Displaying 3 results from an estimated 3 matches for "sub480".
2015 Apr 21
2
[LLVMdev] RFC: Missing canonicalization in LLVM
...at looks like:
while.cond473: ; preds = %while.cond473.outer78, %while.body475
%p_j_x452.0 = phi double [ %105, %while.body475 ], [ %p_j_x452.0.ph82, %while.cond473.outer78 ]
while.body475: ; preds = %while.cond473
%sub480 = fsub fast double %64, %p_j_x452.0
%105 = load double* %x485, align 8, !tbaa !25
After Polly – Prepare code for polly we have:
while.cond473: ; preds = %while.cond473.outer78, %while.body475
%p_j_x452.0.reload = load double* %p_j_x452.0.reg2mem...
2015 Apr 23
2
[LLVMdev] RFC: Missing canonicalization in LLVM
...at looks like:
while.cond473: ; preds = %while.cond473.outer78, %while.body475
%p_j_x452.0 = phi double [ %105, %while.body475 ], [ %p_j_x452.0.ph82, %while.cond473.outer78 ]
while.body475: ; preds = %while.cond473
%sub480 = fsub fast double %64, %p_j_x452.0
%105 = load double* %x485, align 8, !tbaa !25
After Polly – Prepare code for polly we have:
while.cond473: ; preds = %while.cond473.outer78, %while.body475
%p_j_x452.0.reload = load double* %p_j_x452.0.reg2mem...
2015 Jan 21
3
[LLVMdev] RFC: Missing canonicalization in LLVM
> On Jan 21, 2015, at 3:02 PM, Chandler Carruth <chandlerc at gmail.com> wrote:
>
>
> On Wed, Jan 21, 2015 at 2:43 PM, Pete Cooper <peter_cooper at apple.com <mailto:peter_cooper at apple.com>> wrote:
> The first thing that springs to mind is that I don’t trust the backend to get this right. I don’t think it will understand when an i32 load/store would have been