NIR (SSA form) for fragment shader: NIR (SSA form) for fragment shader: shader: MESA_SHADER_FRAGMENT shader: MESA_SHADER_FRAGMENT name: GLSL1 name: GLSL1 inputs: 0 inputs: 0 outputs: 0 outputs: 0 uniforms: 20 uniforms: 20 shared: 0 shared: 0 decl_var uniform INTERP_MODE_NONE float _MaxRadiusOrKInPaper (1, 0, 0) decl_var uniform INTERP_MODE_NONE float _MaxRadiusOrKInPaper (1, 0, 0) decl_var uniform INTERP_MODE_NONE sampler2D _MainTex (2, 4, 0) decl_var uniform INTERP_MODE_NONE sampler2D _MainTex (2, 4, 0) decl_var uniform INTERP_MODE_NONE vec4 _MainTex_TexelSize (3, 4, 0) decl_var uniform INTERP_MODE_NONE vec4 _MainTex_TexelSize (3, 4, 0) decl_var shader_in INTERP_MODE_SMOOTH float packed:xlv_TEXCOORD0 (VARYING_SLOT_VAR0.x, 31, 0) decl_var shader_in INTERP_MODE_SMOOTH float packed:xlv_TEXCOORD0 (VARYING_SLOT_VAR0.x, 31, 0) decl_var shader_in INTERP_MODE_SMOOTH float packed:xlv_TEXCOORD0@0 (VARYING_SLOT_VAR0.y, 31, 0) decl_var shader_in INTERP_MODE_SMOOTH float packed:xlv_TEXCOORD0@0 (VARYING_SLOT_VAR0.y, 31, 0) decl_var shader_out INTERP_MODE_NONE vec4 gl_out_FragData0 (FRAG_RESULT_DATA0, 8, 0) decl_var shader_out INTERP_MODE_NONE vec4 gl_out_FragData0 (FRAG_RESULT_DATA0, 8, 0) decl_function main (0 params) decl_function main (0 params) impl main { impl main { block block_0: block block_0: /* preds: */ /* preds: */ vec1 32 ssa_0 = undefined vec1 32 ssa_0 = undefined vec1 32 ssa_1 = load_const (0x3f000000 /* 0.500000 */) vec1 32 ssa_1 = load_const (0x3f000000 /* 0.500000 */) vec1 32 ssa_2 = load_const (0xbf000000 /* -0.500000 */) vec1 32 ssa_2 = load_const (0xbf000000 /* -0.500000 */) vec1 32 ssa_3 = load_const (0xbf800000 /* -1.000000 */) vec1 32 ssa_3 = load_const (0xbf800000 /* -1.000000 */) vec1 32 ssa_4 = load_const (0x00000000 /* 0.000000 */) vec1 32 ssa_4 = load_const (0x00000000 /* 0.000000 */) vec1 32 ssa_5 = load_const (0x00000001 /* 0.000000 */) vec1 32 ssa_5 = load_const (0x00000001 /* 0.000000 */) vec2 32 ssa_6 = intrinsic load_barycentric_pixel () (1) /* interp_mode=1 */ vec2 32 ssa_6 = intrinsic load_barycentric_pixel () (1) /* interp_mode=1 */ vec1 32 ssa_7 = intrinsic load_interpolated_input (ssa_6, ssa_4) (31, 0) /* base=31 */ / vec1 32 ssa_7 = intrinsic load_interpolated_input (ssa_6, ssa_4) (31, 0) /* base=31 */ / vec1 32 ssa_8 = intrinsic load_interpolated_input (ssa_6, ssa_4) (31, 1) /* base=31 */ / vec1 32 ssa_8 = intrinsic load_interpolated_input (ssa_6, ssa_4) (31, 1) /* base=31 */ / vec4 32 ssa_9 = intrinsic load_uniform (ssa_4) (4, 16) /* base=4 */ /* range=16 */ vec4 32 ssa_9 = intrinsic load_uniform (ssa_4) (4, 16) /* base=4 */ /* range=16 */ vec1 32 ssa_10 = intrinsic load_uniform (ssa_4) (0, 4) /* base=0 */ /* range=4 */ vec1 32 ssa_10 = intrinsic load_uniform (ssa_4) (0, 4) /* base=0 */ /* range=4 */ vec1 32 ssa_11 = fmul ssa_10, ssa_1 vec1 32 ssa_11 = fmul ssa_10, ssa_1 vec1 32 ssa_12 = fadd ssa_11, ssa_2 vec1 32 ssa_12 = fadd ssa_11, ssa_2 vec1 32 ssa_13 = ffma -ssa_9.x, ssa_12, ssa_7 vec1 32 ssa_13 = ffma -ssa_9.x, ssa_12, ssa_7 vec1 32 ssa_14 = ffma -ssa_9.y, ssa_12, ssa_8 vec1 32 ssa_14 = ffma -ssa_9.y, ssa_12, ssa_8 vec2 32 ssa_15 = vec2 ssa_13, ssa_14 vec2 32 ssa_15 = vec2 ssa_13, ssa_14 vec4 32 ssa_16 = tex ssa_15 (coord), 0 (texture), 0 (sampler), vec4 32 ssa_16 = tex ssa_15 (coord), 0 (texture), 0 (sampler), vec1 32 ssa_17 = imov ssa_16.x vec1 32 ssa_17 = imov ssa_16.x vec1 32 ssa_18 = imov ssa_16.y vec1 32 ssa_18 = imov ssa_16.y > vec1 32 ssa_19 = undefined > vec1 32 ssa_20 = undefined /* succs: block_1 */ /* succs: block_1 */ loop { loop { block block_1: block block_1: /* preds: block_0 block_4 */ /* preds: block_0 block_4 */ vec1 32 ssa_19 = phi block_0: ssa_0, block_4: ssa_46 | vec1 32 ssa_21 = phi block_0: ssa_0, block_4: ssa_48 vec1 32 ssa_20 = phi block_0: ssa_17, block_4: ssa_44 | vec1 32 ssa_22 = phi block_0: ssa_17, block_4: ssa_46 vec1 32 ssa_21 = phi block_0: ssa_18, block_4: ssa_45 | vec1 32 ssa_23 = phi block_0: ssa_18, block_4: ssa_47 vec1 32 ssa_22 = fadd ssa_10, ssa_3 | vec1 32 ssa_24 = phi block_0: ssa_19, block_4: ssa_49 vec1 32 ssa_23 = f2i32 ssa_22 | vec1 32 ssa_25 = phi block_0: ssa_20, block_4: ssa_50 vec1 32 ssa_24 = i2f32 ssa_23 | vec1 32 ssa_26 = fadd ssa_10, ssa_3 vec1 32 ssa_25 = fmul ssa_24, ssa_22 | vec1 32 ssa_27 = f2i32 ssa_26 vec1 32 ssa_26 = i2f32 ssa_19 | vec1 32 ssa_28 = i2f32 ssa_27 vec1 32 ssa_27 = flt32 ssa_25, ssa_26 | vec1 32 ssa_29 = fmul ssa_28, ssa_26 /* succs: block_2 block_3 */ /* succs: block_2 block_3 */ if ssa_27 { | if ssa_25 { block block_2: block block_2: /* preds: block_1 */ /* preds: block_1 */ break break /* succs: block_5 */ /* succs: block_5 */ } else { } else { block block_3: block block_3: /* preds: block_1 */ /* preds: block_1 */ /* succs: block_4 */ /* succs: block_4 */ } } block block_4: block block_4: /* preds: block_3 */ /* preds: block_3 */ vec1 32 ssa_28 = frcp ssa_10 | vec1 32 ssa_30 = frcp ssa_10 vec1 32 ssa_29 = fmul ssa_26, ssa_28 | vec1 32 ssa_31 = fmul ssa_24, ssa_30 vec1 32 ssa_30 = ffract ssa_29 | vec1 32 ssa_32 = ffract ssa_31 vec1 32 ssa_31 = fmul ssa_30, ssa_10 | vec1 32 ssa_33 = fmul ssa_32, ssa_10 vec1 32 ssa_32 = f2i32 ssa_10 | vec1 32 ssa_34 = f2i32 ssa_10 vec1 32 ssa_33 = idiv ssa_19, ssa_32 | vec1 32 ssa_35 = idiv