NIR (SSA form) for fragment shader: shader: MESA_SHADER_FRAGMENT name: BLORP-blit inputs: 0 outputs: 0 uniforms: 0 shared: 0 decl_var shader_in INTERP_MODE_FLAT vec4 coord_transform (VARYING_SLOT_VAR3, 33, 0) decl_var shader_in INTERP_MODE_FLAT uint src_z (VARYING_SLOT_VAR5, 35, 0) decl_var shader_in INTERP_MODE_SMOOTH vec4 gl_FragCoord (VARYING_SLOT_POS, 0, 0) decl_var shader_out INTERP_MODE_NONE vec4 gl_FragColor (FRAG_RESULT_COLOR, 4, 0) decl_function main returning void impl main { block block_0: /* preds: */ vec2 32 ssa_0 = intrinsic load_barycentric_pixel () () (1) /* interp_mode=1 */ vec1 32 ssa_1 = load_const (0x00000000 /* 0.000000 */) vec4 32 ssa_2 = intrinsic load_interpolated_input (ssa_0, ssa_1) () (0, 0) /* base=0 */ /* component=0 */ vec1 32 ssa_3 = f2i32 ssa_2.x vec1 32 ssa_4 = f2i32 ssa_2.y vec1 32 ssa_5 = i2f32 ssa_3 vec1 32 ssa_6 = i2f32 ssa_4 vec4 32 ssa_7 = intrinsic load_input (ssa_1) () (33, 0) /* base=33 */ /* component=0 */ /* coord_transform */ vec1 32 ssa_8 = ffma ssa_5, ssa_7.x, ssa_7.y vec1 32 ssa_9 = ffma ssa_6, ssa_7.z, ssa_7.w vec1 32 ssa_10 = f2i32 ssa_8 vec1 32 ssa_11 = f2i32 ssa_9 vec1 32 ssa_12 = intrinsic load_input (ssa_1) () (35, 0) /* base=35 */ /* component=0 */ /* src_z */ vec3 32 ssa_13 = vec3 ssa_10, ssa_11, ssa_12 vec4 32 ssa_14 = txf ssa_13 (coord), ssa_1 (lod), 0 (texture) 0 (sampler) intrinsic store_output (ssa_14, ssa_1) () (4, 15, 0) /* base=4 */ /* wrmask=xyzw */ /* component=0 */ /* gl_FragColor */ /* succs: block_0 */ block block_0: } NIR (final form) for fragment shader: shader: MESA_SHADER_FRAGMENT name: BLORP-blit inputs: 0 outputs: 0 uniforms: 0 shared: 0 decl_var shader_in INTERP_MODE_FLAT vec4 coord_transform (VARYING_SLOT_VAR3, 33, 0) decl_var shader_in INTERP_MODE_FLAT uint src_z (VARYING_SLOT_VAR5, 35, 0) decl_var shader_in INTERP_MODE_SMOOTH vec4 gl_FragCoord (VARYING_SLOT_POS, 0, 0) decl_var shader_out INTERP_MODE_NONE vec4 gl_FragColor (FRAG_RESULT_COLOR, 4, 0) decl_function main returning void impl main { block block_0: /* preds: */ vec2 32 ssa_0 = intrinsic load_barycentric_pixel () () (1) /* interp_mode=1 */ vec1 32 ssa_1 = load_const (0x00000000 /* 0.000000 */) vec4 32 ssa_2 = intrinsic load_interpolated_input (ssa_0, ssa_1) () (0, 0) /* base=0 */ /* component=0 */ vec1 32 ssa_3 = f2i32 ssa_2.x vec1 32 ssa_4 = f2i32 ssa_2.y vec1 32 ssa_5 = i2f32 ssa_3 vec1 32 ssa_6 = i2f32 ssa_4 vec4 32 ssa_7 = intrinsic load_input (ssa_1) () (33, 0) /* base=33 */ /* component=0 */ /* coord_transform */ vec1 32 ssa_8 = ffma ssa_5, ssa_7.x, ssa_7.y vec1 32 ssa_9 = ffma ssa_6, ssa_7.z, ssa_7.w vec1 32 ssa_10 = f2i32 ssa_8 vec1 32 ssa_11 = f2i32 ssa_9 vec1 32 ssa_12 = intrinsic load_input (ssa_1) () (35, 0) /* base=35 */ /* component=0 */ /* src_z */ vec3 32 ssa_13 = vec3 ssa_10, ssa_11, ssa_12 vec4 32 ssa_14 = txf ssa_13 (coord), ssa_1 (lod), 0 (texture) 0 (sampler) intrinsic store_output (ssa_14, ssa_1) () (4, 15, 0) /* base=4 */ /* wrmask=xyzw */ /* component=0 */ /* gl_FragColor */ /* succs: block_0 */ block block_0: } Native code for unnamed fragment shader BLORP-blit SIMD8 shader: 18 instructions. 0 loops. 310 cycles. 0:0 spills:fills. Promoted 0 constants. Compacted 288 to 208 bytes (28%) START B0 (310 cycles) add(16) g2<1>UW g1.4<1,4,0>UW 0x11001010V { align1 WE_all 1H }; mov(8) g10<1>F g4.3<0,1,0>F { align1 1Q compacted }; mov(8) g11<1>F g4.7<0,1,0>F { align1 1Q }; mov(8) g12<1>F g5.3<0,1,0>F { align1 1Q compacted }; mov(8) g9<1>F g5.7<0,1,0>F { align1 1Q }; mov(8) g15<1>F g6.3<0,1,0>F { align1 1Q compacted }; mov(8) g4<1>F g2.4<8,4,1>UW { align1 1Q }; mov(8) g3<1>F g2<8,4,1>UW { align1 1Q }; mov(8) g6<1>D g4<8,8,1>F { align1 1Q compacted }; mov(8) g5<1>D g3<8,8,1>F { align1 1Q compacted }; mov(8) g8<1>F g6<8,8,1>D { align1 1Q compacted }; mov(8) g7<1>F g5<8,8,1>D { align1 1Q compacted }; mad(8) g10<1>F g11<4,4,1>F g10<4,4,1>F g7<4,4,1>F { align16 1Q compacted }; mad(8) g11<1>F g9<4,4,1>F g12<4,4,1>F g8<4,4,1>F { align16 1Q compacted }; mov(8) g13<1>D g10<8,8,1>F { align1 1Q compacted }; mov(8) g14<1>D g11<8,8,1>F { align1 1Q compacted }; send(8) g124<1>UW g13<8,8,1>F sampler ld_lz SIMD8 Surface = 1 Sampler = 0 mlen 3 rlen 4 { align1 1Q }; sendc(8) null<1>UW g124<8,8,1>F render RT write SIMD8 LastRT Surface = 0 mlen 4 rlen 0 { align1 1Q EOT }; nop ; END B0 Native code for unnamed fragment shader BLORP-blit SIMD16 shader: 18 instructions. 0 loops. 328 cycles. 0:0 spills:fills. Promoted 0 constants. Compacted 288 to 208 bytes (28%) START B0 (328 cycles) add(32) g2<1>UW g1.4<1,4,0>UW 0x11001010V { align1 WE_all }; mov(16) g20<1>F g6.3<0,1,0>F { align1 1H compacted }; mov(16) g22<1>F g6.7<0,1,0>F { align1 1H }; mov(16) g24<1>F g7.3<0,1,0>F { align1 1H compacted }; mov(16) g16<1>F g7.7<0,1,0>F { align1 1H }; mov(16) g30<1>F g8.3<0,1,0>F { align1 1H compacted }; mov(16) g4<1>F g2<8,4,1>UW { align1 1H }; mov(16) g6<1>F g2.4<8,4,1>UW { align1 1H }; mov(16) g8<1>D g4<8,8,1>F { align1 1H compacted }; mov(16) g10<1>D g6<8,8,1>F { align1 1H compacted }; mov(16) g12<1>F g8<8,8,1>D { align1 1H compacted }; mov(16) g14<1>F g10<8,8,1>D { align1 1H compacted }; mad(16) g18<1>F g22<4,4,1>F g20<4,4,1>F g12<4,4,1>F { align16 1H compacted }; mad(16) g20<1>F g16<4,4,1>F g24<4,4,1>F g14<4,4,1>F { align16 1H compacted }; mov(16) g26<1>D g18<8,8,1>F { align1 1H compacted }; mov(16) g28<1>D g20<8,8,1>F { align1 1H compacted }; send(16) g120<1>UW g26<8,8,1>F sampler ld_lz SIMD16 Surface = 1 Sampler = 0 mlen 6 rlen 8 { align1 1H }; sendc(16) null<1>UW g120<8,8,1>F render RT write SIMD16 LastRT Surface = 0 mlen 8 rlen 0 { align1 1H EOT }; nop ; END B0 NIR (SSA form) for fragment shader: shader: MESA_SHADER_FRAGMENT inputs: 0 outputs: 0 uniforms: 0 shared: 0 decl_var uniform INTERP_MODE_NONE sampler2D samplerFont (0, 0, 0) decl_var shader_in INTERP_MODE_SMOOTH vec2 inUV (VARYING_SLOT_VAR0, 30, 0) decl_var shader_out INTERP_MODE_NONE vec4 outFragColor (FRAG_RESULT_DATA0, 8, 0) decl_function main returning void impl main { block block_0: /* preds: */ vec1 32 ssa_0 = load_const (0x3f800000 /* 1.000000 */) vec2 32 ssa_1 = intrinsic load_barycentric_pixel () () (1) /* interp_mode=1 */ vec1 32 ssa_2 = load_const (0x00000000 /* 0.000000 */) vec2 32 ssa_3 = intrinsic load_interpolated_input (ssa_1, ssa_2) () (30, 0) /* base=30 */ /* component=0 */ vec4 32 ssa_4 = tex ssa_3 (coord), 0 (texture) 0 (sampler) vec4 32 ssa_5 = vec4 ssa_4.x, ssa_4.x, ssa_4.x, ssa_0 intrinsic store_output (ssa_5, ssa_2) () (8, 15, 0) /* base=8 */ /* wrmask=xyzw */ /* component=0 */ /* outFragColor */ /* succs: block_0 */ block block_0: } NIR (final form) for fragment shader: shader: MESA_SHADER_FRAGMENT inputs: 0 outputs: 0 uniforms: 0 shared: 0 decl_var uniform INTERP_MODE_NONE sampler2D samplerFont (0, 0, 0) decl_var shader_in INTERP_MODE_SMOOTH vec2 inUV (VARYING_SLOT_VAR0, 30, 0) decl_var shader_out INTERP_MODE_NONE vec4 outFragColor (FRAG_RESULT_DATA0, 8, 0) decl_function main returning void impl main { block block_0: /* preds: */ vec1 32 ssa_0 = load_const (0x3f800000 /* 1.000000 */) vec2 32 ssa_1 = intrinsic load_barycentric_pixel () () (1) /* interp_mode=1 */ vec1 32 ssa_2 = load_const (0x00000000 /* 0.000000 */) vec2 32 ssa_3 = intrinsic load_interpolated_input (ssa_1, ssa_2) () (30, 0) /* base=30 */ /* component=0 */ vec4 32 ssa_4 = tex ssa_3 (coord), 0 (texture) 0 (sampler) vec4 32 ssa_5 = vec4 ssa_4.x, ssa_4.x, ssa_4.x, ssa_0 intrinsic store_output (ssa_5, ssa_2) () (8, 15, 0) /* base=8 */ /* wrmask=xyzw */ /* component=0 */ /* outFragColor */ /* succs: block_0 */ block block_0: } Native code for unnamed fragment shader (null) SIMD8 shader: 7 instructions. 0 loops. 240 cycles. 0:0 spills:fills. Promoted 0 constants. Compacted 112 to 80 bytes (29%) START B0 (240 cycles) pln(8) g5<1>F g4<0,1,0>F g2<8,8,1>F { align1 1Q compacted }; pln(8) g6<1>F g4.4<0,1,0>F g2<8,8,1>F { align1 1Q compacted }; mov(8) g127<1>F 1F { align1 1Q }; send(8) g126<1>UW g5<8,8,1>F sampler sample SIMD8 Surface = 1 Sampler = 0 mlen 2 rlen 1 { align1 1Q }; mov(8) g124<1>F g126<8,8,1>F { align1 1Q compacted }; mov(8) g125<1>F g126<8,8,1>F { align1 1Q compacted }; sendc(8) null<1>UW g124<8,8,1>F render RT write SIMD8 LastRT Surface = 0 mlen 4 rlen 0 { align1 1Q EOT }; END B0 Native code for unnamed fragment shader (null) SIMD16 shader: 7 instructions. 0 loops. 252 cycles. 0:0 spills:fills. Promoted 0 constants. Compacted 112 to 80 bytes (29%) START B0 (252 cycles) pln(16) g7<1>F g6<0,1,0>F g2<8,8,1>F { align1 1H compacted }; pln(16) g9<1>F g6.4<0,1,0>F g2<8,8,1>F { align1 1H compacted }; mov(16) g126<1>F 1F { align1 1H }; send(16) g124<1>UW g7<8,8,1>F sampler sample SIMD16 Surface = 1 Sampler = 0 mlen 4 rlen 2 { align1 1H }; mov(16) g120<1>F g124<8,8,1>F { align1 1H compacted }; mov(16) g122<1>F g124<8,8,1>F { align1 1H compacted }; sendc(16) null<1>UW g120<8,8,1>F render RT write SIMD16 LastRT Surface = 0 mlen 8 rlen 0 { align1 1H EOT }; END B0 NIR (SSA form) for fragment shader: shader: MESA_SHADER_FRAGMENT name: BLORP-blit inputs: 0 outputs: 0 uniforms: 0 shared: 0 decl_var shader_in INTERP_MODE_FLAT vec4 coord_transform (VARYING_SLOT_VAR3, 33, 0) decl_var shader_in INTERP_MODE_FLAT uint src_z (VARYING_SLOT_VAR5, 35, 0) decl_var shader_in INTERP_MODE_SMOOTH vec4 gl_FragCoord (VARYING_SLOT_POS, 0, 0) decl_var shader_out INTERP_MODE_NONE vec4 gl_FragColor (FRAG_RESULT_COLOR, 4, 0) decl_function main returning void impl main { block block_0: /* preds: */ vec2 32 ssa_0 = intrinsic load_barycentric_pixel () () (1) /* interp_mode=1 */ vec1 32 ssa_1 = load_const (0x00000000 /* 0.000000 */) vec4 32 ssa_2 = intrinsic load_interpolated_input (ssa_0, ssa_1) () (0, 0) /* base=0 */ /* component=0 */ vec1 32 ssa_3 = f2i32 ssa_2.x vec1 32 ssa_4 = f2i32 ssa_2.y vec1 32 ssa_5 = i2f32 ssa_3 vec1 32 ssa_6 = i2f32 ssa_4 vec4 32 ssa_7 = intrinsic load_input (ssa_1) () (33, 0) /* base=33 */ /* component=0 */ /* coord_transform */ vec1 32 ssa_8 = ffma ssa_5, ssa_7.x, ssa_7.y vec1 32 ssa_9 = ffma ssa_6, ssa_7.z, ssa_7.w vec1 32 ssa_10 = f2i32 ssa_8 vec1 32 ssa_11 = f2i32 ssa_9 vec1 32 ssa_12 = intrinsic load_input (ssa_1) () (35, 0) /* base=35 */ /* component=0 */ /* src_z */ vec3 32 ssa_13 = vec3 ssa_10, ssa_11, ssa_12 vec4 32 ssa_14 = txf ssa_13 (coord), ssa_1 (lod), 0 (texture) 0 (sampler) intrinsic store_output (ssa_14, ssa_1) () (4, 15, 0) /* base=4 */ /* wrmask=xyzw */ /* component=0 */ /* gl_FragColor */ /* succs: block_0 */ block block_0: } NIR (final form) for fragment shader: shader: MESA_SHADER_FRAGMENT name: BLORP-blit inputs: 0 outputs: 0 uniforms: 0 shared: 0 decl_var shader_in INTERP_MODE_FLAT vec4 coord_transform (VARYING_SLOT_VAR3, 33, 0) decl_var shader_in INTERP_MODE_FLAT uint src_z (VARYING_SLOT_VAR5, 35, 0) decl_var shader_in INTERP_MODE_SMOOTH vec4 gl_FragCoord (VARYING_SLOT_POS, 0, 0) decl_var shader_out INTERP_MODE_NONE vec4 gl_FragColor (FRAG_RESULT_COLOR, 4, 0) decl_function main returning void impl main { block block_0: /* preds: */ vec2 32 ssa_0 = intrinsic load_barycentric_pixel () () (1) /* interp_mode=1 */ vec1 32 ssa_1 = load_const (0x00000000 /* 0.000000 */) vec4 32 ssa_2 = intrinsic load_interpolated_input (ssa_0, ssa_1) () (0, 0) /* base=0 */ /* component=0 */ vec1 32 ssa_3 = f2i32 ssa_2.x vec1 32 ssa_4 = f2i32 ssa_2.y vec1 32 ssa_5 = i2f32 ssa_3 vec1 32 ssa_6 = i2f32 ssa_4 vec4 32 ssa_7 = intrinsic load_input (ssa_1) () (33, 0) /* base=33 */ /* component=0 */ /* coord_transform */ vec1 32 ssa_8 = ffma ssa_5, ssa_7.x, ssa_7.y vec1 32 ssa_9 = ffma ssa_6, ssa_7.z, ssa_7.w vec1 32 ssa_10 = f2i32 ssa_8 vec1 32 ssa_11 = f2i32 ssa_9 vec1 32 ssa_12 = intrinsic load_input (ssa_1) () (35, 0) /* base=35 */ /* component=0 */ /* src_z */ vec3 32 ssa_13 = vec3 ssa_10, ssa_11, ssa_12 vec4 32 ssa_14 = txf ssa_13 (coord), ssa_1 (lod), 0 (texture) 0 (sampler) intrinsic store_output (ssa_14, ssa_1) () (4, 15, 0) /* base=4 */ /* wrmask=xyzw */ /* component=0 */ /* gl_FragColor */ /* succs: block_0 */ block block_0: } Native code for unnamed fragment shader BLORP-blit SIMD8 shader: 18 instructions. 0 loops. 310 cycles. 