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 @store_i64_stride3_vf16(<16 x i64>* %in.vecptr0, <16 x i64>* %in.vecptr1, <16 x i64>* %in.vecptr2, <48 x i64>* %out.vec) nounwind { %in.vec0 = load <16 x i64>, <16 x i64>* %in.vecptr0, align 32 %in.vec1 = load <16 x i64>, <16 x i64>* %in.vecptr1, align 32 %in.vec2 = load <16 x i64>, <16 x i64>* %in.vecptr2, align 32 %concat01 = shufflevector <16 x i64> %in.vec0, <16 x i64> %in.vec1, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31> %concat2u = shufflevector <16 x i64> %in.vec2, <16 x i64> poison, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef> %concat012 = shufflevector <32 x i64> %concat01, <32 x i64> %concat2u, <48 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 45, i32 46, i32 47> %interleaved.vec = shufflevector <48 x i64> %concat012, <48 x i64> poison, <48 x i32> <i32 0, i32 16, i32 32, i32 1, i32 17, i32 33, i32 2, i32 18, i32 34, i32 3, i32 19, i32 35, i32 4, i32 20, i32 36, i32 5, i32 21, i32 37, i32 6, i32 22, i32 38, i32 7, i32 23, i32 39, i32 8, i32 24, i32 40, i32 9, i32 25, i32 41, i32 10, i32 26, i32 42, i32 11, i32 27, i32 43, i32 12, i32 28, i32 44, i32 13, i32 29, i32 45, i32 14, i32 30, i32 46, i32 15, i32 31, i32 47> store <48 x i64> %interleaved.vec, <48 x i64>* %out.vec, align 32 ret void }
analysis source #2
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
OSACA (0.5.2)
llvm-mca (assertions trunk)
llvm-mca (trunk)
Options
Source code
.text .intel_syntax noprefix .file "example.ll" .globl store_i64_stride3_vf16 # -- Begin function store_i64_stride3_vf16 .p2align 4, 0x90 .type store_i64_stride3_vf16,@function store_i64_stride3_vf16: # @store_i64_stride3_vf16 # %bb.0: vmovaps ymm0, ymmword ptr [rdi] vmovaps ymm4, ymmword ptr [rdi + 32] vmovaps ymm7, ymmword ptr [rdi + 64] vmovaps ymm3, ymmword ptr [rdi + 96] vmovaps ymm2, ymmword ptr [rdx] vmovaps ymm6, ymmword ptr [rdx + 96] vmovaps ymm8, ymmword ptr [rdx + 32] vmovaps ymm10, ymmword ptr [rdx + 64] vinsertf128 ymm1, ymm0, xmmword ptr [rdx], 1 vmovddup xmm5, qword ptr [rsi] # xmm5 = mem[0,0] vpermpd ymm9, ymm0, 100 # ymm9 = ymm0[0,1,2,1] vblendps ymm5, ymm9, ymm5, 12 # ymm5 = ymm9[0,1],ymm5[2,3],ymm9[4,5,6,7] vblendps ymm1, ymm5, ymm1, 48 # ymm1 = ymm5[0,1,2,3],ymm1[4,5],ymm5[6,7] vmovups ymmword ptr [rsp - 40], ymm1 # 32-byte Spill vinsertf128 ymm5, ymm0, xmmword ptr [rdx + 64], 1 vmovddup xmm9, qword ptr [rsi + 64] # xmm9 = mem[0,0] vpermpd ymm11, ymm7, 100 # ymm11 = ymm7[0,1,2,1] vblendps ymm9, ymm11, ymm9, 12 # ymm9 = ymm11[0,1],ymm9[2,3],ymm11[4,5,6,7] vblendps ymm5, ymm9, ymm5, 48 # ymm5 = ymm9[0,1,2,3],ymm5[4,5],ymm9[6,7] vperm2f128 ymm9, ymm7, ymm10, 49 # ymm9 = ymm7[2,3],ymm10[2,3] vmovaps xmm11, xmmword