mirror of
https://github.com/RPCS3/llvm.git
synced 2024-12-13 14:47:00 +00:00
7c9c6ed761
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
41 lines
1.8 KiB
LLVM
41 lines
1.8 KiB
LLVM
; RUN: opt -S -loop-reduce < %s | FileCheck %s
|
|
; Complex addressing mode are costly.
|
|
; Make loop-reduce prefer unscaled accesses.
|
|
; On X86, reg1 + 1*reg2 has the same cost as reg1 + 8*reg2.
|
|
; Therefore, LSR currently prefers to fold as much computation as possible
|
|
; in the addressing mode.
|
|
; <rdar://problem/16730541>
|
|
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-macosx"
|
|
|
|
define void @mulDouble(double* nocapture %a, double* nocapture %b, double* nocapture %c) {
|
|
; CHECK: @mulDouble
|
|
entry:
|
|
br label %for.body
|
|
|
|
for.body: ; preds = %for.body, %entry
|
|
; CHECK: [[IV:%[^ ]+]] = phi i64 [ [[IVNEXT:%[^,]+]], %for.body ], [ 0, %entry ]
|
|
; Only one induction variable should have been generated.
|
|
; CHECK-NOT: phi
|
|
%indvars.iv = phi i64 [ 1, %entry ], [ %indvars.iv.next, %for.body ]
|
|
%tmp = add nsw i64 %indvars.iv, -1
|
|
%arrayidx = getelementptr inbounds double, double* %b, i64 %tmp
|
|
%tmp1 = load double, double* %arrayidx, align 8
|
|
; The induction variable should carry the scaling factor: 1.
|
|
; CHECK: [[IVNEXT]] = add nuw nsw i64 [[IV]], 1
|
|
%indvars.iv.next = add i64 %indvars.iv, 1
|
|
%arrayidx2 = getelementptr inbounds double, double* %c, i64 %indvars.iv.next
|
|
%tmp2 = load double, double* %arrayidx2, align 8
|
|
%mul = fmul double %tmp1, %tmp2
|
|
%arrayidx4 = getelementptr inbounds double, double* %a, i64 %indvars.iv
|
|
store double %mul, double* %arrayidx4, align 8
|
|
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
|
|
; Comparison should be 19 * 1 = 19.
|
|
; CHECK: icmp eq i32 {{%[^,]+}}, 19
|
|
%exitcond = icmp eq i32 %lftr.wideiv, 20
|
|
br i1 %exitcond, label %for.end, label %for.body
|
|
|
|
for.end: ; preds = %for.body
|
|
ret void
|
|
}
|