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#
GLSL
Go
Haskell
HLSL
Hook
Hylo
IL
ispc
Java
Julia
Kotlin
LLVM IR
LLVM MIR
Modula-2
Nim
Objective-C
Objective-C++
OCaml
Odin
OpenCL C
Pascal
Pony
Python
Racket
Ruby
Rust
Snowball
Scala
Slang
Solidity
Spice
SPIR-V
Swift
LLVM TableGen
Toit
TypeScript Native
V
Vala
Visual Basic
Vyper
WASM
Zig
Javascript
GIMPLE
Ygen
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 19.1.0
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 19.1.0
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 19.1.0
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_i8_stride6_vf32(<32 x i8>* %in.vecptr0, <32 x i8>* %in.vecptr1, <32 x i8>* %in.vecptr2, <32 x i8>* %in.vecptr3, <32 x i8>* %in.vecptr4, <32 x i8>* %in.vecptr5, <192 x i8>* %out.vec) nounwind { %in.vec0 = load <32 x i8>, <32 x i8>* %in.vecptr0, align 32 %in.vec1 = load <32 x i8>, <32 x i8>* %in.vecptr1, align 32 %in.vec2 = load <32 x i8>, <32 x i8>* %in.vecptr2, align 32 %in.vec3 = load <32 x i8>, <32 x i8>* %in.vecptr3, align 32 %in.vec4 = load <32 x i8>, <32 x i8>* %in.vecptr4, align 32 %in.vec5 = load <32 x i8>, <32 x i8>* %in.vecptr5, align 32 tail call void asm sideeffect "# LLVM-MCA-BEGIN", "~{dirflag},~{fpsr},~{flags}"() %concat01 = shufflevector <32 x i8> %in.vec0, <32 x i8> %in.vec1, <64 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, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63> %concat23 = shufflevector <32 x i8> %in.vec2, <32 x i8> %in.vec3, <64 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, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63> %concat45 = shufflevector <32 x i8> %in.vec4, <32 x i8> %in.vec5, <64 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, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63> %concat0123 = shufflevector <64 x i8> %concat01, <64 x i8> %concat23, <128 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, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63, i32 64, i32 65, i32 66, i32 67, i32 68, i32 69, i32 70, i32 71, i32 72, i32 73, i32 74, i32 75, i32 76, i32 77, i32 78, i32 79, i32 80, i32 81, i32 82, i32 83, i32 84, i32 85, i32 86, i32 87, i32 88, i32 89, i32 90, i32 91, i32 92, i32 93, i32 94, i32 95, i32 96, i32 97, i32 98, i32 99, i32 100, i32 101, i32 102, i32 103, i32 104, i32 105, i32 106, i32 107, i32 108, i32 109, i32 110, i32 111, i32 112, i32 113, i32 114, i32 115, i32 116, i32 117, i32 118, i32 119, i32 120, i32 121, i32 122, i32 123, i32 124, i32 125, i32 126, i32 127> %concat45uu = shufflevector <64 x i8> %concat45, <64 x i8> poison, <128 