mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-10-07 05:55:44 +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
89 lines
2.5 KiB
LLVM
89 lines
2.5 KiB
LLVM
; RUN: opt < %s -O2 -force-vector-interleave=2 -force-vector-width=4 -debug-only=loop-vectorize -stats -S 2>&1 | FileCheck %s
|
|
; REQUIRES: asserts
|
|
|
|
; Loop from "rotated"
|
|
; CHECK: LV: Loop hints: force=enabled
|
|
; Loop from "nonrotated"
|
|
; CHECK: LV: Loop hints: force=enabled
|
|
; No more loops in the module
|
|
; CHECK-NOT: LV: Loop hints: force=
|
|
; In total only 1 loop should be rotated.
|
|
; CHECK: 1 loop-rotate
|
|
|
|
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"
|
|
|
|
; See http://reviews.llvm.org/D3348 for details.
|
|
|
|
;
|
|
; Test #1
|
|
;
|
|
; Ensure that "llvm.loop.vectorize.enable" metadata was not lost prior to LoopVectorize pass.
|
|
; In past LoopRotate was clearing that metadata.
|
|
;
|
|
; The source C code is:
|
|
; void rotated(float *a, int size)
|
|
; {
|
|
; int t = 0;
|
|
; #pragma omp simd
|
|
; for (int i = 0; i < size; ++i) {
|
|
; a[i] = a[i-5] * a[i+2];
|
|
; ++t;
|
|
; }
|
|
;}
|
|
|
|
define void @rotated(float* nocapture %a, i64 %size) {
|
|
entry:
|
|
%cmp1 = icmp sgt i64 %size, 0
|
|
br i1 %cmp1, label %for.header, label %for.end
|
|
|
|
for.header:
|
|
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
|
|
%cmp2 = icmp sgt i64 %indvars.iv, %size
|
|
br i1 %cmp2, label %for.end, label %for.body
|
|
|
|
for.body:
|
|
|
|
%0 = add nsw i64 %indvars.iv, -5
|
|
%arrayidx = getelementptr inbounds float, float* %a, i64 %0
|
|
%1 = load float, float* %arrayidx, align 4, !llvm.mem.parallel_loop_access !1
|
|
%2 = add nsw i64 %indvars.iv, 2
|
|
%arrayidx2 = getelementptr inbounds float, float* %a, i64 %2
|
|
%3 = load float, float* %arrayidx2, align 4, !llvm.mem.parallel_loop_access !1
|
|
%mul = fmul float %1, %3
|
|
%arrayidx4 = getelementptr inbounds float, float* %a, i64 %indvars.iv
|
|
store float %mul, float* %arrayidx4, align 4, !llvm.mem.parallel_loop_access !1
|
|
|
|
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
|
|
br label %for.header, !llvm.loop !1
|
|
|
|
for.end:
|
|
ret void
|
|
}
|
|
|
|
!1 = !{!1, !2}
|
|
!2 = !{!"llvm.loop.vectorize.enable", i1 true}
|
|
|
|
;
|
|
; Test #2
|
|
;
|
|
; Ensure that "llvm.loop.vectorize.enable" metadata was not lost even
|
|
; if loop was not rotated (see http://reviews.llvm.org/D3348#comment-4).
|
|
;
|
|
define i32 @nonrotated(i32 %a) {
|
|
entry:
|
|
br label %loop_cond
|
|
loop_cond:
|
|
%indx = phi i32 [ 1, %entry ], [ %inc, %loop_inc ]
|
|
%cmp = icmp ne i32 %indx, %a
|
|
br i1 %cmp, label %return, label %loop_inc
|
|
loop_inc:
|
|
%inc = add i32 %indx, 1
|
|
br label %loop_cond, !llvm.loop !3
|
|
return:
|
|
ret i32 0
|
|
}
|
|
|
|
!3 = !{!3, !4}
|
|
!4 = !{!"llvm.loop.vectorize.enable", i1 true}
|