ptr [rdx + 80] vblendps ymm9, ymm11, ymm9, 204 # ymm9 = ymm11[0,1],ymm9[2,3],ymm11[4,5],ymm9[6,7] vbroadcastsd ymm11, qword ptr [rsi + 88] vblendps ymm9, ymm9, ymm11, 48 # ymm9 = ymm9[0,1,2,3],ymm11[4,5],ymm9[6,7] vinsertf128 ymm11, ymm0, xmmword ptr [rdx + 32], 1 vmovddup xmm12, qword ptr [rsi + 32] # xmm12 = mem[0,0] vpermpd ymm13, ymm4, 100 # ymm13 = ymm4[0,1,2,1] vblendps ymm12, ymm13, ymm12, 12 # ymm12 = ymm13[0,1],ymm12[2,3],ymm13[4,5,6,7] vblendps ymm11, ymm12, ymm11, 48 # ymm11 = ymm12[0,1,2,3],ymm11[4,5],ymm12[6,7] vperm2f128 ymm12, ymm4, ymm8, 49 # ymm12 = ymm4[2,3],ymm8[2,3] vmovaps xmm13, xmmword ptr [rdx + 48] vblendps ymm12, ymm13, ymm12, 204 # ymm12 = ymm13[0,1],ymm12[2,3],ymm13[4,5],ymm12[6,7] vbroadcastsd ymm13, qword ptr [rsi + 56] vblendps ymm12, ymm12, ymm13, 48 # ymm12 = ymm12[0,1,2,3],ymm13[4,5],ymm12[6,7] vinsertf128 ymm13, ymm0, xmmword ptr [rdx + 96], 1 vmovddup xmm14, qword ptr [rsi + 96] # xmm14 = mem[0,0] vpermpd ymm15, ymm3, 100 # ymm15 = ymm3[0,1,2,1] vblendps ymm14, ymm15, ymm14, 12 # ymm14 = ymm15[0,1],ymm14[2,3],ymm15[4,5,6,7] vblendps ymm13, ymm14, ymm13, 48 # ymm13 = ymm14[0,1,2,3],ymm13[4,5],ymm14[6,7] vperm2f128 ymm14, ymm3, ymm6, 49 # ymm14 = ymm3[2,3],ymm6[2,3] vmovaps xmm15, xmmword ptr [rdx + 112] vblendps ymm14, ymm15, ymm14, 204 # ymm14 = ymm15[0,1],ymm14[2,3],ymm15[4,5],ymm14[6,7] vbroadcastsd ymm15, qword ptr [rsi + 120] vblendps ymm14, ymm14, ymm15, 48 # ymm14 = ymm14[0,1,2,3],ymm15[4,5],ymm14[6,7] vperm2f128 ymm15, ymm0, ymm2, 49 # ymm15 = ymm0[2,3],ymm2[2,3] vmovaps xmm1, xmmword ptr [rdx + 16] vblendps ymm1, ymm1, ymm15, 204 # ymm1 = ymm1[0,1],ymm15[2,3],ymm1[4,5],ymm15[6,7] vbroadcastsd ymm15, qword ptr [rsi + 24] vblendps ymm1, ymm1, ymm15, 48 # ymm1 = ymm1[0,1,2,3],ymm15[4,5],ymm1[6,7] vpermilps ymm15, ymmword ptr [rsi + 64], 78 # ymm15 = mem[2,3,0,1,6,7,4,5] vblendps ymm10, ymm15, ymm10, 12 # ymm10 = ymm15[0,1],ymm10[2,3],ymm15[4,5,6,7] vblendps ymm7, ymm10, ymm7, 48 # ymm7 = ymm10[0,1,2,3],ymm7[4,5],ymm10[6,7] vpermilps ymm10, ymmword ptr [rsi + 32], 78 # ymm10 = mem[2,3,0,1,6,7,4,5] vblendps ymm8, ymm10, ymm8, 12 # ymm8 = ymm10[0,1],ymm8[2,3],ymm10[4,5,6,7] vblendps ymm4, ymm8, ymm4, 48 # ymm4 = ymm8[0,1,2,3],ymm4[4,5],ymm8[6,7] vpermilps ymm8, ymmword ptr [rsi + 96], 78 # ymm8 = mem[2,3,0,1,6,7,4,5] vblendps ymm6, ymm8, ymm6, 12 # ymm6 = ymm8[0,1],ymm6[2,3],ymm8[4,5,6,7] vblendps ymm3, ymm6, ymm3, 48 # ymm3 = ymm6[0,1,2,3],ymm3[4,5],ymm6[6,7] vpermilps ymm6, ymmword ptr [rsi], 78 # ymm6 = mem[2,3,0,1,6,7,4,5] vblendps ymm2, ymm6, ymm2, 12 # ymm2 = ymm6[0,1],ymm2[2,3],ymm6[4,5,6,7] vblendps ymm0, ymm2, ymm0, 48 # ymm0 = ymm2[0,1,2,3],ymm0[4,5],ymm2[6,7]
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