llvm-6502/test/Transforms/BBVectorize/X86/loop1.ll
David Blaikie 7c9c6ed761 [opaque pointer type] Add textual IR support for explicit type parameter to load instruction
Essentially the same as the GEP change in r230786.

A similar migration script can be used to update test cases, though a few more
test case improvements/changes were required this time around: (r229269-r229278)

import fileinput
import sys
import re

pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)")

for line in sys.stdin:
  sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line))

Reviewers: rafael, dexonsmith, grosser

Differential Revision: http://reviews.llvm.org/D7649

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@230794 91177308-0d34-0410-b5e6-96231b3b80d8
2015-02-27 21:17:42 +00:00

62 lines
2.8 KiB
LLVM

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"
target triple = "x86_64-unknown-linux-gnu"
; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -mcpu=corei7 -bb-vectorize -bb-vectorize-req-chain-depth=3 -instcombine -gvn -S | FileCheck %s
; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -mcpu=corei7 -basicaa -loop-unroll -unroll-threshold=45 -unroll-allow-partial -bb-vectorize -bb-vectorize-req-chain-depth=3 -instcombine -gvn -S | FileCheck %s -check-prefix=CHECK-UNRL
; The second check covers the use of alias analysis (with loop unrolling).
define void @test1(double* noalias %out, double* noalias %in1, double* noalias %in2) nounwind uwtable {
entry:
br label %for.body
; CHECK-LABEL: @test1(
; CHECK-UNRL-LABEL: @test1(
for.body: ; preds = %for.body, %entry
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
%arrayidx = getelementptr inbounds double, double* %in1, i64 %indvars.iv
%0 = load double, double* %arrayidx, align 8
%arrayidx2 = getelementptr inbounds double, double* %in2, i64 %indvars.iv
%1 = load double, double* %arrayidx2, align 8
%mul = fmul double %0, %0
%mul3 = fmul double %0, %1
%add = fadd double %mul, %mul3
%add4 = fadd double %1, %1
%add5 = fadd double %add4, %0
%mul6 = fmul double %0, %add5
%add7 = fadd double %add, %mul6
%mul8 = fmul double %1, %1
%add9 = fadd double %0, %0
%add10 = fadd double %add9, %0
%mul11 = fmul double %mul8, %add10
%add12 = fadd double %add7, %mul11
%arrayidx14 = getelementptr inbounds double, double* %out, i64 %indvars.iv
store double %add12, double* %arrayidx14, align 8
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, 10
br i1 %exitcond, label %for.end, label %for.body
; CHECK: insertelement
; CHECK-NEXT: insertelement
; CHECK-NEXT: fadd <2 x double>
; CHECK-NEXT: insertelement
; CHECK-NEXT: insertelement
; CHECK-NEXT: fadd <2 x double>
; CHECK-NEXT: insertelement
; CHECK-NEXT: fmul <2 x double>
; CHECK-UNRL: %mul = fmul <2 x double> %2, %2
; CHECK-UNRL: %mul3 = fmul <2 x double> %2, %3
; CHECK-UNRL: %add = fadd <2 x double> %mul, %mul3
; CHECK-UNRL: %add4 = fadd <2 x double> %3, %3
; CHECK-UNRL: %add5 = fadd <2 x double> %add4, %2
; CHECK-UNRL: %mul6 = fmul <2 x double> %2, %add5
; CHECK-UNRL: %add7 = fadd <2 x double> %add, %mul6
; CHECK-UNRL: %mul8 = fmul <2 x double> %3, %3
; CHECK-UNRL: %add9 = fadd <2 x double> %2, %2
; CHECK-UNRL: %add10 = fadd <2 x double> %add9, %2
; CHECK-UNRL: %mul11 = fmul <2 x double> %mul8, %add10
; CHECK-UNRL: %add12 = fadd <2 x double> %add7, %mul11
for.end: ; preds = %for.body
ret void
}