mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-17 18:31:04 +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
70 lines
2.4 KiB
LLVM
70 lines
2.4 KiB
LLVM
; RUN: opt -loop-vectorize -force-vector-width=2 -force-vector-interleave=1 -S < %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"
|
|
|
|
@A = common global [1024 x float] zeroinitializer, align 16
|
|
@B = common global [1024 x float] zeroinitializer, align 16
|
|
|
|
; Make sure we can vectorize in the presence of hoistable conditional loads.
|
|
; CHECK-LABEL: @hoist_cond_load(
|
|
; CHECK: load <2 x float>
|
|
|
|
define void @hoist_cond_load() {
|
|
entry:
|
|
br label %for.body
|
|
for.body:
|
|
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %if.end9 ]
|
|
%arrayidx = getelementptr inbounds [1024 x float], [1024 x float]* @A, i64 0, i64 %indvars.iv
|
|
%arrayidx2 = getelementptr inbounds [1024 x float], [1024 x float]* @B, i64 0, i64 %indvars.iv
|
|
%0 = load float, float* %arrayidx2, align 4
|
|
%cmp3 = fcmp oeq float %0, 0.000000e+00
|
|
br i1 %cmp3, label %if.end9, label %if.else
|
|
|
|
if.else:
|
|
%1 = load float, float* %arrayidx, align 4
|
|
br label %if.end9
|
|
|
|
if.end9:
|
|
%tmp.0 = phi float [ %1, %if.else ], [ 0.000000e+00, %for.body ]
|
|
store float %tmp.0, float* %arrayidx, align 4
|
|
%indvars.iv.next = add i64 %indvars.iv, 1
|
|
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
|
|
%exitcond = icmp ne i32 %lftr.wideiv, 1024
|
|
br i1 %exitcond, label %for.body, label %for.end
|
|
|
|
for.end:
|
|
ret void
|
|
}
|
|
|
|
; However, we can't hoist loads whose address we have not seen unconditionally
|
|
; accessed.
|
|
; CHECK-LABEL: @dont_hoist_cond_load(
|
|
; CHECK-NOT: load <2 x float>
|
|
|
|
define void @dont_hoist_cond_load() {
|
|
entry:
|
|
br label %for.body
|
|
for.body:
|
|
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %if.end9 ]
|
|
%arrayidx = getelementptr inbounds [1024 x float], [1024 x float]* @A, i64 0, i64 %indvars.iv
|
|
%arrayidx2 = getelementptr inbounds [1024 x float], [1024 x float]* @B, i64 0, i64 %indvars.iv
|
|
%0 = load float, float* %arrayidx2, align 4
|
|
%cmp3 = fcmp oeq float %0, 0.000000e+00
|
|
br i1 %cmp3, label %if.end9, label %if.else
|
|
|
|
if.else:
|
|
%1 = load float, float* %arrayidx, align 4
|
|
br label %if.end9
|
|
|
|
if.end9:
|
|
%tmp.0 = phi float [ %1, %if.else ], [ 0.000000e+00, %for.body ]
|
|
store float %tmp.0, float* %arrayidx2, align 4
|
|
%indvars.iv.next = add i64 %indvars.iv, 1
|
|
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
|
|
%exitcond = icmp ne i32 %lftr.wideiv, 1024
|
|
br i1 %exitcond, label %for.body, label %for.end
|
|
|
|
for.end:
|
|
ret void
|
|
}
|