ssa_21, ssa_34 vec1 32 ssa_34 = i2f32 ssa_33 | vec1 32 ssa_36 = i2f32 ssa_35 vec1 32 ssa_35 = ffma ssa_31, ssa_9.x, ssa_13 | vec1 32 ssa_37 = ffma ssa_33, ssa_9.x, ssa_13 vec1 32 ssa_36 = ffma ssa_34, ssa_9.y, ssa_14 | vec1 32 ssa_38 = ffma ssa_36, ssa_9.y, ssa_14 vec2 32 ssa_37 = vec2 ssa_35, ssa_36 | vec2 32 ssa_39 = vec2 ssa_37, ssa_38 vec4 32 ssa_38 = txl ssa_37 (coord), ssa_4 (lod), 0 (texture), 0 (sampler), | vec4 32 ssa_40 = txl ssa_39 (coord), ssa_4 (lod), 0 (texture), 0 (sampler), vec1 32 ssa_39 = fmul ssa_21, ssa_21 | vec1 32 ssa_41 = fmul ssa_23, ssa_23 vec1 32 ssa_40 = ffma ssa_20, ssa_20, ssa_39 | vec1 32 ssa_42 = ffma ssa_22, ssa_22, ssa_41 vec1 32 ssa_41 = fmul ssa_38.y, ssa_38.y | vec1 32 ssa_43 = fmul ssa_40.y, ssa_40.y vec1 32 ssa_42 = ffma ssa_38.x, ssa_38.x, ssa_41 | vec1 32 ssa_44 = ffma ssa_40.x, ssa_40.x, ssa_43 vec1 32 ssa_43 = flt32 ssa_42, ssa_40 | vec1 32 ssa_45 = flt32 ssa_44, ssa_42 vec1 32 ssa_44 = b32csel ssa_43, ssa_20, ssa_38.x | vec1 32 ssa_46 = b32csel ssa_45, ssa_22, ssa_40.x vec1 32 ssa_45 = b32csel ssa_43, ssa_21, ssa_38.y | vec1 32 ssa_47 = b32csel ssa_45, ssa_23, ssa_40.y vec1 32 ssa_46 = iadd ssa_19, ssa_5 | vec1 32 ssa_48 = iadd ssa_21, ssa_5 > vec1 32 ssa_49 = i2f32 ssa_48 > vec1 32 ssa_50 = flt32 ssa_29, ssa_49 /* succs: block_1 */ /* succs: block_1 */ } } block block_5: block block_5: /* preds: block_2 */ /* preds: block_2 */ vec4 32 ssa_47 = vec4 ssa_20, ssa_21, ssa_4, ssa_4 | vec4 32 ssa_51 = vec4 ssa_22, ssa_23, ssa_4, ssa_4 intrinsic store_output (ssa_47, ssa_4) (8, 15, 0) /* base=8 */ /* wrmask=xyzw */ /* comp | intrinsic store_output (ssa_51, ssa_4) (8, 15, 0) /* base=8 */ /* wrmask=xyzw */ /* comp /* succs: block_6 */ /* succs: block_6 */ block block_6: block block_6: } } Native code for unnamed fragment shader GLSL1 Native code for unnamed fragment shader GLSL1 SIMD8 shader: 36 instructions. 1 loops. 4400 cycles. 0:0 spills:fills. Promoted 0 constants. Com | SIMD8 shader: 37 instructions. 1 loops. 4260 cycles. 0:0 spills:fills. Promoted 0 constants. Com START B0 (60 cycles) START B0 (60 cycles) pln(8) g6<1>F g5<0,1,0>F g2<8,8,1>F { align1 1Q compacted }; pln(8) g6<1>F g5<0,1,0>F g2<8,8,1>F { align1 1Q compacted }; pln(8) g18<1>F g5.4<0,1,0>F g2<8,8,1>F { align1 1Q compacted }; | pln(8) g7<1>F g5.4<0,1,0>F g2<8,8,1>F { align1 1Q compacted }; mul(8) g8<1>F g4<0,1,0>F 0x3f000000F /* 0.5F */ { align1 1Q }; mul(8) g8<1>F g4<0,1,0>F 0x3f000000F /* 0.5F */ { align1 1Q }; add(8) g9<1>F g8<8,8,1>F 0xbf000000F /* -0.5F */ { align1 1Q }; | add(8) g11<1>F g8<8,8,1>F 0xbf000000F /* -0.5F */ { align1 1Q }; mad(8) g26<1>F g6<4,4,1>F