sassycrown/punktfunk
1
0
Fork 0
forked from unom/punktfunk
Code Pull Requests Activity
Files
191c9a4e188dffabc17b99fb4110f0e9666f4510
punktfunk/crates/pf-encode/src/enc/linux/cursor_blend.ptx
T
enricobuehlerandClaude Opus 4.8 9a36ea2132 refactor(host/W6.2): extract the video encode backends into the pf-encode crate 
encode.rs + encode/* (NVENC, VAAPI, native AMF, AMF/QSV ffmpeg, direct-SDK
NVENC/CUDA, raw Vulkan-Video, PyroWave, openh264) move into crates/pf-encode
behind one Encoder trait + open_video selector (plan §W6). The crate speaks the
shared frame vocabulary (pf-frame: CapturedFrame/PixelFormat + the DXGI identity
D3d11Frame/make_device) and pf-zerocopy (CUDA context/buffers), and NEVER
pf-capture — the capture→encode edge is one-way (ZeroCopyPolicy, prior commit).

Dep moves: the heavy encoder deps (ffmpeg-next, the NVENC SDK, openh264,
pyrowave-sys) move from the host to pf-encode; the host's
nvenc/amf-qsv/vulkan-encode/pyrowave features now FORWARD to pf-encode/*. The
host keeps a mod-encode shim (pub use pf_encode) so every crate::encode::* path
(negotiator + GameStream/native/mgmt planes) is unchanged.

resolve_render_adapter_luid moves from the host's windows/win_adapter.rs into
pf-gpu (both pf-encode and pf-capture need it as a peer of GPU selection); its 5
call sites (encode amf/nvenc, capture idd_push/synthetic_nv12, vdisplay manager)
rewire to pf_gpu::resolve_render_adapter_luid and win_adapter.rs is deleted.
pf-frame's make_device gains a # Safety section (public-unsafe-fn lint, latent
since the pf-frame carve — a full-workspace -D warnings clippy catches it).

Verified: Linux clippy -D warnings (pf-encode + host nvenc,vulkan-encode,pyrowave
--all-targets) + 13/13 pf-encode + 299/299 host tests; Windows clippy -D warnings
(pf-encode nvenc,amf-qsv --all-targets + host nvenc,amf-qsv --all-targets)
Finished exit 0.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-17 10:42:51 +02:00

577 lines
16 KiB
Plaintext
Raw Blame History

//
// Generated by NVIDIA NVVM Compiler
//
// Compiler Build ID: CL-38244171
// Cuda compilation tools, release 13.3, V13.3.73
// Based on NVVM 7.0.1
//
.version 9.3
.target sm_75
.address_size 64
// .globl blend_argb
.visible .entry blend_argb(
.param .u64 blend_argb_param_0,
.param .u32 blend_argb_param_1,
.param .u32 blend_argb_param_2,
.param .u32 blend_argb_param_3,
.param .u64 blend_argb_param_4,
.param .u32 blend_argb_param_5,
.param .u32 blend_argb_param_6,
.param .u32 blend_argb_param_7,