0:0 spills:fills. Promoted 0 constants. Compacted 288 to 208 bytes (28%) START B0 (310 cycles) add(16) g2<1>UW g1.4<1,4,0>UW 0x11001010V { align1 WE_all 1H }; mov(8) g10<1>F g4.3<0,1,0>F { align1 1Q compacted }; mov(8) g11<1>F g4.7<0,1,0>F { align1 1Q }; mov(8) g12<1>F g5.3<0,1,0>F { align1 1Q compacted }; mov(8) g9<1>F g5.7<0,1,0>F { align1 1Q }; mov(8) g15<1>F g6.3<0,1,0>F { align1 1Q compacted }; mov(8) g4<1>F g2.4<8,4,1>UW { align1 1Q }; mov(8) g3<1>F g2<8,4,1>UW { align1 1Q }; mov(8) g6<1>D g4<8,8,1>F { align1 1Q compacted }; mov(8) g5<1>D g3<8,8,1>F { align1 1Q compacted }; mov(8) g8<1>F g6<8,8,1>D { align1 1Q compacted }; mov(8) g7<1>F g5<8,8,1>D { align1 1Q compacted }; mad(8) g10<1>F g11<4,4,1>F g10<4,4,1>F g7<4,4,1>F { align16 1Q compacted }; mad(8) g11<1>F g9<4,4,1>F g12<4,4,1>F g8<4,4,1>F { align16 1Q compacted }; mov(8) g13<1>D g10<8,8,1>F { align1 1Q compacted }; mov(8) g14<1>D g11<8,8,1>F { align1 1Q compacted }; send(8) g124<1>UW g13<8,8,1>F sampler ld_lz SIMD8 Surface = 1 Sampler = 0 mlen 3 rlen 4 { align1 1Q }; sendc(8) null<1>UW g124<8,8,1>F render RT write SIMD8 LastRT Surface = 0 mlen 4 rlen 0 { align1 1Q EOT }; nop ; END B0 Native code for unnamed fragment shader BLORP-blit SIMD16 shader: 18 instructions. 0 loops. 328 cycles. 0:0 spills:fills. Promoted 0 constants. Compacted 288 to 208 bytes (28%) START B0 (328 cycles) add(32) g2<1>UW g1.4<1,4,0>UW 0x11001010V { align1 WE_all }; mov(16) g20<1>F g6.3<0,1,0>F { align1 1H compacted }; mov(16) g22<1>F g6.7<0,1,0>F { align1 1H }; mov(16) g24<1>F g7.3<0,1,0>F { align1 1H compacted }; mov(16) g16<1>F g7.7<0,1,0>F { align1 1H }; mov(16) g30<1>F g8.3<0,1,0>F { align1 1H compacted }; mov(16) g4<1>F g2<8,4,1>UW { align1 1H }; mov(16) g6<1>F g2.4<8,4,1>UW { align1 1H }; mov(16) g8<1>D g4<8,8,1>F { align1 1H compacted }; mov(16) g10<1>D g6<8,8,1>F { align1 1H compacted }; mov(16) g12<1>F g8<8,8,1>D { align1 1H compacted }; mov(16) g14<1>F g10<8,8,1>D { align1 1H compacted }; mad(16) g18<1>F g22<4,4,1>F g20<4,4,1>F g12<4,4,1>F { align16 1H compacted }; mad(16) g20<1>F g16<4,4,1>F g24<4,4,1>F g14<4,4,1>F { align16 1H compacted }; mov(16) g26<1>D g18<8,8,1>F { align1 1H compacted }; mov(16) g28<1>D g20<8,8,1>F { align1 1H compacted }; send(16) g120<1>UW g26<8,8,1>F sampler ld_lz SIMD16 Surface = 1 Sampler = 0 mlen 6 rlen 8 { align1 1H }; sendc(16) null<1>UW g120<8,8,1>F render RT write SIMD16 LastRT Surface = 0 mlen 8 rlen 0 { align1 1H EOT }; nop ; END B0 NIR (SSA form) for fragment shader: shader: MESA_SHADER_FRAGMENT name: BLORP-blit inputs: 0 outputs: 0 uniforms: 0 shared: 0 decl_var shader_in INTERP_MODE_FLAT vec4 coord_transform (VARYING_SLOT_VAR3, 33, 0) decl_var shader_in INTERP_MODE_FLAT uint src_z (VARYING_SLOT_VAR5, 35, 0) decl_var shader_in INTERP_MODE_SMOOTH vec4 gl_FragCoord (VARYING_SLOT_POS, 0, 0) decl_var shader_out INTERP_MODE_NONE vec4 gl_FragColor (FRAG_RESULT_COLOR, 4, 0) decl_function main returning void impl main { block block_0: /* preds: */ vec2 32 ssa_0 = intrinsic load_barycentric_pixel () () (1) /* interp_mode=1 */ vec1 32 ssa_1 = load_const (0x00000000 /* 0.000000 */) vec4 32 ssa_2 = intrinsic load_interpolated_input (ssa_0, ssa_1) () (0, 0) /* base=0 */ /* component=0 */ vec1 32 ssa_3 = f2i32 ssa_2.x vec1 32 ssa_4 = f2i32 ssa_2.y vec1 32 ssa_5 = i2f32 ssa_3 vec1 32 ssa_6 = i2f32 ssa_4 vec4 32 ssa_7 = intrinsic load_input (ssa_1) () (33, 0) /* base=33 */ /* component=0 */ /* coord_transform */ vec1 32 ssa_8 = ffma ssa_5, ssa_7.x, ssa_7.y vec1 32 ssa_9 = ffma ssa_6, ssa_7.z, ssa_7.w vec1 32 ssa_10 = f2i32 ssa_8 vec1 32 ssa_11 = f2i32 ssa_9 vec1 32 ssa_12 = intrinsic load_input (ssa_1) () (35, 0) /* base=35 */ /* component=0 */ /* src_z */ vec3 32 ssa_13 = vec3 ssa_10, ssa_11, ssa_12 vec4 32 ssa_14 = txf ssa_13 (coord), ssa_1 (lod), 0 (texture) 0 (sampler) intrinsic store_output (ssa_14, ssa_1) () (4, 15, 0) /* base=4 */ /* wrmask=xyzw */ /* component=0 */ /* gl_FragColor */ /* succs: block_0 */ block block_0: } NIR (final form) for fragment shader: shader: MESA_SHADER_FRAGMENT name: BLORP-blit inputs: 0 outputs: 0 uniforms: 0 shared: 0 decl_var shader_in INTERP_MODE_FLAT vec4 coord_transform (VARYING_SLOT_VAR3, 33, 0) decl_var shader_in INTERP_MODE_FLAT uint src_z (VARYING_SLOT_VAR5, 35, 0) decl_var shader_in INTERP_MODE_SMOOTH vec4 gl_FragCoord (VARYING_SLOT_POS, 0, 0) decl_var shader_out INTERP_MODE_NONE vec4 gl_FragColor (FRAG_RESULT_COLOR, 4, 0) decl_function main returning void impl main { block block_0: /* preds: */ vec2 32 ssa_0 = intrinsic load_barycentric_pixel () () (1) /* interp_mode=1 */ vec1 32 ssa_1 = load_const (0x00000000 /* 0.000000 */) vec4 32 ssa_2 = intrinsic load_interpolated_input (ssa_0, ssa_1) () (0, 0) /* base=0 */ /* component=0 */ vec1 32 ssa_3 = f2i32 ssa_2.x vec1 32 ssa_4 = f2i32 ssa_2.y vec1 32 ssa_5 = i2f32 ssa_3 vec1 32 ssa_6 = i2f32 ssa_4 vec4 32 ssa_7 = intrinsic load_input (ssa_1) () (33, 0) /* base=33 */ /* component=0 */ /* coord_transform */ vec1 32 ssa_8 = ffma ssa_5, ssa_7.x, ssa_7.y vec1 32 ssa_9 = ffma ssa_6, ssa_7.z, ssa_7.w vec1 32 ssa_10 = f2i32 ssa_8 vec1 32 ssa_11 = f2i32 ssa_9 vec1 32 ssa_12 = intrinsic load_input (ssa_1) () (35, 0) /* base=35 */ /* component=0 */ /* src_z */ vec3 32 ssa_13 = vec3 ssa_10, ssa_11, ssa_12 vec4 32 ssa_14 = txf ssa_13 (coord), ssa_1 (lod), 0 (texture) 0 (sampler) intrinsic store_output (ssa_14, ssa_1) () (4, 15, 0) /* base=4 */ /* wrmask=xyzw */ /* component=0 */ /* gl_FragColor */ /* succs: block_0 */ block block_0: } Native code for unnamed fragment shader BLORP-blit SIMD8 shader: 18 instructions. 0 loops. 310 cycles. 0:0 spills:fills. Promoted 0 constants. Compacted 288 to 208 bytes (28%) START B0 (310 cycles) add(16) g2<1>UW g1.4<1,4,0>UW 0x11001010V { align1 WE_all 1H }; mov(8) g10<1>F g4.3<0,1,0>F { align1 1Q compacted }; mov(8) g11<1>F g4.7<0,1,0>F { align1 1Q }; mov(8) g12<1>F g5.3<0,1,0>F { align1 1Q compacted }; mov(8) g9<1>F g5.7<0,1,0>F { align1 1Q }; mov(8) g15<1>F g6.3<0,1,0>F { align1 1Q compacted }; mov(8) g4<1>F g2.4<8,4,1>UW { align1 1Q }; mov(8) g3<1>F g2<8,4,1>UW { align1 1Q }; mov(8) g6<1>D g4<8,8,1>F { align1 1Q compacted }; mov(8) g5<1>D g3<8,8,1>F { align1 1Q compacted }; mov(8) g8<1>F g6<8,8,1>D { align1 1Q compacted }; mov(8) g7<1>F g5<8,8,1>D { align1 1Q compacted }; mad(8) g10<1>F g11<4,4,1>F g10<4,4,1>F g7<4,4,1>F { align16 1Q compacted }; mad(8) g11<1>F g9<4,4,1>F g12<4,4,1>F g8<4,4,1>F { align16 1Q compacted }; mov(8) g13<1>D g10<8,8,1>F { align1 1Q compacted }; mov(8) g14<1>D g11<8,8,1>F { align1 1Q compacted }; send(8) g124<1>UW g13<8,8,1>F sampler ld_lz SIMD8 Surface = 1 Sampler = 0 mlen 3 rlen 4 { align1 1Q }; sendc(8) null<1>UW g124<8,8,1>F render RT write SIMD8 LastRT Surface = 0 mlen 4 rlen 0 { align1 1Q EOT }; nop ; END B0 Native code for unnamed fragment shader BLORP-blit SIMD16 shader: 18 instructions. 0 loops. 328 cycles. 0:0 spills:fills. Promoted 0 constants. Compacted 288 to 208 bytes (28%) START B0 (328 cycles) add(32) g2<1>UW g1.4<1,4,0>UW 0x11001010V { align1 WE_all }; mov(16) g20<1>F g6.3<0,1,0>F { align1 1H compacted }; mov(16) g22<1>F g6.7<0,1,0>F { align1 1H }; mov(16) g24<1>F g7.3<0,1,0>F { align1 1H compacted }; mov(16) g16<1>F g7.7<0,1,0>F { align1 1H }; mov(16) g30<1>F g8.3<0,1,0>F { align1 1H compacted }; mov(16) g4<1>F g2<8,4,1>UW { align1 1H }; mov(16) g6<1>F g2.4<8,4,1>UW { align1 1H }; mov(16) g8<1>D g4<8,8,1>F { align1 1H compacted }; mov(16) g10<1>D g6<8,8,1>F { align1 1H compacted }; mov(16) g12<1>F g8<8,8,1>D { align1 1H compacted }; mov(16) g14<1>F g10<8,8,1>D { align1 1H compacted }; mad(16) g18<1>F g22<4,4,1>F g20<4,4,1>F g12<4,4,1>F { align16 1H compacted }; mad(16) g20<1>F g16<4,4,1>F g24<4,4,1>F g14<4,4,1>F { align16 1H compacted }; mov(16) g26<1>D g18<8,8,1>F { align1 1H compacted }; mov(16) g28<1>D g20<8,8,1>F { align1 1H compacted }; send(16) g120<1>UW g26<8,8,1>F sampler ld_lz SIMD16 Surface = 1 Sampler = 0 mlen 6 rlen 8 { align1 1H }; sendc(16) null<1>UW g120<8,8,1>F render RT write SIMD16 LastRT Surface = 0 mlen 8 rlen 0 { align1 1H EOT }; nop ; END B0 NIR (SSA form) for fragment shader: shader: MESA_SHADER_FRAGMENT name: BLORP-blit inputs: 0 outputs: 0 uniforms: 0 shared: 0 decl_var shader_in INTERP_MODE_FLAT vec4 coord_transform (VARYING_SLOT_VAR3, 33, 0) decl_var shader_in INTERP_MODE_FLAT uint src_z (VARYING_SLOT_VAR5, 35, 0) decl_var shader_in INTERP_MODE_FLAT uvec2 src_offset (VARYING_SLOT_VAR4, 34, 0) decl_var shader_in INTERP_MODE_FLAT uvec2 dst_offset (VARYING_SLOT_VAR4, 34, 0) decl_var shader_in INTERP_MODE_SMOOTH vec4 gl_FragCoord (VARYING_SLOT_POS, 0, 0) decl_var shader_out INTERP_MODE_NONE vec4 gl_FragColor (FRAG_RESULT_COLOR, 4, 0) decl_function main returning void impl main { block block_0: /* preds: */ vec2 32 ssa_0 = intrinsic load_barycentric_pixel () () (1) /* interp_mode=1 */ vec1 32 ssa_1 = load_const (0x00000000 /* 0.000000 */) vec4 32 ssa_2 = intrinsic load_interpolated_input (ssa_0, ssa_1) () (0, 0) /* base=0 */ /* component=0 */ vec1 32 ssa_3 = f2i32 ssa_2.x vec1 32 ssa_4 = f2i32 ssa_2.y vec2 32 ssa_5 = intrinsic load_input (ssa_1) () (34, 2) /* base=34 */ /* component=2 */ /* dst_offset */ vec1 32 ssa_6 = iadd ssa_3, -ssa_5.x vec1 32 ssa_7 = iadd ssa_4, -ssa_5.y vec1 32 ssa_8 = i2f32 ssa_6 vec1 32 ssa_9 = i2f32 ssa_7 vec4 32 ssa_10 = intrinsic load_input (ssa_1) () (33, 0) /* base=33 */ /* component=0 */ /* coord_transform */ vec1 32 ssa_11 = ffma ssa_8, ssa_10.x, ssa_10.y vec1 32 ssa_12 = ffma ssa_9, ssa_10.z, ssa_10.w vec1 32 ssa_13 = f2i32 ssa_11 vec1 32 ssa_14 = f2i32 ssa_12 vec2 32 ssa_15 = intrinsic load_input (ssa_1) () (34, 0) /* base=34 */ /* component=0 */ /* src_offset */ vec1 32 ssa_16 = iadd ssa_13, ssa_15.x vec1 32 ssa_17 = iadd ssa_14, ssa_15.y vec1 32 ssa_18 = intrinsic load_input (ssa_1) () (35, 0) /* base=35 */ /* component=0 */ /* src_z */ vec3 32 ssa_19 = vec3 ssa_16, ssa_17, ssa_18 vec4 32 ssa_20 = txf ssa_19 (coord), ssa_1 (lod), 0 (texture) 0 (sampler) intrinsic store_output (ssa_20, ssa_1) () (4, 15, 0) /* base=4 */ /* wrmask=xyzw */ /* component=0 */ /* gl_FragColor */ /* succs: block_0 */ block block_0: } NIR (final form) for fragment shader: shader: MESA_SHADER_FRAGMENT name: BLORP-blit inputs: 0 outputs: 0 uniforms: 0 shared: 0 decl_var shader_in INTERP_MODE_FLAT vec4 coord_transform (VARYING_SLOT_VAR3, 33, 0) decl_var shader_in INTERP_MODE_FLAT uint src_z (VARYING_SLOT_VAR5, 35, 0) decl_var shader_in INTERP_MODE_FLAT uvec2 src_offset (VARYING_SLOT_VAR4, 34, 0) decl_var shader_in INTERP_MODE_FLAT uvec2 dst_offset (VARYING_SLOT_VAR4, 34, 0) decl_var shader_in INTERP_MODE_SMOOTH vec4 gl_FragCoord (VARYING_SLOT_POS, 0, 0) decl_var shader_out INTERP_MODE_NONE vec4 gl_FragColor (FRAG_RESULT_COLOR, 4, 0) decl_function main returning void impl main { block block_0: /* preds: */ vec2 32 ssa_0 = intrinsic load_barycentric_pixel () () (1) /* interp_mode=1 */ vec1 32 ssa_1 = load_const (0x00000000 /* 0.000000 */) vec4 32 ssa_2 = intrinsic load_interpolated_input (ssa_0, ssa_1) () (0, 0) /* base=0 */ /* component=0 */ vec1 32 ssa_3 = f2i32 ssa_2.x vec1 32 ssa_4 = f2i32 ssa_2.y vec2 32 ssa_5 = intrinsic load_input (ssa_1) () (34, 2) /* base=34 */ /* component=2 */ /* dst_offset */ vec1 32 ssa_6 = iadd ssa_3, -ssa_5.x vec1 32 ssa_7 = iadd ssa_4, -ssa_5.y vec1 32 ssa_8 = i2f32 ssa_6 vec1 32 ssa_9 = i2f32 ssa_7 vec4 32 ssa_10 = intrinsic load_input (ssa_1) () (33, 0) /* base=33 */ /* component=0 */ /* coord_transform */ vec1 32 ssa_11 = ffma ssa_8, ssa_10.x, ssa_10.y vec1 32 ssa_12 = ffma ssa_9, ssa_10.z, ssa_10.w vec1 32 ssa_13 = f2i32 ssa_11 vec1 32 ssa_14 = f2i32 ssa_12 vec2 32 ssa_15 = intrinsic load_input (ssa_1) () (34, 0) /* base=34 */ /* component=0 */ /* src_offset */ vec1 32 ssa_16 = iadd ssa_13, ssa_15.x vec1 32 ssa_17 = iadd ssa_14, ssa_15.y vec1 32 ssa_18 = intrinsic load_input (ssa_1) () (35, 0) /* base=35 */ /* component=0 */ /* src_z */ vec3 32 ssa_19 = vec3 ssa_16, ssa_17, ssa_18 vec4 32 ssa_20 = txf ssa_19 (coord), ssa_1 (lod), 0 (texture) 0 (sampler) intrinsic store_output (ssa_20, ssa_1) () (4, 15, 0) /* base=4 */ /* wrmask=xyzw */ /* component=0 */ /* gl_FragColor */ /* succs: block_0 */ block block_0: } Native code for unnamed fragment shader BLORP-blit SIMD8 shader: 26 instructions. 0 loops. 346 cycles. 