mirror of
https://github.com/RPCSX/llvm.git
synced 2024-12-13 23:18:51 +00:00
eafb39b656
Current SCEV expansion will expand SCEV as a sequence of operations and doesn't utilize the value already existed. This will introduce redundent computation which may not be cleaned up throughly by following optimizations. This patch introduces an ExprValueMap which is a map from SCEV to the set of equal values with the same SCEV. When a SCEV is expanded, the set of values is checked and reused whenever possible before generating a sequence of operations. The original commit triggered regressions in Polly tests. The regressions exposed two problems which have been fixed in current version. 1. Polly will generate a new function based on the old one. To generate an instruction for the new function, it builds SCEV for the old instruction, applies some tranformation on the SCEV generated, then expands the transformed SCEV and insert the expanded value into new function. Because SCEV expansion may reuse value cached in ExprValueMap, the value in old function may be inserted into new function, which is wrong. In SCEVExpander::expand, there is a logic to check the cached value to be used should dominate the insertion point. However, for the above case, the check always passes. That is because the insertion point is in a new function, which is unreachable from the old function. However for unreachable node, DominatorTreeBase::dominates thinks it will be dominated by any other node. The fix is to simply add a check that the cached value to be used in expansion should be in the same function as the insertion point instruction. 2. When the SCEV is of scConstant type, expanding it directly is cheaper than reusing a normal value cached. Although in the cached value set in ExprValueMap, there is a Constant type value, but it is not easy to find it out -- the cached Value set is not sorted according to the potential cost. Existing reuse logic in SCEVExpander::expand simply chooses the first legal element from the cached value set. The fix is that when the SCEV is of scConstant type, don't try the reuse logic. simply expand it. Differential Revision: http://reviews.llvm.org/D12090 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@259736 91177308-0d34-0410-b5e6-96231b3b80d8
41 lines
1.4 KiB
LLVM
41 lines
1.4 KiB
LLVM
; RUN: opt -S -indvars < %s | FileCheck %s
|
|
|
|
; Provide legal integer types.
|
|
target datalayout = "n8:16:32:64"
|
|
|
|
|
|
define void @test1(float* nocapture %autoc, float* nocapture %data, float %d, i32 %data_len, i32 %sample) nounwind {
|
|
entry:
|
|
%sub = sub i32 %data_len, %sample
|
|
%cmp4 = icmp eq i32 %data_len, %sample
|
|
br i1 %cmp4, label %for.end, label %for.body
|
|
|
|
for.body: ; preds = %entry, %for.body
|
|
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
|
|
%0 = trunc i64 %indvars.iv to i32
|
|
%add = add i32 %0, %sample
|
|
%idxprom = zext i32 %add to i64
|
|
%arrayidx = getelementptr inbounds float, float* %data, i64 %idxprom
|
|
%1 = load float, float* %arrayidx, align 4
|
|
%mul = fmul float %1, %d
|
|
%arrayidx2 = getelementptr inbounds float, float* %autoc, i64 %indvars.iv
|
|
%2 = load float, float* %arrayidx2, align 4
|
|
%add3 = fadd float %2, %mul
|
|
store float %add3, float* %arrayidx2, align 4
|
|
%indvars.iv.next = add i64 %indvars.iv, 1
|
|
%3 = trunc i64 %indvars.iv.next to i32
|
|
%cmp = icmp ult i32 %3, %sub
|
|
br i1 %cmp, label %for.body, label %for.end
|
|
|
|
for.end: ; preds = %for.body, %entry
|
|
ret void
|
|
|
|
; CHECK-LABEL: @test1(
|
|
|
|
; check that we turn the IV test into an eq.
|
|
; CHECK: %lftr.wideiv = trunc i64 %indvars.iv.next to i32
|
|
; CHECK: %exitcond = icmp ne i32 %lftr.wideiv, %sub
|
|
; CHECK: br i1 %exitcond, label %for.body, label %for.end.loopexit
|
|
}
|
|
|