Compiler Explorer

Source code

target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"

; Function Attrs: noinline
define void @_Z18Softmax_ActivationPA10_fS0_([10 x float]* %l_Z2, [10 x float]* %out) #0 {
entry:
  %l_Z2.addr = alloca [10 x float]*, align 8
  %out.addr = alloca [10 x float]*, align 8
  %max = alloca [10 x float], align 16
  %i = alloca i32, align 4
  %j = alloca i32, align 4
  store [10 x float]* %l_Z2, [10 x float]** %l_Z2.addr, align 8
  store [10 x float]* %out, [10 x float]** %out.addr, align 8
  br label %SA_MAX2

SA_MAX2:                                          ; preds = %entry
  store i32 0, i32* %i, align 4
  br label %for.cond

for.cond:                                         ; preds = %for.inc17, %SA_MAX2
  %0 = load i32, i32* %i, align 4
  %cmp = icmp slt i32 %0, 10
  br i1 %cmp, label %for.body, label %for.end19

for.body:                                         ; preds = %for.cond
  %1 = load i32, i32* %i, align 4
  %idxprom = sext i32 %1 to i64 
  %arrayidx = getelementptr inbounds [10 x float], [10 x float]* %max, i64 0, i64 %idxprom
  store float 0.000000e+00, float* %arrayidx, align 4
  br label %SA_MAX1

SA_MAX1:                                          ; preds = %for.body
  store i32 0, i32* %j, align 4
  br label %for.cond1

for.cond1:                                        ; preds = %for.inc, %SA_MAX1
  %2 = load i32, i32* %j, align 4
  %cmp2 = icmp slt i32 %2, 10
  br i1 %cmp2, label %for.body3, label %for.end

for.body3:                                        ; preds = %for.cond1
  %3 = load [10 x float]*, [10 x float]** %l_Z2.addr, align 8
  %4 = load i32, i32* %j, align 4
  %idxprom4 = sext i32 %4 to i64 
  %arrayidx5 = getelementptr inbounds [10 x float], [10 x float]* %3, i64 %idxprom4
  %5 = load i32, i32* %i, align 4
  %idxprom6 = sext i32 %5 to i64 
  %arrayidx7 = getelementptr inbounds [10 x float], [10 x float]* %arrayidx5, i64 0, i64 %idxprom6
    %6 = load float, float* %arrayidx7, align 4
  %7 = load i32, i32* %i, align 4
  %idxprom8 = sext i32 %7 to i64
  %arrayidx9 = getelementptr inbounds [10 x float], [10 x float]* %max, i64 0, i64 %idxprom8
  %8 = load float, float* %arrayidx9, align 4
  %cmp10 = fcmp ogt float %6, %8
  br i1 %cmp10, label %if.then, label %if.end

if.then:                                          ; preds = %for.body3
  %9 = load [10 x float]*, [10 x float]** %l_Z2.addr, align 8
  %10 = load i32, i32* %j, align 4
  %idxprom11 = sext i32 %10 to i64
  %arrayidx12 = getelementptr inbounds [10 x float], [10 x float]* %9, i64 %idxprom11
  %11 = load i32, i32* %i, align 4
  %idxprom13 = sext i32 %11 to i64
  %arrayidx14 = getelementptr inbounds [10 x float], [10 x float]* %arrayidx12, i64 0, i64 %idxprom13
  %12 = load float, float* %arrayidx14, align 4
  %13 = load i32, i32* %i, align 4
  %idxprom15 = sext i32 %13 to i64
  %arrayidx16 = getelementptr inbounds [10 x float], [10 x float]* %max, i64 0, i64 %idxprom15
  store float %12, float* %arrayidx16, align 4
  br label %if.end

if.end:                                           ; preds = %if.then, %for.body3
  br label %for.inc

for.inc:                                          ; preds = %if.end
  %14 = load i32, i32* %j, align 4
  %inc = add nsw i32 %14, 1
  store i32 %inc, i32* %j, align 4
  br label %for.cond1

for.end:                                          ; preds = %for.cond1
  br label %for.inc17

for.inc17:                                        ; preds = %for.end
  %15 = load i32, i32* %i, align 4
  %inc18 = add nsw i32 %15, 1
  store i32 %inc18, i32* %i, align 4
  br label %for.cond

for.end19:                                        ; preds = %for.cond
  %16 = load [10 x float]*, [10 x float]** %out.addr, align 8
  %arraydecay = getelementptr inbounds [10 x float], [10 x float]* %max, i32 0, i32 0
  call void @_Z3fooPA10_fPf([10 x float]* %16, float* %arraydecay)
  ret void
}

declare void @_Z3fooPA10_fPf([10 x float]*, float*) #1

attributes #0 = { noinline "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-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="x86-64" "target-features"="+fxsr,+mmx,+sse,+sse2,+x87" "unsafe-fp-math"="false" "use-soft-float"="false" }
attributes #1 = { "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-cpu"="x86-64" "target-features"="+fxsr,+mmx,+sse,+sse2,+x87" "unsafe-fp-math"="false" "use-soft-float"="false" }