Displaying 3 results from an estimated 3 matches for "nph12".
2010 Sep 07
2
[LLVMdev] loop fusion
...e the following program, in which I would like the 2 loops
(iterating the same number of times) to be merged into 1, after which
other nice optimizations such as mem2reg will apply:
; ModuleID = 'test'
define void @vector([16 x float]* nocapture %arg, [16 x float]*
nocapture %ret) {
bb.nph12:
%0 = alloca [16 x float], align 4 ; <[16 x float]*>
[#uses=2]
br label %loop
loop: ; preds = %loop,
%bb.nph12
%indvar13 = phi i64 [ 0, %bb.nph12 ], [ %indvar.next14, %loop ] ;
<i64> [#uses=3]
%gep = getelementptr...
2010 Sep 07
0
[LLVMdev] loop fusion
...e the following program, in which I would like the 2 loops
(iterating the same number of times) to be merged into 1, after which
other nice optimizations such as mem2reg will apply:
; ModuleID = 'test'
define void @vector([16 x float]* nocapture %arg, [16 x float]*
nocapture %ret) {
bb.nph12:
%0 = alloca [16 x float], align 4 ; <[16 x float]*>
[#uses=2]
br label %loop
loop: ; preds = %loop, %bb.nph12
%indvar13 = phi i64 [ 0, %bb.nph12 ], [ %indvar.next14, %loop ] ;
<i64> [#uses=3]
%gep = getelementptr...
2010 Sep 08
0
[LLVMdev] loop fusion
...would like the 2 loops
> (iterating the same number of times) to be merged into 1, after which
> other nice optimizations such as mem2reg will apply:
>
> ; ModuleID = 'test'
>
> define void @vector([16 x float]* nocapture %arg, [16 x float]*
> nocapture %ret) {
> bb.nph12:
> %0 = alloca [16 x float], align 4 ;<[16 x float]*>
> [#uses=2]
> br label %loop
>
> loop: ; preds = %loop,
> %bb.nph12
> %indvar13 = phi i64 [ 0, %bb.nph12 ], [ %indvar.next14, %loop ] ;
> <i64...