.param .u32 blend_argb_param_8
)
{
.reg .pred %p<10>;
.reg .b16 %rs<2>;
.reg .b32 %r<34>;
.reg .b64 %rd<17>;
ld.param.u64 %rd2, [blend_argb_param_0];
ld.param.u32 %r5, [blend_argb_param_1];
ld.param.u32 %r6, [blend_argb_param_2];
ld.param.u32 %r7, [blend_argb_param_3];
ld.param.u64 %rd3, [blend_argb_param_4];
ld.param.u32 %r8, [blend_argb_param_5];
ld.param.u32 %r11, [blend_argb_param_6];
ld.param.u32 %r9, [blend_argb_param_7];
ld.param.u32 %r10, [blend_argb_param_8];
mov.u32 %r12, %ntid.x;
mov.u32 %r13, %ctaid.x;
mov.u32 %r14, %tid.x;
mad.lo.s32 %r1, %r13, %r12, %r14;
mov.u32 %r15, %ntid.y;
mov.u32 %r16, %ctaid.y;
mov.u32 %r17, %tid.y;
mad.lo.s32 %r2, %r16, %r15, %r17;
setp.ge.s32 %p1, %r1, %r8;
setp.ge.s32 %p2, %r2, %r11;
or.pred %p3, %p1, %p2;
@%p3 bra $L__BB0_4;
add.s32 %r3, %r1, %r9;
add.s32 %r4, %r2, %r10;
or.b32 %r18, %r4, %r3;
setp.lt.s32 %p4, %r18, 0;
setp.ge.s32 %p5, %r3, %r6;
or.pred %p6, %p5, %p4;
setp.ge.s32 %p7, %r4, %r7;
or.pred %p8, %p7, %p6;
@%p8 bra $L__BB0_4;
mad.lo.s32 %r19, %r2, %r8, %r1;
mul.wide.s32 %rd4, %r19, 4;
cvta.to.global.u64 %rd5, %rd3;
add.s64 %rd1, %rd5, %rd4;
ld.global.u8 %rs1, [%rd1+3];
setp.eq.s16 %p9, %rs1, 0;
@%p9 bra $L__BB0_4;
cvt.u32.u16 %r20, %rs1;
mul.wide.s32 %rd6, %r4, %r5;
mul.wide.s32 %rd7, %r3, 4;
add.s64 %rd8, %rd6, %rd7;
cvta.to.global.u64 %rd9, %rd2;
add.s64 %rd10, %rd9, %rd8;
ld.global.u8 %r21, [%rd10];
ld.global.u8 %r22, [%rd1+2];
xor.b32 %r23, %r20, 255;
mul.lo.s32 %r24, %r23, %r21;
mad.lo.s32 %r25, %r22, %r20, %r24;
mul.wide.u32 %rd11, %r25, -2139062143;
shr.u64 %rd12, %rd11, 39;
st.global.u8 [%rd10], %rd12;
ld.global.u8 %r26, [%rd10+1];
ld.global.u8 %r27, [%rd1+1];
mul.lo.s32 %r28, %r23, %r26;
mad.lo.s32 %r29, %r27, %r20, %r28;
mul.wide.u32 %rd13, %r29, -2139062143;
shr.u64 %rd14, %rd13, 39;
st.global.u8 [%rd10+1], %rd14;
ld.global.u8 %r30, [%rd10+2];
ld.global.u8 %r31, [%rd1];
mul.lo.s32 %r32, %r23, %r30;
mad.lo.s32 %r33, %r31, %r20, %r32;
mul.wide.u32 %rd15, %r33, -2139062143;
shr.u64 %rd16, %rd15, 39;
st.global.u8 [%rd10+2], %rd16;
$L__BB0_4:
ret;
}
// .globl blend_yuv444
.visible .entry blend_yuv444(
.param .u64 blend_yuv444_param_0,
.param .u32 blend_yuv444_param_1,
.param .u32 blend_yuv444_param_2,
.param .u32 blend_yuv444_param_3,
.param .u64 blend_yuv444_param_4,
.param .u32 blend_yuv444_param_5,
.param .u32 blend_yuv444_param_6,
.param .u32 blend_yuv444_param_7,
.param .u32 blend_yuv444_param_8
)
{
.reg .pred %p<10>;
.reg .b16 %rs<5>;
.reg .f32 %f<16>;
.reg .b32 %r<49>;