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, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63, 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, 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, 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, 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> %concat012345 = shufflevector <128 x i8> %concat0123, <128 x i8> %concat45uu, <192 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, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60, i32 61, i32 62, i32 63, i32 64, i32 65, i32 66, i32 67, i32 68, i32 69, i32 70, i32 71, i32 72, i32 73, i32 74, i32 75, i32 76, i32 77, i32 78, i32 79, i32 80, i32 81, i32 82, i32 83, i32 84, i32 85, i32 86, i32 87, i32 88, i32 89, i32 90, i32 91, i32 92, i32 93, i32 94, i32 95, i32 96, i32 97, i32 98, i32 99, i32 100, i32 101, i32 102, i32 103, i32 104, i32 105, i32 106, i32 107, i32 108, i32 109, i32 110, i32 111, i32 112, i32 113, i32 114, i32 115, i32 116, i32 117, i32 118, i32 119, i32 120, i32 121, i32 122, i32 123, i32 124, i32 125, i32 126, i32 127, i32 128, i32 129, i32 130, i32 131, i32 132, i32 133, i32 134, i32 135, i32 136, i32 137, i32 138, i32 139, i32 140, i32 141, i32 142, i32 143, i32 144, i32 145, i32 146, i32 147, i32 148, i32 149, i32 150, i32 151, i32 152, i32 153, i32 154, i32 155, i32 156, i32 157, i32 158, i32 159, i32 160, i32 161, i32 162, i32 163, i32 164, i32 165, i32 166, i32 167, i32 168, i32 169, i32 170, i32 171, i32 172, i32 173, i32 174, i32 175, i32 176, i32 177, i32 178, i32 179, i32 180, i32 181, i32 182, i32 183, i32 184, i32 185, i32 186, i32 187, i32 188, i32 189, i32 190, i32 191> %interleaved.vec = shufflevector <192 x i8> %concat012345, <192 x i8> poison, <192 x i32> <i32 0, i32 32, i32 64, i32 96, i32 128, i32 160, i32 1, i32 33, i32 65, i32 97, i32 129, i32 161, i32 2, i32 34, i32 66, i32 98, i32 130, i32 162, i32 3, i32 35, i32 67, i32 99, i32 131, i32 163, i32 4, i32 36, i32 68, i32 100, i32 132, i32 164, i32 5, i32 37, i32 69, i32 101, i32 133, i32 165, i32 6, i32 38, i32 70, i32 102, i32 134, i32 166, i32 7, i32 39, i32 71, i32 103, i32 135, i32 167, i32 8, i32 40, i32 72, i32 104, i32 136, i32 168, i32 9, i32 41, i32 73, i32 105, i32 137, i32 169, i32 10, i32 42, i32 74, i32 106, i32 138, i32 170, i32 11, i32 43, i32 75, i32 107, i32 139, i32 171, i32 12, i32 44, i32 76, i32 108, i32 140, i32 172, i32 13, i32 45, i32 77, i32 109, i32 141, i32 173, i32 14, i32 46, i32 78, i32 110, i32 142, i32 174, i32 15, i32 47, i32 79, i32 111, i32 143, i32 175, i32 16, i32 48, i32 80, i32 112, i32 144, i32 176, i32 