forked from OSchip/llvm-project
47 lines
1.9 KiB
LLVM
47 lines
1.9 KiB
LLVM
; RUN: opt < %s -loop-vectorize -force-vector-interleave=1 -force-vector-width=4 -dce -instcombine -S | FileCheck %s
|
|
|
|
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
|
|
;CHECK-LABEL: @foo(
|
|
;CHECK: fadd fast <4 x float>
|
|
;CHECK: ret
|
|
define float @foo(float* nocapture %A, i32* nocapture %n) nounwind uwtable readonly ssp {
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
|
|
%sum.04 = phi float [ 0.000000e+00, %entry ], [ %add, %for.body ]
|
|
%arrayidx = getelementptr inbounds float, float* %A, i64 %indvars.iv
|
|
%0 = load float, float* %arrayidx, align 4
|
|
%add = fadd fast float %sum.04, %0
|
|
%indvars.iv.next = add i64 %indvars.iv, 1
|
|
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
|
|
%exitcond = icmp eq i32 %lftr.wideiv, 200
|
|
br i1 %exitcond, label %for.end, label %for.body
|
|
|
|
for.end: ; preds = %for.body
|
|
ret float %add
|
|
}
|
|
|
|
;CHECK-LABEL: @foosub(
|
|
;CHECK: fsub fast <4 x float>
|
|
;CHECK: ret
|
|
define float @foosub(float* nocapture %A, i32* nocapture %n) nounwind uwtable readonly ssp {
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
|
|
%sum.04 = phi float [ 0.000000e+00, %entry ], [ %sub, %for.body ]
|
|
%arrayidx = getelementptr inbounds float, float* %A, i64 %indvars.iv
|
|
%0 = load float, float* %arrayidx, align 4
|
|
%sub = fsub fast float %sum.04, %0
|
|
%indvars.iv.next = add i64 %indvars.iv, 1
|
|
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
|
|
%exitcond = icmp eq i32 %lftr.wideiv, 200
|
|
br i1 %exitcond, label %for.end, label %for.body
|
|
|
|
for.end: ; preds = %for.body
|
|
ret float %sub
|
|
}
|