; ModuleID = '<stdin>'
source_filename = "kernel.cpp.kernel.tmp.cpp"
target datalayout = "e-p:64:64-p1:64:64-p2:64:64-p3:32:32-p4:32:32-p5:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64-A5"
target triple = "amdgcn--amdhsa-hcc"

%struct.grid_launch_parm = type { %struct.gl_dim3, %struct.gl_dim3, i32, i32, i32, %"class.hc::accelerator_view"*, %"class.hc::completion_future"* }
%struct.gl_dim3 = type { i32, i32, i32 }
%"class.hc::accelerator_view" = type opaque
%"class.hc::completion_future" = type opaque

@llvm.used = appending global [1 x i8*] [i8* bitcast (void (%struct.grid_launch_parm addrspace(5)*, float*, float*, i32)* @__hcLaunchKernel__Z15matrixTranspose16grid_launch_parmPfS0_i to i8*)], section "llvm.metadata"

; Function Attrs: alwaysinline nounwind
define void @_Z15matrixTranspose16grid_launch_parmPfS0_i(%struct.grid_launch_parm addrspace(5)* byval nocapture readnone align 8 %lp, float* nocapture %out, float* nocapture readonly %in, i32 %width) #0 {
  %call = tail call i64 @hc_get_group_size(i32 0) #2
  %call1 = tail call i64 @hc_get_group_id(i32 0) #2
  %mul = mul nsw i64 %call1, %call
  %call2 = tail call i64 @hc_get_workitem_id(i32 0) #2
  %add = add nsw i64 %mul, %call2
  %conv = trunc i64 %add to i32
  %call3 = tail call i64 @hc_get_group_size(i32 1) #2
  %call4 = tail call i64 @hc_get_group_id(i32 1) #2
  %mul5 = mul nsw i64 %call4, %call3
  %call6 = tail call i64 @hc_get_workitem_id(i32 1) #2
  %add7 = add nsw i64 %mul5, %call6
  %conv8 = trunc i64 %add7 to i32
  %mul9 = mul nsw i32 %conv, %width
  %add10 = add nsw i32 %mul9, %conv8
  %idxprom = sext i32 %add10 to i64
  %arrayidx = getelementptr inbounds float, float* %out, i64 %idxprom
  %mul11 = mul nsw i32 %conv8, %width
  %add12 = add nsw i32 %mul11, %conv
  %idxprom13 = sext i32 %add12 to i64
  %arrayidx14 = getelementptr inbounds float, float* %in, i64 %idxprom13
  %1 = load float, float* %arrayidx14, align 4, !tbaa !2
  %2 = tail call float asm sideeffect "v_mov_b32_e32 $0, $1", "=v,v"(float %1) #3, !srcloc !6
  store float %2, float* %arrayidx, align 4, !tbaa !2
  ret void
}

; Function Attrs: nounwind readnone
declare i64 @hc_get_group_size(i32) local_unnamed_addr #1

; Function Attrs: nounwind readnone
declare i64 @hc_get_group_id(i32) local_unnamed_addr #1

; Function Attrs: nounwind readnone
declare i64 @hc_get_workitem_id(i32) local_unnamed_addr #1

declare void @__hcLaunchKernel__Z15matrixTranspose16grid_launch_parmPfS0_i(%struct.grid_launch_parm addrspace(5)*, float*, float*, i32)

attributes #0 = { alwaysinline nounwind "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "hc_grid_launch" "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "target-features"="+fp64-fp16-denormals,-fp32-denormals" "unsafe-fp-math"="false" "use-soft-float"="false" }
attributes #1 = { nounwind readnone "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "target-features"="+fp64-fp16-denormals,-fp32-denormals" "unsafe-fp-math"="false" "use-soft-float"="false" }
attributes #2 = { nobuiltin nounwind readnone }
attributes #3 = { nounwind }

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

!0 = !{i32 1, !"wchar_size", i32 4}
!1 = !{!"HCC clang version 5.0.0  (based on HCC 1.0.17312-d1f4a8a-19aa706-56b5abe )"}
!2 = !{!3, !3, i64 0}
!3 = !{!"float", !4, i64 0}
!4 = !{!"omnipotent char", !5, i64 0}
!5 = !{!"Simple C++ TBAA"}
!6 = !{i32 460}