Thanks for using Compiler Explorer
Sponsors
Jakt
C++
Ada
Analysis
Android Java
Android Kotlin
Assembly
C
C3
Carbon
C++ (Circle)
CIRCT
Clean
CMake
CMakeScript
COBOL
C++ for OpenCL
MLIR
Cppx
Cppx-Blue
Cppx-Gold
Cpp2-cppfront
Crystal
C#
CUDA C++
D
Dart
Elixir
Erlang
Fortran
F#
Go
Haskell
HLSL
Hook
Hylo
ispc
Java
Julia
Kotlin
LLVM IR
LLVM MIR
Modula-2
Nim
Objective-C
Objective-C++
OCaml
OpenCL C
Pascal
Pony
Python
Racket
Ruby
Rust
Snowball
Scala
Solidity
Spice
Swift
LLVM TableGen
Toit
TypeScript Native
V
Vala
Visual Basic
Zig
Javascript
GIMPLE
llvm source #1
Output
Compile to binary object
Link to binary
Execute the code
Intel asm syntax
Demangle identifiers
Verbose demangling
Filters
Unused labels
Library functions
Directives
Comments
Horizontal whitespace
Debug intrinsics
Compiler
clang (assertions trunk)
clang (trunk)
clang 10.0.0
clang 10.0.1
clang 11.0.0
clang 11.0.1
clang 12.0.0
clang 12.0.1
clang 13.0.0
clang 14.0.0
clang 15.0.0
clang 16.0.0
clang 17.0.1
clang 18.1.0
clang 4.0.1
clang 5.0.0
clang 6.0.0
clang 7.0.0
clang 8.0.0
clang 9.0.0
llc (assertions trunk)
llc (trunk)
llc 10.0.0
llc 10.0.1
llc 11.0.0
llc 11.0.1
llc 12.0.0
llc 12.0.1
llc 13.0.0
llc 14.0.0
llc 15.0.0
llc 16.0.0
llc 17.0.1
llc 18.1.0
llc 3.2
llc 3.3
llc 3.9.1
llc 4.0.0
llc 4.0.1
llc 5.0.0
llc 6.0.0
llc 7.0.0
llc 8.0.0
llc 9.0.0
opt (assertions trunk)
opt (trunk)
opt 10.0.0
opt 10.0.1
opt 11.0.0
opt 11.0.1
opt 12.0.0
opt 12.0.1
opt 13.0.0
opt 14.0.0
opt 15.0.0
opt 16.0.0
opt 17.0.1
opt 18.1.0
opt 3.2
opt 3.3
opt 3.9.1
opt 4.0.0
opt 4.0.1
opt 5.0.0
opt 6.0.0
opt 7.0.0
opt 8.0.0
opt 9.0.0
Options
Source code
define void @"julia__avx_!_9613"([2 x <8 x double>]* noalias nocapture sret %0, { [1 x { i64 }], { { [4 x i64] }, double, double } }* nocapture nonnull readonly align 8 dereferenceable(56) %1) { top: %2 = getelementptr inbounds { [1 x { i64 }], { { [4 x i64] }, double, double } }, { [1 x { i64 }], { { [4 x i64] }, double, double } }* %1, i64 0, i32 0, i64 0, i32 0 %3 = load i64, i64* %2, align 8 %4 = icmp sgt i64 %3, 0 call void @llvm.assume(i1 %4) %5 = getelementptr inbounds { [1 x { i64 }], { { [4 x i64] }, double, double } }, { [1 x { i64 }], { { [4 x i64] }, double, double } }* %1, i64 0, i32 1, i32 0, i32 0, i64 2 %6 = getelementptr inbounds { [1 x { i64 }], { { [4 x i64] }, double, double } }, { [1 x { i64 }], { { [4 x i64] }, double, double } }* %1, i64 0, i32 1, i32 0, i32 0, i64 3 %7 = bitcast i64* %5 to double** %8 = load double*, double** %7, align 8 %res.i159 = shl nuw i64 %3, 1 %indname.i = add i64 %res.i159, -32 %ptr.1.i157 = getelementptr inbounds double, double* %8, i64 %indname.i %ptr.1.i154 = getelementptr inbounds double, double* %8, i64 %res.i159 %ptr.2.i155 = ptrtoint double* %ptr.1.i154 to i64 %ptr.1.i151 = getelementptr inbounds double, double* %ptr.1.i157, i64 16 %ptr.2.i152 = ptrtoint double* %ptr.1.i151 to i64 %9 = icmp ult i64 %3, 16 %10 = ptrtoint double* %8 to i64 %11 = load i64, i64* %6, align 