mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-20 03:23:01 +02:00
ab043ff680
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
llvm-svn: 230794
42 lines
1.8 KiB
LLVM
42 lines
1.8 KiB
LLVM
; RUN: opt < %s -loop-vectorize -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx -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"
|
|
target triple = "x86_64-apple-macosx10.8.0"
|
|
|
|
@c = common global [2048 x i32] zeroinitializer, align 16
|
|
@b = common global [2048 x i32] zeroinitializer, align 16
|
|
@d = common global [2048 x i32] zeroinitializer, align 16
|
|
@a = common global [2048 x i32] zeroinitializer, align 16
|
|
|
|
; The program below gathers and scatters data. We better not vectorize it.
|
|
;CHECK-LABEL: @cost_model_1(
|
|
;CHECK-NOT: <2 x i32>
|
|
;CHECK-NOT: <4 x i32>
|
|
;CHECK-NOT: <8 x i32>
|
|
;CHECK: ret void
|
|
define void @cost_model_1() nounwind uwtable noinline ssp {
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
|
|
%0 = shl nsw i64 %indvars.iv, 1
|
|
%arrayidx = getelementptr inbounds [2048 x i32], [2048 x i32]* @c, i64 0, i64 %0
|
|
%1 = load i32, i32* %arrayidx, align 8
|
|
%idxprom1 = sext i32 %1 to i64
|
|
%arrayidx2 = getelementptr inbounds [2048 x i32], [2048 x i32]* @b, i64 0, i64 %idxprom1
|
|
%2 = load i32, i32* %arrayidx2, align 4
|
|
%arrayidx4 = getelementptr inbounds [2048 x i32], [2048 x i32]* @d, i64 0, i64 %indvars.iv
|
|
%3 = load i32, i32* %arrayidx4, align 4
|
|
%idxprom5 = sext i32 %3 to i64
|
|
%arrayidx6 = getelementptr inbounds [2048 x i32], [2048 x i32]* @a, i64 0, i64 %idxprom5
|
|
store i32 %2, i32* %arrayidx6, align 4
|
|
%indvars.iv.next = add i64 %indvars.iv, 1
|
|
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
|
|
%exitcond = icmp eq i32 %lftr.wideiv, 256
|
|
br i1 %exitcond, label %for.end, label %for.body
|
|
|
|
for.end: ; preds = %for.body
|
|
ret void
|
|
}
|