17, i32 49, i32 81, i32 113, i32 145, i32 177, i32 18, i32 50, i32 82, i32 114, i32 146, i32 178, i32 19, i32 51, i32 83, i32 115, i32 147, i32 179, i32 20, i32 52, i32 84, i32 116, i32 148, i32 180, i32 21, i32 53, i32 85, i32 117, i32 149, i32 181, i32 22, i32 54, i32 86, i32 118, i32 150, i32 182, i32 23, i32 55, i32 87, i32 119, i32 151, i32 183, i32 24, i32 56, i32 88, i32 120, i32 152, i32 184, i32 25, i32 57, i32 89, i32 121, i32 153, i32 185, i32 26, i32 58, i32 90, i32 122, i32 154, i32 186, i32 27, i32 59, i32 91, i32 123, i32 155, i32 187, i32 28, i32 60, i32 92, i32 124, i32 156, i32 188, i32 29, i32 61, i32 93, i32 125, i32 157, i32 189, i32 30, i32 62, i32 94, i32 126, i32 158, i32 190, i32 31, i32 63, i32 95, i32 127, i32 159, i32 191> tail call void asm sideeffect "# LLVM-MCA-END", "~{dirflag},~{fpsr},~{flags}"() store <192 x i8> %interleaved.vec, <192 x i8>* %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 (0.6.1)
llvm-mca (assertions trunk)
llvm-mca (trunk)
Options
Source code
vmovdqu ymmword ptr [rsp - 80], ymm7 # 32-byte Spill vmovdqu ymmword ptr [rsp - 48], ymm11 # 32-byte Spill vmovdqa xmm10, xmmword ptr [rip + .LCPI0_0] # xmm10 = <5,8,7,6,9,u,u,10,u,u,u,u,u,u,u,u> vpshufb xmm2, xmm13, xmm10 vpshufb xmm3, xmm0, xmm10 vmovdqa xmm6, xmm0 vmovdqa xmmword ptr [rsp - 128], xmm0 # 16-byte Spill vpunpcklbw xmm2, xmm3, xmm2 # xmm2 = xmm3[0],xmm2[0],xmm3[1],xmm2[1],xmm3[2],xmm2[2],xmm3[3],xmm2[3],xmm3[4],xmm2[4],xmm3[5],xmm2[5],xmm3[6],xmm2[6],xmm3[7],xmm2[7] vpermq ymm2, ymm2, 64 # ymm2 = ymm2[0,0,0,1] vmovdqa xmm10, xmmword ptr [rip + .LCPI0_1] # xmm10 = <6,5,8,7,u,9,u,u,u,u,u,u,u,u,u,u> vpshufb xmm3, xmm12, xmm10 vpshufb xmm4, xmm15, xmm10 vpunpcklbw xmm3, xmm4, xmm3 # xmm3 = xmm4[0],xmm3[0],xmm4[1],xmm3[1],xmm4[2],xmm3[2],xmm4[3],xmm3[3],xmm4[4],xmm3[4],xmm4[5],xmm3[5],xmm4[6],xmm3[6],xmm4[7],xmm3[7] vpermq ymm3, ymm3, 64 # ymm3 = ymm3[0,0,0,1] vmovdqa ymm0, ymmword ptr [rip + .LCPI0_2] # ymm0 = <255,255,0,0,u,u,255,255,0,0,u,u,255,255,0,0,u,u,255,255,0,0,u,u,255,255,0,0,u,u,255,255> vpblendvb ymm2, ymm3, ymm2, ymm0 vmovdqu ymmword ptr [rsp + 16], ymm2 # 32-byte Spill vmovdqa ymm2, ymmword ptr [rip + .LCPI0_5] # ymm2 = <5,8,7,6,9,u,u,10,u,u,u,u,u,u,u,u,5,8,7,6,9,u,u,10,u,u,u,u,u,u,u,u> vpshufb ymm3, ymm8, ymm2 vpshufb ymm2, ymm9, ymm2 vpunpcklbw ymm2, ymm2, ymm3 # ymm2 = ymm2[0],ymm3[0],ymm2[1],ymm3[1],ymm2[2],ymm3[2],ymm2[3],ymm3[3],ymm2[4],ymm3[4],ymm2[5],ymm3[5],ymm2[6],ymm3[6],ymm2[7],ymm3[7],ymm2[16],ymm3[16],ymm2[17],ymm3[17],ymm2[18],ymm3[18],ymm2[19],ymm3[19],ymm2[20],ymm3[20],ymm2[21],ymm3[21],ymm2[22],ymm3[22],ymm2[23],ymm3[23] vpermq