llvm-6502/test/Analysis/CostModel/X86/loop_v2.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

40 lines
1.7 KiB
LLVM

; RUN: opt < %s -cost-model -analyze -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx | 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"
target triple = "x86_64-apple-macosx10.9.0"
define i32 @foo(i32* nocapture %A) nounwind uwtable readonly ssp {
vector.ph:
br label %vector.body
vector.body: ; preds = %vector.body, %vector.ph
%index = phi i64 [ 0, %vector.ph ], [ %index.next, %vector.body ]
%vec.phi = phi <2 x i32> [ zeroinitializer, %vector.ph ], [ %12, %vector.body ]
%0 = getelementptr inbounds i32, i32* %A, i64 %index
%1 = bitcast i32* %0 to <2 x i32>*
%2 = load <2 x i32>, <2 x i32>* %1, align 4
%3 = sext <2 x i32> %2 to <2 x i64>
;CHECK: cost of 1 {{.*}} extract
%4 = extractelement <2 x i64> %3, i32 0
%5 = getelementptr inbounds i32, i32* %A, i64 %4
;CHECK: cost of 1 {{.*}} extract
%6 = extractelement <2 x i64> %3, i32 1
%7 = getelementptr inbounds i32, i32* %A, i64 %6
%8 = load i32, i32* %5, align 4
;CHECK: cost of 1 {{.*}} insert
%9 = insertelement <2 x i32> undef, i32 %8, i32 0
%10 = load i32, i32* %7, align 4
;CHECK: cost of 1 {{.*}} insert
%11 = insertelement <2 x i32> %9, i32 %10, i32 1
%12 = add nsw <2 x i32> %11, %vec.phi
%index.next = add i64 %index, 2
%13 = icmp eq i64 %index.next, 192
br i1 %13, label %for.end, label %vector.body
for.end: ; preds = %vector.body
%14 = extractelement <2 x i32> %12, i32 0
%15 = extractelement <2 x i32> %12, i32 1
%16 = add i32 %14, %15
ret i32 %16
}