%p116 bra BB0_87;
|
|
bra.uni BB0_85;
|
|
|
|
BB0_87:
|
|
add.f32 %f1112, %f1162, %f1162;
|
|
selp.f32 %f1213, %f1112, 0f00000000, %p83;
|
|
bra.uni BB0_88;
|
|
|
|
BB0_85:
|
|
setp.geu.f32 %p117, %f1162, 0f00000000;
|
|
@%p117 bra BB0_88;
|
|
|
|
cvt.rzi.f32.f32 %f1111, %f927;
|
|
setp.neu.f32 %p118, %f1111, 0f3EE66666;
|
|
selp.f32 %f1213, 0f7FFFFFFF, %f1213, %p118;
|
|
|
|
BB0_88:
|
|
add.f32 %f1113, %f190, 0f3EE66666;
|
|
mov.b32 %r156, %f1113;
|
|
setp.lt.s32 %p120, %r156, 2139095040;
|
|
@%p120 bra BB0_93;
|
|
|
|
setp.gtu.f32 %p121, %f190, 0f7F800000;
|
|
@%p121 bra BB0_92;
|
|
bra.uni BB0_90;
|
|
|
|
BB0_92:
|
|
add.f32 %f1213, %f1162, 0f3EE66666;
|
|
bra.uni BB0_93;
|
|
|
|
BB0_90:
|
|
setp.neu.f32 %p122, %f190, 0f7F800000;
|
|
@%p122 bra BB0_93;
|
|
|
|
selp.f32 %f1213, 0fFF800000, 0f7F800000, %p7;
|
|
|
|
BB0_93:
|
|
setp.eq.f32 %p123, %f1162, 0f3F800000;
|
|
selp.f32 %f1114, 0f3F800000, %f1213, %p123;
|
|
cvt.u64.u32 %rd53, %r3;
|
|
cvt.u64.u32 %rd52, %r2;
|
|
mov.u64 %rd56, image;
|
|
cvta.global.u64 %rd51, %rd56;
|
|
// inline asm
|
|
call (%rd50), _rt_buffer_get_64, (%rd51, %r28, %r29, %rd52, %rd53, %rd13, %rd13);
|
|
// inline asm
|
|
cvt.sat.f32.f32 %f1115, %f1114;
|
|
mul.f32 %f1116, %f1115, 0f437FFD71;
|
|
cvt.rzi.u32.f32 %r159, %f1116;
|
|
cvt.sat.f32.f32 %f1117, %f189;
|
|
mul.f32 %f1118, %f1117, 0f437FFD71;
|
|
cvt.rzi.u32.f32 %r160, %f1118;
|
|
cvt.sat.f32.f32 %f1119, %f176;
|
|
mul.f32 %f1120, %f1119, 0f437FFD71;
|
|
cvt.rzi.u32.f32 %r161, %f1120;
|
|
cvt.u16.u32 %rs19, %r159;
|
|
cvt.u16.u32 %rs20, %r161;
|
|
cvt.u16.u32 %rs21, %r160;
|
|
mov.u16 %rs22, 255;
|
|
st.v4.u8 [%rd50], {%rs19, %rs21, %rs20, %rs22};
|
|
ld.global.u32 %r198, [imageEnabled];
|
|
|
|
BB0_94:
|
|
and.b32 %r162, %r198, 4;
|
|
setp.eq.s32 %p124, %r162, 0;
|
|
@%p124 bra BB0_98;
|
|
|
|
ld.global.u32 %r163, [additive];
|
|
setp.eq.s32 %p125, %r163, 0;
|
|
cvt.u64.u32 %rd4, %r2;
|
|
cvt.u64.u32 %rd5, %r3;
|
|
mov.f32 %f1121, 0f3F800000;
|
|
// inline asm
|
|
{ cvt.rn.f16.f32 %rs23, %f1121;}
|
|
|
|
// inline asm
|
|
@%p125 bra BB0_97;
|
|
|
|
mov.u64 %rd69, image_HDR;
|
|
cvta.global.u64 %rd58, %rd69;
|
|
mov.u32 %r167, 8;
|
|
// inline asm
|
|
call (%rd57), _rt_buffer_get_64, (%rd58, %r28, %r167, %rd4, %rd5, %rd13, %rd13);
|
|
// inline asm
|
|
ld.v4.u16 {%rs30, %rs31, %rs32, %rs33}, [%rd57];
|
|
// inline asm
|
|
{ cvt.f32.f16 %f1122, %rs30;}
|
|
|
|
// inline asm
|
|
// inline asm
|
|
