mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-08-31 12:30:06 +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
94 lines
3.1 KiB
LLVM
94 lines
3.1 KiB
LLVM
; RUN: opt < %s -loop-vectorize -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx -debug-only=loop-vectorize -stats -S 2>&1 | FileCheck %s
|
|
; REQUIRES: asserts
|
|
|
|
; CHECK: LV: Loop hints: force=enabled
|
|
; CHECK: LV: Loop hints: force=?
|
|
; No more loops in the module
|
|
; CHECK-NOT: LV: Loop hints: force=
|
|
; CHECK: 2 loop-vectorize - Number of loops analyzed for vectorization
|
|
; CHECK: 1 loop-vectorize - Number of loops vectorized
|
|
|
|
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"
|
|
|
|
;
|
|
; The source code for the test:
|
|
;
|
|
; #include <math.h>
|
|
; void foo(float* restrict A, float * restrict B, int size)
|
|
; {
|
|
; for (int i = 0; i < size; ++i) A[i] = sinf(B[i]);
|
|
; }
|
|
;
|
|
|
|
;
|
|
; This loop will be vectorized, although the scalar cost is lower than any of vector costs, but vectorization is explicitly forced in metadata.
|
|
;
|
|
|
|
define void @vectorized(float* noalias nocapture %A, float* noalias nocapture %B, i32 %size) {
|
|
entry:
|
|
%cmp6 = icmp sgt i32 %size, 0
|
|
br i1 %cmp6, label %for.body.preheader, label %for.end
|
|
|
|
for.body.preheader:
|
|
br label %for.body
|
|
|
|
for.body:
|
|
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %for.body.preheader ]
|
|
%arrayidx = getelementptr inbounds float, float* %B, i64 %indvars.iv
|
|
%0 = load float, float* %arrayidx, align 4, !llvm.mem.parallel_loop_access !1
|
|
%call = tail call float @llvm.sin.f32(float %0)
|
|
%arrayidx2 = getelementptr inbounds float, float* %A, i64 %indvars.iv
|
|
store float %call, float* %arrayidx2, align 4, !llvm.mem.parallel_loop_access !1
|
|
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
|
|
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
|
|
%exitcond = icmp eq i32 %lftr.wideiv, %size
|
|
br i1 %exitcond, label %for.end.loopexit, label %for.body, !llvm.loop !1
|
|
|
|
for.end.loopexit:
|
|
br label %for.end
|
|
|
|
for.end:
|
|
ret void
|
|
}
|
|
|
|
!1 = !{!1, !2}
|
|
!2 = !{!"llvm.loop.vectorize.enable", i1 true}
|
|
|
|
;
|
|
; This method will not be vectorized, as scalar cost is lower than any of vector costs.
|
|
;
|
|
|
|
define void @not_vectorized(float* noalias nocapture %A, float* noalias nocapture %B, i32 %size) {
|
|
entry:
|
|
%cmp6 = icmp sgt i32 %size, 0
|
|
br i1 %cmp6, label %for.body.preheader, label %for.end
|
|
|
|
for.body.preheader:
|
|
br label %for.body
|
|
|
|
for.body:
|
|
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %for.body.preheader ]
|
|
%arrayidx = getelementptr inbounds float, float* %B, i64 %indvars.iv
|
|
%0 = load float, float* %arrayidx, align 4, !llvm.mem.parallel_loop_access !3
|
|
%call = tail call float @llvm.sin.f32(float %0)
|
|
%arrayidx2 = getelementptr inbounds float, float* %A, i64 %indvars.iv
|
|
store float %call, float* %arrayidx2, align 4, !llvm.mem.parallel_loop_access !3
|
|
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
|
|
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
|
|
%exitcond = icmp eq i32 %lftr.wideiv, %size
|
|
br i1 %exitcond, label %for.end.loopexit, label %for.body, !llvm.loop !3
|
|
|
|
for.end.loopexit:
|
|
br label %for.end
|
|
|
|
for.end:
|
|
ret void
|
|
}
|
|
|
|
declare float @llvm.sin.f32(float) nounwind readnone
|
|
|
|
; Dummy metadata
|
|
!3 = !{!3}
|
|
|