Compiler Explorer

Source code

; ModuleID = 'test.acdeec3141bb4e39-cgu.0'
source_filename = "test.acdeec3141bb4e39-cgu.0"
target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-i128:128-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"

; Function Attrs: nonlazybind uwtable
define void @foo(ptr sret([1024 x i8]) align 1024 %_0, i16 %m, i16 %n, i16 %k, ptr align 1024 %a, ptr align 1024 %b, ptr align 1024 %c) unnamed_addr #0 {
start:
  %0 = load <256 x i32>, ptr %a, align 1024
  %1 = load <256 x i32>, ptr %b, align 1024
  %2 = load <256 x i32>, ptr %c, align 1024
  %3 = bitcast <256 x i32> %0 to x86_amx
  %4 = bitcast <256 x i32> %1 to x86_amx
  %5 = bitcast <256 x i32> %2 to x86_amx
  %6 = call x86_amx @llvm.x86.tdpbuud.internal(i16 %m, i16 %n, i16 %k, x86_amx %3, x86_amx %4, x86_amx %5) #1
  %7 = bitcast x86_amx %6 to <256 x i32>
  store <256 x i32> %7, ptr %_0, align 1024
  ret void
}

; Function Attrs: nounwind
declare x86_amx @llvm.x86.tdpbuud.internal(i16, i16, i16, x86_amx, x86_amx, x86_amx) unnamed_addr #1

attributes #0 = { nonlazybind uwtable "probe-stack"="inline-asm" "target-cpu"="x86-64" "target-features"="+amx-int8,+amx-tile" }
attributes #1 = { nounwind }

!llvm.module.flags = !{!0, !1}
!llvm.ident = !{!2}

!0 = !{i32 8, !"PIC Level", i32 2}
!1 = !{i32 2, !"RtLibUseGOT", i32 1}
!2 = !{!"rustc version 1.88.0-dev"}