g9<4,4,1>F -g4.1<0,1,0>F { align16 1Q }; | mad(8) g25<1>F g6<4,4,1>F g11<4,4,1>F -g4.1<0,1,0>F { align16 1Q }; mad(8) g27<1>F g18<4,4,1>F g9<4,4,1>F -g4.2<0,1,0>F { align16 1Q }; | mad(8) g26<1>F g7<4,4,1>F g11<4,4,1>F -g4.2<0,1,0>F { align16 1Q }; send(8) g124<1>UW g26<0,1,0>F 0x04220001 | send(8) g124<1>UW g25<0,1,0>F 0x04220001 sampler MsgDesc: sample SIMD8 Surface = 1 Sampler = 0 mlen 2 rlen 2 sampler MsgDesc: sample SIMD8 Surface = 1 Sampler = 0 mlen 2 rlen 2 END B0 ->B1 END B0 ->B1 START B2 <-B1 <-B3 (82 cycles) | START B2 <-B1 <-B3 (52 cycles) add(8) g10<1>F g4<0,1,0>F 0xbf800000F /* -1F */ { align1 1Q }; add(8) g10<1>F g4<0,1,0>F 0xbf800000F /* -1F */ { align1 1Q }; END B1 ->B2 ->B4 END B1 ->B2 ->B4 mov(8) g14<1>F g2<8,8,1>D { align1 1Q compacted }; | mov.nz.f0.0(8) null<1>D g5<8,8,1>D { align1 1Q }; mov(8) g11<1>D g10<8,8,1>F { align1 1Q compacted }; | mov(8) g20<1>D g10<8,8,1>F { align1 1Q compacted }; mov(8) g12<1>F g11<8,8,1>D { align1 1Q compacted }; | mov(8) g12<1>F g20<8,8,1>D { align1 1Q compacted }; mul(8) g13<1>F g12<8,8,1>F g10<8,8,1>F { align1 1Q compacted }; mul(8) g13<1>F g12<8,8,1>F g10<8,8,1>F { align1 1Q compacted }; cmp.l.f0.0(8) null<1>F g13<8,8,1>F g14<8,8,1>F { align1 1Q compacted }; | (+f0.0) break(8) JIP: 200 UIP: 200 { align1 1Q }; (+f0.0) break(8) JIP: 184 UIP: 184 { align1 1Q }; < END B2 ->B1 ->B3 END B2 ->B1 ->B3 START B3 <-B2 (348 cycles) | START B3 <-B2 (364 cycles) math inv(8) g15<1>F g4<0,1,0>F null<8,8,1>F { align1 1Q compacted }; | math inv(8) g14<1>F g4<0,1,0>F null<8,8,1>F { align1 1Q compacted }; mov(8) g19<1>D g4<0,1,0>F { align1 1Q compacted }; | mov(8) g18<1>D g4<0,1,0>F { align1 1Q compacted }; mul(8) g22<1>F g125<8,8,1>F g125<8,8,1>F { align1 1Q compacted }; | mul(8) g21<1>F g125<8,8,1>F g125<8,8,1>F { align1 1Q compacted }; math intdiv(8) g20<1>D g2<8,8,1>D g19<8,8,1>D { align1 1Q compacted }; | math intdiv(8) g19<1>D g2<8,8,1>D g18<8,8,1>D { align1 1Q compacted }; mul(8) g16<1>F g14<8,8,1>F g15<8,8,1>F { align1 1Q compacted }; | mul(8) g15<1>F g3<8,8,1>F g14<8,8,1>F { align1 1Q compacted }; add(8) g2<1>D g2<8,8,1>D 1D { align1 1Q compacted }; add(8) g2<1>D g2<8,8,1>D 1D { align1 1Q compacted }; mad(8) g23<1>F g22<4,4,1>F g124<4,4,1>F g124<4,4,1>F { align16 1Q compac | mad(8) g22<1>F g21<4,4,1>F g124<4,4,1>F g124<4,4,1>F { align16 1Q compac mov(8) g21<1>F g20<8,8,1>D { align1 1Q compacted }; | mov(8) g9<1>F g19<8,8,1>D { align1 1Q compacted }; frc(8) g17<1>F g16<8,8,1>F { align1 1Q compacted }; | frc(8) g16<1>F g15<8,8,1>F { align1 1Q compacted }; mad(8) g29<1>F g27<4,4,1>F g4.2<0,1,0>F g21<4,4,1>F { align16 1Q }; | mov(8) g3<1>F g2<8,8,1>D { align1 1Q compacted }; mul(8) g7<1>F g17<8,8,1>F g4<0,1,0>F { align1 1Q compacted }; | mad(8) g28<1>F g26<4,4,1>F g4.2<0,1,0>F g9<4,4,1>F { align16 1Q }; mad(8) g28<1>F g26<4,4,1>F g4.1<0,1,0>F g7<4,4,1>F { align16 1Q }; | mul(8) g17<1>F g16<8,8,1>F g4<0,1,0>F { align1 1Q compacted }; send(8) g5<1>UW g28<0,1,0>F 0x04238001 | mad(8) g27<1>F g25<4,4,1>F g4.1<0,1,0>F g17<4,4,1>F { align16 1Q }; > send(8) g6<1>UW g27<0,1,0>F 0x04238001 sampler MsgDesc: sample_lz SIMD8 Surface = 1 Sampler = 0 mlen 2 rlen sampler MsgDesc: sample_lz SIMD8 Surface = 1 Sampler = 0 mlen 2 rlen mul(8) g24<1>F g6<8,8,1>F g6<8,8,1>F { align1 1Q compacted }; | mul(8) g23<1>F g7<8,8,1>F g7<8,8,1>F { align1 1Q compacted }; mad(8) g25<1>F g24<4,4,1>F g5<4,4,1>F g5<4,4,1>F { align16 1Q compacte | mad(8) g24<1>F g23<4,4,1>F g6<4,4,1>F g6<4,4,1>F { align16 1Q compacte cmp.l.f0.0(8) null<1>F g25<8,8,1>F g23<8,8,1>F { align1 1Q compacted }; | cmp.l.f0.0(8) null<1>F g24<8,8,1>F g22<8,8,1>F { align1 1Q compacted }; (+f0.0) sel(8) g124<1>UD g124<8,8,1>UD g5<8,8,1>UD { align1 1Q compacted }; | (+f0.0) sel(8) g124<1>UD g124<8,8,1>UD g6<8,8,1>UD { align1 1Q compacted }; (+f0.0) sel(8) g125<1>UD g125<8,8,1>UD g6<8,8,1>UD { align1 1Q compacted }; | (+f0.0) sel(8) g125<1>UD g125<8,8,1>UD g7<8,8,1>UD { align1 1Q compacted }; while(8) JIP: -240 { align1 1Q }; | cmp.l.f0.0(8) g5<1>F g13<8,8,1>F g3<8,8,1>F { align1 1Q compacted }; > while(8) JIP: -256 { align1 1Q }; END B3 ->B2 END B3 ->B2 START B4 <-B1 (20 cycles) START B4 <-B1 (20 cycles) mov(8) g126<1>F 0x0VF /* [0F, 0F, 0F, 0F]VF */ { align1 1Q compacted } mov(8) g126<1>F 0x0VF /* [0F, 0F, 0F, 0F]VF */ { align1 1Q compacted } mov(8) g127<1>F 0x0VF /* [0F, 0F, 0F, 0F]VF */ { align1 1Q compacted } mov(8) g127<1>F 0x0VF /* [0F, 0F, 0F, 0F]VF */ { align1 1Q compacted } sendc(8) null<1>UW g124<0,1,0>F 0x88031400 sendc(8) null<1>UW g124<0,1,0>F 0x88031400 render MsgDesc: RT write SIMD8 LastRT Surface = 0 mlen 4 rlen 0 { al render MsgDesc: RT write SIMD8 LastRT Surface = 0 mlen 4 rlen 0 { al END B4 END B4 Native code for unnamed fragment shader GLSL1 Native code for unnamed fragment shader GLSL1 SIMD16 shader: 37 instructions. 1 loops. 4784 cycles. 0:0 spills:fills. Promoted 0 constants. Co | SIMD16 shader: 38 instructions. 1 loops. 4644 cycles. 