0:0 spills:fills. Promoted 0 constants. Compacted 416 to 288 bytes (31%) START B0 (346 cycles) add(16) g2<1>UW g1.4<1,4,0>UW 0x11001010V { align1 WE_all 1H }; mov(8) g10<1>F g7.3<0,1,0>F { align1 1Q compacted }; mov(8) g9<1>F g7.7<0,1,0>F { align1 1Q }; mov(8) g15<1>F g4.3<0,1,0>F { align1 1Q compacted }; mov(8) g16<1>F g4.7<0,1,0>F { align1 1Q }; mov(8) g17<1>F g5.3<0,1,0>F { align1 1Q compacted }; mov(8) g14<1>F g5.7<0,1,0>F { align1 1Q }; mov(8) g20<1>F g6.3<0,1,0>F { align1 1Q compacted }; mov(8) g19<1>F g6.7<0,1,0>F { align1 1Q }; mov(8) g23<1>F g8.3<0,1,0>F { align1 1Q compacted }; mov(8) g4<1>F g2.4<8,4,1>UW { align1 1Q }; mov(8) g3<1>F g2<8,4,1>UW { align1 1Q }; mov(8) g6<1>D g4<8,8,1>F { align1 1Q compacted }; mov(8) g5<1>D g3<8,8,1>F { align1 1Q compacted }; add(8) g11<1>D g6<8,8,1>D -g9<8,8,1>D { align1 1Q compacted }; add(8) g10<1>D g5<8,8,1>D -g10<8,8,1>D { align1 1Q compacted }; mov(8) g13<1>F g11<8,8,1>D { align1 1Q compacted }; mov(8) g12<1>F g10<8,8,1>D { align1 1Q compacted }; mad(8) g15<1>F g16<4,4,1>F g15<4,4,1>F g12<4,4,1>F { align16 1Q compacted }; mad(8) g16<1>F g14<4,4,1>F g17<4,4,1>F g13<4,4,1>F { align16 1Q compacted }; mov(8) g17<1>D g15<8,8,1>F { align1 1Q compacted }; mov(8) g18<1>D g16<8,8,1>F { align1 1Q compacted }; add(8) g21<1>D g17<8,8,1>D g20<8,8,1>D { align1 1Q compacted }; add(8) g22<1>D g18<8,8,1>D g19<8,8,1>D { align1 1Q compacted }; send(8) g124<1>UW g21<8,8,1>F sampler ld_lz SIMD8 Surface = 1 Sampler = 0 mlen 3 rlen 4 { align1 1Q }; sendc(8) null<1>UW g124<8,8,1>F render RT write SIMD8 LastRT Surface = 0 mlen 4 rlen 0 { align1 1Q EOT }; nop ; END B0 Native code for unnamed fragment shader BLORP-blit SIMD16 shader: 26 instructions. 0 loops. 376 cycles. 0:0 spills:fills. Promoted 0 constants. Compacted 416 to 288 bytes (31%) START B0 (376 cycles) add(32) g11<1>UW g1.4<1,4,0>UW 0x11001010V { align1 WE_all }; mov(16) g25<1>F g9.3<0,1,0>F { align1 1H compacted }; mov(16) g21<1>F g9.7<0,1,0>F { align1 1H }; mov(16) g35<1>F g6.3<0,1,0>F { align1 1H compacted }; mov(16) g37<1>F g6.7<0,1,0>F { align1 1H }; mov(16) g39<1>F g7.3<0,1,0>F { align1 1H compacted }; mov(16) g31<1>F g7.7<0,1,0>F { align1 1H }; mov(16) g43<1>F g8.3<0,1,0>F { align1 1H compacted }; mov(16) g41<1>F g8.7<0,1,0>F { align1 1H }; mov(16) g13<1>F g11<8,4,1>UW { align1 1H }; mov(16) g15<1>F g11.4<8,4,1>UW { align1 1H }; mov(16) g6<1>F g10.3<0,1,0>F { align1 1H compacted }; mov(16) g17<1>D g13<8,8,1>F { align1 1H compacted }; mov(16) g19<1>D g15<8,8,1>F { align1 1H compacted }; add(16) g23<1>D g17<8,8,1>D -g25<8,8,1>D { align1 1H compacted }; add(16) g25<1>D g19<8,8,1>D -g21<8,8,1>D { align1 1H compacted }; mov(16) g27<1>F g23<8,8,1>D { align1 1H compacted }; mov(16) g29<1>F g25<8,8,1>D { align1 1H compacted }; mad(16) g33<1>F g37<4,4,1>F g35<4,4,1>F g27<4,4,1>F { align16 1H compacted }; mad(16) g35<1>F g31<4,4,1>F g39<4,4,1>F g29<4,4,1>F { align16 1H compacted }; mov(16) g37<1>D g33<8,8,1>F { align1 1H compacted }; mov(16) g39<1>D g35<8,8,1>F { align1 1H compacted }; add(16) g2<1>D g37<8,8,1>D g43<8,8,1>D { align1 1H compacted }; add(16) g4<1>D g39<8,8,1>D g41<8,8,1>D { align1 1H compacted }; send(16) g120<1>UW g2<8,8,1>F sampler ld_lz SIMD16 Surface = 1 Sampler = 0 mlen 6 rlen 8 { align1 1H }; sendc(16) null<1>UW g120<8,8,1>F render RT write SIMD16 LastRT Surface = 0 mlen 8 rlen 0 { align1 1H EOT }; nop ; END B0 NIR (SSA form) for fragment shader: shader: MESA_SHADER_FRAGMENT inputs: 0 outputs: 0 uniforms: 0 shared: 0 decl_var uniform INTERP_MODE_NONE sampler2DMS samplerPosition (0, 0, 1) decl_var uniform INTERP_MODE_NONE sampler2DMS samplerAlbedo (0, 0, 3) decl_var uniform INTERP_MODE_NONE sampler2DMS samplerNormal (0, 0, 2) decl_var shader_in INTERP_MODE_SMOOTH vec2 inUV (VARYING_SLOT_VAR0, 30, 0) decl_var shader_out INTERP_MODE_NONE vec4 outFragcolor (FRAG_RESULT_DATA0, 8, 0) decl_function main returning void impl main { block block_0: /* preds: */ vec1 32 ssa_0 = load_const (0x3f800000 /* 1.000000 */) vec1 32 ssa_1 = load_const (0x00000008 /* 0.000000 */) vec1 32 ssa_2 = load_const (0x00000001 /* 0.000000 */) vec1 32 ssa_3 = load_const (0x00000000 /* 0.000000 */) vec2 32 ssa_4 = txs 0 (texture) 0 (sampler) vec2 32 ssa_5 = intrinsic load_barycentric_pixel () () (1) /* interp_mode=1 */ vec2 32 ssa_6 = intrinsic load_interpolated_input (ssa_5, ssa_3) () (30, 0) /* base=30 */ /* component=0 */ vec1 32 ssa_7 = i2f32 ssa_4.x vec1 32 ssa_8 = i2f32 ssa_4.y vec1 32 ssa_9 = fmul ssa_6.x, ssa_7 vec1 32 ssa_10 = fmul ssa_6.y, ssa_8 vec1 32 ssa_11 = f2i32 ssa_9 vec1 32 ssa_12 = f2i32 ssa_10 vec2 32 ssa_13 = vec2 ssa_11, ssa_12 vec4 32 ssa_14 = txf_ms ssa_13 (coord), ssa_3 (ms_index), 2 (texture) 0 (sampler) vec4 32 ssa_15 = txf_ms ssa_13 (coord), ssa_2 (ms_index), 2 (texture) 0 (sampler) vec1 32 ssa_16 = fadd ssa_14.x, ssa_15.x vec1 32 ssa_17 = fadd ssa_14.y, ssa_15.y vec1 32 ssa_18 = fadd ssa_14.z, ssa_15.z vec1 32 ssa_19 = load_const (0x00000002 /* 0.000000 */) vec4 32 ssa_20 = txf_ms ssa_13 (coord), ssa_19 (ms_index), 2 (texture) 0 (sampler) vec1 32 ssa_21 = fadd ssa_16, ssa_20.x vec1 32 ssa_22 = fadd ssa_17, ssa_20.y vec1 32 ssa_23 = fadd ssa_18, ssa_20.z vec1 32 ssa_24 = load_const (0x00000003 /* 0.000000 */) vec4 32 ssa_25 = txf_ms ssa_13 (coord), ssa_24 (ms_index), 2 (texture) 0 (sampler) vec1 32 ssa_26 = fadd ssa_21, ssa_25.x vec1 32 ssa_27 = fadd ssa_22, ssa_25.y vec1 32 ssa_28 = fadd ssa_23, ssa_25.z vec1 32 ssa_29 = load_const (0x00000004 /* 0.000000 */) vec4 32 ssa_30 = txf_ms ssa_13 (coord), ssa_29 (ms_index), 2 (texture) 0 (sampler) vec1 32 ssa_31 = fadd ssa_26, ssa_30.x vec1 32 ssa_32 = fadd ssa_27, ssa_30.y vec1 32 ssa_33 = fadd ssa_28, ssa_30.z vec1 32 ssa_34 = load_const (0x00000005 /* 0.000000 */) vec4 32 ssa_35 = txf_ms ssa_13 (coord), ssa_34 (ms_index), 2 (texture) 0 (sampler) vec1 32 ssa_36 = fadd ssa_31, ssa_35.x vec1 32 ssa_37 = fadd ssa_32, ssa_35.y vec1 32 ssa_38 = fadd ssa_33, ssa_35.z vec1 32 ssa_39 = load_const (0x00000006 /* 0.000000 */) vec4 32 ssa_40 = txf_ms ssa_13 (coord), ssa_39 (ms_index), 2 (texture) 0 (sampler) vec1 32 ssa_41 = fadd ssa_36, ssa_40.x vec1 32 ssa_42 = fadd ssa_37, ssa_40.y vec1 32 ssa_43 = fadd ssa_38, ssa_40.z vec1 32 ssa_44 = load_const (0x00000007 /* 0.000000 */) vec4 32 ssa_45 = txf_ms ssa_13 (coord), ssa_44 (ms_index), 2 (texture) 0 (sampler) vec1 32 ssa_46 = fadd ssa_41, ssa_45.x vec1 32 ssa_47 = fadd ssa_42, ssa_45.y vec1 32 ssa_48 = fadd ssa_43, ssa_45.z vec1 32 ssa_49 = load_const (0x3e000000 /* 0.125000 */) /* succs: block_1 */ loop { block block_1: /* preds: block_0 block_4 */ vec1 32 ssa_50 = phi block_0: ssa_3, block_4: ssa_423 vec1 32 ssa_51 = phi block_0: ssa_3, block_4: ssa_424 vec1 32 ssa_52 = phi block_0: ssa_3, block_4: ssa_425 vec1 32 ssa_53 = phi block_0: ssa_3, block_4: ssa_426 vec1 32 ssa_54 = ilt ssa_53, ssa_1 /* succs: block_2 block_3 */ if ssa_54 { block block_2: /* preds: block_1 */ /* succs: block_4 */ } else { block block_3: /* preds: block_1 */ break /* succs: block_5 */ } block block_4: /* preds: block_2 */ vec4 32 ssa_55 = txf_ms ssa_13 (coord), ssa_53 (ms_index), 0 (texture) 0 (sampler) vec4 32 ssa_56 = txf_ms ssa_13 (coord), ssa_53 (ms_index), 1 (texture) 0 (sampler) vec4 32 ssa_57 = txf_ms ssa_13 (coord), ssa_53 (ms_index), 2 (texture) 0 (sampler) vec1 32 ssa_58 = load_const (0x41000000 /* 8.000000 */) vec1 32 ssa_59 = load_const (0x40000000 /* 2.000000 */) vec4 32 ssa_60 = intrinsic load_ubo (ssa_24, ssa_3) () () vec1 32 ssa_61 = fadd ssa_60.x, -ssa_55.x vec1 32 ssa_62 = fadd ssa_60.y, -ssa_55.y vec1 32 ssa_63 = fadd ssa_60.z, -ssa_55.z vec1 32 ssa_64 = fmul ssa_62, ssa_62 vec1 32 ssa_65 = ffma ssa_61, ssa_61, ssa_64 vec1 32 ssa_66 = ffma ssa_63, ssa_63, ssa_65 vec1 32 ssa_67 = fsqrt ssa_66 vec1 32 ssa_68 = load_const (0x000000c0 /* 0.000000 */) vec4 32 ssa_69 = intrinsic load_ubo (ssa_24, ssa_68) () () vec1 32 ssa_70 = fadd ssa_69.x, -ssa_55.x vec1 32 ssa_71 = fadd ssa_69.y, -ssa_55.y vec1 32 ssa_72 = fadd ssa_69.z, -ssa_55.z vec1 32 ssa_73 = fmul ssa_71, ssa_71 vec1 32 ssa_74 = ffma ssa_70, ssa_70, ssa_73 vec1 32 ssa_75 = ffma ssa_72, ssa_72, ssa_74 vec1 32 ssa_76 = frsq ssa_75 vec1 32 ssa_77 = fmul ssa_70, ssa_76 vec1 32 ssa_78 = fmul ssa_71, ssa_76 vec1 32 ssa_79 = fmul ssa_72, ssa_76 vec1 32 ssa_80 = frsq ssa_66 vec1 32 ssa_81 = fmul ssa_61, ssa_80 vec1 32 ssa_82 = fmul ssa_62, ssa_80 vec1 32 ssa_83 = fmul ssa_63, ssa_80 vec1 32 ssa_84 = load_const (0x0000001c /* 0.000000 */) vec1 32 ssa_85 = intrinsic load_ubo (ssa_24, ssa_84) () () vec1 32 ssa_86 = ffma ssa_67, ssa_67, ssa_0 vec1 32 ssa_87 = frcp ssa_86 vec1 32 ssa_88 = fmul ssa_85, ssa_87 vec1 32 ssa_89 = fmul ssa_56.y, ssa_56.y vec1 32 ssa_90 = ffma ssa_56.x, ssa_56.x, ssa_89 vec1 32 ssa_91 = ffma ssa_56.z, ssa_56.z, ssa_90 vec1 32 ssa_92 = frsq ssa_91 vec1 32 ssa_93 = fmul ssa_56.x, ssa_92 vec1 32 ssa_94 = fmul ssa_56.y, ssa_92 vec1 32 ssa_95 = fmul ssa_56.z, ssa_92 vec1 32 ssa_96 = fmul ssa_94, ssa_82 vec1 32 ssa_97 = ffma ssa_93, ssa_81, ssa_96 vec1 32 ssa_98 = ffma ssa_95, ssa_83, ssa_97 vec1 32 ssa_99 = fmax ssa_3, ssa_98 vec1 32 ssa_100 = load_const (0x00000010 /* 0.000000 */) vec3 32 ssa_101 = intrinsic load_ubo (ssa_24, ssa_100) () () vec1 32 ssa_102 = fmul ssa_101.x, ssa_57.x vec1 32 ssa_103 = fmul ssa_101.y, ssa_57.y vec1 32 ssa_104 = fmul ssa_101.z, ssa_57.z vec1 32 ssa_105 = fmul ssa_102, ssa_99 vec1 32 ssa_106 = fmul ssa_103, ssa_99 vec1 32 ssa_107 = fmul ssa_104, ssa_99 vec1 32 ssa_108 = ffma -ssa_93, ssa_81, -ssa_96 vec1 32 ssa_109 = ffma -ssa_95, ssa_83, ssa_108 vec1 32 ssa_110 = fmul ssa_109, ssa_93 vec1 32 ssa_111 = fmul ssa_109, ssa_94 vec1 32 ssa_112 = fmul ssa_109, ssa_95 vec1 32 ssa_113 = ffma -ssa_59, ssa_110, -ssa_81 vec1 32 ssa_114 = ffma -ssa_59, ssa_111, -ssa_82 vec1 32 ssa_115 = ffma -ssa_59, ssa_112, -ssa_83 vec1 32 ssa_116 = fmul ssa_114, ssa_78 vec1 32 ssa_117 = ffma ssa_113, ssa_77, ssa_116 vec1 32 ssa_118 = ffma ssa_115, ssa_79, ssa_117 vec1 32 ssa_119 = fmax ssa_3, ssa_118 vec1 32 ssa_120 = fmul ssa_101.x, ssa_57.w vec1 32 ssa_121 = fmul ssa_101.y, ssa_57.w vec1 32 ssa_122 = fmul ssa_101.z, ssa_57.w vec1 32 ssa_123 = fpow ssa_119, ssa_58 vec1 32 ssa_124 = fmul ssa_120, ssa_123 vec1 32 ssa_125 = fmul ssa_121, ssa_123 vec1 32 ssa_126 = fmul ssa_122, ssa_123 vec1 32 ssa_127 = fmul ssa_124, ssa_88 vec1 32 ssa_128 = fmul ssa_125, ssa_88 vec1 32 ssa_129 = fmul ssa_126, ssa_88 vec1 32 ssa_130 = ffma ssa_105, ssa_88, ssa_127 vec1 32 ssa_131 = ffma ssa_106, ssa_88, ssa_128 vec1 32 ssa_132 = ffma ssa_107, ssa_88, ssa_129 vec1 32 ssa_133 = load_const (0x00000020 /* 0.000000 */) vec4 32 ssa_134 = intrinsic load_ubo (ssa_24, ssa_133) () () vec1 32 ssa_135 = fadd ssa_134.x, -ssa_55.x vec1 32 ssa_136 = fadd ssa_134.y, -ssa_55.y vec1 32 ssa_137 = fadd ssa_134.z, -ssa_55.z vec1 32 ssa_138 = fmul ssa_136, ssa_136 vec1 32 ssa_139 = ffma ssa_135, ssa_135, ssa_138 vec1 32 ssa_140 = ffma ssa_137, ssa_137, ssa_139 vec1 32 ssa_141 = fsqrt ssa_140 vec1 32 ssa_142 = frsq ssa_140 vec1 32 ssa_143 = fmul ssa_135, ssa_142 vec1 32 ssa_144 = fmul ssa_136, ssa_142 vec1 32 ssa_145 = fmul ssa_137, ssa_142 vec1 32 ssa_146 = load_const (0x0000003c /* 0.000000 */) vec1 32 ssa_147 = intrinsic load_ubo (ssa_24, ssa_146) () () vec1 32 ssa_148 = ffma ssa_141, ssa_141, ssa_0 vec1 32 ssa_149 = frcp ssa_148 vec1 32 ssa_150 = fmul ssa_147, ssa_149 vec1 32 ssa_151 = fmul ssa_94, ssa_144 vec1 32 ssa_152 = ffma ssa_93, ssa_143, ssa_151 vec1 32 ssa_153 = ffma ssa_95, ssa_145, ssa_152 vec1 32 ssa_154 = fmax ssa_3, ssa_153 vec1 32 ssa_155 = load_const (0x00000030 /* 0.000000 */) vec3 32 ssa_156 = intrinsic load_ubo (ssa_24, ssa_155) () () vec1 32 ssa_157 = fmul ssa_156.x, ssa_57.x vec1 32 ssa_158 = fmul ssa_156.y, ssa_57.y vec1 32 ssa_159 = fmul ssa_156.z, ssa_57.z vec1 32 ssa_160 = fmul ssa_157, ssa_154 vec1 32 ssa_161 = fmul ssa_158, ssa_154 vec1 32 ssa_162 = fmul ssa_159, ssa_154 vec1 32 ssa_163 = ffma -ssa_93, ssa_143, -ssa_151 vec1 32 ssa_164 = ffma -ssa_95, ssa_145, ssa_163 vec1 32 ssa_165 = fmul ssa_164, ssa_93 vec1 32 ssa_166 = fmul ssa_164, ssa_94 vec1 32 ssa_167 = fmul ssa_164, ssa_95 vec1 32 ssa_168 = ffma -ssa_59, ssa_165, -ssa_143 vec1 32 ssa_169 = ffma -ssa_59, ssa_166, -ssa_144 vec1 32 ssa_170 = ffma -ssa_59, ssa_167, -ssa_145 vec1 32 ssa_171 = fmul ssa_169, ssa_78 vec1 32 ssa_172 = ffma ssa_168, ssa_77, ssa_171 vec1 32 ssa_173 = ffma ssa_170, ssa_79, ssa_172 vec1 32 ssa_174 = fmax ssa_3, ssa_173 vec1 32 ssa_175 = fmul ssa_156.x, ssa_57.w vec1 32 ssa_176 = fmul ssa_156.y, ssa_57.w vec1 32 ssa_177 = fmul ssa_156.z, ssa_57.w vec1 32 ssa_178 = fpow ssa_174, ssa_58 vec1 32 ssa_179 = fmul ssa_175, ssa_178 vec1 32 ssa_180 = fmul ssa_176, ssa_178 vec1 32 ssa_181 = fmul ssa_177, ssa_178 vec1 32 ssa_182 = fmul ssa_179, ssa_150 vec1 32 ssa_183 = fmul ssa_180, ssa_150 vec1 32 ssa_184 = fmul ssa_181, ssa_150 vec1 32 ssa_185 = ffma ssa_160, ssa_150, ssa_182 vec1 32 ssa_186 = ffma ssa_161, ssa_150, ssa_183 vec1 32 ssa_187 = ffma ssa_162, ssa_150, ssa_184 vec1 32 ssa_188 = fadd ssa_130, ssa_185 vec1 32 ssa_189 = fadd ssa_131, ssa_186 vec1 32 ssa_190 = fadd ssa_132, ssa_187 vec1 32 