.reg .b64 %rd<14>;
ld.param.u64 %rd2, [blend_yuv444_param_0];
ld.param.u32 %r5, [blend_yuv444_param_1];
ld.param.u32 %r6, [blend_yuv444_param_2];
ld.param.u32 %r7, [blend_yuv444_param_3];
ld.param.u64 %rd3, [blend_yuv444_param_4];
ld.param.u32 %r8, [blend_yuv444_param_5];
ld.param.u32 %r11, [blend_yuv444_param_6];
ld.param.u32 %r9, [blend_yuv444_param_7];
ld.param.u32 %r10, [blend_yuv444_param_8];
mov.u32 %r12, %ntid.x;
mov.u32 %r13, %ctaid.x;
mov.u32 %r14, %tid.x;
mad.lo.s32 %r1, %r13, %r12, %r14;
mov.u32 %r15, %ntid.y;
mov.u32 %r16, %ctaid.y;
mov.u32 %r17, %tid.y;
mad.lo.s32 %r2, %r16, %r15, %r17;
setp.ge.s32 %p1, %r1, %r8;
setp.ge.s32 %p2, %r2, %r11;
or.pred %p3, %p1, %p2;
@%p3 bra $L__BB1_4;
add.s32 %r3, %r1, %r9;
add.s32 %r4, %r2, %r10;
or.b32 %r18, %r4, %r3;
setp.lt.s32 %p4, %r18, 0;
setp.ge.s32 %p5, %r3, %r6;
or.pred %p6, %p5, %p4;
setp.ge.s32 %p7, %r4, %r7;
or.pred %p8, %p7, %p6;
@%p8 bra $L__BB1_4;
mad.lo.s32 %r19, %r2, %r8, %r1;
mul.wide.s32 %rd4, %r19, 4;
cvta.to.global.u64 %rd5, %rd3;
add.s64 %rd1, %rd5, %rd4;
ld.global.u8 %rs1, [%rd1+3];
setp.eq.s16 %p9, %rs1, 0;
@%p9 bra $L__BB1_4;
cvt.u32.u16 %r20, %rs1;
ld.global.u8 %rs2, [%rd1];
cvt.rn.f32.u16 %f1, %rs2;
ld.global.u8 %rs3, [%rd1+1];
cvt.rn.f32.u16 %f2, %rs3;
ld.global.u8 %rs4, [%rd1+2];
cvt.rn.f32.u16 %f3, %rs4;
fma.rn.f32 %f4, %f1, 0f3E3AFB7F, 0f41800000;
fma.rn.f32 %f5, %f2, 0f3F1D3C36, %f4;
fma.rn.f32 %f6, %f3, 0f3D7DF3B6, %f5;
add.f32 %f7, %f6, 0f3F000000;
cvt.rzi.s32.f32 %r21, %f7;
fma.rn.f32 %f8, %f1, 0fBDCE075F, 0f43000000;
fma.rn.f32 %f9, %f2, 0fBEAD5CFB, %f8;
fma.rn.f32 %f10, %f3, 0f3EE0DED3, %f9;
add.f32 %f11, %f10, 0f3F000000;
cvt.rzi.s32.f32 %r22, %f11;
fma.rn.f32 %f12, %f1, 0f3EE0DED3, 0f43000000;
fma.rn.f32 %f13, %f2, 0fBECC3C9F, %f12;
fma.rn.f32 %f14, %f3, 0fBD25119D, %f13;
add.f32 %f15, %f14, 0f3F000000;
cvt.rzi.s32.f32 %r23, %f15;
mul.wide.s32 %rd6, %r4, %r5;
cvt.s64.s32 %rd7, %r3;
add.s64 %rd8, %rd6, %rd7;
cvta.to.global.u64 %rd9, %rd2;
add.s64 %rd10, %rd9, %rd8;
ld.global.u8 %r24, [%rd10];
mul.lo.s32 %r25, %r21, %r20;
xor.b32 %r26, %r20, 255;
mad.lo.s32 %r27, %r26, %r24, %r25;
mul.hi.s32 %r28, %r27, -2139062143;
add.s32 %r29, %r28, %r27;
shr.u32 %r30, %r29, 31;
shr.u32 %r31, %r29, 7;
add.s32 %r32, %r31, %r30;
st.global.u8 [%rd10], %r32;
mul.wide.s32 %rd11, %r7, %r5;
add.s64 %rd12, %rd10, %rd11;
ld.global.u8 %r33, [%rd12];
mul.lo.s32 %r34, %r22, %r20;
mad.lo.s32 %r35, %r26, %r33, %r34;
mul.hi.s32 %r36, %r35, -2139062143;
add.s32 %r37, %r36, %r35;