8 br i1 %9, label %L93, label %L30.preheader L30.preheader: ; preds = %top %.not172 = icmp slt i64 %indname.i, 0 br i1 %.not172, label %L88, label %L61 L61: ; preds = %L61, %L30.preheader %value_phi20178 = phi <8 x double> [ %res.i118, %L61 ], [ zeroinitializer, %L30.preheader ] %value_phi19177 = phi <8 x double> [ %res.i119, %L61 ], [ zeroinitializer, %L30.preheader ] %value_phi16176 = phi <8 x double> [ %res.i124, %L61 ], [ zeroinitializer, %L30.preheader ] %value_phi15175 = phi <8 x double> [ %res.i125, %L61 ], [ zeroinitializer, %L30.preheader ] %value_phi9174 = phi i64 [ %ptr.2.i114, %L61 ], [ %11, %L30.preheader ] %value_phi173 = phi i64 [ %ptr.2.i117, %L61 ], [ %10, %L30.preheader ] %ptr.1.i148 = inttoptr i64 %value_phi173 to <16 x double>* %res.i149 = load <16 x double>, <16 x double>* %ptr.1.i148, align 8 %res.i147 = shufflevector <16 x double> %res.i149, <16 x double> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14> %res.i146 = shufflevector <16 x double> %res.i149, <16 x double> undef, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15> %ptr.0.i143 = inttoptr i64 %value_phi173 to double* %ptr.1.i144 = getelementptr inbounds double, double* %ptr.0.i143, i64 16 %ptr.1.i141 = bitcast double* %ptr.1.i144 to <16 x double>* %res.i142 = load <16 x double>, <16 x double>* %ptr.1.i141, align 8 %res.i140 = shufflevector <16 x double> %res.i142, <16 x double> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14> %res.i139 = shufflevector <16 x double> %res.i142, <16 x double> undef, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15> %ptr.1.i137 = inttoptr i64 %value_phi9174 to <16 x double>* %res.i138 = load <16 x double>, <16 x double>* %ptr.1.i137, align 8 %res.i136 = shufflevector <16 x double> %res.i138, <16 x double> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14> %res.i135 = shufflevector <16 x double> %res.i138, <16 x double> undef, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15> %ptr.0.i132 = inttoptr i64 %value_phi9174 to double* %ptr.1.i133 = getelementptr inbounds double, double* %ptr.0.i132, i64 16 %ptr.1.i130 = bitcast double* %ptr.1.i133 to <16 x double>* %res.i131 = load <16 x double>, <16 x double>* %ptr.1.i130, align 8 %res.i129 = shufflevector <16 x double> %res.i131, <16 x double> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14> %res.i128 = shufflevector <16 x double> %res.i131, <16 x double> undef, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15> %res.i127 = call nsz contract <8 x double> @llvm.fma.v8f64(<8 x double> %res.i146, <8 x double> %res.i135, <8 x double> %value_phi15175) %res.i126 = call nsz contract <8 x double> @llvm.fma.v8f64(<8 x double> %res.i139, <8 x double> %res.i128, <8 x double> %value_phi16176) %res.i125 = call nsz contract <8 x double> @llvm.fma.v8f64(<8 x double> %res.i147, <8 x double> %res.i136, <8 x double> %res.i127) %res.i124 = call nsz contract <8 x double> @llvm.fma.v8f64(<8 x double> %res.i140, <8 