ssa_191 = load_const (0x00000040 /* 0.000000 */) vec4 32 ssa_192 = intrinsic load_ubo (ssa_24, ssa_191) () () vec1 32 ssa_193 = fadd ssa_192.x, -ssa_55.x vec1 32 ssa_194 = fadd ssa_192.y, -ssa_55.y vec1 32 ssa_195 = fadd ssa_192.z, -ssa_55.z vec1 32 ssa_196 = fmul ssa_194, ssa_194 vec1 32 ssa_197 = ffma ssa_193, ssa_193, ssa_196 vec1 32 ssa_198 = ffma ssa_195, ssa_195, ssa_197 vec1 32 ssa_199 = fsqrt ssa_198 vec1 32 ssa_200 = frsq ssa_198 vec1 32 ssa_201 = fmul ssa_193, ssa_200 vec1 32 ssa_202 = fmul ssa_194, ssa_200 vec1 32 ssa_203 = fmul ssa_195, ssa_200 vec1 32 ssa_204 = load_const (0x0000005c /* 0.000000 */) vec1 32 ssa_205 = intrinsic load_ubo (ssa_24, ssa_204) () () vec1 32 ssa_206 = ffma ssa_199, ssa_199, ssa_0 vec1 32 ssa_207 = frcp ssa_206 vec1 32 ssa_208 = fmul ssa_205, ssa_207 vec1 32 ssa_209 = fmul ssa_94, ssa_202 vec1 32 ssa_210 = ffma ssa_93, ssa_201, ssa_209 vec1 32 ssa_211 = ffma ssa_95, ssa_203, ssa_210 vec1 32 ssa_212 = fmax ssa_3, ssa_211 vec1 32 ssa_213 = load_const (0x00000050 /* 0.000000 */) vec3 32 ssa_214 = intrinsic load_ubo (ssa_24, ssa_213) () () vec1 32 ssa_215 = fmul ssa_214.x, ssa_57.x vec1 32 ssa_216 = fmul ssa_214.y, ssa_57.y vec1 32 ssa_217 = fmul ssa_214.z, ssa_57.z vec1 32 ssa_218 = fmul ssa_215, ssa_212 vec1 32 ssa_219 = fmul ssa_216, ssa_212 vec1 32 ssa_220 = fmul ssa_217, ssa_212 vec1 32 ssa_221 = ffma -ssa_93, ssa_201, -ssa_209 vec1 32 ssa_222 = ffma -ssa_95, ssa_203, ssa_221 vec1 32 ssa_223 = fmul ssa_222, ssa_93 vec1 32 ssa_224 = fmul ssa_222, ssa_94 vec1 32 ssa_225 = fmul ssa_222, ssa_95 vec1 32 ssa_226 = ffma -ssa_59, ssa_223, -ssa_201 vec1 32 ssa_227 = ffma -ssa_59, ssa_224, -ssa_202 vec1 32 ssa_228 = ffma -ssa_59, ssa_225, -ssa_203 vec1 32 ssa_229 = fmul ssa_227, ssa_78 vec1 32 ssa_230 = ffma ssa_226, ssa_77, ssa_229 vec1 32 ssa_231 = ffma ssa_228, ssa_79, ssa_230 vec1 32 ssa_232 = fmax ssa_3, ssa_231 vec1 32 ssa_233 = fmul ssa_214.x, ssa_57.w vec1 32 ssa_234 = fmul ssa_214.y, ssa_57.w vec1 32 ssa_235 = fmul ssa_214.z, ssa_57.w vec1 32 ssa_236 = fpow ssa_232, ssa_58 vec1 32 ssa_237 = fmul ssa_233, ssa_236 vec1 32 ssa_238 = fmul ssa_234, ssa_236 vec1 32 ssa_239 = fmul ssa_235, ssa_236 vec1 32 ssa_240 = fmul ssa_237, ssa_208 vec1 32 ssa_241 = fmul ssa_238, ssa_208 vec1 32 ssa_242 = fmul ssa_239, ssa_208 vec1 32 ssa_243 = ffma ssa_218, ssa_208, ssa_240 vec1 32 ssa_244 = ffma ssa_219, ssa_208, ssa_241 vec1 32 ssa_245 = ffma ssa_220, ssa_208, ssa_242 vec1 32 ssa_246 = fadd ssa_188, ssa_243 vec1 32 ssa_247 = fadd ssa_189, ssa_244 vec1 32 ssa_248 = fadd ssa_190, ssa_245 vec1 32 ssa_249 = load_const (0x00000060 /* 0.000000 */) vec4 32 ssa_250 = intrinsic load_ubo (ssa_24, ssa_249) () () vec1 32 ssa_251 = fadd ssa_250.x, -ssa_55.x vec1 32 ssa_252 = fadd ssa_250.y, -ssa_55.y vec1 32 ssa_253 = fadd ssa_250.z, -ssa_55.z vec1 32 ssa_254 = fmul ssa_252, ssa_252 vec1 32 ssa_255 = ffma ssa_251, ssa_251, ssa_254 vec1 32 ssa_256 = ffma ssa_253, ssa_253, ssa_255 vec1 32 ssa_257 = fsqrt ssa_256 vec1 32 ssa_258 = frsq ssa_256 vec1 32 ssa_259 = fmul ssa_251, ssa_258 vec1 32 ssa_260 = fmul ssa_252, ssa_258 vec1 32 ssa_261 = fmul ssa_253, ssa_258 vec1 32 ssa_262 = load_const (0x0000007c /* 0.000000 */) vec1 32 ssa_263 = intrinsic load_ubo (ssa_24, ssa_262) () () vec1 32 ssa_264 = ffma ssa_257, ssa_257, ssa_0 vec1 32 ssa_265 = frcp ssa_264 vec1 32 ssa_266 = fmul ssa_263, ssa_265 vec1 32 ssa_267 = fmul ssa_94, ssa_260 vec1 32 ssa_268 = ffma ssa_93, ssa_259, ssa_267 vec1 32 ssa_269 = ffma ssa_95, ssa_261, ssa_268 vec1 32 ssa_270 = fmax ssa_3, ssa_269 vec1 32 ssa_271 = load_const (0x00000070 /* 0.000000 */) vec3 32 ssa_272 = intrinsic load_ubo (ssa_24, ssa_271) () () vec1 32 ssa_273 = fmul ssa_272.x, ssa_57.x vec1 32 ssa_274 = fmul ssa_272.y, ssa_57.y vec1 32 ssa_275 = fmul ssa_272.z, ssa_57.z vec1 32 ssa_276 = fmul ssa_273, ssa_270 vec1 32 ssa_277 = fmul ssa_274, ssa_270 vec1 32 ssa_278 = fmul ssa_275, ssa_270 vec1 32 ssa_279 = ffma -ssa_93, ssa_259, -ssa_267 vec1 32 ssa_280 = ffma -ssa_95, ssa_261, ssa_279 vec1 32 ssa_281 = fmul ssa_280, ssa_93 vec1 32 ssa_282 = fmul ssa_280, ssa_94 vec1 32 ssa_283 = fmul ssa_280, ssa_95 vec1 32 ssa_284 = ffma -ssa_59, ssa_281, -ssa_259 vec1 32 ssa_285 = ffma -ssa_59, ssa_282, -ssa_260 vec1 32 ssa_286 = ffma -ssa_59, ssa_283, -ssa_261 vec1 32 ssa_287 = fmul ssa_285, ssa_78 vec1 32 ssa_288 = ffma ssa_284, ssa_77, ssa_287 vec1 32 ssa_289 = ffma ssa_286, ssa_79, ssa_288 vec1 32 ssa_290 = fmax ssa_3, ssa_289 vec1 32 ssa_291 = fmul ssa_272.x, ssa_57.w vec1 32 ssa_292 = fmul ssa_272.y, ssa_57.w vec1 32 ssa_293 = fmul ssa_272.z, ssa_57.w vec1 32 ssa_294 = fpow ssa_290, ssa_58 vec1 32 ssa_295 = fmul ssa_291, ssa_294 vec1 32 ssa_296 = fmul ssa_292, ssa_294 vec1 32 ssa_297 = fmul ssa_293, ssa_294 vec1 32 ssa_298 = fmul ssa_295, ssa_266 vec1 32 ssa_299 = fmul ssa_296, ssa_266 vec1 32 ssa_300 = fmul ssa_297, ssa_266 vec1 32 ssa_301 = ffma ssa_276, ssa_266, ssa_298 vec1 32 ssa_302 = ffma ssa_277, ssa_266, ssa_299 vec1 32 ssa_303 = ffma ssa_278, ssa_266, ssa_300 vec1 32 ssa_304 = fadd ssa_246, ssa_301 vec1 32 ssa_305 = fadd ssa_247, ssa_302 vec1 32 ssa_306 = fadd ssa_248, ssa_303 vec1 32 ssa_307 = load_const (0x00000080 /* 0.000000 */) vec4 32 ssa_308 = intrinsic load_ubo (ssa_24, ssa_307) () () vec1 32 ssa_309 = fadd ssa_308.x, -ssa_55.x vec1 32 ssa_310 = fadd ssa_308.y, -ssa_55.y vec1 32 ssa_311 = fadd ssa_308.z, -ssa_55.z vec1 32 ssa_312 = fmul ssa_310, ssa_310 vec1 32 ssa_313 = ffma ssa_309, ssa_309, ssa_312 vec1 32 ssa_314 = ffma ssa_311, ssa_311, ssa_313 vec1 32 ssa_315 = fsqrt ssa_314 vec1 32 ssa_316 = frsq ssa_314 vec1 32 ssa_317 = fmul ssa_309, ssa_316 vec1 32 ssa_318 = fmul ssa_310, ssa_316 vec1 32 ssa_319 = fmul ssa_311, ssa_316 vec1 32 ssa_320 = load_const (0x0000009c /* 0.000000 */) vec1 32 ssa_321 = intrinsic load_ubo (ssa_24, ssa_320) () () vec1 32 ssa_322 = ffma ssa_315, ssa_315, ssa_0 vec1 32 ssa_323 = frcp ssa_322 vec1 32 ssa_324 = fmul ssa_321, ssa_323 vec1 32 ssa_325 = fmul ssa_94, ssa_318 vec1 32 ssa_326 = ffma ssa_93, ssa_317, ssa_325 vec1 32 ssa_327 = ffma ssa_95, ssa_319, ssa_326 vec1 32 ssa_328 = fmax ssa_3, ssa_327 vec1 32 ssa_329 = load_const (0x00000090 /* 0.000000 */) vec3 32 ssa_330 = intrinsic load_ubo (ssa_24, ssa_329) () () vec1 32 ssa_331 = fmul ssa_330.x, ssa_57.x vec1 32 ssa_332 = fmul ssa_330.y, ssa_57.y vec1 32 ssa_333 = fmul ssa_330.z, ssa_57.z vec1 32 ssa_334 = fmul ssa_331, ssa_328 vec1 32 ssa_335 = fmul ssa_332, ssa_328 vec1 32 ssa_336 = fmul ssa_333, ssa_328 vec1 32 ssa_337 = ffma -ssa_93, ssa_317, -ssa_325 vec1 32 ssa_338 = ffma -ssa_95, ssa_319, ssa_337 vec1 32 ssa_339 = fmul ssa_338, ssa_93 vec1 32 ssa_340 = fmul ssa_338, ssa_94 vec1 32 ssa_341 = fmul ssa_338, ssa_95 vec1 32 ssa_342 = ffma -ssa_59, ssa_339, -ssa_317 vec1 32 ssa_343 = ffma -ssa_59, ssa_340, -ssa_318 vec1 32 ssa_344 = ffma -ssa_59, ssa_341, -ssa_319 vec1 32 ssa_345 = fmul ssa_343, ssa_78 vec1 32 ssa_346 = ffma ssa_342, ssa_77, ssa_345 vec1 32 ssa_347 = ffma ssa_344, ssa_79, ssa_346 vec1 32 ssa_348 = fmax ssa_3, ssa_347 vec1 32 ssa_349 = fmul ssa_330.x, ssa_57.w vec1 32 ssa_350 = fmul ssa_330.y, ssa_57.w vec1 32 ssa_351 = fmul ssa_330.z, ssa_57.w vec1 32 ssa_352 = fpow ssa_348, ssa_58 vec1 32 ssa_353 = fmul ssa_349, ssa_352 vec1 32 ssa_354 = fmul ssa_350, ssa_352 vec1 32 ssa_355 = fmul ssa_351, ssa_352 vec1 32 ssa_356 = fmul ssa_353, ssa_324 vec1 32 ssa_357 = fmul ssa_354, ssa_324 vec1 32 ssa_358 = fmul ssa_355, ssa_324 vec1 32 ssa_359 = ffma ssa_334, ssa_324, ssa_356 vec1 32 ssa_360 = ffma ssa_335, ssa_324, ssa_357 vec1 32 ssa_361 = ffma ssa_336, ssa_324, ssa_358 vec1 32 ssa_362 = fadd ssa_304, ssa_359 vec1 32 ssa_363 = fadd ssa_305, ssa_360 vec1 32 ssa_364 = fadd ssa_306, ssa_361 vec1 32 ssa_365 = load_const (0x000000a0 /* 0.000000 */) vec4 32 ssa_366 = intrinsic load_ubo (ssa_24, ssa_365) () () vec1 32 ssa_367 = fadd ssa_366.x, -ssa_55.x vec1 32 ssa_368 = fadd ssa_366.y, -ssa_55.y vec1 32 ssa_369 = fadd ssa_366.z, -ssa_55.z vec1 32 ssa_370 = fmul ssa_368, ssa_368 vec1 32 ssa_371 = ffma ssa_367, ssa_367, ssa_370 vec1 32 ssa_372 = ffma ssa_369, ssa_369, ssa_371 vec1 32 ssa_373 = fsqrt ssa_372 vec1 32 ssa_374 = frsq ssa_372 vec1 32 ssa_375 = fmul ssa_367, ssa_374 vec1 32 ssa_376 = fmul ssa_368, ssa_374 vec1 32 ssa_377 = fmul ssa_369, ssa_374 vec1 32 ssa_378 = load_const (0x000000bc /* 0.000000 */) vec1 32 ssa_379 = intrinsic load_ubo (ssa_24, ssa_378) () () vec1 32 ssa_380 = ffma ssa_373, ssa_373, ssa_0 vec1 32 ssa_381 = frcp ssa_380 vec1 32 ssa_382 = fmul ssa_379, ssa_381 vec1 32 ssa_383 = fmul ssa_94, ssa_376 vec1 32 ssa_384 = ffma ssa_93, ssa_375, ssa_383 vec1 32 ssa_385 = ffma ssa_95, ssa_377, ssa_384 vec1 32 ssa_386 = fmax ssa_3, ssa_385 vec1 32 ssa_387 = load_const (0x000000b0 /* 0.000000 */) vec3 32 ssa_388 = intrinsic load_ubo (ssa_24, ssa_387) () () vec1 32 ssa_389 = fmul ssa_388.x, ssa_57.x vec1 32 ssa_390 = fmul ssa_388.y, ssa_57.y vec1 32 ssa_391 = fmul ssa_388.z, ssa_57.z vec1 32 ssa_392 = fmul ssa_389, ssa_386 vec1 32 ssa_393 = fmul ssa_390, ssa_386 vec1 32 ssa_394 = fmul ssa_391, ssa_386 vec1 32 ssa_395 = ffma -ssa_93, ssa_375, -ssa_383 vec1 32 ssa_396 = ffma -ssa_95, ssa_377, ssa_395 vec1 32 ssa_397 = fmul ssa_396, ssa_93 vec1 32 ssa_398 = fmul ssa_396, ssa_94 vec1 32 ssa_399 = fmul ssa_396, ssa_95 vec1 32 ssa_400 = ffma -ssa_59, ssa_397, -ssa_375 vec1 32 ssa_401 = ffma -ssa_59, ssa_398, -ssa_376 vec1 32 ssa_402 = ffma -ssa_59, ssa_399, -ssa_377 vec1 32 ssa_403 = fmul ssa_401, ssa_78 vec1 32 ssa_404 = ffma ssa_400, ssa_77, ssa_403 vec1 32 ssa_405 = ffma ssa_402, ssa_79, ssa_404 vec1 32 ssa_406 = fmax ssa_3, ssa_405 vec1 32 ssa_407 = fmul ssa_388.x, ssa_57.w vec1 32 ssa_408 = fmul ssa_388.y, ssa_57.w vec1 32 ssa_409 = fmul ssa_388.z, ssa_57.w vec1 32 ssa_410 = fpow ssa_406, ssa_58 vec1 32 ssa_411 = fmul ssa_407, ssa_410 vec1 32 ssa_412 = fmul ssa_408, ssa_410 vec1 32 ssa_413 = fmul ssa_409, ssa_410 vec1 32 ssa_414 = fmul ssa_411, ssa_382 vec1 32 ssa_415 = fmul ssa_412, ssa_382 vec1 32 ssa_416 = fmul ssa_413, ssa_382 vec1 32 ssa_417 = ffma ssa_392, ssa_382, ssa_414 vec1 32 ssa_418 = ffma ssa_393, ssa_382, ssa_415 vec1 32 ssa_419 = ffma ssa_394, ssa_382, ssa_416 vec1 32 ssa_420 = fadd ssa_362, ssa_417 vec1 32 ssa_421 = fadd ssa_363, ssa_418 vec1 32 ssa_422 = fadd ssa_364, ssa_419 vec1 32 ssa_423 = fadd ssa_50, ssa_420 vec1 32 ssa_424 = fadd ssa_51, ssa_421 vec1 32 ssa_425 = fadd ssa_52, ssa_422 vec1 32 ssa_426 = iadd ssa_53, ssa_2 /* succs: block_1 */ } block block_5: /* preds: block_3 */ vec1 32 ssa_427 = load_const (0x3c99999a /* 0.018750 */) vec1 32 ssa_428 = fmul ssa_50, ssa_49 vec1 32 ssa_429 = fmul ssa_51, ssa_49 vec1 32 ssa_430 = fmul ssa_52, ssa_49 vec1 32 ssa_431 = ffma ssa_427, ssa_46, ssa_428 vec1 32 ssa_432 = ffma ssa_427, ssa_47, ssa_429 vec1 32 ssa_433 = ffma ssa_427, ssa_48, ssa_430 vec4 32 ssa_434 = vec4 ssa_431, ssa_432, ssa_433, ssa_0 intrinsic store_output (ssa_434, ssa_3) () (8, 15, 0) /* base=8 */ /* wrmask=xyzw */ /* component=0 */ /* outFragcolor */ /* succs: block_0 */ block block_0: } NIR (final form) for fragment shader: shader: MESA_SHADER_FRAGMENT inputs: 0 outputs: 0 uniforms: 0 shared: 0 decl_var uniform INTERP_MODE_NONE sampler2DMS samplerPosition (0, 0, 1) decl_var uniform INTERP_MODE_NONE sampler2DMS samplerAlbedo (0, 0, 3) decl_var uniform INTERP_MODE_NONE sampler2DMS samplerNormal (0, 0, 2) decl_var shader_in INTERP_MODE_SMOOTH vec2 inUV (VARYING_SLOT_VAR0, 30, 0) decl_var shader_out INTERP_MODE_NONE vec4 outFragcolor (FRAG_RESULT_DATA0, 8, 0) decl_function main returning void impl main { decl_reg vec1 32 r7 decl_reg vec1 32 r8 decl_reg vec1 32 r9 decl_reg vec1 32 r10 block block_0: /* preds: */ vec1 32 ssa_0 = load_const (0x3f800000 /* 1.000000 */) vec1 32 ssa_1 = load_const (0x00000008 /* 0.000000 */) vec1 32 ssa_2 = load_const (0x00000001 /* 0.000000 */) vec1 32 ssa_3 = load_const (0x00000000 /* 0.000000 */) vec2 32 ssa_4 = txs 0 (texture) 0 (sampler) vec2 32 ssa_5 = intrinsic load_barycentric_pixel () () (1) /* interp_mode=1 */ vec2 32 ssa_6 = intrinsic load_interpolated_input (ssa_5, ssa_3) () (30, 0) /* base=30 */ /* component=0 */ vec1 32 ssa_7 = i2f32 ssa_4.x vec1 32 ssa_8 = i2f32 ssa_4.y vec1 32 ssa_9 = fmul ssa_6.x, ssa_7 vec1 32 ssa_10 = fmul ssa_6.y, ssa_8 vec1 32 ssa_11 = f2i32 ssa_9 vec1 32 ssa_12 = f2i32 ssa_10 vec2 32 ssa_13 = vec2 ssa_11, ssa_12 vec4 32 ssa_14 = txf_ms ssa_13 (coord), ssa_3 (ms_index), 2 (texture) 0 (sampler) vec4 32 ssa_15 = txf_ms ssa_13 (coord), ssa_2 (ms_index), 2 (texture) 0 (sampler) vec1 32 ssa_16 = fadd ssa_14.x, ssa_15.x vec1 32 ssa_17 = fadd ssa_14.y, ssa_15.y vec1 32 ssa_18 = fadd ssa_14.z, ssa_15.z vec1 32 ssa_19 = load_const (0x00000002 /* 0.000000 */) vec4 32 ssa_20 = txf_ms ssa_13 (coord), ssa_19 (ms_index), 2 (texture) 0 (sampler) vec1 32 ssa_21 = fadd ssa_16, ssa_20.x vec1 32 ssa_22 = fadd ssa_17, ssa_20.y vec1 32 ssa_23 = fadd ssa_18, ssa_20.z vec1 32 ssa_24 = load_const (0x00000003 /* 0.000000 */) vec4 32 ssa_25 = txf_ms ssa_13 (coord), ssa_24 (ms_index), 2 (texture) 0 (sampler) vec1 32 ssa_26 = fadd ssa_21, ssa_25.x vec1 32 ssa_27 = fadd ssa_22, ssa_25.y vec1 32 ssa_28 = fadd ssa_23, ssa_25.z vec1 32 ssa_29 = load_const (0x00000004 /* 0.000000 */) vec4 32 ssa_30 = txf_ms ssa_13 (coord), ssa_29 (ms_index), 2 (texture) 0 (sampler) vec1 32 ssa_31 = fadd ssa_26, ssa_30.x vec1 32 ssa_32 = fadd ssa_27, ssa_30.y vec1 32 ssa_33 = fadd ssa_28, ssa_30.z vec1 32 ssa_34 = load_const (0x00000005 /* 0.000000 */) vec4 32 ssa_35 = txf_ms ssa_13 (coord), ssa_34 (ms_index), 2 (texture) 0 (sampler) vec1 32 ssa_36 = fadd ssa_31, ssa_35.x vec1 32 ssa_37 = fadd ssa_32, ssa_35.y vec1 32 ssa_38 = fadd ssa_33, ssa_35.z vec1 32 ssa_39 = load_const (0x00000006 /* 0.000000 */) vec4 32 ssa_40 = txf_ms ssa_13 (coord), ssa_39 (ms_index), 2 (texture) 0 (sampler) vec1 32 ssa_41 = fadd ssa_36, ssa_40.x vec1 32 ssa_42 = fadd ssa_37, ssa_40.y vec1 32 ssa_43 = fadd ssa_38, ssa_40.z vec1 32 ssa_44 = load_const (0x00000007 /* 0.000000 */) vec4 32 ssa_45 = txf_ms ssa_13 (coord), ssa_44 (ms_index), 2 (texture) 0 (sampler) vec1 32 ssa_46 = fadd ssa_41, ssa_45.x vec1 32 ssa_47 = fadd ssa_42, ssa_45.y vec1 32 ssa_48 = fadd ssa_43, ssa_45.z vec1 32 ssa_49 = load_const (0x3e000000 /* 0.125000 */) r10 = imov ssa_3 r9 = imov r10 r8 = imov r9 r7 = imov r8 /* succs: block_1 */ loop { block block_1: /* preds: block_0 block_4 */ vec1 32 ssa_54 = ilt r10, ssa_1 /* succs: block_2 block_3 */ if ssa_54 { block block_2: /* preds: block_1 */ /* succs: block_4 */ } else { block block_3: /* preds: block_1 */ break /* succs: block_5 */ } block block_4: /* preds: block_2 */ vec4 32 ssa_55 = txf_ms ssa_13 (coord), r10 (ms_index), 0 (texture) 0 (sampler) vec4 32 ssa_56 = txf_ms ssa_13 (coord), r10 (ms_index), 1 (texture) 0 (sampler) vec4 32 ssa_57 = txf_ms ssa_13 (coord), r10 (ms_index), 2 (texture) 0 (sampler) vec1 32 ssa_58 = load_const (0x41000000 /* 8.000000 */) vec1 32 ssa_59 = load_const (0x40000000 /* 2.000000 */) vec4 32 ssa_60 = intrinsic load_ubo (ssa_24, ssa_3) () () vec1 32 ssa_61 = fadd ssa_60.x, -ssa_55.x vec1 32 ssa_62 = fadd ssa_60.y, -ssa_55.y vec1 32 ssa_63 = fadd ssa_60.z, -ssa_55.z vec1 32 ssa_64 = fmul ssa_62, ssa_62 vec1 32 ssa_65 = ffma ssa_61, ssa_61, ssa_64 vec1 32 ssa_66 = ffma ssa_63, ssa_63, ssa_65 vec1 32 ssa_67 = fsqrt ssa_66 vec1 32 ssa_68 = load_const (0x000000c0 /* 0.000000 */) vec4 32 ssa_69 = intrinsic load_ubo (ssa_24, ssa_68) () () vec1 32 ssa_70 = fadd ssa_69.x, -ssa_55.x vec1 32 ssa_71 = fadd ssa_69.y, -ssa_55.y vec1 32 ssa_72 = fadd ssa_69.z, -ssa_55.z vec1 32 ssa_73 = fmul ssa_71, ssa_71 vec1 32 ssa_74 = ffma ssa_70, ssa_70, ssa_73 vec1 32 ssa_75 = ffma ssa_72, ssa_72, ssa_74 vec1 32 ssa_76 = frsq ssa_75 vec1 32 ssa_77 = fmul ssa_70, ssa_76 vec1 32 ssa_78 = fmul ssa_71, ssa_76 vec1 32 ssa_79 = fmul ssa_72, ssa_76 vec1 32 ssa_80 = frsq ssa_66 vec1 32 ssa_81 = fmul ssa_61, ssa_80 vec1 32 ssa_82 = fmul ssa_62, ssa_80 vec1 32 ssa_83 = fmul ssa_63, ssa_80 vec1 32 ssa_84 = load_const (0x0000001c /* 0.000000 */) vec1 32 ssa_85 = intrinsic load_ubo (ssa_24, ssa_84) () () vec1 32 ssa_86 = ffma ssa_67, ssa_67, ssa_0 vec1 32 ssa_87 = frcp ssa_86 vec1 32 ssa_88 = fmul ssa_85, ssa_87 vec1 32 ssa_89 = fmul ssa_56.y, ssa_56.y vec1 32 ssa_90 = ffma ssa_56.x, ssa_56.x, ssa_89 vec1 32 ssa_91 = ffma ssa_56.z, ssa_56.z, ssa_90 vec1 32 ssa_92 = frsq ssa_91 vec1 32 ssa_93 = fmul ssa_56.x, ssa_92 vec1 32 ssa_94 = fmul ssa_56.y, ssa_92 vec1 32 ssa_95 = fmul ssa_56.z, ssa_92 vec1 32 ssa_96 = fmul ssa_94, ssa_82 vec1 32 ssa_97 = ffma ssa_93, ssa_81, ssa_96 vec1 32 ssa_98 = ffma ssa_95, ssa_83, ssa_97 vec1 32 ssa_99 = fmax ssa_3, ssa_98 vec1 32 ssa_100 = load_const (0x00000010 /* 0.000000 */) vec3 32 ssa_101 = intrinsic load_ubo (ssa_24, ssa_100) () () vec1 32 ssa_102 = fmul ssa_101.x, ssa_57.x vec1 32 ssa_103 = fmul ssa_101.y, ssa_57.y vec1 32 ssa_104 = fmul ssa_101.z, ssa_57.z vec1 32 ssa_105 = fmul ssa_102, ssa_99 vec1 32 ssa_106 = fmul ssa_103, ssa_99 vec1 32 ssa_107 = fmul ssa_104, ssa_99 vec1 32 ssa_108 = ffma -ssa_93, ssa_81, -ssa_96 vec1 32 ssa_109 = ffma -ssa_95, ssa_83, ssa_108 vec1 32 ssa_110 = fmul ssa_109, ssa_93 vec1 32 ssa_111 = fmul ssa_109, ssa_94 vec1 32 ssa_112 = fmul ssa_109, ssa_95 vec1 32 ssa_113 = ffma -ssa_59, ssa_110, -ssa_81 vec1 32 ssa_114 = ffma -ssa_59, ssa_111, -ssa_82 vec1 32 ssa_115 = ffma -ssa_59, ssa_112, -ssa_83 vec1 32 ssa_116 = fmul ssa_114, ssa_78 vec1 32 ssa_117 = ffma ssa_113, ssa_77, ssa_116 vec1 32 ssa_118 = ffma ssa_115, ssa_79, ssa_117 vec1 32 ssa_119 = fmax ssa_3, ssa_118 vec1 32 ssa_120 = fmul ssa_101.x, ssa_57.w vec1 32 ssa_121 = fmul ssa_101.y, ssa_57.w vec1 32 ssa_122 = fmul ssa_101.z, ssa_57.w vec1 32 ssa_123 = fpow ssa_119, ssa_58 vec1 32 ssa_124 = fmul ssa_120, ssa_123 vec1 32 ssa_125 = fmul ssa_121, ssa_123 vec1 32 ssa_126 = fmul ssa_122, ssa_123 vec1 32 ssa_127 = fmul ssa_124, ssa_88 vec1 32 ssa_128 = fmul ssa_125, ssa_88 vec1 32 ssa_129 = fmul ssa_126, ssa_88 vec1 32 ssa_130 = ffma ssa_105, ssa_88, ssa_127 vec1 32 ssa_131 = ffma ssa_106, ssa_88, ssa_128 vec1 32 ssa_132 = ffma ssa_107, ssa_88, ssa_129 vec1 32 ssa_133 = load_const (0x00000020 /* 0.000000 */) vec4 32 ssa_134 = intrinsic load_ubo (ssa_24, ssa_133) () () vec1 32 ssa_135 = fadd ssa_134.x, -ssa_55.x vec1 32 ssa_136 = fadd ssa_134.y, -ssa_55.y vec1 32 ssa_137 = fadd ssa_134.z, -ssa_55.z vec1 32 ssa_138 = fmul ssa_136, ssa_136 vec1 32 ssa_139 = ffma ssa_135, ssa_135, ssa_138 vec1 32 ssa_140 = ffma ssa_137, ssa_137, ssa_139 vec1 32 ssa_141 = fsqrt ssa_140 vec1 32 ssa_142 = frsq ssa_140 vec1 32 ssa_143 = fmul ssa_135, ssa_142 vec1 32 ssa_144 = fmul ssa_136, ssa_142 vec1 32 ssa_145 = fmul ssa_137, ssa_142 vec1 32 ssa_146 = load_const (0x0000003c /* 0.000000 */) vec1 32 ssa_147 = intrinsic load_ubo (ssa_24, ssa_146) () () vec1 32 ssa_148 = ffma ssa_141, ssa_141, ssa_0 vec1 32 ssa_149 = frcp ssa_148 vec1 32 ssa_150 = fmul ssa_147, ssa_149 vec1 32 ssa_151 = fmul ssa_94, ssa_144 vec1 32 ssa_152 = ffma ssa_93, ssa_143, ssa_151 vec1 32 ssa_153 = ffma ssa_95, ssa_145, ssa_152 vec1 32 ssa_154 = fmax ssa_3, ssa_153 vec1 32 ssa_155 = load_const (0x00000030 /* 0.000000 */) vec3 32 ssa_156 = intrinsic load_ubo (ssa_24, ssa_155) () () vec1 32 ssa_157 = fmul ssa_156.x, ssa_57.x vec1 32 ssa_158 = fmul ssa_156.y, ssa_57.y vec1 32 ssa_159 = fmul ssa_156.z, ssa_57.z vec1 32 ssa_160 = fmul ssa_157, ssa_154 vec1 32 ssa_161 = fmul ssa_158, ssa_154 vec1 32 ssa_162 = fmul ssa_159, ssa_154 vec1 32 ssa_163 = ffma -ssa_93, ssa_143, -ssa_151 vec1 32 ssa_164 = ffma -ssa_95, ssa_145, ssa_163 vec1 32 ssa_165 = fmul ssa_164, ssa_93 vec1 32 ssa_166 = fmul ssa_164, ssa_94 vec1 32 ssa_167 = fmul ssa_164, ssa_95 vec1 32 ssa_168 = ffma -ssa_59, ssa_165, -ssa_143 vec1 32 ssa_169 = ffma -ssa_59, ssa_166, -ssa_144 vec1 32 ssa_170 = ffma -ssa_59, ssa_167, -ssa_145 vec1 32 ssa_171 = fmul ssa_169, ssa_78 vec1 32 ssa_172 = ffma ssa_168, ssa_77, ssa_171 vec1 32 ssa_173 = ffma ssa_170, ssa_79, ssa_172 vec1 32 ssa_174 = fmax ssa_3, ssa_173 vec1 32 ssa_175 = fmul ssa_156.x, ssa_57.w vec1 32 ssa_176 = fmul ssa_156.y, ssa_57.w vec1 32 ssa_177 = fmul ssa_156.z, ssa_57.w vec1 32 ssa_178 = fpow ssa_174, ssa_58 vec1 32 ssa_179 = fmul ssa_175, ssa_178 vec1 32 ssa_180 = fmul ssa_176, ssa_178 vec1 32 ssa_181 = fmul ssa_177, ssa_178 vec1 32 ssa_182 = fmul ssa_179, ssa_150 vec1 32 ssa_183 = fmul ssa_180, ssa_150 vec1 32 ssa_184 = fmul ssa_181, ssa_150 vec1 32 ssa_185 = ffma ssa_160, ssa_150, ssa_182 vec1 32 ssa_186 = ffma ssa_161, ssa_150, ssa_183 vec1 32 ssa_187 = ffma ssa_162, ssa_150, ssa_184 vec1 32 ssa_188 = fadd ssa_130, ssa_185 vec1 32 ssa_189 = fadd ssa_131, ssa_186 vec1 32 ssa_190 = fadd ssa_132, ssa_187 vec1 32 ssa_191 = load_const (0x00000040 /* 0.000000 */) vec4 32 ssa_192 = intrinsic load_ubo (ssa_24, ssa_191) () () vec1 32 ssa_193 = fadd ssa_192.x, -ssa_55.x vec1 32 ssa_194 = fadd ssa_192.y, -ssa_55.y vec1 32 ssa_195 = fadd ssa_192.z, -ssa_55.z vec1 32 ssa_196 = fmul ssa_194, ssa_194 vec1 32 ssa_197 = ffma ssa_193, ssa_193, ssa_196 vec1 32 ssa_198 = ffma ssa_195, ssa_195, ssa_197 vec1 32 ssa_199 = fsqrt ssa_198 vec1 32 ssa_200 = frsq ssa_198 vec1 32 ssa_201 = fmul ssa_193, ssa_200 vec1 32 ssa_202 = fmul ssa_194, ssa_200 vec1 32 ssa_203 = fmul ssa_195, ssa_200 vec1 32 ssa_204 = load_const (0x0000005c /* 0.000000 */) vec1 32 ssa_205 = intrinsic load_ubo (ssa_24, ssa_204) () () vec1 32 ssa_206 = ffma ssa_199, ssa_199, ssa_0 vec1 32 ssa_207 = frcp ssa_206 vec1 32 ssa_208 = fmul ssa_205, ssa_207 vec1 32 ssa_209 = fmul ssa_94, ssa_202 vec1 32 ssa_210 = ffma ssa_93, ssa_201, ssa_209 vec1 32 ssa_211 = ffma ssa_95, ssa_203, ssa_210 vec1 32 ssa_212 = fmax ssa_3, ssa_211 vec1 32 ssa_213 = load_const (0x00000050 /* 0.000000 */) vec3 32 ssa_214 = intrinsic load_ubo (ssa_24, ssa_213) () () vec1 32 ssa_215 = fmul ssa_214.x, ssa_57.x vec1 32 ssa_216 = fmul ssa_214.y, ssa_57.y vec1 32 ssa_217 = fmul ssa_214.z, ssa_57.z vec1 32 ssa_218 = fmul ssa_215, ssa_212 vec1 32 ssa_219 = fmul ssa_216, ssa_212 vec1 32 ssa_220 = fmul ssa_217, ssa_212 vec1 32 ssa_221 = ffma -ssa_93, ssa_201, -ssa_209 vec1 32 ssa_222 = ffma -ssa_95, ssa_203, ssa_221 vec1 32 ssa_223 = fmul ssa_222, ssa_93 vec1 32 ssa_224 = fmul ssa_222, ssa_94 vec1 32 ssa_225 = fmul ssa_222, ssa_95 vec1 32 ssa_226 = ffma -ssa_59, ssa_223, -ssa_201 vec1 32 ssa_227 = ffma -ssa_59, ssa_224, -ssa_202 vec1 32 ssa_228 = ffma -ssa_59, ssa_225, -ssa_203 vec1 32 ssa_229 = fmul ssa_227, ssa_78 vec1 32 ssa_230 = ffma ssa_226, ssa_77, ssa_229 vec1 32 ssa_231 = ffma ssa_228, ssa_79, ssa_230 vec1 32 ssa_232 = fmax ssa_3, ssa_231 vec1 32 ssa_233 = fmul ssa_214.x, ssa_57.w vec1 32 ssa_234 = fmul ssa_214.y, ssa_57.w vec1 32 ssa_235 = fmul ssa_214.z, ssa_57.w vec1 32 ssa_236 = fpow ssa_232, ssa_58 vec1 32 ssa_237 = fmul ssa_233, ssa_236 vec1 32 ssa_238 = fmul ssa_234, ssa_236 vec1 32 ssa_239 = fmul ssa_235, ssa_236 vec1 32 ssa_240 = fmul ssa_237, ssa_208 vec1 32 ssa_241 = fmul ssa_238, ssa_208 vec1 32 ssa_242 = fmul ssa_239, ssa_208 vec1 32 ssa_243 = ffma ssa_218, ssa_208, ssa_240 vec1 32 ssa_244 = ffma ssa_219, ssa_208, ssa_241 vec1 32 ssa_245 = ffma ssa_220, ssa_208, ssa_242 vec1 32 ssa_246 = fadd ssa_188, ssa_243 vec1 32 ssa_247 = fadd ssa_189, ssa_244 vec1 32 ssa_248 = fadd ssa_190, ssa_245 vec1 32 ssa_249 = load_const (0x00000060 /* 0.000000 */) vec4 32 ssa_250 = intrinsic load_ubo (ssa_24, ssa_249) () () vec1 32 ssa_251 = fadd ssa_250.x, -ssa_55.x vec1 32 ssa_252 = fadd ssa_250.y, -ssa_55.y vec1 32 ssa_253 = fadd ssa_250.z, -ssa_55.z vec1 32 ssa_254 = fmul ssa_252, ssa_252 vec1 32 ssa_255 = ffma ssa_251, ssa_251, ssa_254 vec1 32 ssa_256 = ffma ssa_253, ssa_253, ssa_255 vec1 32 ssa_257 = fsqrt ssa_256 vec1 32 ssa_258 = frsq ssa_256 vec1 32 ssa_259 = fmul ssa_251, ssa_258 vec1 32 ssa_260 = fmul ssa_252, ssa_258 vec1 32 ssa_261 = fmul ssa_253, ssa_258 vec1 32 ssa_262 = load_const (0x0000007c /* 0.000000 */) vec1 32 ssa_263 = intrinsic load_ubo (ssa_24, ssa_262) () () vec1 32 ssa_264 = ffma ssa_257, ssa_257, ssa_0 vec1 32 ssa_265 = frcp ssa_264 vec1 32 ssa_266 = fmul ssa_263, ssa_265 vec1 32 ssa_267 = fmul ssa_94, ssa_260 vec1 32 ssa_268 = ffma ssa_93, ssa_259, ssa_267 vec1 32 ssa_269 = ffma ssa_95, ssa_261, ssa_268 vec1 32 ssa_270 = fmax ssa_3, ssa_269 vec1 32 ssa_271 = load_const (0x00000070 /* 0.000000 */) vec3 32 ssa_272 = intrinsic load_ubo (ssa_24, ssa_271) () () vec1 32 ssa_273 = fmul ssa_272.x, ssa_57.x vec1 32 ssa_274 = fmul ssa_272.y, ssa_57.y vec1 32 ssa_275 = fmul ssa_272.z, ssa_57.z vec1 32 ssa_276 = fmul ssa_273, ssa_270 vec1 32 ssa_277 = fmul ssa_274, ssa_270 vec1 32 ssa_278 = fmul ssa_275, ssa_270 vec1 32 ssa_279 = ffma -ssa_93, ssa_259, -ssa_267 vec1 32 ssa_280 = ffma -ssa_95, ssa_261, ssa_279 vec1 32 ssa_281 = fmul ssa_280, ssa_93 vec1 32 ssa_282 = fmul ssa_280, ssa_94 vec1 32 ssa_283 = fmul ssa_280, ssa_95 vec1 32 ssa_284 = ffma -ssa_59, ssa_281, -ssa_259 vec1 32 ssa_285 = ffma -ssa_59, ssa_282, -ssa_260 vec1 32 ssa_286 = ffma -ssa_59, ssa_283, -ssa_261 vec1 32 ssa_287 = fmul ssa_285, ssa_78 