shr.u32 %r38, %r37, 31;
shr.u32 %r39, %r37, 7;
add.s32 %r40, %r39, %r38;
st.global.u8 [%rd12], %r40;
add.s64 %rd13, %rd12, %rd11;
ld.global.u8 %r41, [%rd13];
mul.lo.s32 %r42, %r23, %r20;
mad.lo.s32 %r43, %r26, %r41, %r42;
mul.hi.s32 %r44, %r43, -2139062143;
add.s32 %r45, %r44, %r43;
shr.u32 %r46, %r45, 31;
shr.u32 %r47, %r45, 7;
add.s32 %r48, %r47, %r46;
st.global.u8 [%rd13], %r48;
$L__BB1_4:
ret;
}
// .globl blend_nv12
.visible .entry blend_nv12(
.param .u64 blend_nv12_param_0,
.param .u32 blend_nv12_param_1,
.param .u64 blend_nv12_param_2,
.param .u32 blend_nv12_param_3,
.param .u32 blend_nv12_param_4,
.param .u32 blend_nv12_param_5,
.param .u64 blend_nv12_param_6,
.param .u32 blend_nv12_param_7,
.param .u32 blend_nv12_param_8,
.param .u32 blend_nv12_param_9,
.param .u32 blend_nv12_param_10
)
{
.reg .pred %p<43>;
.reg .b16 %rs<17>;
.reg .f32 %f<108>;
.reg .b32 %r<123>;
.reg .b64 %rd<35>;
ld.param.u64 %rd11, [blend_nv12_param_0];
ld.param.u32 %r21, [blend_nv12_param_1];
ld.param.u64 %rd10, [blend_nv12_param_2];
ld.param.u32 %r22, [blend_nv12_param_3];
ld.param.u32 %r23, [blend_nv12_param_4];
ld.param.u32 %r24, [blend_nv12_param_5];
ld.param.u64 %rd12, [blend_nv12_param_6];
ld.param.u32 %r25, [blend_nv12_param_7];
ld.param.u32 %r26, [blend_nv12_param_8];
ld.param.u32 %r27, [blend_nv12_param_9];
ld.param.u32 %r28, [blend_nv12_param_10];
cvta.to.global.u64 %rd1, %rd11;
cvta.to.global.u64 %rd2, %rd12;
mov.u32 %r29, %ntid.x;
mov.u32 %r30, %ctaid.x;
mov.u32 %r31, %tid.x;
mad.lo.s32 %r32, %r30, %r29, %r31;
mov.u32 %r33, %ntid.y;
mov.u32 %r34, %ctaid.y;
mov.u32 %r35, %tid.y;
mad.lo.s32 %r36, %r34, %r33, %r35;
shl.b32 %r1, %r32, 1;
shl.b32 %r2, %r36, 1;
setp.ge.s32 %p1, %r1, %r25;
setp.ge.s32 %p2, %r2, %r26;
or.pred %p3, %p1, %p2;
mov.f32 %f102, 0f00000000;
mov.f32 %f103, 0f00000000;
mov.f32 %f104, 0f00000000;
@%p3 bra $L__BB2_19;
cvt.s64.s32 %rd3, %r21;
add.s32 %r3, %r2, %r28;
setp.ge.s32 %p4, %r3, %r24;
mul.lo.s32 %r4, %r2, %r25;
mul.wide.s32 %rd4, %r3, %r21;
add.s32 %r5, %r1, %r27;
or.b32 %r38, %r5, %r3;
setp.lt.s32 %p5, %r38, 0;
mov.u32 %r121, 0;
setp.ge.s32 %p6, %r5, %r23;
or.pred %p7, %p6, %p5;
or.pred %p8, %p4, %p7;
@%p8 bra $L__BB2_4;
add.s32 %r40, %r1, %r4;
mul.wide.s32 %rd13, %r40, 4;
add.s64 %rd5, %rd2, %rd13;
ld.global.u8 %rs1, [%rd5+3];
setp.eq.s16 %p9, %rs1, 0;
@%p9 bra $L__BB2_4;
cvt.u32.u16 %r42, %rs1;
ld.global.u8 %rs5, [%rd5];
cvt.rn.f32.u16 %f31, %rs5;
ld.global.u8 %rs6, [%rd5+1];
cvt.rn.f32.u16 %f32, %rs6;