x double> %res.i129, <8 x double> %res.i126) %res.i123 = fneg nsz contract <8 x double> %res.i146 %res.i122 = call nsz contract <8 x double> @llvm.fma.v8f64(<8 x double> %res.i123, <8 x double> %res.i136, <8 x double> %value_phi19177) %res.i121 = fneg nsz contract <8 x double> %res.i139 %res.i120 = call nsz contract <8 x double> @llvm.fma.v8f64(<8 x double> %res.i121, <8 x double> %res.i129, <8 x double> %value_phi20178) %res.i119 = call nsz contract <8 x double> @llvm.fma.v8f64(<8 x double> %res.i147, <8 x double> %res.i135, <8 x double> %res.i122) %res.i118 = call nsz contract <8 x double> @llvm.fma.v8f64(<8 x double> %res.i140, <8 x double> %res.i128, <8 x double> %res.i120) %ptr.1.i116 = getelementptr inbounds double, double* %ptr.0.i143, i64 32 %ptr.2.i117 = ptrtoint double* %ptr.1.i116 to i64 %ptr.1.i113 = getelementptr inbounds double, double* %ptr.0.i132, i64 32 %ptr.2.i114 = ptrtoint double* %ptr.1.i113 to i64 %.not = icmp ugt double* %ptr.1.i116, %ptr.1.i157 br i1 %.not, label %L88, label %L61 L88: ; preds = %L61, %L30.preheader %value_phi.lcssa = phi i64 [ %10, %L30.preheader ], [ %ptr.2.i117, %L61 ] %value_phi9.lcssa = phi i64 [ %11, %L30.preheader ], [ %ptr.2.i114, %L61 ] %value_phi15.lcssa = phi <8 x double> [ zeroinitializer, %L30.preheader ], [ %res.i125, %L61 ] %value_phi16.lcssa = phi <8 x double> [ zeroinitializer, %L30.preheader ], [ %res.i124, %L61 ] %value_phi19.lcssa = phi <8 x double> [ zeroinitializer, %L30.preheader ], [ %res.i119, %L61 ] %value_phi20.lcssa = phi <8 x double> [ zeroinitializer, %L30.preheader ], [ %res.i118, %L61 ] %res.i111 = fadd nsz contract <8 x double> %value_phi15.lcssa, %value_phi16.lcssa %res.i110 = fadd nsz contract <8 x double> %value_phi19.lcssa, %value_phi20.lcssa br label %L93 L93: ; preds = %L88, %top %value_phi23 = phi i64 [ %value_phi.lcssa, %L88 ], [ %10, %top ] %value_phi29 = phi i64 [ %value_phi9.lcssa, %L88 ], [ %11, %top ] %value_phi33 = phi <8 x double> [ %res.i111, %L88 ], [ zeroinitializer, %top ] %value_phi34 = phi <8 x double> [ %res.i110, %L88 ], [ zeroinitializer, %top ] %value_phi29.ptr = inttoptr i64 %value_phi29 to double* %.not160162 = icmp ugt i64 %value_phi23, %ptr.2.i152 br i1 %.not160162, label %L151, label %L137.lr.ph L137.lr.ph: ; preds = %L93 %value_phi25.ptr = inttoptr i64 %value_phi23 to double* br label %L137 L137: ; preds = %L137, %L137.lr.ph %value_phi56.ptr168 = phi double* [ %value_phi29.ptr, %L137.lr.ph ], [ %ptr.1.i92, %L137 ] %value_phi55167 = phi i64 [ %value_phi29, %L137.lr.ph ], [ %ptr.2.i93, %L137 ] %value_phi51.ptr166 = phi double* [ %value_phi25.ptr, %L137.lr.ph ], [ %ptr.1.i95, %L137 ] %value_phi49165 = phi i64 [ %value_phi23, %L137.lr.ph ], [ %ptr.2.i96, %L137 ] %value_phi45164 = phi <8 x double> [ %value_phi34, %L137.lr.ph ], [ %res.i97, %L137 ] %value_phi41163 = phi <8 x double> [ %value_phi33, %L137.lr.ph ], [ %res.i100, %L137 ] %ptr.1.i108 = inttoptr i64 %value_phi49165 to <16 x