vec1 32 ssa_288 = ffma ssa_284, ssa_77, ssa_287 vec1 32 ssa_289 = ffma ssa_286, ssa_79, ssa_288 vec1 32 ssa_290 = fmax ssa_3, ssa_289 vec1 32 ssa_291 = fmul ssa_272.x, ssa_57.w vec1 32 ssa_292 = fmul ssa_272.y, ssa_57.w vec1 32 ssa_293 = fmul ssa_272.z, ssa_57.w vec1 32 ssa_294 = fpow ssa_290, ssa_58 vec1 32 ssa_295 = fmul ssa_291, ssa_294 vec1 32 ssa_296 = fmul ssa_292, ssa_294 vec1 32 ssa_297 = fmul ssa_293, ssa_294 vec1 32 ssa_298 = fmul ssa_295, ssa_266 vec1 32 ssa_299 = fmul ssa_296, ssa_266 vec1 32 ssa_300 = fmul ssa_297, ssa_266 vec1 32 ssa_301 = ffma ssa_276, ssa_266, ssa_298 vec1 32 ssa_302 = ffma ssa_277, ssa_266, ssa_299 vec1 32 ssa_303 = ffma ssa_278, ssa_266, ssa_300 vec1 32 ssa_304 = fadd ssa_246, ssa_301 vec1 32 ssa_305 = fadd ssa_247, ssa_302 vec1 32 ssa_306 = fadd ssa_248, ssa_303 vec1 32 ssa_307 = load_const (0x00000080 /* 0.000000 */) vec4 32 ssa_308 = intrinsic load_ubo (ssa_24, ssa_307) () () vec1 32 ssa_309 = fadd ssa_308.x, -ssa_55.x vec1 32 ssa_310 = fadd ssa_308.y, -ssa_55.y vec1 32 ssa_311 = fadd ssa_308.z, -ssa_55.z vec1 32 ssa_312 = fmul ssa_310, ssa_310 vec1 32 ssa_313 = ffma ssa_309, ssa_309, ssa_312 vec1 32 ssa_314 = ffma ssa_311, ssa_311, ssa_313 vec1 32 ssa_315 = fsqrt ssa_314 vec1 32 ssa_316 = frsq ssa_314 vec1 32 ssa_317 = fmul ssa_309, ssa_316 vec1 32 ssa_318 = fmul ssa_310, ssa_316 vec1 32 ssa_319 = fmul ssa_311, ssa_316 vec1 32 ssa_320 = load_const (0x0000009c /* 0.000000 */) vec1 32 ssa_321 = intrinsic load_ubo (ssa_24, ssa_320) () () vec1 32 ssa_322 = ffma ssa_315, ssa_315, ssa_0 vec1 32 ssa_323 = frcp ssa_322 vec1 32 ssa_324 = fmul ssa_321, ssa_323 vec1 32 ssa_325 = fmul ssa_94, ssa_318 vec1 32 ssa_326 = ffma ssa_93, ssa_317, ssa_325 vec1 32 ssa_327 = ffma ssa_95, ssa_319, ssa_326 vec1 32 ssa_328 = fmax ssa_3, ssa_327 vec1 32 ssa_329 = load_const (0x00000090 /* 0.000000 */) vec3 32 ssa_330 = intrinsic load_ubo (ssa_24, ssa_329) () () vec1 32 ssa_331 = fmul ssa_330.x, ssa_57.x vec1 32 ssa_332 = fmul ssa_330.y, ssa_57.y vec1 32 ssa_333 = fmul ssa_330.z, ssa_57.z vec1 32 ssa_334 = fmul ssa_331, ssa_328 vec1 32 ssa_335 = fmul ssa_332, ssa_328 vec1 32 ssa_336 = fmul ssa_333, ssa_328 vec1 32 ssa_337 = ffma -ssa_93, ssa_317, -ssa_325 vec1 32 ssa_338 = ffma -ssa_95, ssa_319, ssa_337 vec1 32 ssa_339 = fmul ssa_338, ssa_93 vec1 32 ssa_340 = fmul ssa_338, ssa_94 vec1 32 ssa_341 = fmul ssa_338, ssa_95 vec1 32 ssa_342 = ffma -ssa_59, ssa_339, -ssa_317 vec1 32 ssa_343 = ffma -ssa_59, ssa_340, -ssa_318 vec1 32 ssa_344 = ffma -ssa_59, ssa_341, -ssa_319 vec1 32 ssa_345 = fmul ssa_343, ssa_78 vec1 32 ssa_346 = ffma ssa_342, ssa_77, ssa_345 vec1 32 ssa_347 = ffma ssa_344, ssa_79, ssa_346 vec1 32 ssa_348 = fmax ssa_3, ssa_347 vec1 32 ssa_349 = fmul ssa_330.x, ssa_57.w vec1 32 ssa_350 = fmul ssa_330.y, ssa_57.w vec1 32 ssa_351 = fmul ssa_330.z, ssa_57.w vec1 32 ssa_352 = fpow ssa_348, ssa_58 vec1 32 ssa_353 = fmul ssa_349, ssa_352 vec1 32 ssa_354 = fmul ssa_350, ssa_352 vec1 32 ssa_355 = fmul ssa_351, ssa_352 vec1 32 ssa_356 = fmul ssa_353, ssa_324 vec1 32 ssa_357 = fmul ssa_354, ssa_324 vec1 32 ssa_358 = fmul ssa_355, ssa_324 vec1 32 ssa_359 = ffma ssa_334, ssa_324, ssa_356 vec1 32 ssa_360 = ffma ssa_335, ssa_324, ssa_357 vec1 32 ssa_361 = ffma ssa_336, ssa_324, ssa_358 vec1 32 ssa_362 = fadd ssa_304, ssa_359 vec1 32 ssa_363 = fadd ssa_305, ssa_360 vec1 32 ssa_364 = fadd ssa_306, ssa_361 vec1 32 ssa_365 = load_const (0x000000a0 /* 0.000000 */) vec4 32 ssa_366 = intrinsic load_ubo (ssa_24, ssa_365) () () vec1 32 ssa_367 = fadd ssa_366.x, -ssa_55.x vec1 32 ssa_368 = fadd ssa_366.y, -ssa_55.y vec1 32 ssa_369 = fadd ssa_366.z, -ssa_55.z vec1 32 ssa_370 = fmul ssa_368, ssa_368 vec1 32 ssa_371 = ffma ssa_367, ssa_367, ssa_370 vec1 32 ssa_372 = ffma ssa_369, ssa_369, ssa_371 vec1 32 ssa_373 = fsqrt ssa_372 vec1 32 ssa_374 = frsq ssa_372 vec1 32 ssa_375 = fmul ssa_367, ssa_374 vec1 32 ssa_376 = fmul ssa_368, ssa_374 vec1 32 ssa_377 = fmul ssa_369, ssa_374 vec1 32 ssa_378 = load_const (0x000000bc /* 0.000000 */) vec1 32 ssa_379 = intrinsic load_ubo (ssa_24, ssa_378) () () vec1 32 ssa_380 = ffma ssa_373, ssa_373, ssa_0 vec1 32 ssa_381 = frcp ssa_380 vec1 32 ssa_382 = fmul ssa_379, ssa_381 vec1 32 ssa_383 = fmul ssa_94, ssa_376 vec1 32 ssa_384 = ffma ssa_93, ssa_375, ssa_383 vec1 32 ssa_385 = ffma ssa_95, ssa_377, ssa_384 vec1 32 ssa_386 = fmax ssa_3, ssa_385 vec1 32 ssa_387 = load_const (0x000000b0 /* 0.000000 */) vec3 32 ssa_388 = intrinsic load_ubo (ssa_24, ssa_387) () () vec1 32 ssa_389 = fmul ssa_388.x, ssa_57.x vec1 32 ssa_390 = fmul ssa_388.y, ssa_57.y vec1 32 ssa_391 = fmul ssa_388.z, ssa_57.z vec1 32 ssa_392 = fmul ssa_389, ssa_386 vec1 32 ssa_393 = fmul ssa_390, ssa_386 vec1 32 ssa_394 = fmul ssa_391, ssa_386 vec1 32 ssa_395 = ffma -ssa_93, ssa_375, -ssa_383 vec1 32 ssa_396 = ffma -ssa_95, ssa_377, ssa_395 vec1 32 ssa_397 = fmul ssa_396, ssa_93 vec1 32 ssa_398 = fmul ssa_396, ssa_94 vec1 32 ssa_399 = fmul ssa_396, ssa_95 vec1 32 ssa_400 = ffma -ssa_59, ssa_397, -ssa_375 vec1 32 ssa_401 = ffma -ssa_59, ssa_398, -ssa_376 vec1 32 ssa_402 = ffma -ssa_59, ssa_399, -ssa_377 vec1 32 ssa_403 = fmul ssa_401, ssa_78 vec1 32 ssa_404 = ffma ssa_400, ssa_77, ssa_403 vec1 32 ssa_405 = ffma ssa_402, ssa_79, ssa_404 vec1 32 ssa_406 = fmax ssa_3, ssa_405 vec1 32 ssa_407 = fmul ssa_388.x, ssa_57.w vec1 32 ssa_408 = fmul ssa_388.y, ssa_57.w vec1 32 ssa_409 = fmul ssa_388.z, ssa_57.w vec1 32 ssa_410 = fpow ssa_406, ssa_58 vec1 32 ssa_411 = fmul ssa_407, ssa_410 vec1 32 ssa_412 = fmul ssa_408, ssa_410 vec1 32 ssa_413 = fmul ssa_409, ssa_410 vec1 32 ssa_414 = fmul ssa_411, ssa_382 vec1 32 ssa_415 = fmul ssa_412, ssa_382 vec1 32 ssa_416 = fmul ssa_413, ssa_382 vec1 32 ssa_417 = ffma ssa_392, ssa_382, ssa_414 vec1 32 ssa_418 = ffma ssa_393, ssa_382, ssa_415 vec1 32 ssa_419 = ffma ssa_394, ssa_382, ssa_416 vec1 32 ssa_420 = fadd ssa_362, ssa_417 vec1 32 ssa_421 = fadd ssa_363, ssa_418 vec1 32 ssa_422 = fadd ssa_364, ssa_419 r7 = fadd r7, ssa_420 r8 = fadd r8, ssa_421 r9 = fadd r9, ssa_422 r10 = iadd r10, ssa_2 /* succs: block_1 */ } block block_5: /* preds: block_3 */ vec1 32 ssa_427 = load_const (0x3c99999a /* 0.018750 */) vec1 32 ssa_428 = fmul r7, ssa_49 vec1 32 ssa_429 = fmul r8, ssa_49 vec1 32 ssa_430 = fmul r9, ssa_49 vec1 32 ssa_431 = ffma ssa_427, ssa_46, ssa_428 vec1 32 ssa_432 = ffma ssa_427, ssa_47, ssa_429 vec1 32 ssa_433 = ffma ssa_427, ssa_48, ssa_430 vec4 32 ssa_434 = vec4 ssa_431, ssa_432, ssa_433, ssa_0 intrinsic store_output (ssa_434, ssa_3) () (8, 15, 0) /* base=8 */ /* wrmask=xyzw */ /* component=0 */ /* outFragcolor */ /* succs: block_0 */ block block_0: } FS compile failed: Failure to register allocate. Reduce number of live scalar values to avoid this. Native code for unnamed fragment shader (null) SIMD8 shader: 458 instructions. 1 loops. 10794 cycles. 0:0 spills:fills. Promoted 3 constants. Compacted 7328 to 4432 bytes (40%) START B0 (366 cycles) mov(8) g13<1>UD null<8,8,1>F { align1 1Q }; ERROR: src0 is null pln(8) g55<1>F g4<0,1,0>F g2<8,8,1>F { align1 1Q compacted }; pln(8) g12<1>F g4.4<0,1,0>F g2<8,8,1>F { align1 1Q compacted }; mov(8) g14<1>F [0F, 0F, 0F, 0F]VF { align1 1Q compacted }; mov(8) g7<1>F 2.8026e-45F { align1 1Q }; mov(8) g28<1>F 4.2039e-45F { align1 1Q }; mov(8) g33<1>F 5.60519e-45F { align1 1Q }; mov(8) g38<1>F 7.00649e-45F { align1 1Q }; mov(8) g43<1>F 8.40779e-45F { align1 1Q }; mov(8) g48<1>F 9.80909e-45F { align1 1Q }; mov(8) g19<1>UD 0x00000000UD { align1 1Q compacted }; mov(8) g27<1>UD 0x00000000UD { align1 1Q compacted }; mov(8) g26<1>UD 0x00000000UD { align1 1Q compacted }; mov(8) g25<1>UD 0x00000000UD { align1 1Q compacted }; mov(8) g2<1>F 1.4013e-45F { align1 1Q }; send(8) g53<1>UW g13<8,8,1>F sampler resinfo SIMD8 Surface = 1 Sampler = 0 mlen 1 rlen 2 { align1 1Q }; mov(8) g13<1>F g53<8,8,1>D { align1 1Q compacted }; mov(8) g53<1>F g54<8,8,1>D { align1 1Q compacted }; mul(8) g54<1>F g55<8,8,1>F g13<8,8,1>F { align1 1Q compacted }; mul(8) g55<1>F g12<8,8,1>F g53<8,8,1>F { align1 1Q compacted }; mov(8) g17<1>D g54<8,8,1>F { align1 1Q compacted }; mov(8) g18<1>D g55<8,8,1>F { align1 1Q compacted }; mov(8) g5<1>F g17<8,8,1>F { align1 1Q compacted }; mov(8) g10<1>F g17<8,8,1>F { align1 1Q compacted }; mov(8) g31<1>F g17<8,8,1>F { align1 1Q compacted }; mov(8) g36<1>F g17<8,8,1>F { align1 1Q compacted }; mov(8) g41<1>F g17<8,8,1>F { align1 1Q compacted }; mov(8) g46<1>F g17<8,8,1>F { align1 1Q compacted }; mov(8) g51<1>F g17<8,8,1>F { align1 1Q compacted }; send(8) g53<1>UW g17<8,8,1>F sampler ld_mcs SIMD8 Surface = 3 Sampler = 2 mlen 2 rlen 4 { align1 1Q }; mov(8) g6<1>F g18<8,8,1>F { align1 1Q compacted }; mov(8) g11<1>F g18<8,8,1>F { align1 1Q compacted }; mov(8) g32<1>F g18<8,8,1>F { align1 1Q compacted }; mov(8) g37<1>F g18<8,8,1>F { align1 1Q compacted }; mov(8) g42<1>F g18<8,8,1>F { align1 1Q compacted }; mov(8) g47<1>F g18<8,8,1>F { align1 1Q compacted }; mov(8) g52<1>F g18<8,8,1>F { align1 1Q compacted }; mov(8) g15<1>F g53<8,8,1>F { align1 1Q compacted }; mov(8) g16<1>F g54<8,8,1>F { align1 1Q compacted }; mov(8) g3<1>F g53<8,8,1>F { align1 1Q compacted }; mov(8) g4<1>F g54<8,8,1>F { align1 1Q compacted }; mov(8) g8<1>F g53<8,8,1>F { align1 1Q compacted }; mov(8) g9<1>F g54<8,8,1>F { align1 1Q compacted }; mov(8) g29<1>F g53<8,8,1>F { align1 1Q compacted }; mov(8) g30<1>F g54<8,8,1>F { align1 1Q compacted }; mov(8) g34<1>F g53<8,8,1>F { align1 1Q compacted }; mov(8) g35<1>F g54<8,8,1>F { align1 1Q compacted }; mov(8) g39<1>F g53<8,8,1>F { align1 1Q compacted }; mov(8) g40<1>F g54<8,8,1>F { align1 1Q compacted }; mov(8) g44<1>F g53<8,8,1>F { align1 1Q compacted }; mov(8) g45<1>F g54<8,8,1>F { align1 1Q compacted }; mov(8) g49<1>F g53<8,8,1>F { align1 1Q compacted }; mov(8) g50<1>F g54<8,8,1>F { align1 1Q compacted }; send(8) g58<1>UW g2<8,8,1>F sampler ld2dms_w SIMD8 Surface = 3 Sampler = 0 mlen 5 rlen 3 { align1 1Q }; send(8) g61<1>UW g7<8,8,1>F sampler ld2dms_w SIMD8 Surface = 3 Sampler = 0 mlen 5 rlen 3 { align1 1Q }; send(8) g64<1>UW g28<8,8,1>F sampler ld2dms_w SIMD8 Surface = 3 Sampler = 0 mlen 5 rlen 3 { align1 1Q }; send(8) g53<1>UW g14<8,8,1>F sampler ld2dms_w SIMD8 Surface = 3 Sampler = 0 mlen 5 rlen 3 { align1 1Q }; send(8) g67<1>UW g33<8,8,1>F sampler ld2dms_w SIMD8 Surface = 3 Sampler = 0 mlen 5 rlen 3 { align1 1Q }; send(8) g70<1>UW g38<8,8,1>F sampler ld2dms_w SIMD8 Surface = 3 Sampler = 0 mlen 5 rlen 3 { align1 1Q }; send(8) g73<1>UW g43<8,8,1>F sampler ld2dms_w SIMD8 Surface = 3 Sampler = 0 mlen 5 rlen 3 { align1 1Q }; send(8) g2<1>UW g48<8,8,1>F sampler ld2dms_w SIMD8 Surface = 3 Sampler = 0 mlen 5 rlen 3 { align1 1Q }; add(8) g56<1>F g53<8,8,1>F g58<8,8,1>F { align1 1Q compacted }; add(8) g57<1>F g54<8,8,1>F g59<8,8,1>F { align1 1Q compacted }; add(8) g58<1>F g55<8,8,1>F g60<8,8,1>F { align1 1Q compacted }; add(8) g59<1>F g56<8,8,1>F g61<8,8,1>F { align1 1Q compacted }; add(8) g60<1>F g57<8,8,1>F g62<8,8,1>F { align1 1Q compacted }; add(8) g61<1>F g58<8,8,1>F g63<8,8,1>F { align1 1Q compacted }; add(8) g62<1>F g59<8,8,1>F g64<8,8,1>F { align1 1Q compacted }; add(8) g63<1>F g60<8,8,1>F g65<8,8,1>F { align1 1Q compacted }; add(8) g64<1>F g61<8,8,1>F g66<8,8,1>F { align1 1Q compacted }; add(8) g65<1>F g62<8,8,1>F g67<8,8,1>F { align1 1Q compacted }; add(8) g66<1>F g63<8,8,1>F g68<8,8,1>F { align1 1Q compacted }; add(8) g67<1>F g64<8,8,1>F g69<8,8,1>F { align1 1Q compacted }; add(8) g68<1>F g65<8,8,1>F g70<8,8,1>F { align1 1Q compacted }; add(8) g69<1>F g66<8,8,1>F g71<8,8,1>F { align1 1Q compacted }; add(8) g70<1>F g67<8,8,1>F g72<8,8,1>F { align1 1Q compacted }; add(8) g71<1>F g68<8,8,1>F g73<8,8,1>F { align1 1Q compacted }; add(8) g72<1>F g69<8,8,1>F g74<8,8,1>F { align1 1Q compacted }; add(8) g73<1>F g70<8,8,1>F g75<8,8,1>F { align1 1Q compacted }; add(8) g28<1>F g71<8,8,1>F g2<8,8,1>F { align1 1Q compacted }; add(8) g29<1>F g72<8,8,1>F g3<8,8,1>F { align1 1Q compacted }; add(8) g30<1>F g73<8,8,1>F g4<8,8,1>F { align1 1Q compacted }; END B0 ->B1 START B1 <-B0 <-B2 (20 cycles) cmp.l.f0(8) null<1>D g19<8,8,1>D 8D { align1 1Q compacted }; (-f0) break(8) JIP: 3456 UIP: 3456 { align1 1Q }; END B1 ->B3 ->B2 START B2 <-B1 (1018 cycles) send(8) g54<1>UW g17<8,8,1>F sampler ld_mcs SIMD8 Surface = 1 Sampler = 0 mlen 2 rlen 4 { align1 1Q }; mov(8) g22<1>F g17<8,8,1>F { align1 1Q compacted }; mov(8) g23<1>F g18<8,8,1>F { align1 1Q compacted }; send(8) g58<1>UW g17<8,8,1>F sampler ld_mcs SIMD8 Surface = 2 Sampler = 1 mlen 2 rlen 4 { align1 