{ cvt.f32.f16 %f1123, %rs31;}
|
|
|
|
// inline asm
|
|
// inline asm
|
|
{ cvt.f32.f16 %f1124, %rs32;}
|
|
|
|
// inline asm
|
|
// inline asm
|
|
call (%rd63), _rt_buffer_get_64, (%rd58, %r28, %r167, %rd4, %rd5, %rd13, %rd13);
|
|
// inline asm
|
|
add.f32 %f1125, %f1164, %f1122;
|
|
add.f32 %f1126, %f1163, %f1123;
|
|
add.f32 %f1127, %f1162, %f1124;
|
|
// inline asm
|
|
{ cvt.rn.f16.f32 %rs29, %f1127;}
|
|
|
|
// inline asm
|
|
// inline asm
|
|
{ cvt.rn.f16.f32 %rs28, %f1126;}
|
|
|
|
// inline asm
|
|
// inline asm
|
|
{ cvt.rn.f16.f32 %rs27, %f1125;}
|
|
|
|
// inline asm
|
|
st.v4.u16 [%rd63], {%rs27, %rs28, %rs29, %rs23};
|
|
bra.uni BB0_98;
|
|
|
|
BB0_97:
|
|
mov.u64 %rd76, image_HDR;
|
|
cvta.global.u64 %rd71, %rd76;
|
|
mov.u32 %r169, 8;
|
|
// inline asm
|
|
call (%rd70), _rt_buffer_get_64, (%rd71, %r28, %r169, %rd4, %rd5, %rd13, %rd13);
|
|
// inline asm
|
|
// inline asm
|
|
{ cvt.rn.f16.f32 %rs36, %f1162;}
|
|
|
|
// inline asm
|
|
// inline asm
|
|
{ cvt.rn.f16.f32 %rs35, %f1163;}
|
|
|
|
// inline asm
|
|
// inline asm
|
|
{ cvt.rn.f16.f32 %rs34, %f1164;}
|
|
|
|
// inline asm
|
|
st.v4.u16 [%rd70], {%rs34, %rs35, %rs36, %rs23};
|
|
|
|
BB0_98:
|
|
ld.global.u8 %rs37, [imageEnabled];
|
|
and.b16 %rs38, %rs37, 64;
|
|
setp.eq.s16 %p126, %rs38, 0;
|
|
@%p126 bra BB0_110;
|
|
|
|
mul.f32 %f1131, %f19, %f19;
|
|
fma.rn.f32 %f1132, %f20, %f20, %f1131;
|
|
fma.rn.f32 %f1133, %f18, %f18, %f1132;
|
|
sqrt.rn.f32 %f1134, %f1133;
|
|
rcp.rn.f32 %f1135, %f1134;
|
|
mul.f32 %f1136, %f20, %f1135;
|
|
mul.f32 %f1137, %f19, %f1135;
|
|
mul.f32 %f1138, %f18, %f1135;
|
|
cvt.u64.u32 %rd80, %r3;
|
|
cvt.u64.u32 %rd79, %r2;
|
|
mov.u64 %rd83, image_Dir;
|
|
cvta.global.u64 %rd78, %rd83;
|
|
// inline asm
|
|
call (%rd77), _rt_buffer_get_64, (%rd78, %r28, %r29, %rd79, %rd80, %rd13, %rd13);
|
|
// inline asm
|
|
fma.rn.f32 %f1139, %f1136, 0f3F000000, 0f3F000000;
|
|
mul.f32 %f1140, %f1139, 0f437F0000;
|
|
cvt.rzi.u32.f32 %r172, %f1140;
|
|
fma.rn.f32 %f1141, %f1137, 0f3F000000, 0f3F000000;
|
|
mul.f32 %f1142, %f1141, 0f437F0000;
|
|
cvt.rzi.u32.f32 %r173, %f1142;
|
|
fma.rn.f32 %f1143, %f1138, 0f3F000000, 0f3F000000;
|
|
mul.f32 %f1144, %f1143, 0f437F0000;
|
|
cvt.rzi.u32.f32 %r174, %f1144;
|
|
cvt.u16.u32 %rs39, %r174;
|
|
cvt.u16.u32 %rs40, %r173;
|
|
cvt.u16.u32 %rs41, %r172;
|
|
mov.u16 %rs42, 255;
|
|
st.v4.u8 [%rd77], {%rs41, %rs40, %rs39, %rs42};
|
|
|
|
BB0_110:
|
|
ret;
|
|
}
|
|
|
|
|