Skip to content
  1. Sep 27, 2004
  3. Sep 26, 2004
  5. Sep 25, 2004
  7. Sep 24, 2004
  9. Sep 23, 2004
  11. Sep 22, 2004
  13. Sep 21, 2004
    • Chris Lattner's avatar
      Do not fold (X + C1 != C2) if there are other users of the add. Doing · b121ae1c
      Chris Lattner authored 
      this transformation used to take a loop like this:

int Array[1000];
void test(int X) {
  int i;
  for (i = 0; i < 1000; ++i)
    Array[i] += X;
}

Compiled to LLVM is:

no_exit:                ; preds = %entry, %no_exit
        %indvar = phi uint [ 0, %entry ], [ %indvar.next, %no_exit ]            ; <uint> [#uses=2]
        %tmp.4 = getelementptr [1000 x int]* %Array, int 0, uint %indvar                ; <int*> [#uses=2]
        %tmp.7 = load int* %tmp.4               ; <int> [#uses=1]
        %tmp.9 = add int %tmp.7, %X             ; <int> [#uses=1]
        store int %tmp.9, int* %tmp.4
***     %indvar.next = add uint %indvar, 1              ; <uint> [#uses=2]
***     %exitcond = seteq uint %indvar.next, 1000               ; <bool> [#uses=1]
        br bool %exitcond, label %return, label %no_exit

and turn it into a loop like this:

no_exit:                ; preds = %entry, %no_exit
        %indvar = phi uint [ 0, %entry ], [ %indvar.next, %no_exit ]            ; <uint> [#uses=3]
        %tmp.4 = getelementptr [1000 x int]* %Array, int 0, uint %indvar                ; <int*> [#uses=2]
        %tmp.7 = load int* %tmp.4               ; <int> [#uses=1]
        %tmp.9 = add int %tmp.7, %X             ; <int> [#uses=1]
        store int %tmp.9, int* %tmp.4
***     %indvar.next = add uint %indvar, 1              ; <uint> [#uses=1]
***     %exitcond = seteq uint %indvar, 999             ; <bool> [#uses=1]
        br bool %exitcond, label %return, label %no_exit

Note that indvar.next and indvar can no longer be coallesced.  In machine
code terms, this patch changes this code:

.LBBtest_1:     # no_exit
        mov %EDX, OFFSET Array
        mov %ESI, %EAX
        add %ESI, DWORD PTR [%EDX + 4*%ECX]
        mov %EDX, OFFSET Array
        mov DWORD PTR [%EDX + 4*%ECX], %ESI
        mov %EDX, %ECX
        inc %EDX
        cmp %ECX, 999
        mov %ECX, %EDX
        jne .LBBtest_1  # no_exit

into this:

.LBBtest_1:     # no_exit
        mov %EDX, OFFSET Array
        mov %ESI, %EAX
        add %ESI, DWORD PTR [%EDX + 4*%ECX]
        mov %EDX, OFFSET Array
        mov DWORD PTR [%EDX + 4*%ECX], %ESI
        inc %ECX
        cmp %ECX, 1000
        jne .LBBtest_1  # no_exit

We need better instruction selection to get this:

.LBBtest_1:     # no_exit
        add DWORD PTR [Array + 4*%ECX], EAX
        inc %ECX
        cmp %ECX, 1000
        jne .LBBtest_1  # no_exit

... but at least there is less register juggling

llvm-svn: 16473
      b121ae1c
    • Alkis Evlogimenos's avatar
      The real x87 floating point registers should not be allocatable. They · 89dd6373
      Alkis Evlogimenos authored 
      are only used by the stackifier when transforming FPn register
allocations to the real stack file x87 registers.

llvm-svn: 16472
      89dd6373