Small refactor on VectorizerHint for deduplication

Previously, the hint mechanism relied on clean up passes to remove redundant
metadata, which still showed up if running opt at low levels of optimization.
That also has shown that multiple nodes of the same type, but with different
values could still coexist, even if temporary, and cause confusion if the
next pass got the wrong value.

This patch makes sure that, if metadata already exists in a loop, the hint
mechanism will never append a new node, but always replace the existing one.
It also enhances the algorithm to cope with more metadata types in the future
by just adding a new type, not a lot of code.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@215994 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Renato Golin
2014-08-19 17:30:43 +00:00
parent e3cea5fd9a
commit dca126522d
2 changed files with 177 additions and 91 deletions
@@ -0,0 +1,30 @@
; RUN: opt < %s -loop-vectorize -S 2>&1 | FileCheck %s
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
; This test makes sure we don't duplicate the loop vectorizer's metadata
; while marking them as already vectorized (by setting width = 1), even
; at lower optimization levels, where no extra cleanup is done
define void @_Z3fooPf(float* %a) {
entry:
br label %for.body
for.body: ; preds = %for.body, %entry
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
%arrayidx = getelementptr inbounds float* %a, i64 %indvars.iv
%p = load float* %arrayidx, align 4
%mul = fmul float %p, 2.000000e+00
store float %mul, float* %arrayidx, align 4
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp eq i64 %indvars.iv.next, 1024
br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !0
for.end: ; preds = %for.body
ret void
}
!0 = metadata !{metadata !0, metadata !1}
!1 = metadata !{metadata !"llvm.loop.vectorize.width", i32 4}
; CHECK-NOT: !{metadata !"llvm.loop.vectorize.width", i32 4}
; CHECK: !{metadata !"llvm.loop.interleave.count", i32 1}