ld.global.u8 %rs7, [%rd5+2];
cvt.rn.f32.u16 %f33, %rs7;
fma.rn.f32 %f34, %f31, 0f3E3AFB7F, 0f41800000;
fma.rn.f32 %f35, %f32, 0f3F1D3C36, %f34;
fma.rn.f32 %f36, %f33, 0f3D7DF3B6, %f35;
add.f32 %f37, %f36, 0f3F000000;
cvt.rzi.s32.f32 %r43, %f37;
cvt.s64.s32 %rd14, %r5;
add.s64 %rd15, %rd4, %rd14;
add.s64 %rd16, %rd1, %rd15;
ld.global.u8 %r44, [%rd16];
mul.lo.s32 %r45, %r43, %r42;
xor.b32 %r46, %r42, 255;
mad.lo.s32 %r47, %r46, %r44, %r45;
mul.hi.s32 %r48, %r47, -2139062143;
add.s32 %r49, %r48, %r47;
shr.u32 %r50, %r49, 31;
shr.u32 %r51, %r49, 7;
add.s32 %r52, %r51, %r50;
st.global.u8 [%rd16], %r52;
fma.rn.f32 %f38, %f31, 0fBDCE075F, 0f43000000;
fma.rn.f32 %f39, %f32, 0fBEAD5CFB, %f38;
fma.rn.f32 %f40, %f33, 0f3EE0DED3, %f39;
cvt.rn.f32.u16 %f104, %rs1;
fma.rn.f32 %f102, %f40, %f104, 0f00000000;
fma.rn.f32 %f41, %f31, 0f3EE0DED3, 0f43000000;
fma.rn.f32 %f42, %f32, 0fBECC3C9F, %f41;
fma.rn.f32 %f43, %f33, 0fBD25119D, %f42;
fma.rn.f32 %f103, %f43, %f104, 0f00000000;
mov.u32 %r121, 1;
$L__BB2_4:
add.s32 %r7, %r1, 1;
setp.ge.s32 %p10, %r7, %r25;
@%p10 bra $L__BB2_8;
add.s32 %r8, %r7, %r27;
or.b32 %r53, %r8, %r3;
setp.lt.s32 %p12, %r53, 0;
setp.ge.s32 %p13, %r8, %r23;
or.pred %p14, %p13, %p12;
or.pred %p15, %p4, %p14;
@%p15 bra $L__BB2_8;
add.s32 %r54, %r7, %r4;
mul.wide.s32 %rd17, %r54, 4;
add.s64 %rd6, %rd2, %rd17;
ld.global.u8 %rs2, [%rd6+3];
setp.eq.s16 %p16, %rs2, 0;
@%p16 bra $L__BB2_8;
cvt.u32.u16 %r55, %rs2;
ld.global.u8 %rs8, [%rd6];
cvt.rn.f32.u16 %f44, %rs8;
ld.global.u8 %rs9, [%rd6+1];
cvt.rn.f32.u16 %f45, %rs9;
ld.global.u8 %rs10, [%rd6+2];
cvt.rn.f32.u16 %f46, %rs10;
fma.rn.f32 %f47, %f44, 0f3E3AFB7F, 0f41800000;
fma.rn.f32 %f48, %f45, 0f3F1D3C36, %f47;
fma.rn.f32 %f49, %f46, 0f3D7DF3B6, %f48;
add.f32 %f50, %f49, 0f3F000000;
cvt.rzi.s32.f32 %r56, %f50;
cvt.s64.s32 %rd18, %r8;
add.s64 %rd19, %rd4, %rd18;
add.s64 %rd20, %rd1, %rd19;
ld.global.u8 %r57, [%rd20];
mul.lo.s32 %r58, %r56, %r55;
xor.b32 %r59, %r55, 255;
mad.lo.s32 %r60, %r59, %r57, %r58;
mul.hi.s32 %r61, %r60, -2139062143;
add.s32 %r62, %r61, %r60;
shr.u32 %r63, %r62, 31;
shr.u32 %r64, %r62, 7;
add.s32 %r65, %r64, %r63;
st.global.u8 [%rd20], %r65;
fma.rn.f32 %f51, %f44, 0fBDCE075F, 0f43000000;
fma.rn.f32 %f52, %f45, 0fBEAD5CFB, %f51;
fma.rn.f32 %f53, %f46, 0f3EE0DED3, %f52;
cvt.rn.f32.u16 %f54, %rs2;
fma.rn.f32 %f102, %f53, %f54, %f102;
fma.rn.f32 %f55, %f44, 0f3EE0DED3, 0f43000000;
fma.rn.f32 %f56, %f45, 0fBECC3C9F, %f55;
fma.rn.f32 %f57, %f46, 0fBD25119D, %f56;