ymm2, ymm2, 234 # ymm2 = ymm2[2,2,2,3] vmovdqa ymm3, ymmword ptr [rip + .LCPI0_6] # ymm3 = <6,5,8,7,u,9,u,u,u,u,u,u,u,u,u,u,6,5,8,7,u,9,u,u,u,u,u,u,u,u,u,u> vpshufb ymm4, ymm11, ymm3 vpshufb ymm3, ymm7, ymm3 vpunpcklbw ymm3, ymm3, ymm4 # ymm3 = ymm3[0],ymm4[0],ymm3[1],ymm4[1],ymm3[2],ymm4[2],ymm3[3],ymm4[3],ymm3[4],ymm4[4],ymm3[5],ymm4[5],ymm3[6],ymm4[6],ymm3[7],ymm4[7],ymm3[16],ymm4[16],ymm3[17],ymm4[17],ymm3[18],ymm4[18],ymm3[19],ymm4[19],ymm3[20],ymm4[20],ymm3[21],ymm4[21],ymm3[22],ymm4[22],ymm3[23],ymm4[23] vpermq ymm3, ymm3, 234 # ymm3 = ymm3[2,2,2,3] vpblendvb ymm2, ymm3, ymm2, ymm0 vmovdqu ymmword ptr [rsp - 16], ymm2 # 32-byte Spill vpunpcklbw xmm3, xmm5, xmm1 # xmm3 = xmm5[0],xmm1[0],xmm5[1],xmm1[1],xmm5[2],xmm1[2],xmm5[3],xmm1[3],xmm5[4],xmm1[4],xmm5[5],xmm1[5],xmm5[6],xmm1[6],xmm5[7],xmm1[7] vpshuflw xmm3, xmm3, 108 # xmm3 = xmm3[0,3,2,1,4,5,6,7] vpshufhw xmm3, xmm3, 100 # xmm3 = xmm3[0,1,2,3,4,5,6,5] vpermq ymm3, ymm3, 64 # ymm3 = ymm3[0,0,0,1] vpunpcklbw xmm4, xmm6, xmm13 # xmm4 = xmm6[0],xmm13[0],xmm6[1],xmm13[1],xmm6[2],xmm13[2],xmm6[3],xmm13[3],xmm6[4],xmm13[4],xmm6[5],xmm13[5],xmm6[6],xmm13[6],xmm6[7],xmm13[7] vpshuflw xmm4, xmm4, 177 # xmm4 = xmm4[1,0,3,2,4,5,6,7] vpshufhw xmm4, xmm4, 0 # xmm4 = xmm4[0,1,2,3,4,4,4,4] vpermq ymm4, ymm4, 64 # ymm4 = ymm4[0,0,0,1] vpblendvb ymm2, ymm4, ymm3, ymm0 vmovdqu ymmword ptr [rsp - 112], ymm2 # 32-byte Spill vpunpckhbw xmm4, xmm15, xmm12 # xmm4 = xmm15[8],xmm12[8],xmm15[9],xmm12[9],xmm15[10],xmm12[10],xmm15[11],xmm12[11],xmm15[12],xmm12[12],xmm15[13],xmm12[13],xmm15[14],xmm12[14],xmm15[15],xmm12[15] vpshufb xmm4, xmm4, xmmword ptr [rip + .LCPI0_8] # xmm4 = xmm4[4,5,10,11,8,9,6,7,12,13,10,11,12,13,14,15] vpermq ymm4, ymm4, 64 # ymm4 = ymm4[0,0,0,1] vpunpckhbw xmm2, xmm5, xmm1 # xmm2 = xmm5[8],xmm1[8],xmm5[9],xmm1[9],xmm5[10],xmm1[10],xmm5[11],xmm1[11],xmm5[12],xmm1[12],xmm5[13],xmm1[13],xmm5[14],xmm1[14],xmm5[15],xmm1[15] vpshufb xmm2, xmm2, xmmword ptr [rip + .LCPI0_9] # xmm2 = xmm2[8,9,6,7,12,13,10,11,14,15,14,15,14,15,14,15] vpermq ymm2, ymm2, 64 # ymm2 = ymm2[0,0,0,1] vpblendvb ymm14, ymm2, ymm4, ymm0 vmovdqa ymm2, ymmword ptr [rdi] vmovdqa ymm4, ymmword ptr [rsi] vpunpcklbw ymm10, ymm2, ymm4 # ymm10 = ymm2[0],ymm4[0],ymm2[1],ymm4[1],ymm2[2],ymm4[2],ymm2[3],ymm4[3],ymm2[4],ymm4[4],ymm2[5],ymm4[5],ymm2[6],ymm4[6],ymm2[7],ymm4[7],ymm2[16],ymm4[16],ymm2[17],ymm4[17],ymm2[18],ymm4[18],ymm2[19],ymm4[19],ymm2[20],ymm4[20],ymm2[21],ymm4[21],ymm2[22],ymm4[22],ymm2[23],ymm4[23] vpshuflw ymm10, ymm10, 108 # ymm10 = ymm10[0,3,2,1,4,5,6,7,8,11,10,9,12,13,14,15] vpshufhw ymm10, ymm10, 100 # ymm10 = ymm10[0,1,2,3,4,5,6,5,8,9,10,11,12,13,14,13] vpermq ymm10, ymm10, 234 # ymm10 = ymm10[2,2,2,3] vmovdqa ymm7, ymm9 vpunpcklbw ymm3, ymm9, ymm8 # ymm3 = ymm9[0],ymm8[0],ymm9[1],ymm8[1],ymm9[2],ymm8[2],ymm9[3],ymm8[3],ymm9[4],ymm8[4],ymm9[5],ymm8[5],ymm9[6],ymm8[6],ymm9[7],ymm8[7],ymm9[16],ymm8[16],ymm9[17],ymm8[17],ymm9[18],ymm8[18],ymm9[19],ymm8[19],ymm9[20],ymm8[20],ymm9[21],ymm8[21],ymm9[22],ymm8[22],ymm9[23],ymm8[23] vmovdqa ymm11, ymm8 vpshuflw ymm3, ymm3, 177 # ymm3 = ymm3[1,0,3,2,4,5,6,7,9,8,11,10,12,13,14,15] vpshufhw ymm3, ymm3, 0 # ymm3 = ymm3[0,1,2,3,4,4,4,4,8,9,10,11,12,12,12,12] vpermq ymm3, ymm3, 234 # ymm3 = ymm3[2,2,2,3] vpblendvb ymm9, ymm3, ymm10, ymm0 vmovdqu ymm6, ymmword ptr [rsp - 48] # 32-byte Reload vmovdqu ymm3, ymmword ptr [rsp - 80] # 32-byte Reload vpunpckhbw ymm10, ymm3, ymm6 # ymm10 = ymm3[8],ymm6[8],ymm3[9],ymm6[9],ymm3[10],ymm6[10],ymm3[11],ymm6[11],ymm3[12],ymm6[12],ymm3[13],ymm6[13],ymm3[14],ymm6[14],ymm3[15],ymm6[15],ymm3[24],ymm6[24],ymm3[25],ymm6[25],ymm3[26],ymm6[26],ymm3[27],ymm6[27],ymm3[28],ymm6[28],ymm3[29],ymm6[29],ymm3[30],ymm6[30],ymm3[31],ymm6[31] vpshufb ymm10, ymm10, ymmword ptr [rip + .LCPI0_11] # ymm10 = ymm10[u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,20,21,26,27,24,25,22,23,28,29,26,27,28,29,30,31] vpermq ymm10, ymm10, 234 # ymm10 = ymm10[2,2,2,3] vpunpckhbw ymm8, ymm2, ymm4 # ymm8 = ymm2[8],ymm4[8],ymm2[9],ymm4[9],ymm2[10],ymm4[10],ymm2[11],ymm4[11],ymm2[12],ymm4[12],ymm2[13],ymm4[13],ymm2[14],ymm4[14],ymm2[15],ymm4[15],ymm2[24],ymm4[24],ymm2[25],ymm4[25],ymm2[26],ymm4[26],ymm2[27],ymm4[27],ymm2[28],ymm4[28],ymm2[29],ymm4[29],ymm2[30],ymm4[30],ymm2[31],ymm4[31] vpshufb ymm8, ymm8, ymmword ptr [rip + .LCPI0_12] # ymm8 = ymm8[u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,24,25,22,23,28,29,26,27,30,31,30,31,30,31,30,31] vpermq ymm8, ymm8, 234 # ymm8 = ymm8[2,2,2,3] vpblendvb ymm8, ymm8, ymm10, ymm0 vmovdqa xmm10, xmmword ptr [rip + .LCPI0_3] # xmm10 = <u,u,u,u,u,u,u,u,8,7,6,9,u,u,10,u> vpshufb xmm1, xmm1, xmm10 vpshufb xmm0, xmm5, xmm10 vpunpckhbw xmm0, xmm0, xmm1 # xmm0 = xmm0[8],xmm1[8],xmm0[9],xmm1[9],xmm0[10],xmm1[10],xmm0[11],xmm1[11],xmm0[12],xmm1[12],xmm0[13],xmm1[13],xmm0[14],xmm1[14],xmm0[15],xmm1[15] vpermq ymm0, ymm0, 64 # ymm0 = ymm0[0,0,0,1] vmovdqa ymm1, ymmword ptr [rip + .LCPI0_4] # ymm1 = [255,255,255,255,0,0,255,255,255,255,0,0,255,255,255,255,0,0,255,255,255,255,0,0,255,255,255,255,0,0,255,255] vpblendvb ymm0, ymm0, ymmword ptr [rsp + 16], ymm1 # 32-byte Folded Reload vmovdqa ymm10, ymmword ptr [rip + .LCPI0_7] # ymm10 = <8,7,6,9,u,u,10,u,u,u,u,u,u,u,u,u,8,7,6,9,u,u,10,u,u,u,u,u,u,u,u,u> vpshufb