double>* %res.i109 = load <16 x double>, <16 x double>* %ptr.1.i108, align 8 %res.i107 = shufflevector <16 x double> %res.i109, <16 x double> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14> %res.i106 = shufflevector <16 x double> %res.i109, <16 x double> undef, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15> %ptr.1.i104 = inttoptr i64 %value_phi55167 to <16 x double>* %res.i105 = load <16 x double>, <16 x double>* %ptr.1.i104, align 8 %res.i103 = shufflevector <16 x double> %res.i105, <16 x double> undef, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14> %res.i102 = shufflevector <16 x double> %res.i105, <16 x double> undef, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15> %res.i101 = call reassoc nsz arcp contract afn <8 x double> @llvm.fma.v8f64(<8 x double> %res.i106, <8 x double> %res.i102, <8 x double> %value_phi41163) %res.i100 = call reassoc nsz arcp contract afn <8 x double> @llvm.fma.v8f64(<8 x double> %res.i107, <8 x double> %res.i103, <8 x double> %res.i101) %res.i99 = fneg reassoc nsz arcp contract afn <8 x double> %res.i106 %res.i98 = call reassoc nsz arcp contract afn <8 x double> @llvm.fma.v8f64(<8 x double> %res.i99, <8 x double> %res.i103, <8 x double> %value_phi45164) %res.i97 = call reassoc nsz arcp contract afn <8 x double> @llvm.fma.v8f64(<8 x double> %res.i107, <8 x double> %res.i102, <8 x double> %res.i98) %ptr.1.i95 = getelementptr inbounds double, double* %value_phi51.ptr166, i64 16 %ptr.2.i96 = ptrtoint double* %ptr.1.i95 to i64 %ptr.1.i92 = getelementptr inbounds double, double* %value_phi56.ptr168, i64 16 %ptr.2.i93 = ptrtoint double* %ptr.1.i92 to i64 %.not160 = icmp ugt double* %value_phi51.ptr166, %ptr.1.i157 br i1 %.not160, label %L151, label %L137 L151: ; preds = %L137, %L93 %value_phi41.lcssa = phi <8 x double> [ %value_phi33, %L93 ], [ %res.i100, %L137 ] %value_phi45.lcssa = phi <8 x double> [ %value_phi34, %L93 ], [ %res.i97, %L137 ] %value_phi49.lcssa = phi i64 [ %value_phi23, %L93 ], [ %ptr.2.i96, %L137 ] %value_phi55.lcssa.ptr = phi double* [ %value_phi29.ptr, %L93 ], [ %ptr.1.i92, %L137 ] %.not161 = icmp ult i64 %value_phi49.lcssa, %ptr.2.i155 br i1 %.not161, label %L155, label %L180 L155: ; preds = %L151 %12 = trunc i64 %3 to i8 %13 = add i8 %12, 7 %14 = and i8 %13, 7 %15 = xor i8 %14, 7 %16 = lshr i8 -1, %15 %ptr.0.i86 = inttoptr i64 %value_phi49.lcssa to double* %ptr.1.i87 = getelementptr inbounds double, double* %ptr.0.i86, <8 x i64> <i64 0, i64 2, i64 4, i64 6, i64 8, i64 10, i64 12, i64 14> %mask.0.i88 = bitcast i8 %16 to <8 x i1> %res.i89 = call <8 x double> @llvm.masked.gather.v8f64.v8p0f64(<8 x double*> %ptr.1.i87, i32 8, <8 x i1> %mask.0.i88, <8 x double> zeroinitializer) %ptr.1.i82 = getelementptr inbounds double, double* %ptr.0.i86, i64 1 %ptr.2.i83 = getelementptr inbounds double, double* %ptr.1.i82, <8 x i64> <i64 0, i64 2, i64 4, i64 6, i64 8, i64 10, i64 12, i64 14> %res.i85 = call <8 x