llvm dev - Oct 2015 - Redundant Trivial Basic Blocks Caused by select

Hi all,

 

I have a simple test case like this

 

class H

{

public:

    int a;              

    int b;  

    int c;  

};

 

inline int operator < (H& A, H& B)

{

    return (A.a < B.a) ? 1 :

           (A.a > B.a) ? 0 :

           (A.b < B.b) ? 1 :

           (A.b > B.b) ? 0 :

            A.c < B.c;

}

 

int s(H *h, int j)

{

    if (h[j] < h[j+1])  

        j+=2;

 

    return j;

}

 

The generated assembly in AArch64 is like below.  X86 assembly has similar
problem.

 

If(h0.a < h1.a) goto bb0

if (h0.a > h1.a) goto bb1

If(h0.b < h1.b) goto bb2

if (h0.b > h1.b) goto bb3

flag = (h0.c < h1.c)

goto if_end 

bb0: Flag = 1; Goto if_end

bb1: Flag = 0; Goto if_end

bb2: Flag = 1; Goto if_end

bb3: Flag = 0; Goto if_end

if_end: j = select flag, j+2, j

 

The trivial basic blocks bb0 - bb3 can cause huge performance penalty if the
comparison (h[j] < h[j+1]) is in a hot loop.  The IR code of if_end is like
this

 

  %cond = phi i1 [ false, . ], [ true, . ], [ false, . ], [ true, . ],
[%flag, .]

  %add = add i32 %j, 2

  %j.add = select i1 %cond.i, i32 %j, i32 %add

 

Every bool constant in the phi becomes a trivial basic block in the
assembly.  select is generated by SpeculativelyExecuteBB() of simplifyCFG
before function inlining and prevents jump-threading to further optimize the
CFG.  If I run the passes in the order of

 

-inline -instcombine -jump-threading -simplifycfg

 

then the problem is gone.  instcombine can clean the code after inlining so
that jump-threading can optimize the CFG.

 

Please let me know if you have any advice to solve this problem.

 

Thank you,

 

Haicheng

 

-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<http://lists.llvm.org/pipermail/llvm-dev/attachments/20151015/2fd8a471/attachment.html>