0:0 spills:fills. Promoted 0 constants. Co START B0 (78 cycles) START B0 (78 cycles) pln(16) g8<1>F g7<0,1,0>F g2<8,8,1>F { align1 1H compacted }; | pln(16) g12<1>F g7<0,1,0>F g2<8,8,1>F { align1 1H compacted }; pln(16) g10<1>F g7.4<0,1,0>F g2<8,8,1>F { align1 1H compacted }; | pln(16) g14<1>F g7.4<0,1,0>F g2<8,8,1>F { align1 1H compacted }; mul(16) g12<1>F g6<0,1,0>F 0x3f000000F /* 0.5F */ { align1 1H }; | mul(16) g16<1>F g6<0,1,0>F 0x3f000000F /* 0.5F */ { align1 1H }; add(16) g14<1>F g12<8,8,1>F 0xbf000000F /* -0.5F */ { align1 1H }; | add(16) g18<1>F g16<8,8,1>F 0xbf000000F /* -0.5F */ { align1 1H }; mad(16) g2<1>F g8<4,4,1>F g14<4,4,1>F -g6.1<0,1,0>F { align16 1H }; | mad(16) g2<1>F g12<4,4,1>F g18<4,4,1>F -g6.1<0,1,0>F { align16 1H }; mad(16) g4<1>F g10<4,4,1>F g14<4,4,1>F -g6.2<0,1,0>F { align16 1H }; | mad(16) g4<1>F g14<4,4,1>F g18<4,4,1>F -g6.2<0,1,0>F { align16 1H }; send(16) g120<1>UW g2<0,1,0>F 0x08440001 send(16) g120<1>UW g2<0,1,0>F 0x08440001 sampler MsgDesc: sample SIMD16 Surface = 1 Sampler = 0 mlen 4 rlen 4 sampler MsgDesc: sample SIMD16 Surface = 1 Sampler = 0 mlen 4 rlen 4 END B0 ->B1 END B0 ->B1 START B2 <-B1 <-B3 (94 cycles) | START B2 <-B1 <-B3 (62 cycles) add(16) g15<1>F g6<0,1,0>F 0xbf800000F /* -1F */ { align1 1H }; | add(16) g19<1>F g6<0,1,0>F 0xbf800000F /* -1F */ { align1 1H }; END B1 ->B2 ->B4 END B1 ->B2 ->B4 mov(16) g23<1>F g7<8,8,1>D { align1 1H compacted }; | mov.nz.f0.0(16) null<1>D g11<8,8,1>D { align1 1H }; mov(16) g17<1>D g15<8,8,1>F { align1 1H compacted }; | mov(16) g21<1>D g19<8,8,1>F { align1 1H compacted }; mov(16) g19<1>F g17<8,8,1>D { align1 1H compacted }; | mov(16) g23<1>F g21<8,8,1>D { align1 1H compacted }; mul(16) g21<1>F g19<8,8,1>F g15<8,8,1>F { align1 1H compacted }; | mul(16) g25<1>F g23<8,8,1>F g19<8,8,1>F { align1 1H compacted }; cmp.l.f0.0(16) null<1>F g21<8,8,1>F g23<8,8,1>F { align1 1H compacted }; | (+f0.0) break(16) JIP: 208 UIP: 208 { align1 1H }; (+f0.0) break(16) JIP: 192 UIP: 192 { align1 1H }; < END B2 ->B1 ->B3 END B2 ->B1 ->B3 START B3 <-B2 (370 cycles) | START B3 <-B2 (388 cycles) math inv(16) g25<1>F g6<0,1,0>F null<8,8,1>F { align1 1H compacted }; | math inv(16) g27<1>F g6<0,1,0>F null<8,8,1>F { align1 1H compacted }; mov(16) g32<1>D g6<0,1,0>F { align1 1H compacted }; | mov(16) g34<1>D g6<0,1,0>F { align1 1H compacted }; mul(16) g37<1>F g122<8,8,1>F g122<8,8,1>F { align1 1H compacted }; | mul(16) g39<1>F g122<8,8,1>F g122<8,8,1>F { align1 1H compacted }; mul(16) g27<1>F g23<8,8,1>F g25<8,8,1>F { align1 1H compacted }; | mul(16) g29<1>F g9<8,8,1>F g27<8,8,1>F { align1 1H compacted }; math intdiv(8) g34<1>D g7<8,8,1>D g32<8,8,1>D { align1 1Q compacted }; | math intdiv(8) g36<1>D g7<8,8,1>D g34<8,8,1>D { align1 1Q compacted }; math intdiv(8) g35<1>D g8<8,8,1>D g33<8,8,1>D { align1 2Q compacted }; | math intdiv(8) g37<1>D g8<8,8,1>D g35<8,8,1>D { align1 2Q compacted }; mad(16) g39<1>F g37<4,4,1>F