fma.rn.f32 %f103, %f57, %f54, %f103;
add.f32 %f104, %f104, %f54;
add.s32 %r121, %r121, 1;
$L__BB2_8:
add.s32 %r11, %r2, 1;
setp.ge.s32 %p17, %r11, %r26;
add.s32 %r12, %r11, %r28;
add.s32 %r13, %r4, %r25;
cvt.s64.s32 %rd21, %r12;
mul.lo.s64 %rd7, %rd21, %rd3;
@%p17 bra $L__BB2_12;
setp.ge.s32 %p18, %r12, %r24;
or.b32 %r66, %r5, %r12;
setp.lt.s32 %p19, %r66, 0;
or.pred %p21, %p6, %p19;
or.pred %p22, %p18, %p21;
@%p22 bra $L__BB2_12;
add.s32 %r67, %r1, %r13;
mul.wide.s32 %rd22, %r67, 4;
add.s64 %rd8, %rd2, %rd22;
ld.global.u8 %rs3, [%rd8+3];
setp.eq.s16 %p23, %rs3, 0;
@%p23 bra $L__BB2_12;
cvt.u32.u16 %r68, %rs3;
ld.global.u8 %rs11, [%rd8];
cvt.rn.f32.u16 %f58, %rs11;
ld.global.u8 %rs12, [%rd8+1];
cvt.rn.f32.u16 %f59, %rs12;
ld.global.u8 %rs13, [%rd8+2];
cvt.rn.f32.u16 %f60, %rs13;
fma.rn.f32 %f61, %f58, 0f3E3AFB7F, 0f41800000;
fma.rn.f32 %f62, %f59, 0f3F1D3C36, %f61;
fma.rn.f32 %f63, %f60, 0f3D7DF3B6, %f62;
add.f32 %f64, %f63, 0f3F000000;
cvt.rzi.s32.f32 %r69, %f64;
cvt.s64.s32 %rd23, %r5;
add.s64 %rd24, %rd7, %rd23;
add.s64 %rd25, %rd1, %rd24;
ld.global.u8 %r70, [%rd25];
mul.lo.s32 %r71, %r69, %r68;
xor.b32 %r72, %r68, 255;
mad.lo.s32 %r73, %r72, %r70, %r71;
mul.hi.s32 %r74, %r73, -2139062143;
add.s32 %r75, %r74, %r73;
shr.u32 %r76, %r75, 31;
shr.u32 %r77, %r75, 7;
add.s32 %r78, %r77, %r76;
st.global.u8 [%rd25], %r78;
fma.rn.f32 %f65, %f58, 0fBDCE075F, 0f43000000;
fma.rn.f32 %f66, %f59, 0fBEAD5CFB, %f65;
fma.rn.f32 %f67, %f60, 0f3EE0DED3, %f66;
cvt.rn.f32.u16 %f68, %rs3;
fma.rn.f32 %f102, %f67, %f68, %f102;
fma.rn.f32 %f69, %f58, 0f3EE0DED3, 0f43000000;
fma.rn.f32 %f70, %f59, 0fBECC3C9F, %f69;
fma.rn.f32 %f71, %f60, 0fBD25119D, %f70;
fma.rn.f32 %f103, %f71, %f68, %f103;
add.f32 %f104, %f104, %f68;
add.s32 %r121, %r121, 1;
$L__BB2_12:
or.pred %p26, %p17, %p10;
@%p26 bra $L__BB2_16;
setp.ge.s32 %p27, %r12, %r24;
add.s32 %r16, %r7, %r27;
or.b32 %r79, %r16, %r12;
setp.lt.s32 %p28, %r79, 0;
setp.ge.s32 %p29, %r16, %r23;
or.pred %p30, %p29, %p28;
or.pred %p31, %p27, %p30;
@%p31 bra $L__BB2_16;
add.s32 %r80, %r7, %r13;
mul.wide.s32 %rd26, %r80, 4;
add.s64 %rd9, %rd2, %rd26;
ld.global.u8 %rs4, [%rd9+3];
setp.eq.s16 %p32, %rs4, 0;
@%p32 bra $L__BB2_16;
cvt.u32.u16 %r81, %rs4;
ld.global.u8 %rs14, [%rd9];
cvt.rn.f32.u16 %f72, %rs14;
ld.global.u8 %rs15, [%rd9+1];
cvt.rn.f32.u16 %f73, %rs15;
ld.global.u8 %rs16, [%rd9+2];
cvt.rn.f32.u16 %f74, %rs16;
fma.rn.f32 %f75, %f72, 0f3E3AFB7F, 0f41800000;
fma.rn.f32 %f76, %f73, 0f3F1D3C36, %f75;
fma.rn.f32 %f77, %f74, 0f3D7DF3B6, %f76;