ymm4, ymm4, ymm10 vpshufb ymm2, ymm2, ymm10 vpunpcklbw ymm2, ymm2, ymm4 # ymm2 = ymm2[0],ymm4[0],ymm2[1],ymm4[1],ymm2[2],ymm4[2],ymm2[3],ymm4[3],ymm2[4],ymm4[4],ymm2[5],ymm4[5],ymm2[6],ymm4[6],ymm2[7],ymm4[7],ymm2[16],ymm4[16],ymm2[17],ymm4[17],ymm2[18],ymm4[18],ymm2[19],ymm4[19],ymm2[20],ymm4[20],ymm2[21],ymm4[21],ymm2[22],ymm4[22],ymm2[23],ymm4[23] vpermq ymm2, ymm2, 234 # ymm2 = ymm2[2,2,2,3] vpblendvb ymm2, ymm2, ymmword ptr [rsp - 16], ymm1 # 32-byte Folded Reload vpunpcklbw xmm4, xmm15, xmm12 # xmm4 = xmm15[0],xmm12[0],xmm15[1],xmm12[1],xmm15[2],xmm12[2],xmm15[3],xmm12[3],xmm15[4],xmm12[4],xmm15[5],xmm12[5],xmm15[6],xmm12[6],xmm15[7],xmm12[7] vpshuflw xmm4, xmm4, 198 # xmm4 = xmm4[2,1,0,3,4,5,6,7] vpshufhw xmm4, xmm4, 0 # xmm4 = xmm4[0,1,2,3,4,4,4,4] vpermq ymm4, ymm4, 64 # ymm4 = ymm4[0,0,0,1] vpblendvb ymm4, ymm4, ymmword ptr [rsp - 112], ymm1 # 32-byte Folded Reload vmovdqa xmm5, xmmword ptr [rsp - 128] # 16-byte Reload vpunpckhbw xmm5, xmm5, xmm13 # xmm5 = xmm5[8],xmm13[8],xmm5[9],xmm13[9],xmm5[10],xmm13[10],xmm5[11],xmm13[11],xmm5[12],xmm13[12],xmm5[13],xmm13[13],xmm5[14],xmm13[14],xmm5[15],xmm13[15] vpshufb xmm5, xmm5, xmmword ptr [rip + .LCPI0_10] # xmm5 = xmm5[10,11,8,9,6,7,12,13,14,15,14,15,14,15,14,15] vpermq ymm5, ymm5, 64 # ymm5 = ymm5[0,0,0,1] vpblendvb ymm5, ymm5, ymm14, ymm1 vpunpcklbw ymm6, ymm3, ymm6 # ymm6 = ymm3[0],ymm6[0],ymm3[1],ymm6[1],ymm3[2],ymm6[2],ymm3[3],ymm6[3],ymm3[4],ymm6[4],ymm3[5],ymm6[5],ymm3[6],ymm6[6],ymm3[7],ymm6[7],ymm3[16],ymm6[16],ymm3[17],ymm6[17],ymm3[18],ymm6[18],ymm3[19],ymm6[19],ymm3[20],ymm6[20],ymm3[21],ymm6[21],ymm3[22],ymm6[22],ymm3[23],ymm6[23] vpshuflw ymm6, ymm6, 198 # ymm6 = ymm6[2,1,0,3,4,5,6,7,10,9,8,11,12,13,14,15] vpshufhw ymm6, ymm6, 0 # ymm6 = ymm6[0,1,2,3,4,4,4,4,8,9,10,11,12,12,12,12] vpermq ymm6, ymm6, 234 # ymm6 = ymm6[2,2,2,3] vpblendvb ymm3, ymm6, ymm9, ymm1 vpunpckhbw ymm6, ymm7, ymm11 # ymm6 = ymm7[8],ymm11[8],ymm7[9],ymm11[9],ymm7[10],ymm11[10],ymm7[11],ymm11[11],ymm7[12],ymm11[12],ymm7[13],ymm11[13],ymm7[14],ymm11[14],ymm7[15],ymm11[15],ymm7[24],ymm11[24],ymm7[25],ymm11[25],ymm7[26],ymm11[26],ymm7[27],ymm11[27],ymm7[28],ymm11[28],ymm7[29],ymm11[29],ymm7[30],ymm11[30],ymm7[31],ymm11[31] vpshufb ymm6, ymm6, ymmword ptr [rip + .LCPI0_13] # ymm6 = ymm6[u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,26,27,24,25,22,23,28,29,30,31,30,31,30,31,30,31] vpermq ymm6, ymm6, 234 # ymm6 = ymm6[2,2,2,3] vpblendvb ymm1, ymm6, ymm8, ymm1
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
CE on Bluesky
About the author
Statistics
Changelog
Version tree