g120<4,4,1>F g120<4,4,1>F { align16 1H compac | mad(16) g41<1>F g39<4,4,1>F g120<4,4,1>F g120<4,4,1>F { align16 1H compac add(16) g7<1>D g7<8,8,1>D 1D { align1 1H compacted }; add(16) g7<1>D g7<8,8,1>D 1D { align1 1H compacted }; frc(16) g29<1>F g27<8,8,1>F { align1 1H compacted }; | frc(16) g31<1>F g29<8,8,1>F { align1 1H compacted }; mov(16) g36<1>F g34<8,8,1>D { align1 1H compacted }; | mov(16) g38<1>F g36<8,8,1>D { align1 1H compacted }; mul(16) g31<1>F g29<8,8,1>F g6<0,1,0>F { align1 1H compacted }; | mov(16) g9<1>F g7<8,8,1>D { align1 1H compacted }; mad(16) g15<1>F g4<4,4,1>F g6.2<0,1,0>F g36<4,4,1>F { align16 1H }; | mul(16) g33<1>F g31<8,8,1>F g6<0,1,0>F { align1 1H compacted }; mad(16) g13<1>F g2<4,4,1>F g6.1<0,1,0>F g31<4,4,1>F { align16 1H }; | mad(16) g19<1>F g4<4,4,1>F g6.2<0,1,0>F g38<4,4,1>F { align16 1H }; send(16) g9<1>UW g13<0,1,0>F 0x08458001 | mad(16) g17<1>F g2<4,4,1>F g6.1<0,1,0>F g33<4,4,1>F { align16 1H }; > send(16) g13<1>UW g17<0,1,0>F 0x08458001 sampler MsgDesc: sample_lz SIMD16 Surface = 1 Sampler = 0 mlen 4 rle sampler MsgDesc: sample_lz SIMD16 Surface = 1 Sampler = 0 mlen 4 rle mul(16) g41<1>F g11<8,8,1>F g11<8,8,1>F { align1 1H compacted }; | mul(16) g43<1>F g15<8,8,1>F g15<8,8,1>F { align1 1H compacted }; mad(16) g43<1>F g41<4,4,1>F g9<4,4,1>F g9<4,4,1>F { align16 1H compacte | mad(16) g45<1>F g43<4,4,1>F g13<4,4,1>F g13<4,4,1>F { align16 1H compact cmp.l.f0.0(16) null<1>F g43<8,8,1>F g39<8,8,1>F { align1 1H compacted }; | cmp.l.f0.0(16) null<1>F g45<8,8,1>F g41<8,8,1>F { align1 1H compacted }; (+f0.0) sel(16) g120<1>UD g120<8,8,1>UD g9<8,8,1>UD { align1 1H compacted }; | (+f0.0) sel(16) g120<1>UD g120<8,8,1>UD g13<8,8,1>UD { align1 1H compacted }; (+f0.0) sel(16) g122<1>UD g122<8,8,1>UD g11<8,8,1>UD { align1 1H compacted }; | (+f0.0) sel(16) g122<1>UD g122<8,8,1>UD g15<8,8,1>UD { align1 1H compacted }; while(16) JIP: -248 { align1 1H }; | cmp.l.f0.0(16) g11<1>F g25<8,8,1>F g9<8,8,1>F { align1 1H compacted }; > while(16) JIP: -264 { align1 1H }; END B3 ->B2 END B3 ->B2 START B4 <-B1 (26 cycles) START B4 <-B1 (26 cycles) mov(16) g124<1>F 0x0VF /* [0F, 0F, 0F, 0F]VF */ { align1 1H compacted } mov(16) g124<1>F 0x0VF /* [0F, 0F, 0F, 0F]VF */ { align1 1H compacted } mov(16) g126<1>F 0x0VF /* [0F, 0F, 0F, 0F]VF */ { align1 1H compacted } mov(16) g126<1>F 0x0VF /* [0F, 0F, 0F, 0F]VF */ { align1 1H compacted } sendc(16) null<1>UW g120<0,1,0>F 0x90031000 sendc(16) null<1>UW g120<0,1,0>F 0x90031000 render MsgDesc: RT write SIMD16 LastRT Surface = 0 mlen 8 rlen 0 { a render MsgDesc: RT write SIMD16 LastRT Surface = 0 mlen 8 rlen 0 { a END B4 END B4