double> @llvm.masked.gather.v8f64.v8p0f64(<8 x double*> %ptr.2.i83, i32 8, <8 x i1> %mask.0.i88, <8 x double> zeroinitializer) %ptr.1.i78 = getelementptr inbounds double, double* %value_phi55.lcssa.ptr, <8 x i64> <i64 0, i64 2, i64 4, i64 6, i64 8, i64 10, i64 12, i64 14> %res.i80 = call <8 x double> @llvm.masked.gather.v8f64.v8p0f64(<8 x double*> %ptr.1.i78, i32 8, <8 x i1> %mask.0.i88, <8 x double> zeroinitializer) %ptr.1.i73 = getelementptr inbounds double, double* %value_phi55.lcssa.ptr, i64 1 %ptr.2.i74 = getelementptr inbounds double, double* %ptr.1.i73, <8 x i64> <i64 0, i64 2, i64 4, i64 6, i64 8, i64 10, i64 12, i64 14> %res.i76 = call <8 x double> @llvm.masked.gather.v8f64.v8p0f64(<8 x double*> %ptr.2.i74, i32 8, <8 x i1> %mask.0.i88, <8 x double> zeroinitializer) %res.i71 = call reassoc nsz arcp contract afn <8 x double> @llvm.fma.v8f64(<8 x double> %res.i85, <8 x double> %res.i76, <8 x double> %value_phi41.lcssa) %res.i70 = call reassoc nsz arcp contract afn <8 x double> @llvm.fma.v8f64(<8 x double> %res.i89, <8 x double> %res.i80, <8 x double> %res.i71) %res.i69 = select reassoc nsz arcp contract <8 x i1> %mask.0.i88, <8 x double> %res.i70, <8 x double> %value_phi41.lcssa %res.i67 = fneg reassoc nsz arcp contract afn <8 x double> %res.i85 %res.i66 = call reassoc nsz arcp contract afn <8 x double> @llvm.fma.v8f64(<8 x double> %res.i67, <8 x double> %res.i80, <8 x double> %value_phi45.lcssa) %res.i65 = call reassoc nsz arcp contract afn <8 x double> @llvm.fma.v8f64(<8 x double> %res.i89, <8 x double> %res.i76, <8 x double> %res.i66) %res.i = select reassoc nsz arcp contract <8 x i1> %mask.0.i88, <8 x double> %res.i65, <8 x double> %value_phi45.lcssa br label %L180 L180: ; preds = %L155, %L151 %value_phi59 = phi <8 x double> [ %res.i69, %L155 ], [ %value_phi41.lcssa, %L151 ] %value_phi60 = phi <8 x double> [ %res.i, %L155 ], [ %value_phi45.lcssa, %L151 ] %.sroa.0.0..sroa_idx = getelementptr inbounds [2 x <8 x double>], [2 x <8 x double>]* %0, i64 0, i64 0 store <8 x double> %value_phi59, <8 x double>* %.sroa.0.0..sroa_idx, align 64 %.sroa.2.0..sroa_idx61 = getelementptr inbounds [2 x <8 x double>], [2 x <8 x double>]* %0, i64 0, i64 1 store <8 x double> %value_phi60, <8 x double>* %.sroa.2.0..sroa_idx61, align 64 ret void } declare void @llvm.assume(i1) #4 ; Function Attrs: nounwind readnone speculatable willreturn declare <8 x double> @llvm.fma.v8f64(<8 x double>, <8 x double>, <8 x double>) #5 ; Function Attrs: nounwind readonly willreturn declare <8 x double> @llvm.masked.gather.v8f64.v8p0f64(<8 x double*>, i32 immarg, <8 x i1>, <8 x double>) #6 ; Function Attrs: nounwind readnone willreturn declare double @llvm.experimental.vector.reduce.v2.fadd.f64.v8f64(double, <8 x double>) #7
Become a Patron
Sponsor on GitHub
Donate via PayPal
Source on GitHub
Mailing list
Installed libraries
Wiki
Report an issue
How it works
Contact the author
CE on Mastodon
About the author
Statistics
Changelog
Version tree