1Q }; mov(8) g5<1>F g19<8,8,1>F { align1 1Q compacted }; mov(8) g8<1>F g17<8,8,1>F { align1 1Q compacted }; mov(8) g9<1>F g18<8,8,1>F { align1 1Q compacted }; send(8) g62<1>UW g17<8,8,1>F sampler ld_mcs SIMD8 Surface = 3 Sampler = 2 mlen 2 rlen 4 { align1 1Q }; mov(8) g31<1>F g19<8,8,1>F { align1 1Q compacted }; mov(8) g34<1>F g17<8,8,1>F { align1 1Q compacted }; mov(8) g35<1>F g18<8,8,1>F { align1 1Q compacted }; mov(8) g10<1>UD g0<8,8,1>UD { align1 WE_all 1Q compacted }; mov(8) g11<1>UD g0<8,8,1>UD { align1 WE_all 1Q compacted }; mov(1) g24<1>F 1F { align1 WE_all 1N }; mov(8) g12<1>UD g0<8,8,1>UD { align1 WE_all 1Q compacted }; mov(8) g13<1>UD g0<8,8,1>UD { align1 WE_all 1Q compacted }; mov(8) g20<1>F g54<8,8,1>F { align1 1Q compacted }; mov(8) g21<1>F g55<8,8,1>F { align1 1Q compacted }; mov(8) g6<1>F g58<8,8,1>F { align1 1Q compacted }; mov(8) g7<1>F g59<8,8,1>F { align1 1Q compacted }; mov(8) g32<1>F g62<8,8,1>F { align1 1Q compacted }; mov(8) g33<1>F g63<8,8,1>F { align1 1Q compacted }; mov(1) g10.2<1>UD 0x00000000UD { align1 WE_all 1N compacted }; mov(1) g11.2<1>UD 0x0000000cUD { align1 WE_all 1N compacted }; mov(1) g12.2<1>UD 0x00000004UD { align1 WE_all 1N compacted }; mov(1) g13.2<1>UD 0x00000008UD { align1 WE_all 1N compacted }; send(8) g2<1>UW g19<8,8,1>F sampler ld2dms_w SIMD8 Surface = 1 Sampler = 0 mlen 5 rlen 3 { align1 1Q }; add(8) g19<1>D g19<8,8,1>D 1D { align1 1Q compacted }; send(8) g5<1>UW g5<8,8,1>F sampler ld2dms_w SIMD8 Surface = 2 Sampler = 0 mlen 5 rlen 3 { align1 1Q }; send(8) g31<1>UW g31<8,8,1>F sampler ld2dms_w SIMD8 Surface = 3 Sampler = 0 mlen 5 rlen 4 { align1 1Q }; send(16) g8<1>UD g10<8,8,1>UD const (4, 3, 0, 0) mlen 1 rlen 2 { align1 WE_all 1H }; send(16) g51<1>UD g11<8,8,1>UD const (4, 3, 0, 0) mlen 1 rlen 2 { align1 WE_all 1H }; send(16) g10<1>UD g12<8,8,1>UD const (4, 3, 0, 0) mlen 1 rlen 2 { align1 WE_all 1H }; send(16) g12<1>UD g13<8,8,1>UD const (4, 3, 0, 0) mlen 1 rlen 2 { align1 WE_all 1H }; mul(8) g44<1>F g6<8,8,1>F g6<8,8,1>F { align1 1Q compacted }; add(8) g41<1>F g8<0,1,0>F -g2<8,8,1>F { align1 1Q compacted }; add(8) g42<1>F g8.1<0,1,0>F -g3<8,8,1>F { align1 1Q compacted }; add(8) g43<1>F g8.2<0,1,0>F -g4<8,8,1>F { align1 1Q compacted }; mul(8) g35<1>F g8.4<0,1,0>F g31<8,8,1>F { align1 1Q compacted }; mul(8) g36<1>F g8.5<0,1,0>F g32<8,8,1>F { align1 1Q compacted }; mul(8) g37<1>F g8.6<0,1,0>F g33<8,8,1>F { align1 1Q }; mul(8) g38<1>F g8.4<0,1,0>F g34<8,8,1>F { align1 1Q compacted }; mul(8) g39<1>F g8.5<0,1,0>F g34<8,8,1>F { align1 1Q compacted }; mul(8) g40<1>F g8.6<0,1,0>F g34<8,8,1>F { align1 1Q }; add(8) g70<1>F g9<0,1,0>F -g2<8,8,1>F { align1 1Q compacted }; add(8) g71<1>F g9.1<0,1,0>F -g3<8,8,1>F { align1 1Q compacted }; add(8) g77<1>F g9.2<0,1,0>F -g4<8,8,1>F { align1 1Q compacted }; mul(8) g45<1>F g9.4<0,1,0>F g31<8,8,1>F { align1 1Q compacted }; mul(8) g46<1>F g9.5<0,1,0>F g32<8,8,1>F { align1 1Q compacted }; mul(8) g47<1>F g9.6<0,1,0>F g33<8,8,1>F { align1 1Q }; mul(8) g48<1>F g9.4<0,1,0>F g34<8,8,1>F { align1 1Q compacted }; mul(8) g49<1>F g9.5<0,1,0>F g34<8,8,1>F { align1 1Q compacted }; mul(8) g50<1>F g9.6<0,1,0>F g34<8,8,1>F { align1 1Q }; add(8) g54<1>F g51<0,1,0>F -g2<8,8,1>F { align1 1Q compacted }; add(8) g58<1>F g51.1<0,1,0>F -g3<8,8,1>F { align1 1Q compacted }; add(8) g59<1>F g51.2<0,1,0>F -g4<8,8,1>F { align1 1Q compacted }; add(8) g87<1>F g10<0,1,0>F -g2<8,8,1>F { align1 1Q compacted }; add(8) g88<1>F g10.1<0,1,0>F -g3<8,8,1>F { align1 1Q compacted }; add(8) g89<1>F g10.2<0,1,0>F -g4<8,8,1>F { align1 1Q compacted }; mul(8) g55<1>F g10.4<0,1,0>F g31<8,8,1>F { align1 1Q compacted }; mul(8) g56<1>F g10.5<0,1,0>F g32<8,8,1>F { align1 1Q compacted }; mul(8) g57<1>F g10.6<0,1,0>F g33<8,8,1>F { align1 1Q }; mul(8) g61<1>F g10.4<0,1,0>F g34<8,8,1>F { align1 1Q compacted }; mul(8) g62<1>F g10.5<0,1,0>F g34<8,8,1>F { align1 1Q compacted }; mul(8) g63<1>F g10.6<0,1,0>F g34<8,8,1>F { align1 1Q }; add(8) g64<1>F g11<0,1,0>F -g2<8,8,1>F { align1 1Q compacted }; add(8) g65<1>F g11.1<0,1,0>F -g3<8,8,1>F { align1 1Q compacted }; add(8) g66<1>F g11.2<0,1,0>F -g4<8,8,1>F { align1 1Q compacted }; mul(8) g72<1>F g11.4<0,1,0>F g31<8,8,1>F { align1 1Q compacted }; mul(8) g73<1>F g11.5<0,1,0>F g32<8,8,1>F { align1 1Q compacted }; mul(8) g74<1>F g11.6<0,1,0>F g33<8,8,1>F { align1 1Q }; mul(8) g81<1>F g11.4<0,1,0>F g34<8,8,1>F { align1 1Q compacted }; mul(8) g82<1>F g11.5<0,1,0>F g34<8,8,1>F { align1 1Q compacted }; mul(8) g83<1>F g11.6<0,1,0>F g34<8,8,1>F { align1 1Q }; add(8) g84<1>F g12<0,1,0>F -g2<8,8,1>F { align1 1Q compacted }; add(8) g85<1>F g12.1<0,1,0>F -g3<8,8,1>F { align1 1Q compacted }; add(8) g86<1>F g12.2<0,1,0>F -g4<8,8,1>F { align1 1Q compacted }; mul(8) g92<1>F g12.4<0,1,0>F g31<8,8,1>F { align1 1Q compacted }; mul(8) g93<1>F g12.5<0,1,0>F g32<8,8,1>F { align1 1Q compacted }; mul(8) g94<1>F g12.6<0,1,0>F g33<8,8,1>F { align1 1Q }; mul(8) g101<1>F g12.4<0,1,0>F g34<8,8,1>F { align1 1Q compacted }; mul(8) g102<1>F g12.5<0,1,0>F g34<8,8,1>F { align1 1Q compacted }; mul(8) g103<1>F g12.6<0,1,0>F g34<8,8,1>F { align1 1Q }; add(8) g104<1>F g13<0,1,0>F -g2<8,8,1>F { align1 1Q compacted }; add(8) g105<1>F g13.1<0,1,0>F -g3<8,8,1>F { align1 1Q compacted }; add(8) g106<1>F g13.2<0,1,0>F -g4<8,8,1>F { align1 1Q compacted }; mul(8) g113<1>F g13.4<0,1,0>F g31<8,8,1>F { align1 1Q compacted }; mul(8) g114<1>F g13.5<0,1,0>F g32<8,8,1>F { align1 1Q compacted }; mul(8) g115<1>F g13.6<0,1,0>F g33<8,8,1>F { align1 1Q }; mul(8) g123<1>F g13.4<0,1,0>F g34<8,8,1>F { align1 1Q compacted }; mul(8) g124<1>F g13.5<0,1,0>F g34<8,8,1>F { align1 1Q compacted }; mul(8) g125<1>F g13.6<0,1,0>F g34<8,8,1>F { align1 1Q }; mul(8) g78<1>F g71<8,8,1>F g71<8,8,1>F { align1 1Q compacted }; mad(8) g51<1>F g44<4,4,1>F g5<4,4,1>F g5<4,4,1>F { align16 1Q compacted }; mul(8) g60<1>F g58<8,8,1>F g58<8,8,1>F { align1 1Q compacted }; mul(8) g90<1>F g88<8,8,1>F g88<8,8,1>F { align1 1Q compacted }; mul(8) g53<1>F g65<8,8,1>F g65<8,8,1>F { align1 1Q compacted }; mul(8) g68<1>F g85<8,8,1>F g85<8,8,1>F { align1 1Q compacted }; mul(8) g75<1>F g105<8,8,1>F g105<8,8,1>F { align1 1Q compacted }; mul(8) g44<1>F g42<8,8,1>F g42<8,8,1>F { align1 1Q compacted }; mad(8) g79<1>F g78<4,4,1>F g70<4,4,1>F g70<4,4,1>F { align16 1Q compacted }; mad(8) g67<1>F g60<4,4,1>F g54<4,4,1>F g54<4,4,1>F { align16 1Q compacted }; mad(8) g91<1>F g90<4,4,1>F g87<4,4,1>F g87<4,4,1>F { align16 1Q compacted }; mad(8) g52<1>F g51<4,4,1>F g7<4,4,1>F g7<4,4,1>F { align16 1Q compacted }; mad(8) g60<1>F g53<4,4,1>F g64<4,4,1>F g64<4,4,1>F { align16 1Q compacted }; mad(8) g69<1>F g68<4,4,1>F g84<4,4,1>F g84<4,4,1>F { align16 1Q compacted }; mad(8) g76<1>F g75<4,4,1>F g104<4,4,1>F g104<4,4,1>F { align16 1Q compacted }; mad(8) g51<1>F g44<4,4,1>F g41<4,4,1>F g41<4,4,1>F { align16 1Q compacted }; mad(8) g80<1>F g79<4,4,1>F g77<4,4,1>F g77<4,4,1>F { align16 1Q compacted }; mad(8) g68<1>F g67<4,4,1>F g59<4,4,1>F g59<4,4,1>F { align16 1Q compacted }; mad(8) g95<1>F g91<4,4,1>F g89<4,4,1>F g89<4,4,1>F { align16 1Q compacted }; math rsq(8) g53<1>F g52<8,8,1>F null<8,8,1>F { align1 1Q compacted }; mad(8) g67<1>F g60<4,4,1>F g66<4,4,1>F g66<4,4,1>F { align16 1Q compacted }; mad(8) g98<1>F g69<4,4,1>F g86<4,4,1>F g86<4,4,1>F { align16 1Q compacted }; mad(8) g99<1>F g76<4,4,1>F g106<4,4,1>F g106<4,4,1>F { align16 1Q compacted }; mad(8) g52<1>F g51<4,4,1>F g43<4,4,1>F g43<4,4,1>F { align16 1Q compacted }; math rsq(8) g91<1>F g80<8,8,1>F null<8,8,1>F { align1 1Q compacted }; math sqrt(8) g90<1>F g80<8,8,1>F null<8,8,1>F { align1 1Q compacted }; math rsq(8) g69<1>F g68<8,8,1>F null<8,8,1>F { align1 1Q compacted }; mul(8) g76<1>F g7<8,8,1>F g53<8,8,1>F { align1 1Q compacted }; mul(8) g60<1>F g5<8,8,1>F g53<8,8,1>F { align1 1Q compacted }; mul(8) g75<1>F g6<8,8,1>F g53<8,8,1>F { align1 1Q compacted }; math sqrt(8) g96<1>F g95<8,8,1>F null<8,8,1>F { align1 1Q compacted }; math rsq(8) g97<1>F g95<8,8,1>F null<8,8,1>F { align1 1Q compacted }; math sqrt(8) g78<1>F g67<8,8,1>F null<8,8,1>F { align1 1Q compacted }; math rsq(8) g79<1>F g67<8,8,1>F null<8,8,1>F { align1 1Q compacted }; math sqrt(8) g100<1>F g98<8,8,1>F null<8,8,1>F { align1 1Q compacted }; math rsq(8) g108<1>F g98<8,8,1>F null<8,8,1>F { align1 1Q compacted }; math sqrt(8) g107<1>F g99<8,8,1>F null<8,8,1>F { align1 1Q compacted }; math rsq(8) g110<1>F g99<8,8,1>F null<8,8,1>F { align1 1Q compacted }; math sqrt(8) g53<1>F g52<8,8,1>F null<8,8,1>F { align1 1Q compacted }; math rsq(8) g3<1>F g52<8,8,1>F null<8,8,1>F { align1 1Q compacted }; mul(8) g126<1>F g54<8,8,1>F g69<8,8,1>F { align1 1Q compacted }; mul(8) g127<1>F g58<8,8,1>F g69<8,8,1>F { align1 1Q compacted }; mul(8) g2<1>F g59<8,8,1>F g69<8,8,1>F { align1 1Q compacted }; mul(8) g52<1>F g88<8,8,1>F g97<8,8,1>F { align1 1Q compacted }; mul(8) g51<1>F g87<8,8,1>F g97<8,8,1>F { align1 1Q compacted }; mul(8) g67<1>F g64<8,8,1>F g79<8,8,1>F { align1 1Q compacted }; mul(8) g68<1>F g65<8,8,1>F g79<8,8,1>F { align1 1Q compacted }; mul(8) g69<1>F g66<8,8,1>F g79<8,8,1>F { align1 1Q compacted }; mul(8) g88<1>F g85<8,8,1>F g108<8,8,1>F { align1 1Q compacted }; mul(8) g87<1>F g84<8,8,1>F g108<8,8,1>F { align1 1Q compacted }; mul(8) g109<1>F g105<8,8,1>F g110<8,8,1>F { align1 1Q compacted }; mad(8) g7<1>F g24.0<0,1,0>F g53<4,4,1>F g53<4,4,1>F { align16 1Q }; mul(8) g4<1>F g41<8,8,1>F g3<8,8,1>F { align1 1Q compacted }; mul(8) g5<1>F g42<8,8,1>F g3<8,8,1>F { align1 1Q compacted }; mul(8) g6<1>F g43<8,8,1>F g3<8,8,1>F { align1 1Q compacted }; mov(1) g24.1<1>F 2F { align1 WE_all 1N }; mul(8) g53<1>F g89<8,8,1>F g97<8,8,1>F { align1 1Q compacted }; mul(8) g41<1>F g70<8,8,1>F g91<8,8,1>F { align1 1Q compacted }; mul(8) g42<1>F g71<8,8,1>F g91<8,8,1>F { align1 1Q compacted }; mul(8) g85<1>F g75<8,8,1>F g68<8,8,1>F { align1 1Q compacted }; mul(8) g43<1>F g77<8,8,1>F g91<8,8,1>F { align1 1Q compacted }; mul(8) g117<1>F g75<8,8,1>F g88<8,8,1>F { align1 1Q compacted }; mul(8) g89<1>F g86<8,8,1>F g108<8,8,1>F { align1 1Q compacted }; mul(8) g120<1>F g75<8,8,1>F g109<8,8,1>F { align1 1Q compacted }; mul(8) g77<1>F g75<8,8,1>F g5<8,8,1>F { align1 1Q compacted }; math inv(8) g31<1>F g7<8,8,1>F null<8,8,1>F { align1 1Q compacted }; mul(8) g108<1>F g104<8,8,1>F g110<8,8,1>F { align1 1Q compacted }; mad(8) g95<1>F g24.0<0,1,0>F g90<4,4,1>F g90<4,4,1>F { align16 1Q }; mad(8) g99<1>F g24.0<0,1,0>F g96<4,4,1>F g96<4,4,1>F { align16 1Q }; mad(8) g80<1>F g24.0<0,1,0>F g78<4,4,1>F g78<4,4,1>F { align16 1Q }; mad(8) g111<1>F g24.0<0,1,0>F g100<4,4,1>F g100<4,4,1>F { align16 1Q }; mad(8) g112<1>F g24.0<0,1,0>F g107<4,4,1>F g107<4,4,1>F { align16 1Q }; mul(8) g97<1>F g75<8,8,1>F g42<8,8,1>F { align1 1Q compacted }; mul(8) g104<1>F g75<8,8,1>F g52<8,8,1>F { align1 1Q compacted }; mul(8) g110<1>F g106<8,8,1>F g110<8,8,1>F { align1 1Q compacted }; mad(8) g86<1>F g85<4,4,1>F g67<4,4,1>F g60<4,4,1>F { align16 1Q compacted }; mad(8) g118<1>F g117<4,4,1>F g87<4,4,1>F g60<4,4,1>F { align16 1Q compacted }; mad(8) g122<1>F -g117<4,4,1>F g87<4,4,1>F -g60<4,4,1>F { align16 1Q }; mad(8) g78<1>F g77<4,4,1>F g4<4,4,1>F g60<4,4,1>F { align16 1Q compacted }; mad(8) g105<1>F -g77<4,4,1>F g4<4,4,1>F -g60<4,4,1>F { align16 1Q }; mad(8) g7<1>F g120<4,4,1>F g108<4,4,1>F g60<4,4,1>F { align16 1Q compacted }; mad(8) g33<1>F -g120<4,4,1>F g108<4,4,1>F -g60<4,4,1>F { align16 1Q }; mul(8) g32<1>F g8.7<0,1,0>F g31<8,8,1>F { align1 1Q }; math inv(8) g96<1>F g95<8,8,1>F null<8,8,1>F { align1 1Q compacted }; math inv(8) g100<1>F g99<8,8,1>F null<8,8,1>F { align1 1Q compacted }; math inv(8) g84<1>F g80<8,8,1>F null<8,8,1>F { align1 1Q compacted }; mad(8) g98<1>F g97<4,4,1>F g41<4,4,1>F g60<4,4,1>F { align16 1Q compacted }; mad(8) g44<1>F -g97<4,4,1>F g41<4,4,1>F -g60<4,4,1>F { align16 1Q }; math inv(8) g116<1>F g111<8,8,1>F null<8,8,1>F { align1 1Q compacted }; math inv(8) g117<1>F g112<8,8,1>F null<8,8,1>F { align1 1Q compacted }; mad(8) g107<1>F g104<4,4,1>F g51<4,4,1>F g60<4,4,1>F { align16 1Q compacted }; mad(8) g119<1>F -g104<4,4,1>F g51<4,4,1>F -g60<4,4,1>F { align16 1Q }; mad(8) g91<1>F g86<4,4,1>F g69<4,4,1>F g76<4,4,1>F { align16 1Q compacted }; mad(8) g121<1>F g118<4,4,1>F g89<4,4,1>F g76<4,4,1>F { align16 1Q compacted }; mad(8) g3<1>F g122<4,4,1>F g89<4,4,1>F -g76<4,4,1>F { align16 1Q compacted }; mad(8) g97<1>F -g85<4,4,1>F g67<4,4,1>F -g60<4,4,1>F { align16 1Q }; mad(8) g79<1>F g78<4,4,1>F g6<4,4,1>F g76<4,4,1>F { align16 1Q compacted }; mad(8) g106<1>F g105<4,4,1>F g6<4,4,1>F -g76<4,4,1>F { align16 1Q compacted }; mad(8) g31<1>F g7<4,4,1>F g110<4,4,1>F g76<4,4,1>F { align16 1Q compacted }; mul(8) g54<1>F g10.7<0,1,0>F g100<8,8,1>F { align1 1Q }; mul(8) g70<1>F g11.7<0,1,0>F g84<8,8,1>F { align1 1Q }; mad(8) g99<1>F g98<4,4,1>F g43<4,4,1>F g76<4,4,1>F { align16 1Q compacted }; mul(8) g90<1>F g12.7<0,1,0>F g116<8,8,1>F { align1 1Q }; mad(8) g58<1>F g44<4,4,1>F g43<4,4,1>F -g76<4,4,1>F { align16 1Q compacted }; mul(8) g111<1>F g13.7<0,1,0>F g117<8,8,1>F { align1 1Q }; mad(8) g112<1>F g107<4,4,1>F g53<4,4,1>F g76<4,4,1>F { align16 1Q compacted }; mad(8) g120<1>F g119<4,4,1>F g53<4,4,1>F -g76<4,4,1>F { align16 1Q compacted }; sel.ge(8) g71<1>F g91<8,8,1>F 0F { align1 1Q compacted }; mul(8) g44<1>F g9.7<0,1,0>F g96<8,8,1>F { align1 1Q }; mul(8) g100<1>F g3<8,8,1>F g76<8,8,1>F { align1 1Q compacted }; mad(8) g98<1>F g97<4,4,1>F g69<4,4,1>F -g76<4,4,1>F { align16 1Q compacted }; sel.ge(8) g84<1>F g79<8,8,1>F 0F { align1 1Q compacted }; mad(8) g119<1>F g33<4,4,1>F g110<4,4,1>F -g76<4,4,1>F { align16 1Q compacted }; mul(8) g107<1>F g106<8,8,1>F g60<8,8,1>F { align1 1Q compacted }; mul(8) g117<1>F g106<8,8,1>F g76<8,8,1>F { align1 1Q compacted }; mul(8) g116<1>F g106<8,8,1>F g75<8,8,1>F { align1 1Q compacted }; sel.ge(8) g91<1>F g121<8,8,1>F 0F { align1 1Q compacted }; sel.ge(8) g105<1>F g99<8,8,1>F 0F { align1 1Q compacted }; mul(8) g59<1>F g58<8,8,1>F g60<8,8,1>F { align1 1Q compacted }; mul(8) g64<1>F g58<8,8,1>F g75<8,8,1>F { align1 1Q compacted }; mul(8) g65<1>F g58<8,8,1>F g76<8,8,1>F { align1 1Q compacted }; mul(8) g77<1>F g74<8,8,1>F g71<8,8,1>F { align1 1Q compacted }; sel.ge(8) g118<1>F g112<8,8,1>F 0F { align1 1Q compacted }; mul(8) g9<1>F g120<8,8,1>F g76<8,8,1>F { align1 1Q compacted }; mul(8) g7<1>F g120<8,8,1>F g60<8,8,1>F { align1 1Q compacted }; mul(8) g8<1>F g120<8,8,1>F g75<8,8,1>F { align1 1Q compacted }; mul(8) g99<1>F g3<8,8,1>F g75<8,8,1>F { align1 1Q compacted }; mul(8) g85<1>F g35<8,8,1>F g84<8,8,1>F { align1 1Q compacted }; mul(8) g86<1>F g36<8,8,1>F g84<8,8,1>F { align1 1Q compacted }; mul(8) g104<1>F g37<8,8,1>F g84<8,8,1>F { align1 1Q compacted }; mul(8) g79<1>F g98<8,8,1>F g75<8,8,1>F { align1 1Q compacted }; mul(8) g78<1>F g98<8,8,1>F g60<8,8,1>F { align1 1Q compacted }; mul(8) g80<1>F g98<8,8,1>F g76<8,8,1>F { align1 1Q compacted }; mul(8) g121<1>F g119<8,8,1>F g75<8,8,1>F { align1 1Q compacted }; mul(8) g122<1>F g119<8,8,1>F g76<8,8,1>F { align1 1Q compacted }; sel.ge(8) g112<1>F g31<8,8,1>F 0F { align1 1Q compacted }; mul(8) g95<1>F g92<8,8,1>F g91<8,8,1>F { align1 1Q compacted }; mul(8) g96<1>F g93<8,8,1>F g91<8,8,1>F { align1 1Q compacted }; mul(8) g97<1>F g94<8,8,1>F g91<8,8,1>F { align1 1Q compacted }; mul(8) g106<1>F g45<8,8,1>F g105<8,8,1>F { align1 1Q compacted }; mul(8) g120<1>F g119<8,8,1>F g60<8,8,1>F { align1 1Q compacted }; mad(8) g66<1>F -g41<4,4,1>F g59<4,4,1>F -g24.1<0,1,0>F { align16 1Q }; mad(8) g35<1>F -g89<4,4,1>F g100<4,4,1>F -g24.1<0,1,0>F { align16 1Q }; mul(8) g37<1>F g47<8,8,1>F g105<8,8,1>F { align1 1Q compacted }; mad(8) g84<1>F -g42<4,4,1>F g64<4,4,1>F -g24.1<0,1,0>F { align16 1Q }; mul(8) g58<1>F g55<8,8,1>F g118<8,8,1>F { align1 1Q compacted }; mad(8) g12<1>F -g53<4,4,1>F g9<4,4,1>F -g24.1<0,1,0>F { align16 1Q }; mad(8) g10<1>F -g51<4,4,1>F g7<4,4,1>F -g24.1<0,1,0>F { align16 1Q }; mul(8) g98<1>F g3<8,8,1>F g60<8,8,1>F { align1 1Q compacted }; mad(8) g11<1>F -g52<4,4,1>F g8<4,4,1>F -g24.1<0,1,0>F { align16 1Q }; mul(8) g75<1>F g72<8,8,1>F g71<8,8,1>F { align1 1Q compacted }; mad(8) g34<1>F -g88<4,4,1>F g99<4,4,1>F -g24.1<0,1,0>F { align16 1Q }; mul(8) g76<1>F g73<8,8,1>F g71<8,8,1>F { align1 1Q compacted }; mad(8) g119<1>F -g4<4,4,1>F g107<4,4,1>F -g24.1<0,1,0>F { align16 1Q }; mul(8) g59<1>F g56<8,8,1>F g118<8,8,1>F { align1 1Q compacted }; mad(8) g45<1>F -g110<4,4,1>F g122<4,4,1>F -g24.1<0,1,0>F { align16 1Q }; mad(8) g9<1>F -g69<4,4,1>F g80<4,4,1>F -g24.1<0,1,0>F { align16 1Q }; mad(8) g7<1>F -g67<4,4,1>F g78<4,4,1>F -g24.1<0,1,0>F { align16 1Q }; mad(8) g42<1>F -g108<4,4,1>F g120<4,4,1>F -g24.1<0,1,0>F { align16 1Q }; mad(8) g3<1>F -g5<4,4,1>F g116<4,4,1>F -g24.1<0,1,0>F { align16 1Q }; mul(8) g60<1>F g57<8,8,1>F g118<8,8,1>F { align1 1Q compacted }; mad(8) g8<1>F -g68<4,4,1>F g79<4,4,1>F -g24.1<0,1,0>F { align16 1Q }; mad(8) g4<1>F -g6<4,4,1>F g117<4,4,1>F -g24.1<0,1,0>F { align16 1Q }; mul(8) g107<1>F g46<8,8,1>F g105<8,8,1>F { align1 1Q compacted }; mad(8) g33<1>F -g87<4,4,1>F g98<4,4,1>F -g24.1<0,1,0>F { align16 1Q }; mul(8) g108<1>F g84<8,8,1>F g127<8,8,1>F { align1 1Q compacted }; mul(8) g13<1>F g11<8,8,1>F g127<8,8,1>F { align1 1Q compacted }; mul(8) g116<1>F g113<8,8,1>F g112<8,8,1>F { align1 1Q compacted }; mul(8) g118<1>F g115<8,8,1>F g112<8,8,1>F { align1 1Q compacted }; mul(8) g36<1>F g34<8,8,1>F g127<8,8,1>F { align1 1Q compacted }; mul(8) g117<1>F g114<8,8,1>F g112<8,8,1>F { align1 1Q compacted }; mad(8) g105<1>F -g43<4,4,1>F g65<4,4,1>F -g24.1<0,1,0>F { align16 1Q }; mul(8) g5<1>F g3<8,8,1>F g127<8,8,1>F { align1 1Q compacted }; mul(8) g11<1>F g8<8,8,1>F g127<8,8,1>F { align1 1Q compacted }; mad(8) g43<1>F -g109<4,4,1>F g121<4,4,1>F -g24.1<0,1,0>F { align16 1Q }; mad(8) g31<1>F g13<4,4,1>F g126<4,4,1>F g10<4,4,1>F { align16 1Q compacted }; mad(8) g109<1>F g108<4,4,1>F g126<4,4,1>F g66<4,4,1>F { align16 1Q compacted }; mad(8) g41<1>F g36<4,4,1>F g126<4,4,1>F g33<4,4,1>F { align16 1Q compacted }; mad(8) g6<1>F g5<4,4,1>F g126<4,4,1>F g119<4,4,1>F { align16 1Q compacted }; mad(8) g13<1>F g11<4,4,1>F g126<4,4,1>F g7<4,4,1>F { align16 1Q compacted }; mul(8) g46<1>F g43<8,8,1>F g127<8,8,1>F { align1 1Q compacted }; mad(8) g33<1>F g31<4,4,1>F g2<4,4,1>F g12<4,4,1>F { align16 1Q compacted }; mad(8) g110<1>F g109<4,4,1>F g2<4,4,1>F g105<4,4,1>F { align16 1Q compacted }; mad(8) g7<1>F g6<4,4,1>F g2<4,4,1>F g4<4,4,1>F { align16 1Q compacted }; mad(8) g31<1>F g13<4,4,1>F g2<4,4,1>F g9<4,4,1>F { align16 1Q compacted }; mad(8) g47<1>F g46<4,4,1>F g126<4,4,1>F g42<4,4,1>F { align16 1Q compacted }; mad(8) g42<1>F g41<4,4,1>F g2<4,4,1>F g35<4,4,1>F { align16 1Q compacted }; sel.ge(8) g34<1>F g33<8,8,1>F 0F { align1 1Q compacted }; sel.ge(8) g112<1>F g110<8,8,1>F 0F { align1 1Q compacted }; sel.ge(8) g8<1>F g7<8,8,1>F 0F { align1 1Q compacted }; sel.ge(8) g33<1>F g31<8,8,1>F 0F { align1 1Q compacted }; mad(8) g51<1>F g47<4,4,1>F g2<4,4,1>F g45<4,4,1>F { align16 1Q compacted }; math pow(8) g35<1>F g34<8,8,1>F 8F { align1 1Q }; sel.ge(8) g43<1>F g42<8,8,1>F 0F { align1 1Q compacted }; math pow(8) g113<1>F g112<8,8,1>F 8F { align1 1Q }; math pow(8) g9<1>F g8<8,8,1>F 8F { align1 1Q }; math pow(8) g34<1>F g33<8,8,1>F 8F { align1 1Q }; math pow(8) g46<1>F g43<8,8,1>F 8F { align1 1Q }; sel.ge(8) g52<1>F g51<8,8,1>F 0F { align1 1Q compacted }; mul(8) g36<1>F g61<8,8,1>F g35<8,8,1>F { align1 1Q compacted }; mul(8) g114<1>F g48<8,8,1>F g113<8,8,1>F { align1 1Q compacted }; mul(8) g115<1>F g49<8,8,1>F g113<8,8,1>F { align1 1Q compacted }; mul(8) g119<1>F g50<8,8,1>F g113<8,8,1>F { align1 1Q compacted }; math pow(8) g53<1>F g52<8,8,1>F 8F { align1 1Q }; mul(8) g10<1>F g38<8,8,1>F g9<8,8,1>F { align1 1Q compacted }; mul(8) g11<1>F g39<8,8,1>F g9<8,8,1>F { align1 1Q compacted }; mul(8) g12<1>F g40<8,8,1>F g9<8,8,1>F { align1 1Q compacted }; mul(8) g43<1>F g82<8,8,1>F g34<8,8,1>F { align1 1Q compacted }; mul(8) g45<1>F g83<8,8,1>F g34<8,8,1>F { align1 1Q compacted }; mul(8) g38<1>F g62<8,8,1>F g35<8,8,1>F { align1 1Q compacted }; mul(8) g39<1>F g63<8,8,1>F g35<8,8,1>F { align1 1Q compacted }; mul(8) g40<1>F g36<8,8,1>F g54<8,8,1>F { align1 1Q compacted }; mul(8) g50<1>F g102<8,8,1>F g46<8,8,1>F { align1 1Q compacted }; mul(8) g49<1>F g101<8,8,1>F g46<8,8,1>F { align1 1Q compacted }; mul(8) g51<1>F g103<8,8,1>F g46<8,8,1>F { align1 1Q compacted }; mul(8) g120<1>F g114<8,8,1>F g44<8,8,1>F { align1 1Q compacted }; mul(8) g121<1>F g115<8,8,1>F g44<8,8,1>F { align1 1Q compacted }; mul(8) g122<1>F g119<8,8,1>F g44<8,8,1>F { align1 1Q compacted }; mul(8) g35<1>F g81<8,8,1>F g34<8,8,1>F { align1 1Q compacted }; mul(8) g13<1>F g10<8,8,1>F g32<8,8,1>F { align1 1Q compacted }; mul(8) g31<1>F g11<8,8,1>F g32<8,8,1>F { align1 1Q compacted }; mul(8) g33<1>F g12<8,8,1>F g32<8,8,1>F { align1 1Q compacted }; mul(8) g47<1>F g43<8,8,1>F g70<8,8,1>F { align1 1Q compacted }; mul(8) g48<1>F g45<8,8,1>F g70<8,8,1>F { align1 1Q compacted }; mul(8) g56<1>F g123<8,8,1>F g53<8,8,1>F { align1 1Q compacted }; mul(8) g57<1>F g124<8,8,1>F g53<8,8,1>F { align1 1Q compacted }; mul(8) g61<1>F g125<8,8,1>F g53<8,8,1>F { align1 1Q compacted }; mul(8) g41<1>F g38<8,8,1>F g54<8,8,1>F { align1 1Q compacted }; mul(8) g42<1>F g39<8,8,1>F g54<8,8,1>F { align1 1Q compacted }; mul(8) g52<1>F g49<8,8,1>F g90<8,8,1>F { align1 1Q compacted }; mul(8) g55<1>F g51<8,8,1>F g90<8,8,1>F { align1 1Q compacted }; mad(8) g43<1>F g40<4,4,1>F g54<4,4,1>F g58<4,4,1>F { align16 1Q compacted }; mad(8) g123<1>F g120<4,4,1>F g44<4,4,1>F g106<4,4,1>F { align16 1Q compacted }; mad(8) g124<1>F g121<4,4,1>F g44<4,4,1>F g107<4,4,1>F { align16 1Q compacted }; mul(8) g46<1>F g35<8,8,1>F g70<8,8,1>F { align1 1Q compacted }; mad(8) g125<1>F g122<4,4,1>F g44<4,4,1>F g37<4,4,1>F { align16 1Q compacted }; mul(8) g53<1>F g50<8,8,1>F g90<8,8,1>F { align1 1Q compacted }; mad(8) g34<1>F g13<4,4,1>F g32<4,4,1>F g85<4,4,1>F { align16 1Q compacted }; mad(8) g36<1>F g33<4,4,1>F g32<4,4,1>F g104<4,4,1>F { align16 1Q compacted }; mad(8) g51<1>F g48<4,4,1>F g70<4,4,1>F g77<4,4,1>F { align16 1Q compacted }; mul(8) g62<1>F g56<8,8,1>F g111<8,8,1>F { align1 1Q compacted }; mul(8) g63<1>F g57<8,8,1>F g111<8,8,1>F { align1 1Q compacted }; mul(8) g64<1>F g61<8,8,1>F g111<8,8,1>F { align1 1Q compacted }; mad(8) g35<1>F g31<4,4,1>F g32<4,4,1>F g86<4,4,1>F { align16 1Q compacted }; mad(8) g44<1>F g41<4,4,1>F g54<4,4,1>F g59<4,4,1>F { align16 1Q compacted }; mad(8) g45<1>F g42<4,4,1>F g54<4,4,1>F g60<4,4,1>F { align16 1Q compacted }; mad(8) g50<1>F g47<4,4,1>F g70<4,4,1>F g76<4,4,1>F { align16 1Q compacted }; mad(8) g58<1>F g55<4,4,1>F g90<4,4,1>F g97<4,4,1>F { align16 1Q compacted }; mad(8) g56<1>F g52<4,4,1>F g90<4,4,1>F g95<4,4,1>F { align16 1Q compacted }; mad(8) g49<1>F g46<4,4,1>F g70<4,4,1>F g75<4,4,1>F { align16 1Q compacted }; mad(8) g57<1>F g53<4,4,1>F g90<4,4,1>F g96<4,4,1>F { align16 1Q compacted }; add(8) g126<1>F g34<8,8,1>F g123<8,8,1>F { align1 1Q compacted }; mad(8) g65<1>F g62<4,4,1>F g111<4,4,1>F g116<4,4,1>F { align16 1Q compacted }; add(8) g2<1>F g36<8,8,1>F g125<8,8,1>F { align1 1Q compacted }; mad(8) g66<1>F g63<4,4,1>F g111<4,4,1>F g117<4,4,1>F { align16 1Q compacted }; mad(8) g67<1>F g64<4,4,1>F g111<4,4,1>F g118<4,4,1>F { align16 1Q compacted }; add(8) g127<1>F g35<8,8,1>F g124<8,8,1>F { align1 1Q compacted }; add(8) g46<1>F g126<8,8,1>F g43<8,8,1>F { align1 1Q compacted }; add(8) g48<1>F g2<8,8,1>F g45<8,8,1>F { align1 1Q compacted }; add(8) g47<1>F g127<8,8,1>F g44<8,8,1>F { align1 1Q compacted }; add(8) g52<1>F g46<8,8,1>F g49<8,8,1>F { align1 1Q compacted }; add(8) g54<1>F g48<8,8,1>F g51<8,8,1>F { align1 1Q compacted }; add(8) g53<1>F g47<8,8,1>F g50<8,8,1>F { align1 1Q compacted }; add(8) g59<1>F g52<8,8,1>F g56<8,8,1>F { align1 1Q compacted }; add(8) g61<1>F g54<8,8,1>F g58<8,8,1>F { align1 1Q compacted }; add(8) g60<1>F g53<8,8,1>F g57<8,8,1>F { align1 1Q compacted }; add(8) g68<1>F g59<8,8,1>F g65<8,8,1>F { align1 1Q compacted }; add(8) g70<1>F g61<8,8,1>F g67<8,8,1>F { align1 1Q compacted }; add(8) g69<1>F g60<8,8,1>F g66<8,8,1>F { align1 1Q compacted }; add(8) g25<1>F g25<8,8,1>F g68<8,8,1>F { align1 1Q compacted }; add(8) g27<1>F g27<8,8,1>F g70<8,8,1>F { align1 1Q compacted }; add(8) g26<1>F g26<8,8,1>F g69<8,8,1>F { align1 1Q compacted }; while(8) JIP: -3464 { align1 1Q }; END B2 ->B1 START B3 <-B1 (48 cycles) mul(8) g71<1>F g25<8,8,1>F 0.125F { align1 1Q }; mul(8) g72<1>F g26<8,8,1>F 0.125F { align1 1Q }; mul(8) g73<1>F g27<8,8,1>F 0.125F { align1 1Q }; mov(1) g24.2<1>F 0.01875F { align1 WE_all 1N }; mov(8) g127<1>F 1F { align1 1Q }; mad(8) g124<1>F g71<4,4,1>F g28<4,4,1>F g24.2<0,1,0>F { align16 1Q }; mad(8) g125<1>F g72<4,4,1>F g29<4,4,1>F g24.2<0,1,0>F { align16 1Q }; mad(8) g126<1>F g73<4,4,1>F g30<4,4,1>F g24.2<0,1,0>F { align16 1Q }; sendc(8) null<1>UW g124<8,8,1>F render RT write SIMD8 LastRT Surface = 0 mlen 4 rlen 0 { align1 1Q EOT }; nop ; END B3 deferredmultisampling: compiler/brw_fs_generator.cpp:2107: int fs_generator::generate_code(const cfg_t*, int): Assertion `validated' failed.