add.f32 %f78, %f77, 0f3F000000;
cvt.rzi.s32.f32 %r82, %f78;
cvt.s64.s32 %rd27, %r16;
add.s64 %rd28, %rd7, %rd27;
add.s64 %rd29, %rd1, %rd28;
ld.global.u8 %r83, [%rd29];
mul.lo.s32 %r84, %r82, %r81;
xor.b32 %r85, %r81, 255;
mad.lo.s32 %r86, %r85, %r83, %r84;
mul.hi.s32 %r87, %r86, -2139062143;
add.s32 %r88, %r87, %r86;
shr.u32 %r89, %r88, 31;
shr.u32 %r90, %r88, 7;
add.s32 %r91, %r90, %r89;
st.global.u8 [%rd29], %r91;
fma.rn.f32 %f79, %f72, 0fBDCE075F, 0f43000000;
fma.rn.f32 %f80, %f73, 0fBEAD5CFB, %f79;
fma.rn.f32 %f81, %f74, 0f3EE0DED3, %f80;
cvt.rn.f32.u16 %f82, %rs4;
fma.rn.f32 %f102, %f81, %f82, %f102;
fma.rn.f32 %f83, %f72, 0f3EE0DED3, 0f43000000;
fma.rn.f32 %f84, %f73, 0fBECC3C9F, %f83;
fma.rn.f32 %f85, %f74, 0fBD25119D, %f84;
fma.rn.f32 %f103, %f85, %f82, %f103;
add.f32 %f104, %f104, %f82;
add.s32 %r121, %r121, 1;
$L__BB2_16:
setp.eq.s32 %p33, %r121, 0;
setp.le.f32 %p34, %f104, 0f00000000;
or.pred %p35, %p34, %p33;
@%p35 bra $L__BB2_19;
shr.u32 %r92, %r5, 31;
add.s32 %r93, %r5, %r92;
shr.s32 %r19, %r93, 1;
setp.lt.s32 %p36, %r3, -1;
setp.lt.s32 %p37, %r5, -1;
or.pred %p38, %p37, %p36;
and.b32 %r94, %r93, -2;
setp.ge.s32 %p39, %r94, %r23;
or.pred %p40, %p38, %p39;
shr.u32 %r95, %r3, 31;
add.s32 %r96, %r3, %r95;
shr.s32 %r20, %r96, 1;
and.b32 %r97, %r96, -2;
setp.ge.s32 %p41, %r97, %r24;
or.pred %p42, %p40, %p41;
@%p42 bra $L__BB2_19;
div.rn.f32 %f86, %f102, %f104;
add.f32 %f87, %f86, 0f3F000000;
cvt.rzi.s32.f32 %r98, %f87;
div.rn.f32 %f88, %f103, %f104;
add.f32 %f89, %f88, 0f3F000000;
cvt.rzi.s32.f32 %r99, %f89;
cvt.rn.f32.s32 %f90, %r121;
div.rn.f32 %f91, %f104, %f90;
add.f32 %f92, %f91, 0f3F000000;
cvt.rzi.s32.f32 %r100, %f92;
mul.wide.s32 %rd30, %r20, %r22;
mul.wide.s32 %rd31, %r19, 2;
add.s64 %rd32, %rd30, %rd31;
cvta.to.global.u64 %rd33, %rd10;
add.s64 %rd34, %rd33, %rd32;
ld.global.u8 %r101, [%rd34];
mul.lo.s32 %r102, %r100, %r98;
mov.u32 %r103, 255;
sub.s32 %r104, %r103, %r100;
mad.lo.s32 %r105, %r104, %r101, %r102;
mul.hi.s32 %r106, %r105, -2139062143;
add.s32 %r107, %r106, %r105;
shr.u32 %r108, %r107, 31;
shr.u32 %r109, %r107, 7;
add.s32 %r110, %r109, %r108;
st.global.u8 [%rd34], %r110;
ld.global.u8 %r111, [%rd34+1];
mul.lo.s32 %r112, %r100, %r99;
mad.lo.s32 %r113, %r104, %r111, %r112;
mul.hi.s32 %r114, %r113, -2139062143;
add.s32 %r115, %r114, %r113;
shr.u32 %r116, %r115, 31;
shr.u32 %r117, %r115, 7;
add.s32 %r118, %r117, %r116;
st.global.u8 [%rd34+1], %r118;
$L__BB2_19:
ret;
}
View Git Blame Copy Permalink